diff --git a/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td b/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td
index 368665467859f..9f2f11bafe79f 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedNeoverseV1.td
@@ -98,377 +98,452 @@ def V1Write_0c_0Z : SchedWriteRes<[]>;
 
 def V1Write_1c_1B      : SchedWriteRes<[V1UnitB]>   { let Latency = 1; }
 def V1Write_1c_1I      : SchedWriteRes<[V1UnitI]>   { let Latency = 1; }
-def V1Write_1c_1I_1Flg : SchedWriteRes<[V1UnitI, V1UnitFlg]>   { let Latency = 1; }
+def V1Write_1c_1I_1Flg : SchedWriteRes<[V1UnitI, V1UnitFlg]>   { let Latency = 1;
+								 let NumMicroOps = 2; }
 def V1Write_4c_1L      : SchedWriteRes<[V1UnitL]>   { let Latency = 4; }
+def V1Write_4c3_1L     : SchedWriteRes<[V1UnitL]>   { let Latency = 4;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_5c3_1L     : SchedWriteRes<[V1UnitL]>   { let Latency = 5;
+						      let ReleaseAtCycles = [3]; }
+
 def V1Write_6c_1L      : SchedWriteRes<[V1UnitL]>   { let Latency = 6; }
+def V1Write_6c2_1L     : SchedWriteRes<[V1UnitL]>   { let Latency = 6;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_6c3_1L     : SchedWriteRes<[V1UnitL]>   { let Latency = 6;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_7c4_1L     : SchedWriteRes<[V1UnitL]>   { let Latency = 7;
+						      let ReleaseAtCycles = [4]; }
 def V1Write_1c_1L01    : SchedWriteRes<[V1UnitL01]> { let Latency = 1; }
 def V1Write_4c_1L01    : SchedWriteRes<[V1UnitL01]> { let Latency = 4; }
 def V1Write_6c_1L01    : SchedWriteRes<[V1UnitL01]> { let Latency = 6; }
 def V1Write_2c_1M      : SchedWriteRes<[V1UnitM]>   { let Latency = 2; }
-def V1Write_2c_1M_1Flg : SchedWriteRes<[V1UnitM, V1UnitFlg]>   { let Latency = 2; }
+def V1Write_2c_1M_1Flg : SchedWriteRes<[V1UnitM, V1UnitFlg]>   { let Latency = 2;
+								 let NumMicroOps = 2; }
 def V1Write_3c_1M      : SchedWriteRes<[V1UnitM]>   { let Latency = 3; }
-def V1Write_4c_1M      : SchedWriteRes<[V1UnitM]>   { let Latency = 4; }
+def V1Write_4c6_1M     : SchedWriteRes<[V1UnitM]>   { let Latency = 4;
+						      let ReleaseAtCycles = [6]; }
 def V1Write_1c_1M0     : SchedWriteRes<[V1UnitM0]>  { let Latency = 1; }
 def V1Write_2c_1M0     : SchedWriteRes<[V1UnitM0]>  { let Latency = 2; }
+def V1Write_2c2_1M0    : SchedWriteRes<[V1UnitM0]>  { let Latency = 2;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_3c2_1M0    : SchedWriteRes<[V1UnitM0]>  { let Latency = 3;
+						      let ReleaseAtCycles = [2]; }
 def V1Write_3c_1M0     : SchedWriteRes<[V1UnitM0]>  { let Latency = 3; }
 def V1Write_5c_1M0     : SchedWriteRes<[V1UnitM0]>  { let Latency = 5; }
-def V1Write_12c5_1M0   : SchedWriteRes<[V1UnitM0]>  { let Latency = 12;
-                                                      let ReleaseAtCycles = [5]; }
-def V1Write_20c5_1M0   : SchedWriteRes<[V1UnitM0]>  { let Latency = 20;
-                                                      let ReleaseAtCycles = [5]; }
+def V1Write_12c12_1M0  : SchedWriteRes<[V1UnitM0]>  { let Latency = 12;
+						      let ReleaseAtCycles = [12]; }
+def V1Write_20c20_1M0  : SchedWriteRes<[V1UnitM0]>  { let Latency = 20;
+						      let ReleaseAtCycles = [20]; }
 def V1Write_2c_1V      : SchedWriteRes<[V1UnitV]>   { let Latency = 2; }
+def V1Write_2c4_1V     : SchedWriteRes<[V1UnitV]>   { let Latency = 2;
+						      let ReleaseAtCycles = [4]; }
 def V1Write_3c_1V      : SchedWriteRes<[V1UnitV]>   { let Latency = 3; }
 def V1Write_4c_1V      : SchedWriteRes<[V1UnitV]>   { let Latency = 4; }
+def V1Write_4c2_1V     : SchedWriteRes<[V1UnitV]>   { let Latency = 4;
+						      let ReleaseAtCycles = [2]; }
 def V1Write_5c_1V      : SchedWriteRes<[V1UnitV]>   { let Latency = 5; }
+def V1Write_6c3_1V     : SchedWriteRes<[V1UnitV]>   { let Latency = 6;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_12c2_1V    : SchedWriteRes<[V1UnitV1]>  { let Latency = 12;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_14c2_1V    : SchedWriteRes<[V1UnitV1]>  { let Latency = 14;
+						      let ReleaseAtCycles = [2]; }
+
 def V1Write_2c_1V0     : SchedWriteRes<[V1UnitV0]>  { let Latency = 2; }
 def V1Write_3c_1V0     : SchedWriteRes<[V1UnitV0]>  { let Latency = 3; }
 def V1Write_4c_1V0     : SchedWriteRes<[V1UnitV0]>  { let Latency = 4; }
+def V1Write_5c2_1V0    : SchedWriteRes<[V1UnitV0]>  { let Latency = 5;
+						      let ReleaseAtCycles = [2]; }
 def V1Write_6c_1V0     : SchedWriteRes<[V1UnitV0]>  { let Latency = 6; }
-def V1Write_10c7_1V0   : SchedWriteRes<[V1UnitV0]>  { let Latency = 10;
-                                                      let ReleaseAtCycles = [7]; }
-def V1Write_12c7_1V0   : SchedWriteRes<[V1UnitV0]>  { let Latency = 12;
-                                                      let ReleaseAtCycles = [7]; }
-def V1Write_13c10_1V0  : SchedWriteRes<[V1UnitV0]>  { let Latency = 13;
-                                                      let ReleaseAtCycles = [10]; }
-def V1Write_15c7_1V0   : SchedWriteRes<[V1UnitV0]>  { let Latency = 15;
-                                                      let ReleaseAtCycles = [7]; }
-def V1Write_16c7_1V0   : SchedWriteRes<[V1UnitV0]>  { let Latency = 16;
-                                                      let ReleaseAtCycles = [7]; }
-def V1Write_20c7_1V0   : SchedWriteRes<[V1UnitV0]>  { let Latency = 20;
-                                                      let ReleaseAtCycles = [7]; }
+def V1Write_6c4_1V0    : SchedWriteRes<[V1UnitV0]>  { let Latency = 6;
+						      let ReleaseAtCycles = [4]; }
+def V1Write_10c9_1V0	: SchedWriteRes<[V1UnitV0]>  { let Latency = 10;
+                                                      let ReleaseAtCycles = [9]; }
+def V1Write_11c10_1V0	 : SchedWriteRes<[V1UnitV0]> { let Latency = 11;
+						       let ReleaseAtCycles = [10]; }
+def V1Write_12c11_1V0	: SchedWriteRes<[V1UnitV0]>  { let Latency = 12;
+						      let ReleaseAtCycles = [11]; }
+def V1Write_13c12_1V0  : SchedWriteRes<[V1UnitV0]>  { let Latency = 13;
+						      let ReleaseAtCycles = [12]; }
+def V1Write_15c14_1V0	: SchedWriteRes<[V1UnitV0]>  { let Latency = 15;
+						      let ReleaseAtCycles = [14]; }
+def V1Write_16c14_1V0	: SchedWriteRes<[V1UnitV0]>  { let Latency = 16;
+						      let ReleaseAtCycles = [14]; }
+def V1Write_19c18_1V0	 : SchedWriteRes<[V1UnitV0]> { let Latency = 19;
+						       let ReleaseAtCycles = [18]; }
+def V1Write_20c20_1V0	: SchedWriteRes<[V1UnitV0]>  { let Latency = 20;
+						      let ReleaseAtCycles = [20]; }
+
 def V1Write_2c_1V01    : SchedWriteRes<[V1UnitV01]> { let Latency = 2; }
 def V1Write_3c_1V01    : SchedWriteRes<[V1UnitV01]> { let Latency = 3; }
 def V1Write_4c_1V01    : SchedWriteRes<[V1UnitV01]> { let Latency = 4; }
-def V1Write_5c_1V01    : SchedWriteRes<[V1UnitV01]> { let Latency = 5; }
+def V1Write_4c2_1V01   : SchedWriteRes<[V1UnitV01]> { let Latency = 4;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_4c3_1V01   : SchedWriteRes<[V1UnitV01]> { let Latency = 4;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_6c3_1V01   : SchedWriteRes<[V1UnitV01]> { let Latency = 6;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_6c5_1V01   : SchedWriteRes<[V1UnitV01]> { let Latency = 6;
+						      let ReleaseAtCycles = [5]; }
+def V1Write_8c3_1V01   : SchedWriteRes<[V1UnitV01]> { let Latency = 8;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_9c4_1V01   : SchedWriteRes<[V1UnitV01]> { let Latency = 9;
+						      let ReleaseAtCycles = [4]; }
+def V1Write_12c4_1V01  : SchedWriteRes<[V1UnitV01]> { let Latency = 12;
+						      let ReleaseAtCycles = [4]; }
+def V1Write_13c6_1V01  : SchedWriteRes<[V1UnitV01]> { let Latency = 13;
+						      let ReleaseAtCycles = [6]; }
+def V1Write_11c5_1V01  : SchedWriteRes<[V1UnitV01]> { let Latency = 11;
+						      let ReleaseAtCycles = [5]; }
 def V1Write_3c_1V02    : SchedWriteRes<[V1UnitV02]> { let Latency = 3; }
 def V1Write_4c_1V02    : SchedWriteRes<[V1UnitV02]> { let Latency = 4; }
+def V1Write_4c2_1V02   : SchedWriteRes<[V1UnitV02]> { let Latency = 4;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_6c4_1V02   : SchedWriteRes<[V1UnitV02]> { let Latency = 6;
+						      let ReleaseAtCycles = [4]; }
+def V1Write_7c2_1V02   : SchedWriteRes<[V1UnitV02]> { let Latency = 7;
+						      let ReleaseAtCycles = [2]; }
 def V1Write_7c7_1V02   : SchedWriteRes<[V1UnitV02]> { let Latency = 7;
                                                       let ReleaseAtCycles = [7]; }
-def V1Write_10c7_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 10;
-                                                      let ReleaseAtCycles = [7]; }
-def V1Write_13c5_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 13;
+def V1Write_9c3_1V02  : SchedWriteRes<[V1UnitV02]>  { let Latency = 9;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_10c3_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 10;
+						      let ReleaseAtCycles = [3]; }
+def V1Write_10c5_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 10;
                                                       let ReleaseAtCycles = [5]; }
-def V1Write_13c11_1V02 : SchedWriteRes<[V1UnitV02]> { let Latency = 13;
-                                                      let ReleaseAtCycles = [11]; }
+def V1Write_10c9_1V02 : SchedWriteRes<[V1UnitV02]> { let Latency = 10;
+						      let ReleaseAtCycles = [9]; }
+def V1Write_13c13_1V02 : SchedWriteRes<[V1UnitV02]> { let Latency = 13;
+						      let ReleaseAtCycles = [13]; }
 def V1Write_15c7_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 15;
                                                       let ReleaseAtCycles = [7]; }
-def V1Write_16c7_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 16;
-                                                      let ReleaseAtCycles = [7]; }
+def V1Write_15c14_1V02 : SchedWriteRes<[V1UnitV02]> { let Latency = 15;
+						      let ReleaseAtCycles = [14]; }
+def V1Write_16c8_1V02  : SchedWriteRes<[V1UnitV02]> { let Latency = 16;
+						      let ReleaseAtCycles = [8]; }
+def V1Write_16c15_1V02	: SchedWriteRes<[V1UnitV02]> { let Latency = 16;
+						      let ReleaseAtCycles = [15]; }
 def V1Write_2c_1V1     : SchedWriteRes<[V1UnitV1]>  { let Latency = 2; }
 def V1Write_3c_1V1     : SchedWriteRes<[V1UnitV1]>  { let Latency = 3; }
 def V1Write_4c_1V1     : SchedWriteRes<[V1UnitV1]>  { let Latency = 4; }
+def V1Write_8c2_1V1    : SchedWriteRes<[V1UnitV1]>  { let Latency = 8;
+						      let ReleaseAtCycles = [2]; }
+def V1Write_10c2_1V1   : SchedWriteRes<[V1UnitV1]>  { let Latency = 10;
+						      let ReleaseAtCycles = [2]; }
 def V1Write_2c_1V13    : SchedWriteRes<[V1UnitV13]> { let Latency = 2; }
 def V1Write_4c_1V13    : SchedWriteRes<[V1UnitV13]> { let Latency = 4; }
+def V1Write_4c2_1V13   : SchedWriteRes<[V1UnitV13]> { let Latency = 4;
+						      let ReleaseAtCycles = [2]; }
+
 
 //===----------------------------------------------------------------------===//
 // Define generic 2 micro-op types
 
-let Latency = 1, NumMicroOps = 2 in
-def V1Write_1c_1B_1S     : SchedWriteRes<[V1UnitB, V1UnitS]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_1B_1M0    : SchedWriteRes<[V1UnitB, V1UnitM0]>;
-let Latency = 3, NumMicroOps = 2 in
-def V1Write_3c_1I_1M     : SchedWriteRes<[V1UnitI, V1UnitM]>;
-let Latency = 5, NumMicroOps = 2 in
-def V1Write_5c_1I_1L     : SchedWriteRes<[V1UnitI, V1UnitL]>;
-let Latency = 7, NumMicroOps = 2 in
-def V1Write_7c_1I_1L     : SchedWriteRes<[V1UnitI, V1UnitL]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_2L        : SchedWriteRes<[V1UnitL, V1UnitL]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_1L_1M     : SchedWriteRes<[V1UnitL, V1UnitM]>;
-let Latency = 8, NumMicroOps = 2 in
-def V1Write_8c_1L_1V     : SchedWriteRes<[V1UnitL, V1UnitV]>;
-let Latency = 9, NumMicroOps = 2 in
-def V1Write_9c_1L_1V     : SchedWriteRes<[V1UnitL, V1UnitV]>;
-let Latency = 11, NumMicroOps = 2 in
-def V1Write_11c_1L_1V     : SchedWriteRes<[V1UnitL, V1UnitV]>;
-let Latency = 1, NumMicroOps = 2 in
-def V1Write_1c_1L01_1D   : SchedWriteRes<[V1UnitL01, V1UnitD]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_1L01_1S   : SchedWriteRes<[V1UnitL01, V1UnitS]>;
-let Latency = 7, NumMicroOps = 2 in
-def V1Write_7c_1L01_1S   : SchedWriteRes<[V1UnitL01, V1UnitS]>;
-let Latency = 2, NumMicroOps = 2 in
-def V1Write_2c_1L01_1V   : SchedWriteRes<[V1UnitL01, V1UnitV]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_1L01_1V   : SchedWriteRes<[V1UnitL01, V1UnitV]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_1L01_1V   : SchedWriteRes<[V1UnitL01, V1UnitV]>;
-let Latency = 2, NumMicroOps = 2 in
-def V1Write_2c_1L01_1V01 : SchedWriteRes<[V1UnitL01, V1UnitV01]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_1L01_1V01 : SchedWriteRes<[V1UnitL01, V1UnitV01]>;
-let Latency = 2, NumMicroOps = 2 in
-def V1Write_2c_2M0       : SchedWriteRes<[V1UnitM0, V1UnitM0]>;
-let Latency = 3, NumMicroOps = 2 in
-def V1Write_3c_2M0       : SchedWriteRes<[V1UnitM0, V1UnitM0]>;
-let Latency = 9, NumMicroOps = 2 in
-def V1Write_9c_1M0_1L    : SchedWriteRes<[V1UnitM0, V1UnitL]>;
-let Latency = 5, NumMicroOps = 2 in
-def V1Write_5c_1M0_1V    : SchedWriteRes<[V1UnitM0, V1UnitV]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_1M0_1V0    : SchedWriteRes<[V1UnitM0, V1UnitV0]>;
-let Latency = 7, NumMicroOps = 2 in
-def V1Write_7c_1M0_1V0   : SchedWriteRes<[V1UnitM0, V1UnitV1]>;
-let Latency = 5, NumMicroOps = 2 in
-def V1Write_5c_1M0_1V01    : SchedWriteRes<[V1UnitM0, V1UnitV01]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_1M0_1V1   : SchedWriteRes<[V1UnitM0, V1UnitV1]>;
-let Latency = 9, NumMicroOps = 2 in
-def V1Write_9c_1M0_1V1    : SchedWriteRes<[V1UnitM0, V1UnitV1]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_2V        : SchedWriteRes<[V1UnitV, V1UnitV]>;
-let Latency = 8, NumMicroOps = 2 in
-def V1Write_8c_1V_1V01   : SchedWriteRes<[V1UnitV, V1UnitV01]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_2V0       : SchedWriteRes<[V1UnitV0, V1UnitV0]>;
-let Latency = 5, NumMicroOps = 2 in
-def V1Write_5c_2V0       : SchedWriteRes<[V1UnitV0, V1UnitV0]>;
-let Latency = 2, NumMicroOps = 2 in
-def V1Write_2c_2V01      : SchedWriteRes<[V1UnitV01, V1UnitV01]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_2V01      : SchedWriteRes<[V1UnitV01, V1UnitV01]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_2V02      : SchedWriteRes<[V1UnitV02, V1UnitV02]>;
-let Latency = 6, NumMicroOps = 2 in
-def V1Write_6c_2V02      : SchedWriteRes<[V1UnitV02, V1UnitV02]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_1V13_1V   : SchedWriteRes<[V1UnitV13, V1UnitV]>;
-let Latency = 4, NumMicroOps = 2 in
-def V1Write_4c_2V13      : SchedWriteRes<[V1UnitV13, V1UnitV13]>;
+def V1Write_1c_1B_1S	 : SchedWriteRes<[V1UnitB, V1UnitS]> {
+    let Latency = 1;
+    let NumMicroOps = 2;
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 3 micro-op types
+def V1Write_6c_1B_1M0	 : SchedWriteRes<[V1UnitB, V1UnitM0]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+}
 
-let Latency = 2, NumMicroOps = 3 in
-def V1Write_2c_1I_1L01_1V01 : SchedWriteRes<[V1UnitI, V1UnitL01, V1UnitV01]>;
-let Latency = 7, NumMicroOps = 3 in
-def V1Write_7c_2M0_1V01     : SchedWriteRes<[V1UnitM0, V1UnitM0, V1UnitV01]>;
-let Latency = 8, NumMicroOps = 3 in
-def V1Write_8c_1L_2V        : SchedWriteRes<[V1UnitL, V1UnitV, V1UnitV]>;
-let Latency = 6, NumMicroOps = 3 in
-def V1Write_6c_3L           : SchedWriteRes<[V1UnitL, V1UnitL, V1UnitL]>;
-let Latency = 2, NumMicroOps = 3 in
-def V1Write_2c_1L01_1S_1V   : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV]>;
-let Latency = 4, NumMicroOps = 3 in
-def V1Write_4c_1L01_1S_1V   : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV]>;
-let Latency = 2, NumMicroOps = 3 in
-def V1Write_2c_2L01_1V01    : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitV01]>;
-let Latency = 6, NumMicroOps = 3 in
-def V1Write_6c_3V           : SchedWriteRes<[V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 4, NumMicroOps = 3 in
-def V1Write_4c_3V01         : SchedWriteRes<[V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 6, NumMicroOps = 3 in
-def V1Write_6c_3V01         : SchedWriteRes<[V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 8, NumMicroOps = 3 in
-def V1Write_8c_3V01         : SchedWriteRes<[V1UnitV01, V1UnitV01, V1UnitV01]>;
+def V1Write_5c_1I_1L	 : SchedWriteRes<[V1UnitI, V1UnitL]> {
+    let Latency = 5;
+    let NumMicroOps = 2;
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 4 micro-op types
-
-let Latency = 8, NumMicroOps = 4 in
-def V1Write_8c_2M0_2V0   : SchedWriteRes<[V1UnitM0, V1UnitM0,
-                                          V1UnitV0, V1UnitV0]>;
-let Latency = 7, NumMicroOps = 4 in
-def V1Write_7c_4L        : SchedWriteRes<[V1UnitL, V1UnitL, V1UnitL, V1UnitL]>;
-let Latency = 8, NumMicroOps = 4 in
-def V1Write_8c_2L_2V        : SchedWriteRes<[V1UnitL, V1UnitL,
-                                             V1UnitV, V1UnitV]>;
-let Latency = 9, NumMicroOps = 4 in
-def V1Write_9c_2L_2V        : SchedWriteRes<[V1UnitL, V1UnitL,
-                                             V1UnitV, V1UnitV]>;
-let Latency = 11, NumMicroOps = 4 in
-def V1Write_11c_2L_2V       : SchedWriteRes<[V1UnitL, V1UnitL,
-                                             V1UnitV, V1UnitV]>;
-let Latency = 10, NumMicroOps = 4 in
-def V1Write_10c_2L01_2V     : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                             V1UnitV, V1UnitV]>;
-let Latency = 2, NumMicroOps = 4 in
-def V1Write_2c_2L01_2V01    : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                             V1UnitV01, V1UnitV01]>;
-let Latency = 4, NumMicroOps = 4 in
-def V1Write_4c_2L01_2V01    : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                             V1UnitV01, V1UnitV01]>;
-let Latency = 8, NumMicroOps = 4 in
-def V1Write_8c_2L01_2V01    : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                             V1UnitV01, V1UnitV01]>;
-let Latency = 9, NumMicroOps = 4 in
-def V1Write_9c_2L01_2V01    : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                             V1UnitV01, V1UnitV01]>;
-let Latency = 10, NumMicroOps = 4 in
-def V1Write_10c_2L01_2V01   : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                             V1UnitV01, V1UnitV01]>;
-let Latency = 10, NumMicroOps = 4 in
-def V1Write_10c_1V_1V01_2V1 : SchedWriteRes<[V1UnitV, V1UnitV01,
-                                             V1UnitV1, V1UnitV1]>;
-let Latency = 12, NumMicroOps = 4 in
-def V1Write_12c_1V_1V01_2V1 : SchedWriteRes<[V1UnitV, V1UnitV01,
-                                             V1UnitV1, V1UnitV1]>;
-let Latency = 6, NumMicroOps = 4 in
-def V1Write_6c_4V0          : SchedWriteRes<[V1UnitV0, V1UnitV0,
-                                             V1UnitV0, V1UnitV0]>;
-let Latency = 12, NumMicroOps = 4 in
-def V1Write_12c_4V01        : SchedWriteRes<[V1UnitV01, V1UnitV01,
-                                             V1UnitV01, V1UnitV01]>;
-let Latency = 6, NumMicroOps = 4 in
-def V1Write_6c_4V02         : SchedWriteRes<[V1UnitV02, V1UnitV02]>;
+def V1Write_5c3_1I_1L	  : SchedWriteRes<[V1UnitI, V1UnitL]> {
+    let Latency = 5;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [1,3];
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 5 micro-op types
-
-let Latency = 8, NumMicroOps = 5 in
-def V1Write_8c_2L_3V            : SchedWriteRes<[V1UnitL, V1UnitL,
-                                                 V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 14, NumMicroOps = 5 in
-def V1Write_14c_1V_1V0_2V1_1V13 : SchedWriteRes<[V1UnitV,
-                                                 V1UnitV0,
-                                                 V1UnitV1, V1UnitV1,
-                                                 V1UnitV13]>;
-let Latency = 9, NumMicroOps = 5 in
-def V1Write_9c_1V_4V01          : SchedWriteRes<[V1UnitV,
-                                                 V1UnitV01, V1UnitV01,
-                                                 V1UnitV01, V1UnitV01]>;
-let Latency = 6, NumMicroOps = 5 in
-def V1Write_6c_5V01             : SchedWriteRes<[V1UnitV01, V1UnitV01,
-                                                 V1UnitV01, V1UnitV01, V1UnitV01]>;
+def V1Write_7c_1I_1L	 : SchedWriteRes<[V1UnitI, V1UnitL]> {
+    let Latency = 7;
+    let NumMicroOps = 2;
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 6 micro-op types
-
-let Latency = 6, NumMicroOps = 6 in
-def V1Write_6c_3L_3V      : SchedWriteRes<[V1UnitL, V1UnitL, V1UnitL,
-                                           V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 8, NumMicroOps = 6 in
-def V1Write_8c_3L_3V      : SchedWriteRes<[V1UnitL, V1UnitL, V1UnitL,
-                                           V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 2, NumMicroOps = 6 in
-def V1Write_2c_3L01_3V01  : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 5, NumMicroOps = 6 in
-def V1Write_5c_3L01_3V01  : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 6, NumMicroOps = 6 in
-def V1Write_6c_3L01_3V01  : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 11, NumMicroOps = 6 in
-def V1Write_11c_3L01_3V01 : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 11, NumMicroOps = 6 in
-def V1Write_11c_1V_5V01   : SchedWriteRes<[V1UnitV,
-                                           V1UnitV01, V1UnitV01,
-                                           V1UnitV01, V1UnitV01, V1UnitV01]>;
-let Latency = 13, NumMicroOps = 6 in
-def V1Write_13c_6V01      : SchedWriteRes<[V1UnitV01, V1UnitV01, V1UnitV01,
-                                           V1UnitV01, V1UnitV01, V1UnitV01]>;
+def V1Write_6c_1L_1M	     : SchedWriteRes<[V1UnitL, V1UnitM]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 7 micro-op types
+def V1Write_8c_1L_1V	     : SchedWriteRes<[V1UnitL, V1UnitV]> {
+    let Latency = 8;
+    let NumMicroOps = 2;
+}
 
-let Latency = 8, NumMicroOps = 7 in
-def V1Write_8c_3L_4V         : SchedWriteRes<[V1UnitL, V1UnitL, V1UnitL,
-                                              V1UnitV, V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 8, NumMicroOps = 7 in
-def V1Write_13c_3L01_1S_3V01 : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                              V1UnitS,
-                                              V1UnitV01, V1UnitV01, V1UnitV01]>;
+def V1Write_9c2_1L01_1V01    : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 9;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 8 micro-op types
-
-let Latency = 9, NumMicroOps = 8 in
-def V1Write_9c_4L_4V      : SchedWriteRes<[V1UnitL, V1UnitL,
-                                           V1UnitL, V1UnitL,
-                                           V1UnitV, V1UnitV,
-                                           V1UnitV, V1UnitV]>;
-let Latency = 2, NumMicroOps = 8 in
-def V1Write_2c_4L01_4V01  : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                           V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01,
-                                           V1UnitV01, V1UnitV01]>;
-let Latency = 4, NumMicroOps = 8 in
-def V1Write_4c_4L01_4V01  : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                           V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01,
-                                           V1UnitV01, V1UnitV01]>;
-let Latency = 12, NumMicroOps = 8 in
-def V1Write_12c_4L01_4V01 : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                           V1UnitL01, V1UnitL01,
-                                           V1UnitV01, V1UnitV01,
-                                           V1UnitV01, V1UnitV01]>;
+def V1Write_9c6_1L_1V	     : SchedWriteRes<[V1UnitL, V1UnitV]> {
+    let Latency = 9;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [6, 6];
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 10 micro-op types
-
-let Latency = 13, NumMicroOps = 10 in
-def V1Write_13c_4L01_2S_4V01 : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                              V1UnitL01, V1UnitL01,
-                                              V1UnitS, V1UnitS,
-                                              V1UnitV01, V1UnitV01,
-                                              V1UnitV01, V1UnitV01]>;
-let Latency = 7, NumMicroOps = 10 in
-def V1Write_7c_5L01_5V       : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                              V1UnitL01, V1UnitL01, V1UnitL01,
-                                              V1UnitV, V1UnitV,
-                                              V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 11, NumMicroOps = 10 in
-def V1Write_11c_10V0         : SchedWriteRes<[V1UnitV0,
-                                              V1UnitV0, V1UnitV0, V1UnitV0,
-                                              V1UnitV0, V1UnitV0, V1UnitV0,
-                                              V1UnitV0, V1UnitV0, V1UnitV0]>;
+def V1Write_11c12_1L_1V	     : SchedWriteRes<[V1UnitL, V1UnitV]> {
+    let Latency = 11;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [12, 12];
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 12 micro-op types
+def V1Write_1c_1L01_1D	     : SchedWriteRes<[V1UnitL01, V1UnitD]> {
+    let Latency = 1;
+    let NumMicroOps = 2;
+}
 
-let Latency = 7, NumMicroOps = 12 in
-def V1Write_7c_6L01_6V01 : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                          V1UnitL01, V1UnitL01, V1UnitL01,
-                                          V1UnitV01, V1UnitV01, V1UnitV01,
-                                          V1UnitV01, V1UnitV01, V1UnitV01]>;
+def V1Write_6c_1L01_1S	     : SchedWriteRes<[V1UnitL01, V1UnitS]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 15 micro-op types
+def V1Write_7c_1L01_1S	     : SchedWriteRes<[V1UnitL01, V1UnitS]> {
+    let Latency = 7;
+    let NumMicroOps = 2;
+}
 
-let Latency = 7, NumMicroOps = 15 in
-def V1Write_7c_5L01_5S_5V : SchedWriteRes<[V1UnitL01, V1UnitL01,
-                                           V1UnitL01, V1UnitL01, V1UnitL01,
-                                           V1UnitS, V1UnitS,
-                                           V1UnitS, V1UnitS, V1UnitS,
-                                           V1UnitV, V1UnitV,
-                                           V1UnitV, V1UnitV, V1UnitV]>;
+def V1Write_2c_1L01_1V	     : SchedWriteRes<[V1UnitL01, V1UnitV]> {
+    let Latency = 2;
+    let NumMicroOps = 2;
+}
 
+def V1Write_4c2_1L01_1V	      : SchedWriteRes<[V1UnitL01, V1UnitV]> {
+    let Latency = 4;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_6c4_1L01_1V	      : SchedWriteRes<[V1UnitL01, V1UnitV]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [4,4];
+}
+
+def V1Write_7c9_1L01_1V       : SchedWriteRes<[V1UnitL01, V1UnitV]> {
+    let Latency = 7;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [9,9];
+}
+
+def V1Write_11c18_1L01_1V : SchedWriteRes<[V1UnitL01, V1UnitV]> {
+    let Latency = 11;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [18,18];
+}
+
+def V1Write_2c_1L01_1V01     : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 2;
+    let NumMicroOps = 2;
+}
+
+def V1Write_2c2_1L01_1V01    : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 2;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_2c3_1L01_1V01  : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 2;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [3,3];
+}
+
+def V1Write_2c4_1L01_1V01  : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 2;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [4,4];
+}
+
+def V1Write_4c_1L01_1V01     : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 4;
+    let NumMicroOps = 2;
+}
+
+def V1Write_4c2_1L01_1V01    : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 4;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_4c8_1L01_1V01  : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 4;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [8,8];
+}
+
+def V1Write_5c3_1L01_1V01    : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 5;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [3,3];
+}
+
+def V1Write_6c6_1L01_1V01  : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [6,6];
+}
+
+def V1Write_7c12_1L01_1V01 : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 7;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [12,12];
+}
+
+def V1Write_9c_1M0_1L	     : SchedWriteRes<[V1UnitM0, V1UnitL]> {
+    let Latency = 9;
+    let NumMicroOps = 2;
+}
+
+def V1Write_5c_1M0_1V	     : SchedWriteRes<[V1UnitM0, V1UnitV]> {
+    let Latency = 5;
+    let NumMicroOps = 2;
+}
+
+def V1Write_4c_1M0_1V0	  : SchedWriteRes<[V1UnitM0, V1UnitV0]> {
+    let Latency = 4;
+    let NumMicroOps = 2;
+}
+
+def V1Write_7c_1M0_1V0	 : SchedWriteRes<[V1UnitM0, V1UnitV0]> {
+    let Latency = 7;
+    let NumMicroOps = 2;
+}
+
+def V1Write_8c2_1M0_1V0	  : SchedWriteRes<[V1UnitM0, V1UnitV0]> {
+    let Latency = 8;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_5c_1M0_1V01	   : SchedWriteRes<[V1UnitM0, V1UnitV01]> {
+    let Latency = 5;
+    let NumMicroOps = 2;
+}
+
+def V1Write_7c2_1M0_1V01     : SchedWriteRes<[V1UnitM0, V1UnitV01]> {
+    let Latency = 7;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_6c_1M0_1V1	 : SchedWriteRes<[V1UnitM0, V1UnitV1]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+}
+
+def V1Write_9c_1M0_1V1	  : SchedWriteRes<[V1UnitM0, V1UnitV1]> {
+    let Latency = 9;
+    let NumMicroOps = 2;
+}
+
+def V1Write_4c2_1V0	  : SchedWriteRes<[V1UnitV0]> {
+    let Latency = 4;
+    let NumMicroOps = 1;
+    let ReleaseAtCycles = [2];
+}
+
+def V1Write_8c2_2L01_2V01    : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 8;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2, 2];
+}
+
+def V1Write_8c2_1L_1V	     : SchedWriteRes<[V1UnitL, V1UnitV]> {
+    let Latency = 8;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_8c3_1L_1V	     : SchedWriteRes<[V1UnitL, V1UnitV]> {
+    let Latency = 8;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [3,3];
+}
+
+def V1Write_10c8_1L01_1V     : SchedWriteRes<[V1UnitL01, V1UnitV]> {
+    let Latency = 10;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [8,8];
+}
+
+def V1Write_6c2_1L01_1V01    : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 6;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [2,2];
+}
+
+def V1Write_11c6_1L01_1V01 : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 11;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [6,6];
+}
+
+def V1Write_12c8_1L01_1V01 : SchedWriteRes<[V1UnitL01, V1UnitV01]> {
+    let Latency = 12;
+    let NumMicroOps = 2;
+    let ReleaseAtCycles = [8,8];
+}
 
-//===----------------------------------------------------------------------===//
-// Define generic 18 micro-op types
-
-let Latency = 19, NumMicroOps = 18 in
-def V1Write_11c_9L01_9V : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                         V1UnitL01, V1UnitL01, V1UnitL01, 
-                                         V1UnitL01, V1UnitL01, V1UnitL01,
-                                         V1UnitV, V1UnitV, V1UnitV, 
-                                         V1UnitV, V1UnitV, V1UnitV,
-                                         V1UnitV, V1UnitV, V1UnitV]>;
-let Latency = 19, NumMicroOps = 18 in
-def V1Write_19c_18V0    : SchedWriteRes<[V1UnitV0, V1UnitV0, V1UnitV0,
-                                         V1UnitV0, V1UnitV0, V1UnitV0, 
-                                         V1UnitV0, V1UnitV0, V1UnitV0,
-                                         V1UnitV0, V1UnitV0, V1UnitV0, 
-                                         V1UnitV0, V1UnitV0, V1UnitV0,
-                                         V1UnitV0, V1UnitV0, V1UnitV0]>;
 
 //===----------------------------------------------------------------------===//
-// Define generic 27 micro-op types
-
-let Latency = 11, NumMicroOps = 27 in
-def V1Write_11c_9L01_9S_9V : SchedWriteRes<[V1UnitL01, V1UnitL01, V1UnitL01,
-                                            V1UnitL01, V1UnitL01, V1UnitL01, 
-                                            V1UnitL01, V1UnitL01, V1UnitL01,
-                                            V1UnitS, V1UnitS, V1UnitS, 
-                                            V1UnitS, V1UnitS, V1UnitS,
-                                            V1UnitS, V1UnitS, V1UnitS,
-                                            V1UnitV, V1UnitV, V1UnitV, 
-                                            V1UnitV, V1UnitV, V1UnitV,
-                                            V1UnitV, V1UnitV, V1UnitV]>;
+// Define generic 3 micro-op types
+
+def V1Write_2c_1I_1L01_1D : SchedWriteRes<[V1UnitI, V1UnitL01, V1UnitD]> {
+    let Latency = 2;
+    let NumMicroOps = 3;
+}
+
+def V1Write_2c_1I_1L01_1V01 : SchedWriteRes<[V1UnitI, V1UnitL01, V1UnitV01]> {
+    let Latency = 2;
+    let NumMicroOps = 3;
+}
+
+def V1Write_2c_1L01_1S_1V   : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV]> {
+    let Latency = 2;
+    let NumMicroOps = 3;
+}
+
+def V1Write_4c_1L01_1S_1V   : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV]> {
+    let Latency = 4;
+    let NumMicroOps = 3;
+    let ReleaseAtCycles = [2,2,2];
+}
+
+def V1Write_7c9_1L01_1S_1V : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV]> {
+    let Latency = 7;
+    let NumMicroOps = 3;
+    let ReleaseAtCycles = [9,9,9];
+}
+
+def V1Write_11c18_1L01_1S_1V : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV]> {
+    let Latency = 11;
+    let NumMicroOps = 3;
+    let ReleaseAtCycles = [18,18,18];
+}
+
+def V1Write_10c2_1L01_1V01_1S : SchedWriteRes<[V1UnitL01, V1UnitV01, V1UnitS]> {
+    let Latency = 10;
+    let NumMicroOps = 3;
+    let ReleaseAtCycles = [2,2,2];
+}
+
+def V1Write_13c6_1L01_1S_1V01 : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV01]> {
+    let Latency = 13;
+    let NumMicroOps = 3;
+    let ReleaseAtCycles = [6,6,6];
+}
+
+def V1Write_13c8_1L01_1S_1V01 : SchedWriteRes<[V1UnitL01, V1UnitS, V1UnitV01]> {
+    let Latency = 13;
+    let NumMicroOps = 3;
+    let ReleaseAtCycles = [8,8,8];
+}
 
 //===----------------------------------------------------------------------===//
 // Define forwarded types
@@ -528,7 +603,7 @@ def V1Rd_CRC : SchedReadAdvance<1, [V1Wr_CRC]>;
 def V1Wr_ZDOTB : SchedWriteRes<[V1UnitV01]> { let Latency = 3; }
 def V1Rd_ZDOTB : SchedReadAdvance<2, [V1Wr_ZDOTB]>;
 
-def V1Wr_ZUDOTB : SchedWriteRes<[V1UnitV]> { let Latency = 3; }
+def V1Wr_ZUDOTB : SchedWriteRes<[V1UnitV]> { let Latency = 3; let ReleaseAtCycles = [2]; }
 def V1Rd_ZUDOTB : SchedReadAdvance<2, [V1Wr_ZUDOTB]>;
 
 def V1Wr_ZDOTH : SchedWriteRes<[V1UnitV0]> { let Latency = 4; }
@@ -537,7 +612,10 @@ def V1Rd_ZDOTH : SchedReadAdvance<3, [V1Wr_ZDOTH]>;
 def V1Wr_ZMMA : SchedWriteRes<[V1UnitV01]> { let Latency = 3; }
 def V1Rd_ZMMA : SchedReadAdvance<2, [V1Wr_ZMMA]>;
 
-let Latency = 5, NumMicroOps = 2 in
+def V1Wr_ZMABHS	       : SchedWriteRes<[V1UnitV0]> { let Latency = 4; }
+def V1Rd_ZMABHS	       : SchedReadAdvance<2, [V1Wr_ZMABHS]>;
+
+let Latency = 5, NumMicroOps = 1 in
 def V1Wr_ZMAD : SchedWriteRes<[V1UnitV0, V1UnitV0]>;
 def V1Rd_ZMAD : SchedReadAdvance<3, [V1Wr_ZMAD]>;
 
@@ -597,13 +675,19 @@ def : SchedAlias<WriteI, V1Write_1c_1I>;
 
 // ALU, basic, flagset
 def : InstRW<[V1Write_1c_1I_1Flg],
-             (instregex "^(ADD|SUB)S[WX]r[ir]$",
+             (instregex "^(ADD|SUB)S[WX]rr$",
                         "^(ADC|SBC)S[WX]r$",
                         "^ANDS[WX]ri$",
                         "^(AND|BIC)S[WX]rr$")>;
 
+// ALU, basic, no flagset
 // ALU, extend and shift
-def : SchedAlias<WriteIEReg, V1Write_2c_1M>;
+def V1WriteIEReg : SchedWriteVariant<
+		 [SchedVar<RegExtendAndShiftPred, [V1Write_2c_1M]>,
+		  SchedVar<NoSchedPred,		  [V1Write_1c_1I]>]>;
+def : SchedAlias<WriteIEReg, V1WriteIEReg>;
+def : InstRW<[V1WriteIEReg],
+	     (instregex "^(ADD|SUB)[WX]rx$")>;
 
 // Arithmetic, LSL shift, shift <= 4
 // Arithmetic, LSR/ASR/ROR shift or LSL shift > 4
@@ -612,19 +696,33 @@ def V1WriteISReg : SchedWriteVariant<
                       SchedVar<NoSchedPred, [V1Write_2c_1M]>]>;
 def              : SchedAlias<WriteISReg, V1WriteISReg>;
 
+// ALU, basic, no flagset
+// ALU, extend and shift
+def V1WriteIERegS : SchedWriteVariant<
+		 [SchedVar<RegExtendAndShiftPred, [V1Write_2c_1M_1Flg]>,
+		  SchedVar<NoSchedPred,		  [V1Write_1c_1I_1Flg]>]>;
+def : InstRW<[V1WriteIERegS],
+	     (instregex "^(ADD|SUB)S([WX]rx|Xrx64)$")>;
+
 // Arithmetic, flagset, LSL shift, shift <= 4
 // Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4
 def V1WriteISRegS : SchedWriteVariant<
                       [SchedVar<IsCheapLSL,  [V1Write_1c_1I_1Flg]>,
                        SchedVar<NoSchedPred, [V1Write_2c_1M_1Flg]>]>;
 def               : InstRW<[V1WriteISRegS],
-                           (instregex "^(ADD|SUB)S(([WX]r[sx])|Xrx64)$")>;
+			   (instregex "^(ADD|SUB)S(([WX]rs)|([WX]ri))$")>;
 
 // Logical, shift, no flagset
 def : InstRW<[V1Write_1c_1I], (instregex "^(AND|BIC|EON|EOR|ORN|ORR)[WX]rs$")>;
 
-// Logical, shift, flagset
-def : InstRW<[V1Write_2c_1M_1Flg], (instregex "^(AND|BIC)S[WX]rs$")>;
+// AArch64: ALU, basic, flagset
+// AArch64: Logical, shift, flagset
+// AArch32: ALU, basic, unconditional, flagset
+// AArch32: Logical, shift by immed, flagset, unconditional
+def V1WriteLogSRegS : SchedWriteVariant<
+		      [SchedVar<hasShiftedOpndPred, [V1Write_2c_1M_1Flg]>,
+		       SchedVar<NoSchedPred,	    [V1Write_1c_1I_1Flg]>]>;
+def : InstRW<[V1WriteLogSRegS], (instregex "^(AND|BIC)S[XW]rs$")>;
 
 // Flag manipulation instructions
 def : InstRW<[V1Write_1c_1I_1Flg], (instrs SETF8, SETF16, RMIF, CFINV)>;
@@ -634,11 +732,11 @@ def : InstRW<[V1Write_1c_1I_1Flg], (instrs SETF8, SETF16, RMIF, CFINV)>;
 // -----------------------------------------------------------------------------
 
 // Divide
-def : SchedAlias<WriteID32, V1Write_12c5_1M0>;
-def : SchedAlias<WriteID64, V1Write_20c5_1M0>;
+def : SchedAlias<WriteID32, V1Write_12c12_1M0>;
+def : SchedAlias<WriteID64, V1Write_20c20_1M0>;
 
-def : SchedAlias<WriteIM32, V1Write_2c_1M>;
-def : SchedAlias<WriteIM64, V1Write_2c_1M>;
+def : SchedAlias<WriteIM32, V1Write_2c_1M0>;
+def : SchedAlias<WriteIM64, V1Write_2c_1M0>;
 
 // Multiply
 // Multiply accumulate, W-form
@@ -685,7 +783,7 @@ def : InstRW<[V1Write_2c_1M0], (instrs XPACD, XPACI, XPACLRI)>;
 // Bitfield extract, two regs
 def V1WriteExtr : SchedWriteVariant<
                     [SchedVar<IsRORImmIdiomPred, [V1Write_1c_1I]>,
-                     SchedVar<NoSchedPred,       [V1Write_3c_1I_1M]>]>;
+		     SchedVar<NoSchedPred,	 [V1Write_3c_1M]>]>;
 def : SchedAlias<WriteExtr, V1WriteExtr>;
 
 // Bitfield move, basic
@@ -709,18 +807,27 @@ def : SchedAlias<WriteLD, V1Write_4c_1L>;
 def : SchedAlias<WriteLDIdx, V1Write_4c_1L>;
 def : SchedAlias<WriteAdr,   V1Write_1c_1I>;
 
+// Load register, register offset, extend, scale by 2
+// Load register, register offset, extend
+def V1WriteLDRH : SchedWriteVariant<[
+  SchedVar<NeoverseScaledIdxPred, [V1Write_5c_1I_1L]>,
+  SchedVar<NoSchedPred,	  [V1Write_4c_1L]>]>;
+def : InstRW<[V1WriteLDRH, ReadAdrBase], (instregex "^LDRS?H[HWX]ro[WX]$")>;
+
 // Load pair, immed offset
 def : SchedAlias<WriteLDHi, V1Write_4c_1L>;
 def : InstRW<[V1Write_4c_1L, V1Write_0c_0Z], (instrs LDPWi, LDNPWi)>;
+def : InstRW<[V1Write_4c3_1L, V1Write_0c_0Z], (instrs LDPXi, LDNPXi)>;
 def : InstRW<[WriteAdr, V1Write_4c_1L, V1Write_0c_0Z],
              (instrs LDPWpost, LDPWpre)>;
+def : InstRW<[WriteAdr, V1Write_4c3_1L, V1Write_0c_0Z],
+	     (instrs LDPXpost, LDPXpre)>;
 
 // Load pair, signed immed offset, signed words
-def : InstRW<[V1Write_5c_1I_1L, V1Write_0c_0Z], (instrs LDPSWi)>;
+def : InstRW<[V1Write_5c3_1I_1L, V1Write_0c_0Z], (instrs LDPSWi)>;
 
 // Load pair, immed post or pre-index, signed words
-def : InstRW<[WriteAdr, V1Write_5c_1I_1L, V1Write_0c_0Z],
-             (instrs LDPSWpost, LDPSWpre)>;
+def : InstRW<[WriteAdr, V1Write_5c3_1L, V1Write_0c_0Z], (instrs LDPSWpost, LDPSWpre)>;
 
 
 // Store instructions
@@ -729,12 +836,22 @@ def : InstRW<[WriteAdr, V1Write_5c_1I_1L, V1Write_0c_0Z],
 // Store register, immed offset
 def : SchedAlias<WriteST, V1Write_1c_1L01_1D>;
 
+// Store register, immed post-index
+// Store register, immed pre-index
+def : InstRW<[V1Write_1c_1L01_1D], (instrs STRXpost, STRXpre)>;
+
 // Store register, immed offset, index
 def : SchedAlias<WriteSTIdx, V1Write_1c_1L01_1D>;
 
 // Store pair, immed offset
 def : SchedAlias<WriteSTP, V1Write_1c_1L01_1D>;
 
+def V1WriteSTRH : SchedWriteVariant<[
+  SchedVar<NeoverseScaledIdxPred, [V1Write_2c_1I_1L01_1D]>,
+  SchedVar<NoSchedPred,	  [V1Write_1c_1L01_1D]>]>;
+def : InstRW<[V1WriteSTRH, ReadAdrBase],
+	       (instregex "^STRHHro[XW]$")>;
+
 
 // FP data processing instructions
 // -----------------------------------------------------------------------------
@@ -750,21 +867,23 @@ def : SchedAlias<WriteFCmp, V1Write_2c_1V0>;
 
 // FP divide
 // FP square root
-def : SchedAlias<WriteFDiv, V1Write_10c7_1V02>;
+def : SchedAlias<WriteFDiv, V1Write_10c5_1V02>;
 
 // FP divide, H-form
 // FP square root, H-form
-def : InstRW<[V1Write_7c7_1V02], (instrs FDIVHrr, FSQRTHr)>;
+def : InstRW<[V1Write_7c2_1V02], (instrs FDIVHrr, FSQRTHr)>;
 
 // FP divide, S-form
+def : InstRW<[V1Write_10c3_1V02], (instrs FDIVSrr)>;
+
 // FP square root, S-form
-def : InstRW<[V1Write_10c7_1V02], (instrs FDIVSrr, FSQRTSr)>;
+def : InstRW<[V1Write_9c3_1V02], (instrs FSQRTSr)>;
 
 // FP divide, D-form
 def : InstRW<[V1Write_15c7_1V02], (instrs FDIVDrr)>;
 
 // FP square root, D-form
-def : InstRW<[V1Write_16c7_1V02], (instrs FSQRTDr)>;
+def : InstRW<[V1Write_16c8_1V02], (instrs FSQRTDr)>;
 
 // FP multiply
 def : WriteRes<WriteFMul, [V1UnitV]> { let Latency = 3; }
@@ -788,7 +907,7 @@ def : InstRW<[V1Write_2c_1V01], (instregex "^FCSEL[HSD]rrr$")>;
 def : InstRW<[V1Write_3c_1M0], (instregex "^[SU]CVTF[SU][WX][HSD]ri$")>;
 
 // FP convert, from vec to gen reg
-def : InstRW<[V1Write_3c_1V0], (instregex "^FCVT[AMNPZ][SU][SU][WX][HSD]r$")>;
+def : InstRW<[V1Write_3c_1V0], (instregex "^FCVT[AMNPZ][SU][SU][WX][HSD]ri?$")>;
 
 // FP convert, Javascript from vec to gen reg
 def : InstRW<[V1Write_3c_1V0], (instrs FJCVTZS)>;
@@ -835,13 +954,17 @@ def : InstRW<[V1Write_6c_1L, ReadAdrBase], (instregex "^LDR[BSD]ro[WX]$")>;
 
 // Load vector reg, register offset, scale, H/Q-form
 // Load vector reg, register offset, extend, scale, H/Q-form
-def : InstRW<[V1Write_7c_1I_1L, ReadAdrBase], (instregex "^LDR[HQ]ro[WX]$")>;
+def V1WriteLDRV : SchedWriteVariant<[
+  SchedVar<NeoverseScaledIdxPred, [V1Write_7c_1I_1L]>,
+  SchedVar<NoSchedPred,	  [V1Write_6c_1L]>]>;
+
+def : InstRW<[V1WriteLDRV, ReadAdrBase], (instregex "^LDR[HQ]ro[WX]$")>;
 
 // Load vector pair, immed offset, S/D-form
 def : InstRW<[V1Write_6c_1L, V1Write_0c_0Z], (instregex "^LDN?P[SD]i$")>;
 
 // Load vector pair, immed offset, Q-form
-def : InstRW<[V1Write_6c_1L, WriteLDHi], (instrs LDPQi, LDNPQi)>;
+def : InstRW<[V1Write_6c2_1L, V1Write_0c_0Z], (instrs LDPQi, LDNPQi)>;
 
 // Load vector pair, immed post-index, S/D-form
 // Load vector pair, immed pre-index, S/D-form
@@ -850,7 +973,7 @@ def : InstRW<[WriteAdr, V1Write_6c_1L, V1Write_0c_0Z],
 
 // Load vector pair, immed post-index, Q-form
 // Load vector pair, immed pre-index, Q-form
-def : InstRW<[WriteAdr, V1Write_6c_1L, WriteLDHi],
+def : InstRW<[WriteAdr, V1Write_6c2_1L, V1Write_0c_0Z],
              (instrs LDPQpost, LDPQpre)>;
 
 
@@ -862,25 +985,26 @@ def : InstRW<[V1Write_2c_1L01_1V01], (instregex "^STUR[BHSDQ]i$")>;
 
 // Store vector reg, immed post-index, B/H/S/D/Q-form
 // Store vector reg, immed pre-index, B/H/S/D/Q-form
-def : InstRW<[WriteAdr, V1Write_2c_1L01_1V01],
+def : InstRW<[V1Write_2c_1L01_1V01],
              (instregex "^STR[BHSDQ](pre|post)$")>;
 
 // Store vector reg, unsigned immed, B/H/S/D/Q-form
 def : InstRW<[V1Write_2c_1L01_1V01], (instregex "^STR[BHSDQ]ui$")>;
 
-// Store vector reg, register offset, basic, B/S/D-form
-// Store vector reg, register offset, scale, B/S/D-form
-// Store vector reg, register offset, extend, B/S/D-form
-// Store vector reg, register offset, extend, scale, B/S/D-form
+// Store vector reg, register offset, extend, B/H/S/D-form
+// Store vector reg, register offset, extend, Q-form
+// Store vector reg, register offset, extend, scale, H-form
+// Store vector reg, register offset, extend, scale, Q-form
+def V1WriteSTRV : SchedWriteVariant<[
+  SchedVar<NeoverseScaledIdxPred, [V1Write_2c_1I_1L01_1V01]>,
+  SchedVar<NoSchedPred,	  [V1Write_2c_1L01_1V01]>]>;
+def : InstRW<[V1WriteSTRV, ReadAdrBase],
+	       (instregex "^STR[BHQ]ro[XW]$")>;
+
+// Store vector reg, register offset, extend, scale, S/D-form
+// Store vector reg, register offset, scale, S/D-form
 def : InstRW<[V1Write_2c_1L01_1V01, ReadAdrBase],
-             (instregex "^STR[BSD]ro[WX]$")>;
-
-// Store vector reg, register offset, basic, H/Q-form
-// Store vector reg, register offset, scale, H/Q-form
-// Store vector reg, register offset, extend, H/Q-form
-// Store vector reg, register offset, extend, scale, H/Q-form
-def : InstRW<[V1Write_2c_1I_1L01_1V01, ReadAdrBase],
-             (instregex "^STR[HQ]ro[WX]$")>;
+	       (instregex "^STR[DS]ro[XW]$")>;
 
 // Store vector pair, immed offset, S/D/Q-form
 def : InstRW<[V1Write_2c_1L01_1V01], (instregex "^STN?P[SDQ]i$")>;
@@ -892,7 +1016,7 @@ def : InstRW<[WriteAdr, V1Write_2c_1L01_1V01],
 
 // Store vector pair, immed post-index, Q-form
 // Store vector pair, immed pre-index, Q-form
-def : InstRW<[WriteAdr, V1Write_2c_2L01_1V01], (instrs STPQpre, STPQpost)>;
+def : InstRW<[WriteAdr, V1Write_2c2_1L01_1V01], (instrs STPQpre, STPQpost)>;
 
 
 // ASIMD integer instructions
@@ -921,12 +1045,12 @@ def : InstRW<[V1Write_2c_1V13], (instregex "^(ADD|[SU]ADDL)Vv4(i16|i32)v$",
 
 // ASIMD arith, reduce, 8B/8H
 // ASIMD max/min, reduce, 8B/8H
-def : InstRW<[V1Write_4c_1V13_1V], (instregex "^(ADD|[SU]ADDL)Vv8(i8|i16)v$",
+def : InstRW<[V1Write_4c_1V13], (instregex "^(ADD|[SU]ADDL)Vv8(i8|i16)v$",
                                               "^[SU](MAX|MIN)Vv8(i8|i16)v$")>;
 
 // ASIMD arith, reduce, 16B
 // ASIMD max/min, reduce, 16B
-def : InstRW<[V1Write_4c_2V13], (instregex "^(ADD|[SU]ADDL)Vv16i8v$",
+def : InstRW<[V1Write_4c2_1V13], (instregex "^(ADD|[SU]ADDL)Vv16i8v$",
                                            "[SU](MAX|MIN)Vv16i8v$")>;
 
 // ASIMD dot product
@@ -956,23 +1080,25 @@ def : InstRW<[V1Write_4c_1V02], (instregex "^SQDML[AS]L[iv]")>;
 def : InstRW<[V1Write_3c_1V01], (instregex "^PMULL?v(8|16)i8$")>;
 
 // ASIMD multiply long
-def : InstRW<[V1Write_3c_1V02], (instregex "^([SU]|SQD)MULLv")>;
+def : InstRW<[V1Write_3c_1V02], (instregex "^([SU]|SQD)MULL[vi]")>;
 
 // ASIMD shift accumulate
-def : InstRW<[V1Wr_VSA, V1Rd_VSA], (instregex "^[SU]SRAv", "^[SU]RSRAv")>;
+def : InstRW<[V1Wr_VSA, V1Rd_VSA], (instregex "^[SU]R?SRA(v8i8|v16i8|v4i16|v8i16|v2i32|v4i32|v2i64)_shift$",
+					      "^[SU]R?SRAd")>;
 
 // ASIMD shift by immed, complex
 // ASIMD shift by register, complex
 def : InstRW<[V1Write_4c_1V13],
              (instregex "^RSHRNv", "^SQRSHRU?Nv", "^(SQSHLU?|UQSHL)[bhsd]$",
-                        "^(SQSHLU?|UQSHL)(v8i8|v16i8|v4i16|v8i16|v2i32|v4i32|v2i64)_shift$",
-                        "^SQSHU?RNv", "^[SU]RSHRv", "^UQR?SHRNv", 
+                        "^(SQSHLU?|UQSHL|SQSHRUN)(v8i8|v16i8|v4i16|v8i16|v2i32|v4i32|v2i64)_shift$",
+                        "^SQSHU?RNv", "^[SU]RSHRv", "^UQR?SHRNv", "^[SU]Q?R?SHRU?N[bhsd]", "^[SU]RSHRd",
                         "^[SU]Q?RSHLv", "^[SU]QSHLv")>;
 
 // ASIMD shift by immed, basic
 // ASIMD shift by immed and insert, basic
 // ASIMD shift by register, basic
 def : InstRW<[V1Write_2c_1V13], (instregex "^SHLL?v", "^SHRNv", "^[SU]SHLLv",
+					   "^[SU]S?H[LR]d$", "^S[LR]Id$",
                                           "^[SU]SHRv", "^S[LR]Iv", "^[SU]SHLv")>;
 
 
@@ -994,7 +1120,7 @@ def : InstRW<[V1Write_4c_1V], (instregex "^FCADD(v[48]f16|v[24]f32|v2f64)$")>;
 def : InstRW<[V1Wr_FCMA, V1Rd_FCMA], (instregex "^FCMLAv")>;
 
 // ASIMD FP multiply
-def : InstRW<[V1Wr_FPM], (instregex "^FMULX?v")>;
+def : InstRW<[V1Wr_FPM], (instregex "^FMULX?(v|16|32|64)")>;
 
 // ASIMD FP multiply accumulate
 def : InstRW<[V1Wr_FPMA, V1Rd_FPMA], (instregex "^FML[AS]v")>;
@@ -1003,13 +1129,13 @@ def : InstRW<[V1Wr_FPMA, V1Rd_FPMA], (instregex "^FML[AS]v")>;
 def : InstRW<[V1Wr_FPMAL, V1Rd_FPMAL], (instregex "^FML[AS]L2?v")>;
 
 // ASIMD FP convert, long (F16 to F32)
-def : InstRW<[V1Write_4c_2V02], (instregex "^FCVTLv[48]i16$")>;
+def : InstRW<[V1Write_4c2_1V02], (instregex "^FCVTLv[48]i16$")>;
 
 // ASIMD FP convert, long (F32 to F64)
 def : InstRW<[V1Write_3c_1V02], (instregex "^FCVTLv[24]i32$")>;
 
 // ASIMD FP convert, narrow (F32 to F16)
-def : InstRW<[V1Write_4c_2V02], (instregex "^FCVTNv[48]i16$")>;
+def : InstRW<[V1Write_4c2_1V02], (instregex "^FCVTNv[48]i16$")>;
 
 // ASIMD FP convert, narrow (F64 to F32)
 def : InstRW<[V1Write_3c_1V02], (instregex "^FCVTNv[24]i32$",
@@ -1019,31 +1145,31 @@ def : InstRW<[V1Write_3c_1V02], (instregex "^FCVTNv[24]i32$",
 def : InstRW<[V1Write_3c_1V02], (instregex "^FCVT[AMNPZ][SU]v2f(32|64)$",
                                            "^FCVT[AMNPZ][SU]v2i(32|64)_shift$",
                                            "^FCVT[AMNPZ][SU]v1i64$",
+                                           "^FCVT[AMNPZ][SU]v1i32$",
+                                           "^FCVT[AMNPZ][SU]v1f16$",
                                            "^FCVTZ[SU]d$",
+                                           "^FCVTZ[SU]s$",
+                                           "^FCVTZ[SU]h$",
                                            "^[SU]CVTFv2f(32|64)$",
                                            "^[SU]CVTFv2i(32|64)_shift$",
                                            "^[SU]CVTFv1i64$",
-                                           "^[SU]CVTFd$")>;
+                                           "^[SU]CVTFv1i32$",
+                                           "^[SU]CVTFv1i16$",
+                                           "^[SU]CVTFd$",
+                                           "^[SU]CVTFs$",
+                                           "^[SU]CVTFh$")>;
 
 // ASIMD FP convert, other, D-form F16 and Q-form F32
-def : InstRW<[V1Write_4c_2V02], (instregex "^FCVT[AMNPZ][SU]v4f(16|32)$",
+def : InstRW<[V1Write_4c2_1V02], (instregex "^FCVT[AMNPZ][SU]v4f(16|32)$",
                                            "^FCVT[AMNPZ][SU]v4i(16|32)_shift$",
-                                           "^FCVT[AMNPZ][SU]v1i32$",
-                                           "^FCVTZ[SU]s$",
                                            "^[SU]CVTFv4f(16|32)$",
-                                           "^[SU]CVTFv4i(16|32)_shift$",
-                                           "^[SU]CVTFv1i32$",
-                                           "^[SU]CVTFs$")>;
+                                           "^[SU]CVTFv4i(16|32)_shift$")>;
 
 // ASIMD FP convert, other, Q-form F16
-def : InstRW<[V1Write_6c_4V02], (instregex "^FCVT[AMNPZ][SU]v8f16$",
+def : InstRW<[V1Write_6c4_1V02], (instregex "^FCVT[AMNPZ][SU]v8f16$",
                                            "^FCVT[AMNPZ][SU]v8i16_shift$",
-                                           "^FCVT[AMNPZ][SU]v1f16$",
-                                           "^FCVTZ[SU]h$",
                                            "^[SU]CVTFv8f16$",
-                                           "^[SU]CVTFv8i16_shift$",
-                                           "^[SU]CVTFv1i16$",
-                                           "^[SU]CVTFh$")>;
+                                           "^[SU]CVTFv8i16_shift$")>;
 
 // ASIMD FP divide, D-form, F16
 // ASIMD FP square root, D-form, F16
@@ -1051,42 +1177,42 @@ def : InstRW<[V1Write_7c7_1V02], (instrs FDIVv4f16, FSQRTv4f16)>;
 
 // ASIMD FP divide, F32
 // ASIMD FP square root, F32
-def : InstRW<[V1Write_10c7_1V02], (instrs FDIVv2f32, FDIVv4f32,
-                                          FSQRTv2f32, FSQRTv4f32)>;
+def : InstRW<[V1Write_10c5_1V02], (instrs FDIVv2f32, FSQRTv2f32)>;
+def : InstRW<[V1Write_10c9_1V02], (instrs FDIVv4f32, FSQRTv4f32)>;
 
 // ASIMD FP divide, Q-form, F16
-def : InstRW<[V1Write_13c5_1V02], (instrs FDIVv8f16)>;
+def : InstRW<[V1Write_13c13_1V02], (instrs FDIVv8f16)>;
 
 // ASIMD FP divide, Q-form, F64
-def : InstRW<[V1Write_15c7_1V02], (instrs FDIVv2f64)>;
+def : InstRW<[V1Write_15c14_1V02], (instrs FDIVv2f64)>;
 
 // ASIMD FP square root, Q-form, F16
-def : InstRW<[V1Write_13c11_1V02], (instrs FSQRTv8f16)>;
+def : InstRW<[V1Write_13c13_1V02], (instrs FSQRTv8f16)>;
 
 // ASIMD FP square root, Q-form, F64
-def : InstRW<[V1Write_16c7_1V02], (instrs FSQRTv2f64)>;
+def : InstRW<[V1Write_16c15_1V02], (instrs FSQRTv2f64)>;
 
 // ASIMD FP max/min, reduce, F32 and D-form F16
-def : InstRW<[V1Write_4c_2V], (instregex "^F(MAX|MIN)(NM)?Vv4(i16|i32)v$")>;
+def : InstRW<[V1Write_4c2_1V], (instregex "^F(MAX|MIN)(NM)?Vv4(i16|i32)v$")>;
 
 // ASIMD FP max/min, reduce, Q-form F16
-def : InstRW<[V1Write_6c_3V], (instregex "^F(MAX|MIN)(NM)?Vv8i16v$")>;
+def : InstRW<[V1Write_6c3_1V], (instregex "^F(MAX|MIN)(NM)?Vv8i16v$")>;
 
 // ASIMD FP round, D-form F32 and Q-form F64
 def : InstRW<[V1Write_3c_1V02], (instregex "^FRINT[AIMNPXZ]v2f(32|64)$")>;
 
 // ASIMD FP round, D-form F16 and Q-form F32
-def : InstRW<[V1Write_4c_2V02], (instregex "^FRINT[AIMNPXZ]v4f(16|32)$")>;
+def : InstRW<[V1Write_4c2_1V02], (instregex "^FRINT[AIMNPXZ]v4f(16|32)$")>;
 
 // ASIMD FP round, Q-form F16
-def : InstRW<[V1Write_6c_4V02], (instregex "^FRINT[AIMNPXZ]v8f16$")>;
+def : InstRW<[V1Write_6c4_1V02], (instregex "^FRINT[AIMNPXZ]v8f16$")>;
 
 
 // ASIMD BF instructions
 // -----------------------------------------------------------------------------
 
 // ASIMD convert, F32 to BF16
-def : InstRW<[V1Write_4c_1V02], (instrs BFCVTN, BFCVTN2)>;
+def : InstRW<[V1Write_4c2_1V02], (instrs BFCVTN, BFCVTN2)>;
 
 // ASIMD dot product
 def : InstRW<[V1Wr_BFD, V1Rd_BFD], (instregex "^BF(DOT|16DOTlane)v[48]bf16$")>;
@@ -1113,7 +1239,6 @@ def : InstRW<[V1Write_3c_1V02], (instrs BFCVT)>;
 // ASIMD insert, element to element
 // ASIMD move, FP immed
 // ASIMD move, integer immed
-// ASIMD reverse
 // ASIMD table lookup, 1 or 2 table regs
 // ASIMD table lookup extension, 1 table reg
 // ASIMD transfer, element to gen reg
@@ -1132,20 +1257,21 @@ def : InstRW<[V1Write_4c_1V13], (instregex "^[SU]QXTNv", "^SQXTUNv")>;
 // ASIMD reciprocal and square root estimate, D-form F32 and F64
 def : InstRW<[V1Write_3c_1V02], (instrs URECPEv2i32,
                                         URSQRTEv2i32,
-                                        FRECPEv1i32, FRECPEv2f32, FRECPEv1i64,
-                                        FRSQRTEv1i32, FRSQRTEv2f32, FRSQRTEv1i64)>;
+					FRECPEv2f32, FRSQRTEv2f32,
+					FRECPEv1f16, FRECPEv1i32, FRECPEv1i64,
+					FRSQRTEv1f16, FRSQRTEv1i32, FRSQRTEv1i64)>;
 
 // ASIMD reciprocal and square root estimate, Q-form U32
 // ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32 and F64
-def : InstRW<[V1Write_4c_1V02], (instrs URECPEv4i32,
+def : InstRW<[V1Write_4c2_1V02], (instrs URECPEv4i32,
                                         URSQRTEv4i32,
-                                        FRECPEv1f16, FRECPEv4f16,
+					FRECPEv4f16,
                                         FRECPEv4f32, FRECPEv2f64,
-                                        FRSQRTEv1f16, FRSQRTEv4f16,
+					FRSQRTEv4f16,
                                         FRSQRTEv4f32, FRSQRTEv2f64)>;
 
 // ASIMD reciprocal and square root estimate, Q-form F16
-def : InstRW<[V1Write_6c_2V02], (instrs FRECPEv8f16,
+def : InstRW<[V1Write_6c4_1V02], (instrs FRECPEv8f16,
                                         FRSQRTEv8f16)>;
 
 // ASIMD reciprocal exponent
@@ -1155,27 +1281,33 @@ def : InstRW<[V1Write_3c_1V02], (instrs FRECPXv1f16, FRECPXv1i32, FRECPXv1i64)>;
 def : InstRW<[V1Write_4c_1V], (instregex "^FRECPS(16|32|64)$", "^FRECPSv",
                                          "^FRSQRTS(16|32|64)$", "^FRSQRTSv")>;
 
+// ASIMD reverse
+def : InstRW<[V1Write_1c_1I], (instregex "^REVXr$")>;
+
+
 // ASIMD table lookup, 1 or 2 table regs
 // ASIMD table lookup extension, 1 table reg
-def : InstRW<[V1Write_2c_2V01], (instregex "^TBLv(8|16)i8(One|Two)$",
+def : InstRW<[V1Write_2c_1V01], (instregex "^TBLv(8|16)i8(One|Two)$",
                                            "^TBXv(8|16)i8One$")>;
 
 // ASIMD table lookup, 3 table regs
 // ASIMD table lookup extension, 2 table reg
-def : InstRW<[V1Write_4c_2V01], (instrs TBLv8i8Three, TBLv16i8Three,
+def : InstRW<[V1Write_4c2_1V01], (instrs TBLv8i8Three, TBLv16i8Three,
                                         TBXv8i8Two, TBXv16i8Two)>;
 
 // ASIMD table lookup, 4 table regs
-def : InstRW<[V1Write_4c_3V01], (instrs TBLv8i8Four, TBLv16i8Four)>;
+def : InstRW<[V1Write_4c3_1V01], (instrs TBLv8i8Four, TBLv16i8Four)>;
 
 // ASIMD table lookup extension, 3 table reg
-def : InstRW<[V1Write_6c_3V01], (instrs TBXv8i8Three, TBXv16i8Three)>;
+def : InstRW<[V1Write_6c3_1V01], (instrs TBXv8i8Three, TBXv16i8Three)>;
 
 // ASIMD table lookup extension, 4 table reg
-def : InstRW<[V1Write_6c_5V01], (instrs TBXv8i8Four, TBXv16i8Four)>;
+def : InstRW<[V1Write_6c5_1V01], (instrs TBXv8i8Four, TBXv16i8Four)>;
 
 // ASIMD transfer, element to gen reg
-def : InstRW<[V1Write_2c_1V], (instregex "^SMOVvi(((8|16)to(32|64))|32to64)$",
+def : InstRW<[V1Write_2c4_1V], (instregex "^SMOVvi(((8|16)to(32|64))|32to64)$",
+					  "^UMOVvi(8|16|32|64)_idx0$",
+					  "^SMOVvi(8|16|32)to(32|64)_idx0$",
                                          "^UMOVvi(8|16|32|64)$")>;
 
 // ASIMD transfer, gen reg to element
@@ -1192,27 +1324,27 @@ def : InstRW<[WriteAdr, V1Write_6c_1L],
              (instregex "^LD1Onev(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
 
 // ASIMD load, 1 element, multiple, 2 reg
-def : InstRW<[V1Write_6c_2L],
+def : InstRW<[V1Write_6c2_1L],
              (instregex "^LD1Twov(8b|16b|4h|8h|2s|4s|1d|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_6c_2L],
+def : InstRW<[WriteAdr, V1Write_6c2_1L],
              (instregex "^LD1Twov(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
 
 // ASIMD load, 1 element, multiple, 3 reg
-def : InstRW<[V1Write_6c_3L],
+def : InstRW<[V1Write_6c3_1L],
              (instregex "^LD1Threev(8b|16b|4h|8h|2s|4s|1d|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_6c_3L],
+def : InstRW<[WriteAdr, V1Write_6c3_1L],
              (instregex "^LD1Threev(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
 
 // ASIMD load, 1 element, multiple, 4 reg, D-form
-def : InstRW<[V1Write_6c_2L],
+def : InstRW<[V1Write_6c2_1L],
              (instregex "^LD1Fourv(8b|4h|2s|1d)$")>;
-def : InstRW<[WriteAdr, V1Write_6c_2L],
+def : InstRW<[WriteAdr, V1Write_6c2_1L],
              (instregex "^LD1Fourv(8b|4h|2s|1d)_POST$")>;
 
 // ASIMD load, 1 element, multiple, 4 reg, Q-form
-def : InstRW<[V1Write_7c_4L],
+def : InstRW<[V1Write_7c4_1L],
              (instregex "^LD1Fourv(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_7c_4L],
+def : InstRW<[WriteAdr, V1Write_7c4_1L],
              (instregex "^LD1Fourv(16b|8h|4s|2d)_POST$")>;
 
 // ASIMD load, 1 element, one lane
@@ -1225,60 +1357,60 @@ def : InstRW<[WriteAdr, V1Write_8c_1L_1V],
                         "^LD1Rv(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
 
 // ASIMD load, 2 element, multiple, D-form
-def : InstRW<[V1Write_8c_1L_2V],
+def : InstRW<[V1Write_8c_1L_1V],
              (instregex "^LD2Twov(8b|4h|2s)$")>;
-def : InstRW<[WriteAdr, V1Write_8c_1L_2V],
+def : InstRW<[WriteAdr, V1Write_8c_1L_1V],
              (instregex "^LD2Twov(8b|4h|2s)_POST$")>;
                         
 // ASIMD load, 2 element, multiple, Q-form
-def : InstRW<[V1Write_8c_2L_2V],
+def : InstRW<[V1Write_8c2_1L_1V],
              (instregex "^LD2Twov(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_8c_2L_2V],
+def : InstRW<[WriteAdr, V1Write_8c2_1L_1V],
              (instregex "^LD2Twov(16b|8h|4s|2d)_POST$")>;
                         
 // ASIMD load, 2 element, one lane
 // ASIMD load, 2 element, all lanes
-def : InstRW<[V1Write_8c_1L_2V],
+def : InstRW<[V1Write_8c2_1L_1V],
              (instregex "^LD2i(8|16|32|64)$",
                         "^LD2Rv(8b|16b|4h|8h|2s|4s|1d|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_8c_1L_2V],
+def : InstRW<[WriteAdr, V1Write_8c2_1L_1V],
              (instregex "^LD2i(8|16|32|64)_POST$",
                         "^LD2Rv(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
                         
 // ASIMD load, 3 element, multiple, D-form
 // ASIMD load, 3 element, one lane
 // ASIMD load, 3 element, all lanes
-def : InstRW<[V1Write_8c_2L_3V],
+def : InstRW<[V1Write_8c3_1L_1V],
              (instregex "^LD3Threev(8b|4h|2s)$",
                         "^LD3i(8|16|32|64)$",
                         "^LD3Rv(8b|16b|4h|8h|2s|4s|1d|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_8c_2L_3V],
+def : InstRW<[WriteAdr, V1Write_8c3_1L_1V],
              (instregex "^LD3Threev(8b|4h|2s)_POST$",
                         "^LD3i(8|16|32|64)_POST$",
                         "^LD3Rv(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
 
 // ASIMD load, 3 element, multiple, Q-form
-def : InstRW<[V1Write_8c_3L_3V],
+def : InstRW<[V1Write_8c3_1L_1V],
              (instregex "^LD3Threev(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_8c_3L_3V],
+def : InstRW<[WriteAdr, V1Write_8c3_1L_1V],
              (instregex "^LD3Threev(16b|8h|4s|2d)_POST$")>;
 
 // ASIMD load, 4 element, multiple, D-form
 // ASIMD load, 4 element, one lane
 // ASIMD load, 4 element, all lanes
-def : InstRW<[V1Write_8c_3L_4V],
+def : InstRW<[V1Write_8c3_1L_1V],
              (instregex "^LD4Fourv(8b|4h|2s)$",
                         "^LD4i(8|16|32|64)$",
                         "^LD4Rv(8b|16b|4h|8h|2s|4s|1d|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_8c_3L_4V],
+def : InstRW<[WriteAdr, V1Write_8c3_1L_1V],
              (instregex "^LD4Fourv(8b|4h|2s)_POST$",
                         "^LD4i(8|16|32|64)_POST$",
                         "^LD4Rv(8b|16b|4h|8h|2s|4s|1d|2d)_POST$")>;
 
 // ASIMD load, 4 element, multiple, Q-form
-def : InstRW<[V1Write_9c_4L_4V],
+def : InstRW<[V1Write_9c6_1L_1V],
              (instregex "^LD4Fourv(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_9c_4L_4V],
+def : InstRW<[WriteAdr, V1Write_9c6_1L_1V],
              (instregex "^LD4Fourv(16b|8h|4s|2d)_POST$")>;
 
 
@@ -1297,25 +1429,25 @@ def : InstRW<[WriteAdr, V1Write_2c_1L01_1V01],
 // ASIMD store, 1 element, multiple, 2 reg, Q-form
 // ASIMD store, 1 element, multiple, 3 reg, D-form
 // ASIMD store, 1 element, multiple, 4 reg, D-form
-def : InstRW<[V1Write_2c_2L01_2V01],
+def : InstRW<[V1Write_2c2_1L01_1V01],
              (instregex "^ST1Twov(16b|8h|4s|2d)$",
                         "^ST1Threev(8b|4h|2s|1d)$",
                         "^ST1Fourv(8b|4h|2s|1d)$")>;
-def : InstRW<[WriteAdr, V1Write_2c_2L01_2V01],
+def : InstRW<[WriteAdr, V1Write_2c2_1L01_1V01],
              (instregex "^ST1Twov(16b|8h|4s|2d)_POST$",
                         "^ST1Threev(8b|4h|2s|1d)_POST$",
                         "^ST1Fourv(8b|4h|2s|1d)_POST$")>;
 
 // ASIMD store, 1 element, multiple, 3 reg, Q-form
-def : InstRW<[V1Write_2c_3L01_3V01],
+def : InstRW<[V1Write_2c3_1L01_1V01],
              (instregex "^ST1Threev(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_2c_3L01_3V01],
+def : InstRW<[WriteAdr, V1Write_2c3_1L01_1V01],
              (instregex "^ST1Threev(16b|8h|4s|2d)_POST$")>;
 
 // ASIMD store, 1 element, multiple, 4 reg, Q-form
-def : InstRW<[V1Write_2c_4L01_4V01],
+def : InstRW<[V1Write_2c4_1L01_1V01],
              (instregex "^ST1Fourv(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_2c_4L01_4V01],
+def : InstRW<[WriteAdr, V1Write_2c4_1L01_1V01],
              (instregex "^ST1Fourv(16b|8h|4s|2d)_POST$")>;
 
 // ASIMD store, 1 element, one lane
@@ -1334,45 +1466,45 @@ def : InstRW<[WriteAdr, V1Write_4c_1L01_1V01],
 // ASIMD store, 3 element, multiple, D-form
 // ASIMD store, 3 element, one lane
 // ASIMD store, 4 element, one lane, D
-def : InstRW<[V1Write_4c_2L01_2V01],
+def : InstRW<[V1Write_4c2_1L01_1V01],
              (instregex "^ST2Twov(16b|8h|4s|2d)$",
                         "^ST3Threev(8b|4h|2s)$",
                         "^ST3i(8|16|32|64)$",
                         "^ST4i64$")>;
-def : InstRW<[WriteAdr, V1Write_4c_2L01_2V01],
+def : InstRW<[WriteAdr, V1Write_4c2_1L01_1V01],
              (instregex "^ST2Twov(16b|8h|4s|2d)_POST$",
                         "^ST3Threev(8b|4h|2s)_POST$",
                         "^ST3i(8|16|32|64)_POST$",
                         "^ST4i64_POST$")>;
 
 // ASIMD store, 3 element, multiple, Q-form
-def : InstRW<[V1Write_5c_3L01_3V01],
+def : InstRW<[V1Write_5c3_1L01_1V01],
              (instregex "^ST3Threev(16b|8h|4s|2d)$")>;
-def : InstRW<[WriteAdr, V1Write_5c_3L01_3V01],
+def : InstRW<[WriteAdr, V1Write_5c3_1L01_1V01],
              (instregex "^ST3Threev(16b|8h|4s|2d)_POST$")>;
 
 // ASIMD store, 4 element, multiple, D-form
-def : InstRW<[V1Write_6c_3L01_3V01],
+def : InstRW<[V1Write_6c6_1L01_1V01],
              (instregex "^ST4Fourv(8b|4h|2s)$")>;
-def : InstRW<[WriteAdr, V1Write_6c_3L01_3V01],
+def : InstRW<[WriteAdr, V1Write_6c6_1L01_1V01],
              (instregex "^ST4Fourv(8b|4h|2s)_POST$")>;
 
 // ASIMD store, 4 element, multiple, Q-form, B/H/S
-def : InstRW<[V1Write_7c_6L01_6V01],
+def : InstRW<[V1Write_7c12_1L01_1V01],
              (instregex "^ST4Fourv(16b|8h|4s)$")>;
-def : InstRW<[WriteAdr, V1Write_7c_6L01_6V01],
+def : InstRW<[WriteAdr, V1Write_7c12_1L01_1V01],
              (instregex "^ST4Fourv(16b|8h|4s)_POST$")>;
 
 // ASIMD store, 4 element, multiple, Q-form, D
-def : InstRW<[V1Write_4c_4L01_4V01],
+def : InstRW<[V1Write_4c8_1L01_1V01],
              (instrs ST4Fourv2d)>;
-def : InstRW<[WriteAdr, V1Write_4c_4L01_4V01],
+def : InstRW<[WriteAdr, V1Write_4c8_1L01_1V01],
              (instrs ST4Fourv2d_POST)>;
 
 // ASIMD store, 4 element, one lane, B/H/S
-def : InstRW<[V1Write_6c_3L_3V],
+def : InstRW<[V1Write_6c2_1L01_1V01],
              (instregex "^ST4i(8|16|32)$")>;
-def : InstRW<[WriteAdr, V1Write_6c_3L_3V],
+def : InstRW<[WriteAdr, V1Write_6c2_1L01_1V01],
              (instregex "^ST4i(8|16|32)_POST$")>;
 
 
@@ -1424,11 +1556,11 @@ def : InstRW<[V1Write_2c_1M0], (instregex "^BRK[AB]_PP[mz]P$")>;
 def : InstRW<[V1Write_2c_1M0], (instrs BRKN_PPzP, BRKPA_PPzPP, BRKPB_PPzPP)>;
 
 // Loop control, based on predicate and flag setting
-def : InstRW<[V1Write_3c_2M0], (instrs BRKAS_PPzP, BRKBS_PPzP, BRKNS_PPzP,
+def : InstRW<[V1Write_3c2_1M0], (instrs BRKAS_PPzP, BRKBS_PPzP, BRKNS_PPzP,
                                        BRKPAS_PPzPP, BRKPBS_PPzPP)>;
 
 // Loop control, based on GPR
-def : InstRW<[V1Write_3c_2M0], (instregex "^WHILE(LE|LO|LS|LT)_P(WW|XX)_[BHSD]$")>;
+def : InstRW<[V1Write_3c2_1M0], (instregex "^WHILE(LE|LO|LS|LT)_P(WW|XX)_[BHSD]$")>;
 
 // Loop terminate
 def : InstRW<[V1Write_1c_1M0], (instregex "^CTERM(EQ|NE)_(WW|XX)$")>;
@@ -1445,14 +1577,14 @@ def : InstRW<[V1Write_2c_1M0], (instregex "^(CNT|([SU]Q)?(DEC|INC))[BHWD]_XPiI$"
                                           "^[SU]Q(DEC|INC)P_XPWd_[BHSD]$")>;
 
 // Predicate counting vector, active predicate
-def : InstRW<[V1Write_7c_2M0_1V01], (instregex "^([SU]Q)?(DEC|INC)P_ZP_[HSD]$")>;
+def : InstRW<[V1Write_7c2_1M0_1V01], (instregex "^([SU]Q)?(DEC|INC)P_ZP_[HSD]$")>;
 
 // Predicate logical
 def : InstRW<[V1Write_1c_1M0],
              (instregex "^(AND|BIC|EOR|NAND|NOR|ORN|ORR)_PPzPP$")>;
 
 // Predicate logical, flag setting
-def : InstRW<[V1Write_2c_2M0],
+def : InstRW<[V1Write_2c2_1M0],
              (instregex "^(AND|BIC|EOR|NAND|NOR|ORN|ORR)S_PPzPP$")>;
 
 // Predicate reverse
@@ -1475,7 +1607,7 @@ def : InstRW<[V1Write_2c_1M0], (instrs PTEST_PP,
 def : InstRW<[V1Write_1c_1M0], (instrs SEL_PPPP)>;
 
 // Predicate set/initialize, set flags
-def : InstRW<[V1Write_3c_2M0], (instregex "^PTRUES_[BHSD]$")>;
+def : InstRW<[V1Write_3c2_1M0], (instregex "^PTRUES_[BHSD]$")>;
 
 
 
@@ -1495,8 +1627,8 @@ def : InstRW<[V1Write_2c_1V01],
                         "^SUBR_Z(I|P[mZ]Z)_[BHSD]",
                         "^(AND|EOR|ORR)_ZI$",
                         "^(AND|BIC|EOR|EOR(BT|TB)?|ORR)_ZP?ZZ",
-                        "^EOR(BT|TB)_ZZZ_[BHSD]$",
-                        "^(AND|BIC|EOR|NOT|ORR)_ZPmZ_[BHSD]")>;
+			"^EOR(BT|TB)_ZZZ_[BHSD]$",
+			"^(AND|BIC|EOR|NOT|ORR)_ZPmZ_[BHSD]")>;
 
 // Arithmetic, shift
 def : InstRW<[V1Write_2c_1V1],
@@ -1529,14 +1661,15 @@ def : InstRW<[V1Write_3c_1V1], (instregex "^CLAST[AB]_[VZ]PZ_[BHSD]$",
                                           "^SPLICE_ZPZZ?_[BHSD]$")>;
 
 // Convert to floating point, 64b to float or convert to double
-def : InstRW<[V1Write_3c_1V0], (instregex "^[SU]CVTF_ZPmZ_Dto[HSD]",
-                                          "^[SU]CVTF_ZPmZ_StoD")>;
+def : InstRW<[V1Write_3c_1V0], (instregex "^[SU]CVTF_ZPmZ_Dto[HSD]")>;
+
 
 // Convert to floating point, 32b to single or half
-def : InstRW<[V1Write_4c_2V0], (instregex "^[SU]CVTF_ZPmZ_Sto[HS]")>;
+def : InstRW<[V1Write_4c2_1V0], (instregex "^[SU]CVTF_ZPmZ_Sto[HS]",
+					   "^[SU]CVTF_ZPmZ_StoD")>;
 
 // Convert to floating point, 16b to half
-def : InstRW<[V1Write_6c_4V0], (instregex "^[SU]CVTF_ZPmZ_HtoH")>;
+def : InstRW<[V1Write_6c4_1V0], (instregex "^[SU]CVTF_ZPmZ_HtoH")>;
 
 // Copy, scalar
 def : InstRW<[V1Write_5c_1M0_1V01], (instregex "^CPY_ZPmR_[BHSD]$")>;
@@ -1545,11 +1678,11 @@ def : InstRW<[V1Write_5c_1M0_1V01], (instregex "^CPY_ZPmR_[BHSD]$")>;
 def : InstRW<[V1Write_2c_1V01], (instregex "^CPY_ZP([mz]I|mV)_[BHSD]$")>;
 
 // Divides, 32 bit
-def : InstRW<[V1Write_12c7_1V0], (instregex "^[SU]DIVR?_ZPmZ_S",
+def : InstRW<[V1Write_12c11_1V0], (instregex "^[SU]DIVR?_ZPmZ_S",
                                              "^[SU]DIV_ZPZZ_S")>;
 
 // Divides, 64 bit
-def : InstRW<[V1Write_20c7_1V0], (instregex "^[SU]DIVR?_ZPmZ_D",
+def : InstRW<[V1Write_20c20_1V0], (instregex "^[SU]DIVR?_ZPmZ_D",
                                              "^[SU]DIV_ZPZZ_D")>;
 
 // Dot product, 8 bit
@@ -1592,10 +1725,10 @@ def : InstRW<[V1Write_4c_1V0], (instregex "^INDEX_II_[BHS]$")>;
 def : InstRW<[V1Write_7c_1M0_1V0], (instregex "^INDEX_(IR|RI|RR)_[BHS]$")>;
 
 // Horizontal operations, D form, imm, imm
-def : InstRW<[V1Write_5c_2V0], (instrs INDEX_II_D)>;
+def : InstRW<[V1Write_5c2_1V0], (instrs INDEX_II_D)>;
 
 // Horizontal operations, D form, scalar, imm / scalar / imm, scalar
-def : InstRW<[V1Write_8c_2M0_2V0], (instregex "^INDEX_(IR|RI|RR)_D$")>;
+def : InstRW<[V1Write_8c2_1M0_1V0], (instregex "^INDEX_(IR|RI|RR)_D$")>;
 
 // Move prefix
 def : InstRW<[V1Write_2c_1V01], (instregex "^MOVPRFX_ZP[mz]Z_[BHSD]$",
@@ -1611,7 +1744,7 @@ def : InstRW<[V1Write_4c_1V0], (instregex "^MUL_(ZI|ZPmZ|ZZZI|ZZZ)_[BHS]",
                                           "^[SU]MULH_ZPZZ_[BHS]")>;
 
 // Multiply, D element size
-def : InstRW<[V1Write_5c_2V0], (instregex "^MUL_(ZI|ZPmZ|ZZZI|ZZZ)_D",
+def : InstRW<[V1Write_5c2_1V0], (instregex "^MUL_(ZI|ZPmZ|ZZZI|ZZZ)_D",
                                           "^MUL_ZPZZ_D",
                                           "^[SU]MULH_(ZPmZ|ZZZ)_D",
                                           "^[SU]MULH_ZPZZ_D")>;
@@ -1624,29 +1757,29 @@ def : InstRW<[V1Wr_ZMAD, ReadDefault, V1Rd_ZMAD],
 
 // Multiply accumulate, B, H, S element size
 // NOTE: This is not specified in the SOG.
-def : InstRW<[V1Write_4c_1V0], (instregex "^(ML[AS]|MAD|MSB)_(ZPmZZ|ZPZZZ)_[BHS]")>;
+def : InstRW<[V1Wr_ZMABHS, ReadDefault, V1Rd_ZMABHS], (instregex "^(ML[AS]|MAD|MSB)_(ZPmZZ|ZPZZZ)_[BHS]")>;
 
 // Predicate counting vector
-def : InstRW<[V1Write_2c_1V0], (instregex "^([SU]Q)?(DEC|INC)[HWD]_ZPiI$")>;
+def : InstRW<[V1Write_2c_1V01], (instregex "^([SU]Q)?(DEC|INC)[HWD]_ZPiI$")>;
 
 // Reduction, arithmetic, B form
-def : InstRW<[V1Write_14c_1V_1V0_2V1_1V13],
+def : InstRW<[V1Write_14c2_1V],
              (instregex "^[SU](ADD|MAX|MIN)V_VPZ_B")>;
 
 // Reduction, arithmetic, H form
-def : InstRW<[V1Write_12c_1V_1V01_2V1],
+def : InstRW<[V1Write_12c2_1V],
              (instregex "^[SU](ADD|MAX|MIN)V_VPZ_H")>;
 
 // Reduction, arithmetic, S form
-def : InstRW<[V1Write_10c_1V_1V01_2V1],
+def : InstRW<[V1Write_10c2_1V1],
              (instregex "^[SU](ADD|MAX|MIN)V_VPZ_S")>;
 
 // Reduction, arithmetic, D form
-def : InstRW<[V1Write_8c_1V_1V01],
+def : InstRW<[V1Write_8c2_1V1],
              (instregex "^[SU](ADD|MAX|MIN)V_VPZ_D")>;
 
 // Reduction, logical
-def : InstRW<[V1Write_12c_4V01], (instregex "^(AND|EOR|OR)V_VPZ_[BHSD]$")>;
+def : InstRW<[V1Write_12c4_1V01], (instregex "^(AND|EOR|OR)V_VPZ_[BHSD]$")>;
 
 // Reverse, vector
 def : InstRW<[V1Write_2c_1V01], (instregex "^REV_ZZ_[BHSD]$",
@@ -1684,13 +1817,13 @@ def : InstRW<[V1Write_2c_1V01], (instregex "^F(ADD|SUB)_(ZPm[IZ]|ZZZ)_[HSD]",
                                            "^FSUBR_(ZPZI|ZPZZ)_[HSD]")>;
 
 // Floating point associative add, F16
-def : InstRW<[V1Write_19c_18V0], (instrs FADDA_VPZ_H)>;
+def : InstRW<[V1Write_19c18_1V0], (instrs FADDA_VPZ_H)>;
 
 // Floating point associative add, F32
-def : InstRW<[V1Write_11c_10V0], (instrs FADDA_VPZ_S)>;
+def : InstRW<[V1Write_11c10_1V0], (instrs FADDA_VPZ_S)>;
 
 // Floating point associative add, F64
-def : InstRW<[V1Write_8c_3V01], (instrs FADDA_VPZ_D)>;
+def : InstRW<[V1Write_8c3_1V01], (instrs FADDA_VPZ_D)>;
 
 // Floating point compare
 def : InstRW<[V1Write_2c_1V0], (instregex "^FAC(GE|GT)_PPzZZ_[HSD]$",
@@ -1706,29 +1839,29 @@ def : InstRW<[V1Wr_ZFCMA, V1Rd_ZFCMA],              (instregex "^FCMLA_ZZZI_[HS]
 
 // Floating point convert, long or narrow (F16 to F32 or F32 to F16)
 // Floating point convert to integer, F32
-def : InstRW<[V1Write_4c_2V0], (instregex "^FCVT_ZPmZ_(HtoS|StoH)",
-                                          "^FCVTZ[SU]_ZPmZ_(HtoS|StoS)")>;
+def : InstRW<[V1Write_4c2_1V0], (instregex "^FCVT_ZPmZ_(HtoS|StoH)",
+					  "^FCVTZ[SU]_ZPmZ_(StoS|StoD)")>;
 
 // Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)
 // Floating point convert to integer, F64
 def : InstRW<[V1Write_3c_1V0], (instregex "^FCVT_ZPmZ_(HtoD|StoD|DtoS|DtoH)",
-                                          "^FCVTZ[SU]_ZPmZ_(HtoD|StoD|DtoS|DtoD)")>;
+					  "^FCVTZ[SU]_ZPmZ_(DtoS|DtoD)")>;
 
 // Floating point convert to integer, F16
-def : InstRW<[V1Write_6c_4V0], (instregex "^FCVTZ[SU]_ZPmZ_HtoH")>;
+def : InstRW<[V1Write_6c4_1V0], (instregex "^FCVTZ[SU]_ZPmZ_(HtoH|HtoS|HtoD)")>;
 
 // Floating point copy
 def : InstRW<[V1Write_2c_1V01], (instregex "^FCPY_ZPmI_[HSD]$",
                                            "^FDUP_ZI_[HSD]$")>;
 
 // Floating point divide, F16
-def : InstRW<[V1Write_13c10_1V0], (instregex "^FDIVR?_(ZPmZ|ZPZZ)_H")>;
+def : InstRW<[V1Write_13c12_1V0], (instregex "^FDIVR?_(ZPmZ|ZPZZ)_H")>;
 
 // Floating point divide, F32
-def : InstRW<[V1Write_10c7_1V0], (instregex "^FDIVR?_(ZPmZ|ZPZZ)_S")>;
+def : InstRW<[V1Write_10c9_1V0], (instregex "^FDIVR?_(ZPmZ|ZPZZ)_S")>;
 
 // Floating point divide, F64
-def : InstRW<[V1Write_15c7_1V0], (instregex "^FDIVR?_(ZPmZ|ZPZZ)_D")>;
+def : InstRW<[V1Write_15c14_1V0], (instregex "^FDIVR?_(ZPmZ|ZPZZ)_D")>;
 
 // Floating point min/max
 def : InstRW<[V1Write_2c_1V01], (instregex "^F(MAX|MIN)(NM)?_ZPm[IZ]_[HSD]",
@@ -1752,10 +1885,10 @@ def : InstRW<[V1Wr_ZFMA, V1Rd_ZFMA],
 def : InstRW<[V1Write_4c_1V01], (instregex "^F(RECPS|RSQRTS)_ZZZ_[HSD]")>;
 
 // Floating point reciprocal estimate, F16
-def : InstRW<[V1Write_6c_4V0], (instrs FRECPE_ZZ_H, FRSQRTE_ZZ_H)>;
+def : InstRW<[V1Write_6c_1V0], (instrs FRECPE_ZZ_H, FRSQRTE_ZZ_H)>;
 
 // Floating point reciprocal estimate, F32
-def : InstRW<[V1Write_4c_2V0], (instrs FRECPE_ZZ_S, FRSQRTE_ZZ_S)>;
+def : InstRW<[V1Write_4c_1V0], (instrs FRECPE_ZZ_S, FRSQRTE_ZZ_S)>;
 
 // Floating point reciprocal estimate, F64
 def : InstRW<[V1Write_3c_1V0], (instrs FRECPE_ZZ_D, FRSQRTE_ZZ_D)>;
@@ -1764,13 +1897,13 @@ def : InstRW<[V1Write_3c_1V0], (instrs FRECPE_ZZ_D, FRSQRTE_ZZ_D)>;
 def : InstRW<[V1Write_3c_1V0], (instregex "^FRECPX_ZPmZ_[HSD]")>;
 
 // Floating point reduction, F16
-def : InstRW<[V1Write_13c_6V01], (instregex "^F(ADD|((MAX|MIN)(NM)?))V_VPZ_H$")>;
+def : InstRW<[V1Write_13c6_1V01], (instregex "^F(ADD|((MAX|MIN)(NM)?))V_VPZ_H$")>;
 
 // Floating point reduction, F32
-def : InstRW<[V1Write_11c_1V_5V01], (instregex "^F(ADD|((MAX|MIN)(NM)?))V_VPZ_S$")>;
+def : InstRW<[V1Write_11c5_1V01], (instregex "^F(ADD|((MAX|MIN)(NM)?))V_VPZ_S$")>;
 
 // Floating point reduction, F64
-def : InstRW<[V1Write_9c_1V_4V01], (instregex "^F(ADD|((MAX|MIN)(NM)?))V_VPZ_D$")>;
+def : InstRW<[V1Write_9c4_1V01], (instregex "^F(ADD|((MAX|MIN)(NM)?))V_VPZ_D$")>;
 
 // Floating point round to integral, F16
 def : InstRW<[V1Write_6c_1V0], (instregex "^FRINT[AIMNPXZ]_ZPmZ_H")>;
@@ -1782,13 +1915,13 @@ def : InstRW<[V1Write_4c_1V0], (instregex "^FRINT[AIMNPXZ]_ZPmZ_S")>;
 def : InstRW<[V1Write_3c_1V0], (instregex "^FRINT[AIMNPXZ]_ZPmZ_D")>;
 
 // Floating point square root, F16
-def : InstRW<[V1Write_13c10_1V0], (instregex "^FSQRT_ZPmZ_H")>;
+def : InstRW<[V1Write_13c12_1V0], (instregex "^FSQRT_ZPmZ_H")>;
 
 // Floating point square root, F32
-def : InstRW<[V1Write_10c7_1V0], (instregex "^FSQRT_ZPmZ_S")>;
+def : InstRW<[V1Write_10c9_1V0], (instregex "^FSQRT_ZPmZ_S")>;
 
 // Floating point square root, F64
-def : InstRW<[V1Write_16c7_1V0], (instregex "^FSQRT_ZPmZ_D")>;
+def : InstRW<[V1Write_16c14_1V0], (instregex "^FSQRT_ZPmZ_D")>;
 
 // Floating point trigonometric
 def : InstRW<[V1Write_3c_1V01], (instregex "^FEXPA_ZZ_[HSD]$",
@@ -1825,9 +1958,9 @@ def : InstRW<[V1Write_6c_1L_1M], (instrs LDR_PXI)>;
 // Contiguous load, scalar + scalar
 // Contiguous load broadcast, scalar + imm
 // Contiguous load broadcast, scalar + scalar
-def : InstRW<[V1Write_6c_1L01], (instregex "^LD1[BHWD]_IMM$",
+def : InstRW<[V1Write_6c_1L01], (instregex "^LD1[BWD]_IMM$",
                                            "^LD1S?B_[HSD]_IMM$",
-                                           "^LD1S?H_[SD]_IMM$",
+                                           "^LD1SH_[SD]_IMM$",
                                            "^LD1S?W_D_IMM$",
                                            "^LD1[BWD]$",
                                            "^LD1S?B_[HSD]$",
@@ -1838,8 +1971,11 @@ def : InstRW<[V1Write_6c_1L01], (instregex "^LD1[BHWD]_IMM$",
                                            "^LD1RS?H_[SD]_IMM$",
                                            "^LD1RS?W_D_IMM$",
                                            "^LD1RQ_[BHWD]_IMM$",
-                                           "^LD1RQ_[BWD]$")>;
+                                           "^LD1RQ_[BDW]$")>;
+
 def : InstRW<[V1Write_7c_1L01_1S], (instregex "^LD1H$",
+                                              "^LD1H_IMM$",
+					      "^LD1H_[SD]_IMM$",
                                               "^LD1S?H_[SD]$",
                                               "^LD1RQ_H$")>;
 
@@ -1864,42 +2000,47 @@ def : InstRW<[V1Write_6c_1L01], (instregex "^LDNF1[BHWD]_IMM$",
                                            "^LDNF1S?W_D_IMM$")>;
 
 // Contiguous Load two structures to two vectors, scalar + imm
-def : InstRW<[V1Write_8c_2L01_2V01], (instregex "^LD2[BHWD]_IMM$")>;
+def : InstRW<[V1Write_8c2_2L01_2V01], (instregex "^LD2[BHWD]_IMM$")>;
 
 // Contiguous Load two structures to two vectors, scalar + scalar
-def : InstRW<[V1Write_10c_2L01_2V01], (instrs LD2H)>;
-def : InstRW<[V1Write_9c_2L01_2V01],  (instregex "^LD2[BWD]$")>;
+def : InstRW<[V1Write_10c2_1L01_1V01_1S], (instrs LD2H)>;
+def : InstRW<[V1Write_9c2_1L01_1V01],  (instregex "^LD2[BWD]$")>;
 
 // Contiguous Load three structures to three vectors, scalar + imm
-def : InstRW<[V1Write_11c_3L01_3V01], (instregex "^LD3[BHWD]_IMM$")>;
+def : InstRW<[V1Write_11c6_1L01_1V01], (instregex "^LD3[BHWD]_IMM$")>;
 
 // Contiguous Load three structures to three vectors, scalar + scalar
-def : InstRW<[V1Write_13c_3L01_1S_3V01], (instregex "^LD3[BHWD]$")>;
+def : InstRW<[V1Write_13c6_1L01_1S_1V01], (instregex "^LD3[BHWD]$")>;
 
 // Contiguous Load four structures to four vectors, scalar + imm
-def : InstRW<[V1Write_12c_4L01_4V01], (instregex "^LD4[BHWD]_IMM$")>;
+def : InstRW<[V1Write_12c8_1L01_1V01], (instregex "^LD4[BHWD]_IMM$")>;
 
 // Contiguous Load four structures to four vectors, scalar + scalar
-def : InstRW<[V1Write_13c_4L01_2S_4V01], (instregex "^LD4[BHWD]$")>;
+def : InstRW<[V1Write_13c8_1L01_1S_1V01], (instregex "^LD4[BHWD]$")>;
 
 // Gather load, vector + imm, 32-bit element size
-def : InstRW<[V1Write_11c_1L_1V], (instregex "^GLD(FF)?1S?[BH]_S_IMM$",
+def : InstRW<[V1Write_11c12_1L_1V], (instregex "^GLD(FF)?1S?[BH]_S_IMM$",
                                              "^GLD(FF)?1W_IMM$")>;
 
 // Gather load, vector + imm, 64-bit element size
-def : InstRW<[V1Write_9c_2L_2V],
+def : InstRW<[V1Write_9c6_1L_1V],
              (instregex "^GLD(FF)?1S?[BHW]_D_IMM$",
-                        "^GLD(FF)?1S?[BHW]_D(_[SU]XTW)?(_SCALED)?$",
+                        "^GLD(FF)?1S?[BHW]_D(_[SU]XTW)?$",
                         "^GLD(FF)?1D_IMM$",
-                        "^GLD(FF)?1D(_[SU]XTW)?(_SCALED)?$")>;
+                        "^GLD(FF)?1D(_[SU]XTW)?$")>;
+
 
 // Gather load, 32-bit scaled offset
-def : InstRW<[V1Write_11c_2L_2V],
-             (instregex "^GLD(FF)?1S?[HW]_S_[SU]XTW_SCALED$",
-                        "^GLD(FF)?1W_[SU]XTW_SCALED")>;
+def : InstRW<[V1Write_11c12_1L_1V],
+               (instregex "^GLD(FF)?1D(_[US]XTW)?_SCALED$",
+                          "^GLD(FF)?1S?[HW]_D(_[US]XTW)?_SCALED$",
+                          "^GLD(FF)?1S?H_S_[US]XTW_SCALED$",
+                          "^GLD(FF)?1W_[US]XTW_SCALED$",
+                          "^GLDFF1W_D_[US]XTW_SCALED$",
+                          "^GLD1SH_S_[US]XTW_SCALED$")>;
 
 // Gather load, 32-bit unpacked unscaled offset
-def : InstRW<[V1Write_9c_1L_1V],
+def : InstRW<[V1Write_9c6_1L_1V],
              (instregex "^GLD(FF)?1S?[BH]_S_[SU]XTW$",
                         "^GLD(FF)?1W_[SU]XTW$")>;
 
@@ -1918,33 +2059,34 @@ def : InstRW<[V1Write_1c_1L01], (instrs STR_PXI)>;
 def : InstRW<[V1Write_2c_1L01_1V], (instrs STR_ZXI)>;
 
 // Contiguous store, scalar + imm
-// Contiguous store, scalar + scalar
 def : InstRW<[V1Write_2c_1L01_1V], (instregex "^ST1[BHWD]_IMM$",
                                               "^ST1B_[HSD]_IMM$",
                                               "^ST1H_[SD]_IMM$",
-                                              "^ST1W_D_IMM$",
-                                              "^ST1[BWD]$",
+                                              "^ST1W_D_IMM$")>;
+// Contiguous store, scalar + scalar
+def : InstRW<[V1Write_2c_1L01_1V], (instregex "^ST1[BWD]$",
                                               "^ST1B_[HSD]$",
                                               "^ST1W_D$")>;
+
 def : InstRW<[V1Write_2c_1L01_1S_1V], (instregex "^ST1H(_[SD])?$")>;
 
 // Contiguous store two structures from two vectors, scalar + imm
 // Contiguous store two structures from two vectors, scalar + scalar
-def : InstRW<[V1Write_4c_1L01_1V], (instregex "^ST2[BHWD]_IMM$",
+def : InstRW<[V1Write_4c2_1L01_1V], (instregex "^ST2[BHWD]_IMM$",
                                               "^ST2[BWD]$")>;
 def : InstRW<[V1Write_4c_1L01_1S_1V], (instrs ST2H)>;
 
 // Contiguous store three structures from three vectors, scalar + imm
-def : InstRW<[V1Write_7c_5L01_5V], (instregex "^ST3[BHWD]_IMM$")>;
+def : InstRW<[V1Write_7c9_1L01_1V], (instregex "^ST3[BHWD]_IMM$")>;
 
 // Contiguous store three structures from three vectors, scalar + scalar
-def : InstRW<[V1Write_7c_5L01_5S_5V], (instregex "^ST3[BHWD]$")>;
+def : InstRW<[V1Write_7c9_1L01_1S_1V], (instregex "^ST3[BHWD]$")>;
 
 // Contiguous store four structures from four vectors, scalar + imm
-def : InstRW<[V1Write_11c_9L01_9V], (instregex "^ST4[BHWD]_IMM$")>;
+def : InstRW<[V1Write_11c18_1L01_1V], (instregex "^ST4[BHWD]_IMM$")>;
 
 // Contiguous store four structures from four vectors, scalar + scalar
-def : InstRW<[V1Write_11c_9L01_9S_9V], (instregex "^ST4[BHWD]$")>;
+def : InstRW<[V1Write_11c18_1L01_1S_1V], (instregex "^ST4[BHWD]$")>;
 
 // Non temporal store, scalar + imm
 // Non temporal store, scalar + scalar
@@ -1953,29 +2095,34 @@ def : InstRW<[V1Write_2c_1L01_1V], (instregex "^STNT1[BHWD]_ZRI$",
 def : InstRW<[V1Write_2c_1L01_1S_1V], (instrs STNT1H_ZRR)>;
 
 // Scatter store vector + imm 32-bit element size
+def : InstRW<[V1Write_10c8_1L01_1V], (instregex "^SST1[BH]_S_IMM$",
+                                               "^SST1W_IMM$")>;
+
 // Scatter store, 32-bit scaled offset
+def : InstRW<[V1Write_10c8_1L01_1V], (instregex "^SST1(H_S|W)_[SU]XTW_SCALED$")>;
+
 // Scatter store, 32-bit unscaled offset
-def : InstRW<[V1Write_10c_2L01_2V], (instregex "^SST1[BH]_S_IMM$",
-                                               "^SST1W_IMM$",
-                                               "^SST1(H_S|W)_[SU]XTW_SCALED$",
-                                               "^SST1[BH]_S_[SU]XTW$",
+def : InstRW<[V1Write_10c8_1L01_1V], (instregex "^SST1[BH]_S_[SU]XTW$",
                                                "^SST1W_[SU]XTW$")>;
 
 // Scatter store, 32-bit unpacked unscaled offset
+def : InstRW<[V1Write_6c4_1L01_1V], (instregex "^SST1[BHW]_D_[SU]XTW$",
+                                              "^SST1D_[SU]XTW$")>;
+
 // Scatter store, 32-bit unpacked scaled offset
-def : InstRW<[V1Write_6c_1L01_1V], (instregex "^SST1[BHW]_D_[SU]XTW$",
-                                              "^SST1D_[SU]XTW$",
-                                              "^SST1[HW]_D_[SU]XTW_SCALED$",
+def : InstRW<[V1Write_6c4_1L01_1V], (instregex "^SST1[HW]_D_[SU]XTW_SCALED$",
                                               "^SST1D_[SU]XTW_SCALED$")>;
 
 // Scatter store vector + imm 64-bit element size
+def : InstRW<[V1Write_6c4_1L01_1V], (instregex "^SST1[BHW]_D_IMM$",
+                                              "^SST1D_IMM$")>;
+
 // Scatter store, 64-bit scaled offset
+def : InstRW<[V1Write_6c4_1L01_1V], (instregex "^SST1[HW]_D_SCALED$",
+                                                  "^SST1D_SCALED$")>;
+
 // Scatter store, 64-bit unscaled offset
-def : InstRW<[V1Write_6c_1L01_1V], (instregex "^SST1[BHW]_D_IMM$",
-                                              "^SST1D_IMM$",
-                                              "^SST1[HW]_D_SCALED$",
-                                              "^SST1D_SCALED$",
-                                              "^SST1[BHW]_D$",
+def : InstRW<[V1Write_6c4_1L01_1V], (instregex "^SST1[BHW]_D$",
                                               "^SST1D$")>;
 
 
@@ -1990,10 +2137,10 @@ def : InstRW<[V1Write_2c_1M0], (instrs RDFFR_P,
                                        WRFFR)>;
 
 // Read first fault register, predicated
-def : InstRW<[V1Write_3c_2M0], (instrs RDFFR_PPz)>;
+def : InstRW<[V1Write_3c2_1M0], (instrs RDFFR_PPz)>;
 
 // Read first fault register and set flags
-def : InstRW<[V1Write_4c_1M], (instrs RDFFRS_PPz)>;
+def : InstRW<[V1Write_4c6_1M], (instrs RDFFRS_PPz)>;
 
 
 }
diff --git a/llvm/lib/Target/AArch64/AArch64SchedPredNeoverse.td b/llvm/lib/Target/AArch64/AArch64SchedPredNeoverse.td
index 33b76a4f65f05..c26c9b94cc9fa 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedPredNeoverse.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedPredNeoverse.td
@@ -18,6 +18,38 @@ def NeoverseNoLSL : MCSchedPredicate<
                       CheckAll<[CheckShiftLSL,
                                 CheckShiftBy0]>>;
 
+def Check32Ext : CheckAny<[CheckExtUXTB,
+			   CheckExtUXTH,
+			   CheckExtUXTX,
+			   CheckExtSXTB,
+		           CheckExtSXTH,
+			   CheckExtSXTW,
+			   CheckExtSXTX]>;
+
+def Check64Ext : CheckAny<[CheckExtUXTB,
+			   CheckExtUXTH,
+			   CheckExtUXTW,
+			   CheckExtSXTB,
+			   CheckExtSXTH,
+			   CheckExtSXTW,
+			   CheckExtSXTX]>;
+
+// Identify arithmetic instructions with an extended register.
+def RegExtendAndShiftFn : TIIPredicate<"hasExtendAndShiftReg",
+			      MCOpcodeSwitchStatement<
+				[MCOpcodeSwitchCase<
+				   IsArith64ExtOp.ValidOpcodes,
+				     MCReturnStatement<
+				       CheckAll<[
+					 Check64Ext,
+					 CheckAny<[
+					   CheckExtBy1,
+					   CheckExtBy2,
+					   CheckExtBy3,
+					   CheckExtBy4]>]>>>],
+				     MCReturnStatement<FalsePred>>>;
+def RegExtendAndShiftPred   : MCSchedPredicate<RegExtendAndShiftFn>;
+
 // Identify LDR/STR H/Q-form scaled (and potentially extended) FP instructions
 def NeoverseHQForm : MCSchedPredicate<
                        CheckAll<[
@@ -82,3 +114,14 @@ def NeoverseZeroMove : MCSchedPredicate<
                            CheckAll<[CheckOpcode<[MOVID, MOVIv2d_ns]>,
                                      CheckImmOperand<1, 0>]>
                          ]>>;
+
+// Identify a load or store using the register offset addressing mode
+// with a scaled register.
+def NeoverseScaledIdxFn       : TIIPredicate<"isNeoverseScaledAddr",
+                                     MCOpcodeSwitchStatement<
+                                       [MCOpcodeSwitchCase<
+                                          IsLoadStoreRegOffsetOp.ValidOpcodes,
+                                          MCReturnStatement<
+                                            CheckAny<[CheckMemScaled]>>>],
+                                       MCReturnStatement<FalsePred>>>;
+def NeoverseScaledIdxPred     : MCSchedPredicate<NeoverseScaledIdxFn>;
diff --git a/llvm/lib/Target/AArch64/AArch64SchedPredicates.td b/llvm/lib/Target/AArch64/AArch64SchedPredicates.td
index 854d3ce564831..2872529ab202d 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedPredicates.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedPredicates.td
@@ -26,7 +26,7 @@ let FunctionMapper = "AArch64_AM::getArithExtendType" in {
 }
 
 // Check for shifting in extended arithmetic instructions.
-foreach I = {0-3} in {
+foreach I = {0-4} in {
   let FunctionMapper = "AArch64_AM::getArithShiftValue" in
   def CheckExtBy#I                      : CheckImmOperand<3, I>;
 }
@@ -91,11 +91,17 @@ def CheckQForm : CheckFunctionPredicateWithTII<
 >;
 
 // Identify arithmetic instructions with extend.
-def IsArithExtOp           : CheckOpcode<[ADDWrx, ADDXrx, ADDSWrx, ADDSXrx,
-                                          SUBWrx, SUBXrx, SUBSWrx, SUBSXrx,
+def IsArith32ExtOp         : CheckOpcode<[ADDWrx, ADDSWrx,
+                                          SUBWrx, SUBSWrx]>;
+
+def IsArith64ExtOp         : CheckOpcode<[ADDXrx, ADDSXrx,
+                                          SUBXrx, SUBSXrx,
                                           ADDXrx64, ADDSXrx64,
                                           SUBXrx64, SUBSXrx64]>;
 
+def IsArithExtOp           : CheckOpcode<!listconcat(IsArith32ExtOp.ValidOpcodes,
+						     IsArith64ExtOp.ValidOpcodes)>;
+
 // Identify arithmetic immediate instructions.
 def IsArithImmOp           : CheckOpcode<[ADDWri, ADDXri, ADDSWri, ADDSXri,
                                           SUBWri, SUBXri, SUBSWri, SUBSXri]>;
@@ -276,6 +282,28 @@ def IsCheapLSL        : MCSchedPredicate<
                                 CheckShiftBy3,
                                 CheckShiftBy4]>]>>;
 
+// Check for arith LSL shift <= 4
+def IsCheapArithLSL    : MCSchedPredicate<
+                          CheckAll<
+                            [CheckShiftLSL,
+                             CheckAny<
+                               [CheckExtBy0,
+                                CheckExtBy1,
+                                CheckExtBy2,
+                                CheckExtBy3,
+                                CheckExtBy4]>]>>;
+
+// Check if logical instruction has shifted operand
+def hasShiftedOpndFn  : TIIPredicate<"hasShiftedOpnd",
+                                     MCOpcodeSwitchStatement<
+                                       [MCOpcodeSwitchCase<
+                                          IsLogicShiftOp.ValidOpcodes,
+                                          MCReturnStatement<
+					    CheckAll<[CheckAny<[CheckShiftLSL,CheckShiftLSR,CheckShiftASR]>,
+                                                      CheckNot<CheckShiftBy0>]>>>],
+                                       MCReturnStatement<FalsePred>>>;
+def hasShiftedOpndPred     : MCSchedPredicate<hasShiftedOpndFn>;
+
 // Idioms.
 
 // Identify an instruction that effectively transfers a register to another.
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-basic-instructions.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-basic-instructions.s
index a5330b9d6d2d6..ab89f98564cbc 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-basic-instructions.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-basic-instructions.s
@@ -1392,16 +1392,16 @@ drps
 # CHECK-NEXT:  1      1     0.25                        sub	w4, w20, #546, lsl #12
 # CHECK-NEXT:  1      1     0.25                        sub	sp, sp, #288
 # CHECK-NEXT:  1      1     0.25                        sub	wsp, w19, #16
-# CHECK-NEXT:  1      1     0.33                        adds	w13, w23, #291, lsl #12
-# CHECK-NEXT:  1      1     0.33                        cmn	w2, #4095
-# CHECK-NEXT:  1      1     0.33                        adds	w20, wsp, #0
-# CHECK-NEXT:  1      1     0.33                        cmn	x3, #1, lsl #12
-# CHECK-NEXT:  1      1     0.33                        cmp	sp, #20, lsl #12
-# CHECK-NEXT:  1      1     0.33                        cmp	x30, #4095
-# CHECK-NEXT:  1      1     0.33                        subs	x4, sp, #3822
-# CHECK-NEXT:  1      1     0.33                        cmn	w3, #291, lsl #12
-# CHECK-NEXT:  1      1     0.33                        cmn	wsp, #1365
-# CHECK-NEXT:  1      1     0.33                        cmn	sp, #1092, lsl #12
+# CHECK-NEXT:  2      2     0.50                        adds	w13, w23, #291, lsl #12
+# CHECK-NEXT:  2      1     0.33                        cmn	w2, #4095
+# CHECK-NEXT:  2      1     0.33                        adds	w20, wsp, #0
+# CHECK-NEXT:  2      2     0.50                        cmn	x3, #1, lsl #12
+# CHECK-NEXT:  2      2     0.50                        cmp	sp, #20, lsl #12
+# CHECK-NEXT:  2      1     0.33                        cmp	x30, #4095
+# CHECK-NEXT:  2      1     0.33                        subs	x4, sp, #3822
+# CHECK-NEXT:  2      2     0.50                        cmn	w3, #291, lsl #12
+# CHECK-NEXT:  2      1     0.33                        cmn	wsp, #1365
+# CHECK-NEXT:  2      2     0.50                        cmn	sp, #1092, lsl #12
 # CHECK-NEXT:  1      1     0.25                        mov	sp, x30
 # CHECK-NEXT:  1      1     0.25                        mov	wsp, w20
 # CHECK-NEXT:  1      1     0.25                        mov	x11, sp
@@ -1432,32 +1432,32 @@ drps
 # CHECK-NEXT:  1      2     0.50                        add	x2, x3, x4, asr #0
 # CHECK-NEXT:  1      2     0.50                        add	x5, x6, x7, asr #21
 # CHECK-NEXT:  1      2     0.50                        add	x8, x9, x10, asr #63
-# CHECK-NEXT:  1      1     0.33                        adds	w3, w5, w7
-# CHECK-NEXT:  1      1     0.33                        cmn	w3, w5
-# CHECK-NEXT:  1      1     0.33                        adds	w20, wzr, w4
-# CHECK-NEXT:  1      1     0.33                        adds	w4, w6, wzr
-# CHECK-NEXT:  1      1     0.33                        adds	w11, w13, w15
-# CHECK-NEXT:  1      1     0.33                        adds	w9, w3, wzr, lsl #1
-# CHECK-NEXT:  1      2     0.50                        adds	w17, w29, w20, lsl #31
-# CHECK-NEXT:  1      2     0.50                        adds	w21, w22, w23, lsr #0
-# CHECK-NEXT:  1      2     0.50                        adds	w24, w25, w26, lsr #18
-# CHECK-NEXT:  1      2     0.50                        adds	w27, w28, w29, lsr #31
-# CHECK-NEXT:  1      2     0.50                        adds	w2, w3, w4, asr #0
-# CHECK-NEXT:  1      2     0.50                        adds	w5, w6, w7, asr #21
-# CHECK-NEXT:  1      2     0.50                        adds	w8, w9, w10, asr #31
-# CHECK-NEXT:  1      1     0.33                        adds	x3, x5, x7
-# CHECK-NEXT:  1      1     0.33                        cmn	x3, x5
-# CHECK-NEXT:  1      1     0.33                        adds	x20, xzr, x4
-# CHECK-NEXT:  1      1     0.33                        adds	x4, x6, xzr
-# CHECK-NEXT:  1      1     0.33                        adds	x11, x13, x15
-# CHECK-NEXT:  1      2     0.50                        adds	x9, x3, xzr, lsl #10
-# CHECK-NEXT:  1      1     0.33                        adds	x17, x29, x20, lsl #3
-# CHECK-NEXT:  1      2     0.50                        adds	x21, x22, x23, lsr #0
-# CHECK-NEXT:  1      2     0.50                        adds	x24, x25, x26, lsr #18
-# CHECK-NEXT:  1      2     0.50                        adds	x27, x28, x29, lsr #63
-# CHECK-NEXT:  1      2     0.50                        adds	x2, x3, x4, asr #0
-# CHECK-NEXT:  1      2     0.50                        adds	x5, x6, x7, asr #21
-# CHECK-NEXT:  1      2     0.50                        adds	x8, x9, x10, asr #63
+# CHECK-NEXT:  2      1     0.33                        adds	w3, w5, w7
+# CHECK-NEXT:  2      1     0.33                        cmn	w3, w5
+# CHECK-NEXT:  2      1     0.33                        adds	w20, wzr, w4
+# CHECK-NEXT:  2      1     0.33                        adds	w4, w6, wzr
+# CHECK-NEXT:  2      1     0.33                        adds	w11, w13, w15
+# CHECK-NEXT:  2      1     0.33                        adds	w9, w3, wzr, lsl #1
+# CHECK-NEXT:  2      2     0.50                        adds	w17, w29, w20, lsl #31
+# CHECK-NEXT:  2      2     0.50                        adds	w21, w22, w23, lsr #0
+# CHECK-NEXT:  2      2     0.50                        adds	w24, w25, w26, lsr #18
+# CHECK-NEXT:  2      2     0.50                        adds	w27, w28, w29, lsr #31
+# CHECK-NEXT:  2      2     0.50                        adds	w2, w3, w4, asr #0
+# CHECK-NEXT:  2      2     0.50                        adds	w5, w6, w7, asr #21
+# CHECK-NEXT:  2      2     0.50                        adds	w8, w9, w10, asr #31
+# CHECK-NEXT:  2      1     0.33                        adds	x3, x5, x7
+# CHECK-NEXT:  2      1     0.33                        cmn	x3, x5
+# CHECK-NEXT:  2      1     0.33                        adds	x20, xzr, x4
+# CHECK-NEXT:  2      1     0.33                        adds	x4, x6, xzr
+# CHECK-NEXT:  2      1     0.33                        adds	x11, x13, x15
+# CHECK-NEXT:  2      2     0.50                        adds	x9, x3, xzr, lsl #10
+# CHECK-NEXT:  2      1     0.33                        adds	x17, x29, x20, lsl #3
+# CHECK-NEXT:  2      2     0.50                        adds	x21, x22, x23, lsr #0
+# CHECK-NEXT:  2      2     0.50                        adds	x24, x25, x26, lsr #18
+# CHECK-NEXT:  2      2     0.50                        adds	x27, x28, x29, lsr #63
+# CHECK-NEXT:  2      2     0.50                        adds	x2, x3, x4, asr #0
+# CHECK-NEXT:  2      2     0.50                        adds	x5, x6, x7, asr #21
+# CHECK-NEXT:  2      2     0.50                        adds	x8, x9, x10, asr #63
 # CHECK-NEXT:  1      1     0.25                        sub	w3, w5, w7
 # CHECK-NEXT:  1      1     0.25                        sub	wzr, w3, w5
 # CHECK-NEXT:  1      1     0.25                        sub	w4, w6, wzr
@@ -1482,78 +1482,78 @@ drps
 # CHECK-NEXT:  1      2     0.50                        sub	x2, x3, x4, asr #0
 # CHECK-NEXT:  1      2     0.50                        sub	x5, x6, x7, asr #21
 # CHECK-NEXT:  1      2     0.50                        sub	x8, x9, x10, asr #63
-# CHECK-NEXT:  1      1     0.33                        subs	w3, w5, w7
-# CHECK-NEXT:  1      1     0.33                        cmp	w3, w5
-# CHECK-NEXT:  1      1     0.33                        subs	w4, w6, wzr
-# CHECK-NEXT:  1      1     0.33                        subs	w11, w13, w15
-# CHECK-NEXT:  1      1     0.33                        subs	w9, w3, wzr, lsl #1
-# CHECK-NEXT:  1      2     0.50                        subs	w17, w29, w20, lsl #31
-# CHECK-NEXT:  1      2     0.50                        subs	w21, w22, w23, lsr #0
-# CHECK-NEXT:  1      2     0.50                        subs	w24, w25, w26, lsr #18
-# CHECK-NEXT:  1      2     0.50                        subs	w27, w28, w29, lsr #31
-# CHECK-NEXT:  1      2     0.50                        subs	w2, w3, w4, asr #0
-# CHECK-NEXT:  1      2     0.50                        subs	w5, w6, w7, asr #21
-# CHECK-NEXT:  1      2     0.50                        subs	w8, w9, w10, asr #31
-# CHECK-NEXT:  1      1     0.33                        subs	x3, x5, x7
-# CHECK-NEXT:  1      1     0.33                        cmp	x3, x5
-# CHECK-NEXT:  1      1     0.33                        subs	x4, x6, xzr
-# CHECK-NEXT:  1      1     0.33                        subs	x11, x13, x15
-# CHECK-NEXT:  1      2     0.50                        subs	x9, x3, xzr, lsl #10
-# CHECK-NEXT:  1      1     0.33                        subs	x17, x29, x20, lsl #3
-# CHECK-NEXT:  1      2     0.50                        subs	x21, x22, x23, lsr #0
-# CHECK-NEXT:  1      2     0.50                        subs	x24, x25, x26, lsr #18
-# CHECK-NEXT:  1      2     0.50                        subs	x27, x28, x29, lsr #63
-# CHECK-NEXT:  1      2     0.50                        subs	x2, x3, x4, asr #0
-# CHECK-NEXT:  1      2     0.50                        subs	x5, x6, x7, asr #21
-# CHECK-NEXT:  1      2     0.50                        subs	x8, x9, x10, asr #63
-# CHECK-NEXT:  1      1     0.33                        cmn	wzr, w4
-# CHECK-NEXT:  1      1     0.33                        cmn	w5, wzr
-# CHECK-NEXT:  1      1     0.33                        cmn	w6, w7
-# CHECK-NEXT:  1      1     0.33                        cmn	w8, w9, lsl #1
-# CHECK-NEXT:  1      2     0.50                        cmn	w10, w11, lsl #31
-# CHECK-NEXT:  1      2     0.50                        cmn	w12, w13, lsr #0
-# CHECK-NEXT:  1      2     0.50                        cmn	w14, w15, lsr #21
-# CHECK-NEXT:  1      2     0.50                        cmn	w16, w17, lsr #31
-# CHECK-NEXT:  1      2     0.50                        cmn	w18, w19, asr #0
-# CHECK-NEXT:  1      2     0.50                        cmn	w20, w21, asr #22
-# CHECK-NEXT:  1      2     0.50                        cmn	w22, w23, asr #31
-# CHECK-NEXT:  1      1     0.33                        cmn	x0, x3
-# CHECK-NEXT:  1      1     0.33                        cmn	xzr, x4
-# CHECK-NEXT:  1      1     0.33                        cmn	x5, xzr
-# CHECK-NEXT:  1      1     0.33                        cmn	x6, x7
-# CHECK-NEXT:  1      2     0.50                        cmn	x8, x9, lsl #15
-# CHECK-NEXT:  1      1     0.33                        cmn	x10, x11, lsl #3
-# CHECK-NEXT:  1      2     0.50                        cmn	x12, x13, lsr #0
-# CHECK-NEXT:  1      2     0.50                        cmn	x14, x15, lsr #41
-# CHECK-NEXT:  1      2     0.50                        cmn	x16, x17, lsr #63
-# CHECK-NEXT:  1      2     0.50                        cmn	x18, x19, asr #0
-# CHECK-NEXT:  1      2     0.50                        cmn	x20, x21, asr #55
-# CHECK-NEXT:  1      2     0.50                        cmn	x22, x23, asr #63
-# CHECK-NEXT:  1      1     0.33                        cmp	w0, w3
-# CHECK-NEXT:  1      1     0.33                        cmp	wzr, w4
-# CHECK-NEXT:  1      1     0.33                        cmp	w5, wzr
-# CHECK-NEXT:  1      1     0.33                        cmp	w6, w7
-# CHECK-NEXT:  1      1     0.33                        cmp	w8, w9, lsl #1
-# CHECK-NEXT:  1      2     0.50                        cmp	w10, w11, lsl #31
-# CHECK-NEXT:  1      2     0.50                        cmp	w12, w13, lsr #0
-# CHECK-NEXT:  1      2     0.50                        cmp	w14, w15, lsr #21
-# CHECK-NEXT:  1      2     0.50                        cmp	w18, w19, asr #0
-# CHECK-NEXT:  1      2     0.50                        cmp	w20, w21, asr #22
-# CHECK-NEXT:  1      2     0.50                        cmp	w22, w23, asr #31
-# CHECK-NEXT:  1      1     0.33                        cmp	x0, x3
-# CHECK-NEXT:  1      1     0.33                        cmp	xzr, x4
-# CHECK-NEXT:  1      1     0.33                        cmp	x5, xzr
-# CHECK-NEXT:  1      1     0.33                        cmp	x6, x7
-# CHECK-NEXT:  1      2     0.50                        cmp	x8, x9, lsl #15
-# CHECK-NEXT:  1      1     0.33                        cmp	x10, x11, lsl #3
-# CHECK-NEXT:  1      2     0.50                        cmp	x12, x13, lsr #0
-# CHECK-NEXT:  1      2     0.50                        cmp	x14, x15, lsr #41
-# CHECK-NEXT:  1      2     0.50                        cmp	x16, x17, lsr #63
-# CHECK-NEXT:  1      2     0.50                        cmp	x18, x19, asr #0
-# CHECK-NEXT:  1      2     0.50                        cmp	x20, x21, asr #55
-# CHECK-NEXT:  1      2     0.50                        cmp	x22, x23, asr #63
-# CHECK-NEXT:  1      1     0.33                        cmp	wzr, w0
-# CHECK-NEXT:  1      1     0.33                        cmp	xzr, x0
+# CHECK-NEXT:  2      1     0.33                        subs	w3, w5, w7
+# CHECK-NEXT:  2      1     0.33                        cmp	w3, w5
+# CHECK-NEXT:  2      1     0.33                        subs	w4, w6, wzr
+# CHECK-NEXT:  2      1     0.33                        subs	w11, w13, w15
+# CHECK-NEXT:  2      1     0.33                        subs	w9, w3, wzr, lsl #1
+# CHECK-NEXT:  2      2     0.50                        subs	w17, w29, w20, lsl #31
+# CHECK-NEXT:  2      2     0.50                        subs	w21, w22, w23, lsr #0
+# CHECK-NEXT:  2      2     0.50                        subs	w24, w25, w26, lsr #18
+# CHECK-NEXT:  2      2     0.50                        subs	w27, w28, w29, lsr #31
+# CHECK-NEXT:  2      2     0.50                        subs	w2, w3, w4, asr #0
+# CHECK-NEXT:  2      2     0.50                        subs	w5, w6, w7, asr #21
+# CHECK-NEXT:  2      2     0.50                        subs	w8, w9, w10, asr #31
+# CHECK-NEXT:  2      1     0.33                        subs	x3, x5, x7
+# CHECK-NEXT:  2      1     0.33                        cmp	x3, x5
+# CHECK-NEXT:  2      1     0.33                        subs	x4, x6, xzr
+# CHECK-NEXT:  2      1     0.33                        subs	x11, x13, x15
+# CHECK-NEXT:  2      2     0.50                        subs	x9, x3, xzr, lsl #10
+# CHECK-NEXT:  2      1     0.33                        subs	x17, x29, x20, lsl #3
+# CHECK-NEXT:  2      2     0.50                        subs	x21, x22, x23, lsr #0
+# CHECK-NEXT:  2      2     0.50                        subs	x24, x25, x26, lsr #18
+# CHECK-NEXT:  2      2     0.50                        subs	x27, x28, x29, lsr #63
+# CHECK-NEXT:  2      2     0.50                        subs	x2, x3, x4, asr #0
+# CHECK-NEXT:  2      2     0.50                        subs	x5, x6, x7, asr #21
+# CHECK-NEXT:  2      2     0.50                        subs	x8, x9, x10, asr #63
+# CHECK-NEXT:  2      1     0.33                        cmn	wzr, w4
+# CHECK-NEXT:  2      1     0.33                        cmn	w5, wzr
+# CHECK-NEXT:  2      1     0.33                        cmn	w6, w7
+# CHECK-NEXT:  2      1     0.33                        cmn	w8, w9, lsl #1
+# CHECK-NEXT:  2      2     0.50                        cmn	w10, w11, lsl #31
+# CHECK-NEXT:  2      2     0.50                        cmn	w12, w13, lsr #0
+# CHECK-NEXT:  2      2     0.50                        cmn	w14, w15, lsr #21
+# CHECK-NEXT:  2      2     0.50                        cmn	w16, w17, lsr #31
+# CHECK-NEXT:  2      2     0.50                        cmn	w18, w19, asr #0
+# CHECK-NEXT:  2      2     0.50                        cmn	w20, w21, asr #22
+# CHECK-NEXT:  2      2     0.50                        cmn	w22, w23, asr #31
+# CHECK-NEXT:  2      1     0.33                        cmn	x0, x3
+# CHECK-NEXT:  2      1     0.33                        cmn	xzr, x4
+# CHECK-NEXT:  2      1     0.33                        cmn	x5, xzr
+# CHECK-NEXT:  2      1     0.33                        cmn	x6, x7
+# CHECK-NEXT:  2      2     0.50                        cmn	x8, x9, lsl #15
+# CHECK-NEXT:  2      1     0.33                        cmn	x10, x11, lsl #3
+# CHECK-NEXT:  2      2     0.50                        cmn	x12, x13, lsr #0
+# CHECK-NEXT:  2      2     0.50                        cmn	x14, x15, lsr #41
+# CHECK-NEXT:  2      2     0.50                        cmn	x16, x17, lsr #63
+# CHECK-NEXT:  2      2     0.50                        cmn	x18, x19, asr #0
+# CHECK-NEXT:  2      2     0.50                        cmn	x20, x21, asr #55
+# CHECK-NEXT:  2      2     0.50                        cmn	x22, x23, asr #63
+# CHECK-NEXT:  2      1     0.33                        cmp	w0, w3
+# CHECK-NEXT:  2      1     0.33                        cmp	wzr, w4
+# CHECK-NEXT:  2      1     0.33                        cmp	w5, wzr
+# CHECK-NEXT:  2      1     0.33                        cmp	w6, w7
+# CHECK-NEXT:  2      1     0.33                        cmp	w8, w9, lsl #1
+# CHECK-NEXT:  2      2     0.50                        cmp	w10, w11, lsl #31
+# CHECK-NEXT:  2      2     0.50                        cmp	w12, w13, lsr #0
+# CHECK-NEXT:  2      2     0.50                        cmp	w14, w15, lsr #21
+# CHECK-NEXT:  2      2     0.50                        cmp	w18, w19, asr #0
+# CHECK-NEXT:  2      2     0.50                        cmp	w20, w21, asr #22
+# CHECK-NEXT:  2      2     0.50                        cmp	w22, w23, asr #31
+# CHECK-NEXT:  2      1     0.33                        cmp	x0, x3
+# CHECK-NEXT:  2      1     0.33                        cmp	xzr, x4
+# CHECK-NEXT:  2      1     0.33                        cmp	x5, xzr
+# CHECK-NEXT:  2      1     0.33                        cmp	x6, x7
+# CHECK-NEXT:  2      2     0.50                        cmp	x8, x9, lsl #15
+# CHECK-NEXT:  2      1     0.33                        cmp	x10, x11, lsl #3
+# CHECK-NEXT:  2      2     0.50                        cmp	x12, x13, lsr #0
+# CHECK-NEXT:  2      2     0.50                        cmp	x14, x15, lsr #41
+# CHECK-NEXT:  2      2     0.50                        cmp	x16, x17, lsr #63
+# CHECK-NEXT:  2      2     0.50                        cmp	x18, x19, asr #0
+# CHECK-NEXT:  2      2     0.50                        cmp	x20, x21, asr #55
+# CHECK-NEXT:  2      2     0.50                        cmp	x22, x23, asr #63
+# CHECK-NEXT:  2      1     0.33                        cmp	wzr, w0
+# CHECK-NEXT:  2      1     0.33                        cmp	xzr, x0
 # CHECK-NEXT:  1      1     0.25                        adc	w29, w27, w25
 # CHECK-NEXT:  1      1     0.25                        adc	wzr, w3, w4
 # CHECK-NEXT:  1      1     0.25                        adc	w9, wzr, w10
@@ -1562,14 +1562,14 @@ drps
 # CHECK-NEXT:  1      1     0.25                        adc	xzr, x3, x4
 # CHECK-NEXT:  1      1     0.25                        adc	x9, xzr, x10
 # CHECK-NEXT:  1      1     0.25                        adc	x20, x0, xzr
-# CHECK-NEXT:  1      1     0.33                        adcs	w29, w27, w25
-# CHECK-NEXT:  1      1     0.33                        adcs	wzr, w3, w4
-# CHECK-NEXT:  1      1     0.33                        adcs	w9, wzr, w10
-# CHECK-NEXT:  1      1     0.33                        adcs	w20, w0, wzr
-# CHECK-NEXT:  1      1     0.33                        adcs	x29, x27, x25
-# CHECK-NEXT:  1      1     0.33                        adcs	xzr, x3, x4
-# CHECK-NEXT:  1      1     0.33                        adcs	x9, xzr, x10
-# CHECK-NEXT:  1      1     0.33                        adcs	x20, x0, xzr
+# CHECK-NEXT:  2      1     0.33                        adcs	w29, w27, w25
+# CHECK-NEXT:  2      1     0.33                        adcs	wzr, w3, w4
+# CHECK-NEXT:  2      1     0.33                        adcs	w9, wzr, w10
+# CHECK-NEXT:  2      1     0.33                        adcs	w20, w0, wzr
+# CHECK-NEXT:  2      1     0.33                        adcs	x29, x27, x25
+# CHECK-NEXT:  2      1     0.33                        adcs	xzr, x3, x4
+# CHECK-NEXT:  2      1     0.33                        adcs	x9, xzr, x10
+# CHECK-NEXT:  2      1     0.33                        adcs	x20, x0, xzr
 # CHECK-NEXT:  1      1     0.25                        sbc	w29, w27, w25
 # CHECK-NEXT:  1      1     0.25                        sbc	wzr, w3, w4
 # CHECK-NEXT:  1      1     0.25                        ngc	w9, w10
@@ -1578,26 +1578,26 @@ drps
 # CHECK-NEXT:  1      1     0.25                        sbc	xzr, x3, x4
 # CHECK-NEXT:  1      1     0.25                        ngc	x9, x10
 # CHECK-NEXT:  1      1     0.25                        sbc	x20, x0, xzr
-# CHECK-NEXT:  1      1     0.33                        sbcs	w29, w27, w25
-# CHECK-NEXT:  1      1     0.33                        sbcs	wzr, w3, w4
-# CHECK-NEXT:  1      1     0.33                        ngcs	w9, w10
-# CHECK-NEXT:  1      1     0.33                        sbcs	w20, w0, wzr
-# CHECK-NEXT:  1      1     0.33                        sbcs	x29, x27, x25
-# CHECK-NEXT:  1      1     0.33                        sbcs	xzr, x3, x4
-# CHECK-NEXT:  1      1     0.33                        ngcs	x9, x10
-# CHECK-NEXT:  1      1     0.33                        sbcs	x20, x0, xzr
+# CHECK-NEXT:  2      1     0.33                        sbcs	w29, w27, w25
+# CHECK-NEXT:  2      1     0.33                        sbcs	wzr, w3, w4
+# CHECK-NEXT:  2      1     0.33                        ngcs	w9, w10
+# CHECK-NEXT:  2      1     0.33                        sbcs	w20, w0, wzr
+# CHECK-NEXT:  2      1     0.33                        sbcs	x29, x27, x25
+# CHECK-NEXT:  2      1     0.33                        sbcs	xzr, x3, x4
+# CHECK-NEXT:  2      1     0.33                        ngcs	x9, x10
+# CHECK-NEXT:  2      1     0.33                        sbcs	x20, x0, xzr
 # CHECK-NEXT:  1      1     0.25                        ngc	w3, w12
 # CHECK-NEXT:  1      1     0.25                        ngc	wzr, w9
 # CHECK-NEXT:  1      1     0.25                        ngc	w23, wzr
 # CHECK-NEXT:  1      1     0.25                        ngc	x29, x30
 # CHECK-NEXT:  1      1     0.25                        ngc	xzr, x0
 # CHECK-NEXT:  1      1     0.25                        ngc	x0, xzr
-# CHECK-NEXT:  1      1     0.33                        ngcs	w3, w12
-# CHECK-NEXT:  1      1     0.33                        ngcs	wzr, w9
-# CHECK-NEXT:  1      1     0.33                        ngcs	w23, wzr
-# CHECK-NEXT:  1      1     0.33                        ngcs	x29, x30
-# CHECK-NEXT:  1      1     0.33                        ngcs	xzr, x0
-# CHECK-NEXT:  1      1     0.33                        ngcs	x0, xzr
+# CHECK-NEXT:  2      1     0.33                        ngcs	w3, w12
+# CHECK-NEXT:  2      1     0.33                        ngcs	wzr, w9
+# CHECK-NEXT:  2      1     0.33                        ngcs	w23, wzr
+# CHECK-NEXT:  2      1     0.33                        ngcs	x29, x30
+# CHECK-NEXT:  2      1     0.33                        ngcs	xzr, x0
+# CHECK-NEXT:  2      1     0.33                        ngcs	x0, xzr
 # CHECK-NEXT:  1      1     0.25                        sbfx	x1, x2, #3, #2
 # CHECK-NEXT:  1      1     0.25                        asr	x3, x4, #63
 # CHECK-NEXT:  1      1     0.25                        asr	wzr, wzr, #31
@@ -1784,10 +1784,10 @@ drps
 # CHECK-NEXT:  1      1     0.25                        clz	x26, x4
 # CHECK-NEXT:  1      1     0.25                        cls	w3, w5
 # CHECK-NEXT:  1      1     0.25                        cls	x20, x5
-# CHECK-NEXT:  1      12    5.00                        udiv	w0, w7, w10
-# CHECK-NEXT:  1      20    5.00                        udiv	x9, x22, x4
-# CHECK-NEXT:  1      12    5.00                        sdiv	w12, w21, w0
-# CHECK-NEXT:  1      20    5.00                        sdiv	x13, x2, x1
+# CHECK-NEXT:  1      12    12.00                       udiv	w0, w7, w10
+# CHECK-NEXT:  1      20    20.00                       udiv	x9, x22, x4
+# CHECK-NEXT:  1      12    12.00                       sdiv	w12, w21, w0
+# CHECK-NEXT:  1      20    20.00                       sdiv	x13, x2, x1
 # CHECK-NEXT:  1      1     0.25                        lsl	w11, w12, w13
 # CHECK-NEXT:  1      1     0.25                        lsl	x14, x15, x16
 # CHECK-NEXT:  1      1     0.25                        lsr	w17, w18, w19
@@ -1855,10 +1855,10 @@ drps
 # CHECK-NEXT:  1      2     0.50                        umull	x11, w13, w17
 # CHECK-NEXT:  1      2     0.50                        smnegl	x11, w13, w17
 # CHECK-NEXT:  1      2     0.50                        umnegl	x11, w13, w17
-# CHECK-NEXT:  2      3     0.50                        extr	w3, w5, w7, #0
-# CHECK-NEXT:  2      3     0.50                        extr	w11, w13, w17, #31
-# CHECK-NEXT:  2      3     0.50                        extr	x3, x5, x7, #15
-# CHECK-NEXT:  2      3     0.50                        extr	x11, x13, x17, #63
+# CHECK-NEXT:  1      3     0.50                        extr	w3, w5, w7, #0
+# CHECK-NEXT:  1      3     0.50                        extr	w11, w13, w17, #31
+# CHECK-NEXT:  1      3     0.50                        extr	x3, x5, x7, #15
+# CHECK-NEXT:  1      3     0.50                        extr	x11, x13, x17, #63
 # CHECK-NEXT:  1      1     0.25                        ror	x19, x23, #24
 # CHECK-NEXT:  1      1     0.25                        ror	x29, xzr, #63
 # CHECK-NEXT:  1      1     0.25                        ror	w9, w13, #31
@@ -1891,7 +1891,7 @@ drps
 # CHECK-NEXT:  1      2     0.25                        fmov	s0, s1
 # CHECK-NEXT:  1      2     0.25                        fabs	s2, s3
 # CHECK-NEXT:  1      2     0.25                        fneg	s4, s5
-# CHECK-NEXT:  1      10    3.50                        fsqrt	s6, s7
+# CHECK-NEXT:  1      9     1.00                        fsqrt	s6, s7
 # CHECK-NEXT:  1      3     0.50                        fcvt	d8, s9
 # CHECK-NEXT:  1      3     0.50                        fcvt	h10, s11
 # CHECK-NEXT:  1      3     0.50                        frintn	s12, s13
@@ -1904,7 +1904,7 @@ drps
 # CHECK-NEXT:  1      2     0.25                        fmov	d0, d1
 # CHECK-NEXT:  1      2     0.25                        fabs	d2, d3
 # CHECK-NEXT:  1      2     0.25                        fneg	d4, d5
-# CHECK-NEXT:  1      16    3.50                        fsqrt	d6, d7
+# CHECK-NEXT:  1      16    4.00                        fsqrt	d6, d7
 # CHECK-NEXT:  1      3     0.50                        fcvt	s8, d9
 # CHECK-NEXT:  1      3     0.50                        fcvt	h10, d11
 # CHECK-NEXT:  1      3     0.50                        frintn	d12, d13
@@ -1917,7 +1917,7 @@ drps
 # CHECK-NEXT:  1      3     0.50                        fcvt	s26, h27
 # CHECK-NEXT:  1      3     0.50                        fcvt	d28, h29
 # CHECK-NEXT:  1      3     0.25                        fmul	s20, s19, s17
-# CHECK-NEXT:  1      10    3.50                        fdiv	s1, s2, s3
+# CHECK-NEXT:  1      10    1.50                        fdiv	s1, s2, s3
 # CHECK-NEXT:  1      2     0.25                        fadd	s4, s5, s6
 # CHECK-NEXT:  1      2     0.25                        fsub	s7, s8, s9
 # CHECK-NEXT:  1      2     0.25                        fmax	s10, s11, s12
@@ -1942,42 +1942,42 @@ drps
 # CHECK-NEXT:  1      4     0.25                        fnmadd	d3, d13, d0, d23
 # CHECK-NEXT:  1      4     0.25                        fnmsub	s3, s5, s6, s31
 # CHECK-NEXT:  1      4     0.25                        fnmsub	d3, d13, d0, d23
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	w3, h5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	wzr, h20, #13
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	w19, h0, #32
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x3, h5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x12, h30, #45
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x19, h0, #64
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	w3, s5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	wzr, s20, #13
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	w19, s0, #32
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x3, s5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x12, s30, #45
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x19, s0, #64
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	w3, d5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	wzr, d20, #13
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	w19, d0, #32
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x3, d5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x12, d30, #45
-# CHECK-NEXT:  1      3     0.50                        fcvtzs	x19, d0, #64
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	w3, h5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	wzr, h20, #13
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	w19, h0, #32
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x3, h5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x12, h30, #45
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x19, h0, #64
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	w3, s5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	wzr, s20, #13
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	w19, s0, #32
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x3, s5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x12, s30, #45
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x19, s0, #64
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	w3, d5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	wzr, d20, #13
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	w19, d0, #32
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x3, d5, #1
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x12, d30, #45
-# CHECK-NEXT:  1      3     0.50                        fcvtzu	x19, d0, #64
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	w3, h5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	wzr, h20, #13
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	w19, h0, #32
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x3, h5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x12, h30, #45
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x19, h0, #64
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	w3, s5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	wzr, s20, #13
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	w19, s0, #32
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x3, s5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x12, s30, #45
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x19, s0, #64
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	w3, d5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	wzr, d20, #13
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	w19, d0, #32
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x3, d5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x12, d30, #45
+# CHECK-NEXT:  1      3     1.00                        fcvtzs	x19, d0, #64
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	w3, h5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	wzr, h20, #13
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	w19, h0, #32
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x3, h5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x12, h30, #45
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x19, h0, #64
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	w3, s5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	wzr, s20, #13
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	w19, s0, #32
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x3, s5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x12, s30, #45
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x19, s0, #64
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	w3, d5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	wzr, d20, #13
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	w19, d0, #32
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x3, d5, #1
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x12, d30, #45
+# CHECK-NEXT:  1      3     1.00                        fcvtzu	x19, d0, #64
 # CHECK-NEXT:  1      3     1.00                        scvtf	h23, w19, #1
 # CHECK-NEXT:  1      3     1.00                        scvtf	h31, wzr, #20
 # CHECK-NEXT:  1      3     1.00                        scvtf	h14, w0, #32
@@ -2182,9 +2182,9 @@ drps
 # CHECK-NEXT:  3      1     0.50           *            str	w19, [sp], #255
 # CHECK-NEXT:  3      1     0.50           *            str	w20, [x30], #1
 # CHECK-NEXT:  3      1     0.50           *            str	w21, [x12], #-256
-# CHECK-NEXT:  3      1     0.50           *            str	xzr, [x9], #255
-# CHECK-NEXT:  3      1     0.50           *            str	x2, [x3], #1
-# CHECK-NEXT:  3      1     0.50           *            str	x19, [x12], #-256
+# CHECK-NEXT:  2      1     0.50           *            str	xzr, [x9], #255
+# CHECK-NEXT:  2      1     0.50           *            str	x2, [x3], #1
+# CHECK-NEXT:  2      1     0.50           *            str	x19, [x12], #-256
 # CHECK-NEXT:  2      4     0.33    *                   ldrb	w9, [x2], #255
 # CHECK-NEXT:  2      4     0.33    *                   ldrb	w10, [x3], #1
 # CHECK-NEXT:  2      4     0.33    *                   ldrb	w10, [x3], #-256
@@ -2212,18 +2212,18 @@ drps
 # CHECK-NEXT:  2      4     0.33    *                   ldrsh	wzr, [x9], #255
 # CHECK-NEXT:  2      4     0.33    *                   ldrsh	w2, [x3], #1
 # CHECK-NEXT:  2      4     0.33    *                   ldrsh	w19, [x12], #-256
-# CHECK-NEXT:  3      2     0.50           *            str	b0, [x0], #255
-# CHECK-NEXT:  3      2     0.50           *            str	b3, [x3], #1
-# CHECK-NEXT:  3      2     0.50           *            str	b5, [sp], #-256
-# CHECK-NEXT:  3      2     0.50           *            str	h10, [x10], #255
-# CHECK-NEXT:  3      2     0.50           *            str	h13, [x23], #1
-# CHECK-NEXT:  3      2     0.50           *            str	h15, [sp], #-256
-# CHECK-NEXT:  3      2     0.50           *            str	s20, [x20], #255
-# CHECK-NEXT:  3      2     0.50           *            str	s23, [x23], #1
-# CHECK-NEXT:  3      2     0.50           *            str	s25, [x0], #-256
-# CHECK-NEXT:  3      2     0.50           *            str	d20, [x20], #255
-# CHECK-NEXT:  3      2     0.50           *            str	d23, [x23], #1
-# CHECK-NEXT:  3      2     0.50           *            str	d25, [x0], #-256
+# CHECK-NEXT:  2      2     0.50           *            str	b0, [x0], #255
+# CHECK-NEXT:  2      2     0.50           *            str	b3, [x3], #1
+# CHECK-NEXT:  2      2     0.50           *            str	b5, [sp], #-256
+# CHECK-NEXT:  2      2     0.50           *            str	h10, [x10], #255
+# CHECK-NEXT:  2      2     0.50           *            str	h13, [x23], #1
+# CHECK-NEXT:  2      2     0.50           *            str	h15, [sp], #-256
+# CHECK-NEXT:  2      2     0.50           *            str	s20, [x20], #255
+# CHECK-NEXT:  2      2     0.50           *            str	s23, [x23], #1
+# CHECK-NEXT:  2      2     0.50           *            str	s25, [x0], #-256
+# CHECK-NEXT:  2      2     0.50           *            str	d20, [x20], #255
+# CHECK-NEXT:  2      2     0.50           *            str	d23, [x23], #1
+# CHECK-NEXT:  2      2     0.50           *            str	d25, [x0], #-256
 # CHECK-NEXT:  2      6     0.33    *                   ldr	b0, [x0], #255
 # CHECK-NEXT:  2      6     0.33    *                   ldr	b3, [x3], #1
 # CHECK-NEXT:  2      6     0.33    *                   ldr	b5, [sp], #-256
@@ -2239,9 +2239,9 @@ drps
 # CHECK-NEXT:  2      6     0.33    *                   ldr	q20, [x1], #255
 # CHECK-NEXT:  2      6     0.33    *                   ldr	q23, [x9], #1
 # CHECK-NEXT:  2      6     0.33    *                   ldr	q25, [x20], #-256
-# CHECK-NEXT:  3      2     0.50           *            str	q10, [x1], #255
-# CHECK-NEXT:  3      2     0.50           *            str	q22, [sp], #1
-# CHECK-NEXT:  3      2     0.50           *            str	q21, [x20], #-256
+# CHECK-NEXT:  2      2     0.50           *            str	q10, [x1], #255
+# CHECK-NEXT:  2      2     0.50           *            str	q22, [sp], #1
+# CHECK-NEXT:  2      2     0.50           *            str	q21, [x20], #-256
 # CHECK-NEXT:  2      4     0.33    *                   ldr	x3, [x4, #0]!
 # CHECK-NEXT:  3      1     0.50           *            strb	w9, [x2, #255]!
 # CHECK-NEXT:  3      1     0.50           *            strb	w10, [x3, #1]!
@@ -2252,9 +2252,9 @@ drps
 # CHECK-NEXT:  3      1     0.50           *            str	w19, [sp, #255]!
 # CHECK-NEXT:  3      1     0.50           *            str	w20, [x30, #1]!
 # CHECK-NEXT:  3      1     0.50           *            str	w21, [x12, #-256]!
-# CHECK-NEXT:  3      1     0.50           *            str	xzr, [x9, #255]!
-# CHECK-NEXT:  3      1     0.50           *            str	x2, [x3, #1]!
-# CHECK-NEXT:  3      1     0.50           *            str	x19, [x12, #-256]!
+# CHECK-NEXT:  2      1     0.50           *            str	xzr, [x9, #255]!
+# CHECK-NEXT:  2      1     0.50           *            str	x2, [x3, #1]!
+# CHECK-NEXT:  2      1     0.50           *            str	x19, [x12, #-256]!
 # CHECK-NEXT:  2      4     0.33    *                   ldrb	w9, [x2, #255]!
 # CHECK-NEXT:  2      4     0.33    *                   ldrb	w10, [x3, #1]!
 # CHECK-NEXT:  2      4     0.33    *                   ldrb	w10, [x3, #-256]!
@@ -2282,18 +2282,18 @@ drps
 # CHECK-NEXT:  2      4     0.33    *                   ldrsh	wzr, [x9, #255]!
 # CHECK-NEXT:  2      4     0.33    *                   ldrsh	w2, [x3, #1]!
 # CHECK-NEXT:  2      4     0.33    *                   ldrsh	w19, [x12, #-256]!
-# CHECK-NEXT:  3      2     0.50           *            str	b0, [x0, #255]!
-# CHECK-NEXT:  3      2     0.50           *            str	b3, [x3, #1]!
-# CHECK-NEXT:  3      2     0.50           *            str	b5, [sp, #-256]!
-# CHECK-NEXT:  3      2     0.50           *            str	h10, [x10, #255]!
-# CHECK-NEXT:  3      2     0.50           *            str	h13, [x23, #1]!
-# CHECK-NEXT:  3      2     0.50           *            str	h15, [sp, #-256]!
-# CHECK-NEXT:  3      2     0.50           *            str	s20, [x20, #255]!
-# CHECK-NEXT:  3      2     0.50           *            str	s23, [x23, #1]!
-# CHECK-NEXT:  3      2     0.50           *            str	s25, [x0, #-256]!
-# CHECK-NEXT:  3      2     0.50           *            str	d20, [x20, #255]!
-# CHECK-NEXT:  3      2     0.50           *            str	d23, [x23, #1]!
-# CHECK-NEXT:  3      2     0.50           *            str	d25, [x0, #-256]!
+# CHECK-NEXT:  2      2     0.50           *            str	b0, [x0, #255]!
+# CHECK-NEXT:  2      2     0.50           *            str	b3, [x3, #1]!
+# CHECK-NEXT:  2      2     0.50           *            str	b5, [sp, #-256]!
+# CHECK-NEXT:  2      2     0.50           *            str	h10, [x10, #255]!
+# CHECK-NEXT:  2      2     0.50           *            str	h13, [x23, #1]!
+# CHECK-NEXT:  2      2     0.50           *            str	h15, [sp, #-256]!
+# CHECK-NEXT:  2      2     0.50           *            str	s20, [x20, #255]!
+# CHECK-NEXT:  2      2     0.50           *            str	s23, [x23, #1]!
+# CHECK-NEXT:  2      2     0.50           *            str	s25, [x0, #-256]!
+# CHECK-NEXT:  2      2     0.50           *            str	d20, [x20, #255]!
+# CHECK-NEXT:  2      2     0.50           *            str	d23, [x23, #1]!
+# CHECK-NEXT:  2      2     0.50           *            str	d25, [x0, #-256]!
 # CHECK-NEXT:  2      6     0.33    *                   ldr	b0, [x0, #255]!
 # CHECK-NEXT:  2      6     0.33    *                   ldr	b3, [x3, #1]!
 # CHECK-NEXT:  2      6     0.33    *                   ldr	b5, [sp, #-256]!
@@ -2309,9 +2309,9 @@ drps
 # CHECK-NEXT:  2      6     0.33    *                   ldr	q20, [x1, #255]!
 # CHECK-NEXT:  2      6     0.33    *                   ldr	q23, [x9, #1]!
 # CHECK-NEXT:  2      6     0.33    *                   ldr	q25, [x20, #-256]!
-# CHECK-NEXT:  3      2     0.50           *            str	q10, [x1, #255]!
-# CHECK-NEXT:  3      2     0.50           *            str	q22, [sp, #1]!
-# CHECK-NEXT:  3      2     0.50           *            str	q21, [x20, #-256]!
+# CHECK-NEXT:  2      2     0.50           *            str	q10, [x1, #255]!
+# CHECK-NEXT:  2      2     0.50           *            str	q22, [sp, #1]!
+# CHECK-NEXT:  2      2     0.50           *            str	q21, [x20, #-256]!
 # CHECK-NEXT:  2      1     0.50           *            sttrb	w9, [sp]
 # CHECK-NEXT:  2      1     0.50           *            sttrh	wzr, [x12, #255]
 # CHECK-NEXT:  2      1     0.50           *            sttr	w16, [x0, #-256]
@@ -2363,16 +2363,16 @@ drps
 # CHECK-NEXT:  1      4     0.33    *                   ldrsb	x18, [x22, w10, sxtw]
 # CHECK-NEXT:  1      4     0.33    *                   ldrsh	w3, [sp, x5]
 # CHECK-NEXT:  1      4     0.33    *                   ldrsh	w9, [x27, x6]
-# CHECK-NEXT:  1      4     0.33    *                   ldrh	w10, [x30, x7, lsl #1]
+# CHECK-NEXT:  2      5     0.33    *                   ldrh	w10, [x30, x7, lsl #1]
 # CHECK-NEXT:  2      1     0.50           *            strh	w11, [x29, x3, sxtx]
 # CHECK-NEXT:  1      4     0.33    *                   ldrh	w12, [x28, xzr, sxtx]
-# CHECK-NEXT:  1      4     0.33    *                   ldrsh	x13, [x27, x5, sxtx #1]
+# CHECK-NEXT:  2      5     0.33    *                   ldrsh	x13, [x27, x5, sxtx #1]
 # CHECK-NEXT:  1      4     0.33    *                   ldrh	w14, [x26, w6, uxtw]
 # CHECK-NEXT:  1      4     0.33    *                   ldrh	w15, [x25, w7, uxtw]
-# CHECK-NEXT:  1      4     0.33    *                   ldrsh	w16, [x24, w8, uxtw #1]
+# CHECK-NEXT:  2      5     0.33    *                   ldrsh	w16, [x24, w8, uxtw #1]
 # CHECK-NEXT:  1      4     0.33    *                   ldrh	w17, [x23, w9, sxtw]
 # CHECK-NEXT:  1      4     0.33    *                   ldrh	w18, [x22, w10, sxtw]
-# CHECK-NEXT:  2      1     0.50           *            strh	w19, [x21, wzr, sxtw #1]
+# CHECK-NEXT:  3      2     0.50           *            strh	w19, [x21, wzr, sxtw #1]
 # CHECK-NEXT:  1      4     0.33    *                   ldr	w3, [sp, x5]
 # CHECK-NEXT:  1      6     0.33    *                   ldr	s9, [x27, x6]
 # CHECK-NEXT:  1      4     0.33    *                   ldr	w10, [x30, x7, lsl #2]
@@ -2397,28 +2397,28 @@ drps
 # CHECK-NEXT:  1      4     0.33    *                   ldr	x17, [x23, w9, sxtw]
 # CHECK-NEXT:  1      4     0.33    *                   ldr	x18, [x22, w10, sxtw]
 # CHECK-NEXT:  2      2     0.50           *            str	d19, [x21, wzr, sxtw #3]
-# CHECK-NEXT:  2      7     0.33    *                   ldr	q3, [sp, x5]
-# CHECK-NEXT:  2      7     0.33    *                   ldr	q9, [x27, x6]
+# CHECK-NEXT:  1      6     0.33    *                   ldr	q3, [sp, x5]
+# CHECK-NEXT:  1      6     0.33    *                   ldr	q9, [x27, x6]
 # CHECK-NEXT:  2      7     0.33    *                   ldr	q10, [x30, x7, lsl #4]
-# CHECK-NEXT:  3      2     0.50           *            str	q11, [x29, x3, sxtx]
-# CHECK-NEXT:  3      2     0.50           *            str	q12, [x28, xzr, sxtx]
+# CHECK-NEXT:  2      2     0.50           *            str	q11, [x29, x3, sxtx]
+# CHECK-NEXT:  2      2     0.50           *            str	q12, [x28, xzr, sxtx]
 # CHECK-NEXT:  3      2     0.50           *            str	q13, [x27, x5, sxtx #4]
-# CHECK-NEXT:  2      7     0.33    *                   ldr	q14, [x26, w6, uxtw]
-# CHECK-NEXT:  2      7     0.33    *                   ldr	q15, [x25, w7, uxtw]
+# CHECK-NEXT:  1      6     0.33    *                   ldr	q14, [x26, w6, uxtw]
+# CHECK-NEXT:  1      6     0.33    *                   ldr	q15, [x25, w7, uxtw]
 # CHECK-NEXT:  2      7     0.33    *                   ldr	q16, [x24, w8, uxtw #4]
-# CHECK-NEXT:  2      7     0.33    *                   ldr	q17, [x23, w9, sxtw]
-# CHECK-NEXT:  3      2     0.50           *            str	q18, [x22, w10, sxtw]
+# CHECK-NEXT:  1      6     0.33    *                   ldr	q17, [x23, w9, sxtw]
+# CHECK-NEXT:  2      2     0.50           *            str	q18, [x22, w10, sxtw]
 # CHECK-NEXT:  2      7     0.33    *                   ldr	q19, [x21, wzr, sxtw #4]
 # CHECK-NEXT:  1      4     0.33    *                   ldp	w3, w5, [sp]
 # CHECK-NEXT:  2      1     0.50           *            stp	wzr, w9, [sp, #252]
 # CHECK-NEXT:  1      4     0.33    *                   ldp	w2, wzr, [sp, #-256]
 # CHECK-NEXT:  1      4     0.33    *                   ldp	w9, w10, [sp, #4]
-# CHECK-NEXT:  2      5     0.33    *                   ldpsw	x9, x10, [sp, #4]
-# CHECK-NEXT:  2      5     0.33    *                   ldpsw	x9, x10, [x2, #-256]
-# CHECK-NEXT:  2      5     0.33    *                   ldpsw	x20, x30, [sp, #252]
-# CHECK-NEXT:  2      4     0.67    *                   ldp	x21, x29, [x2, #504]
-# CHECK-NEXT:  2      4     0.67    *                   ldp	x22, x23, [x3, #-512]
-# CHECK-NEXT:  2      4     0.67    *                   ldp	x24, x25, [x4, #8]
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x9, x10, [sp, #4]
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x9, x10, [x2, #-256]
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x20, x30, [sp, #252]
+# CHECK-NEXT:  1      4     1.00    *                   ldp	x21, x29, [x2, #504]
+# CHECK-NEXT:  1      4     1.00    *                   ldp	x22, x23, [x3, #-512]
+# CHECK-NEXT:  1      4     1.00    *                   ldp	x24, x25, [x4, #8]
 # CHECK-NEXT:  1      6     0.33    *                   ldp	s29, s28, [sp, #252]
 # CHECK-NEXT:  2      2     0.50           *            stp	s27, s26, [sp, #-256]
 # CHECK-NEXT:  1      6     0.33    *                   ldp	s1, s2, [x3, #44]
@@ -2427,52 +2427,52 @@ drps
 # CHECK-NEXT:  1      6     0.33    *                   ldp	d2, d3, [x30, #-8]
 # CHECK-NEXT:  2      2     0.50           *            stp	q3, q5, [sp]
 # CHECK-NEXT:  2      2     0.50           *            stp	q17, q19, [sp, #1008]
-# CHECK-NEXT:  2      6     0.67    *                   ldp	q23, q29, [x1, #-1024]
+# CHECK-NEXT:  1      6     0.67    *                   ldp	q23, q29, [x1, #-1024]
 # CHECK-NEXT:  2      4     0.33    *                   ldp	w3, w5, [sp], #0
 # CHECK-NEXT:  3      1     0.50           *            stp	wzr, w9, [sp], #252
 # CHECK-NEXT:  2      4     0.33    *                   ldp	w2, wzr, [sp], #-256
 # CHECK-NEXT:  2      4     0.33    *                   ldp	w9, w10, [sp], #4
-# CHECK-NEXT:  3      5     0.50    *                   ldpsw	x9, x10, [sp], #4
-# CHECK-NEXT:  3      5     0.50    *                   ldpsw	x9, x10, [x2], #-256
-# CHECK-NEXT:  3      5     0.50    *                   ldpsw	x20, x30, [sp], #252
-# CHECK-NEXT:  3      4     0.67    *                   ldp	x21, x29, [x2], #504
-# CHECK-NEXT:  3      4     0.67    *                   ldp	x22, x23, [x3], #-512
-# CHECK-NEXT:  3      4     0.67    *                   ldp	x24, x25, [x4], #8
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x9, x10, [sp], #4
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x9, x10, [x2], #-256
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x20, x30, [sp], #252
+# CHECK-NEXT:  2      4     1.00    *                   ldp	x21, x29, [x2], #504
+# CHECK-NEXT:  2      4     1.00    *                   ldp	x22, x23, [x3], #-512
+# CHECK-NEXT:  2      4     1.00    *                   ldp	x24, x25, [x4], #8
 # CHECK-NEXT:  2      6     0.33    *                   ldp	s29, s28, [sp], #252
 # CHECK-NEXT:  3      2     0.50           *            stp	s27, s26, [sp], #-256
 # CHECK-NEXT:  2      6     0.33    *                   ldp	s1, s2, [x3], #44
 # CHECK-NEXT:  3      2     0.50           *            stp	d3, d5, [x9], #504
 # CHECK-NEXT:  3      2     0.50           *            stp	d7, d11, [x10], #-512
 # CHECK-NEXT:  2      6     0.33    *                   ldp	d2, d3, [x30], #-8
-# CHECK-NEXT:  4      2     1.00           *            stp	q3, q5, [sp], #0
-# CHECK-NEXT:  4      2     1.00           *            stp	q17, q19, [sp], #1008
-# CHECK-NEXT:  3      6     0.67    *                   ldp	q23, q29, [x1], #-1024
+# CHECK-NEXT:  3      2     1.00           *            stp	q3, q5, [sp], #0
+# CHECK-NEXT:  3      2     1.00           *            stp	q17, q19, [sp], #1008
+# CHECK-NEXT:  2      6     0.67    *                   ldp	q23, q29, [x1], #-1024
 # CHECK-NEXT:  2      4     0.33    *                   ldp	w3, w5, [sp, #0]!
 # CHECK-NEXT:  3      1     0.50           *            stp	wzr, w9, [sp, #252]!
 # CHECK-NEXT:  2      4     0.33    *                   ldp	w2, wzr, [sp, #-256]!
 # CHECK-NEXT:  2      4     0.33    *                   ldp	w9, w10, [sp, #4]!
-# CHECK-NEXT:  3      5     0.50    *                   ldpsw	x9, x10, [sp, #4]!
-# CHECK-NEXT:  3      5     0.50    *                   ldpsw	x9, x10, [x2, #-256]!
-# CHECK-NEXT:  3      5     0.50    *                   ldpsw	x20, x30, [sp, #252]!
-# CHECK-NEXT:  3      4     0.67    *                   ldp	x21, x29, [x2, #504]!
-# CHECK-NEXT:  3      4     0.67    *                   ldp	x22, x23, [x3, #-512]!
-# CHECK-NEXT:  3      4     0.67    *                   ldp	x24, x25, [x4, #8]!
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x9, x10, [sp, #4]!
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x9, x10, [x2, #-256]!
+# CHECK-NEXT:  2      5     1.00    *                   ldpsw	x20, x30, [sp, #252]!
+# CHECK-NEXT:  2      4     1.00    *                   ldp	x21, x29, [x2, #504]!
+# CHECK-NEXT:  2      4     1.00    *                   ldp	x22, x23, [x3, #-512]!
+# CHECK-NEXT:  2      4     1.00    *                   ldp	x24, x25, [x4, #8]!
 # CHECK-NEXT:  2      6     0.33    *                   ldp	s29, s28, [sp, #252]!
 # CHECK-NEXT:  3      2     0.50           *            stp	s27, s26, [sp, #-256]!
 # CHECK-NEXT:  2      6     0.33    *                   ldp	s1, s2, [x3, #44]!
 # CHECK-NEXT:  3      2     0.50           *            stp	d3, d5, [x9, #504]!
 # CHECK-NEXT:  3      2     0.50           *            stp	d7, d11, [x10, #-512]!
 # CHECK-NEXT:  2      6     0.33    *                   ldp	d2, d3, [x30, #-8]!
-# CHECK-NEXT:  4      2     1.00           *            stp	q3, q5, [sp, #0]!
-# CHECK-NEXT:  4      2     1.00           *            stp	q17, q19, [sp, #1008]!
-# CHECK-NEXT:  3      6     0.67    *                   ldp	q23, q29, [x1, #-1024]!
+# CHECK-NEXT:  3      2     1.00           *            stp	q3, q5, [sp, #0]!
+# CHECK-NEXT:  3      2     1.00           *            stp	q17, q19, [sp, #1008]!
+# CHECK-NEXT:  2      6     0.67    *                   ldp	q23, q29, [x1, #-1024]!
 # CHECK-NEXT:  1      4     0.33    *                   ldnp	w3, w5, [sp]
 # CHECK-NEXT:  2      1     0.50           *            stnp	wzr, w9, [sp, #252]
 # CHECK-NEXT:  1      4     0.33    *                   ldnp	w2, wzr, [sp, #-256]
 # CHECK-NEXT:  1      4     0.33    *                   ldnp	w9, w10, [sp, #4]
-# CHECK-NEXT:  2      4     0.67    *                   ldnp	x21, x29, [x2, #504]
-# CHECK-NEXT:  2      4     0.67    *                   ldnp	x22, x23, [x3, #-512]
-# CHECK-NEXT:  2      4     0.67    *                   ldnp	x24, x25, [x4, #8]
+# CHECK-NEXT:  1      4     1.00    *                   ldnp	x21, x29, [x2, #504]
+# CHECK-NEXT:  1      4     1.00    *                   ldnp	x22, x23, [x3, #-512]
+# CHECK-NEXT:  1      4     1.00    *                   ldnp	x24, x25, [x4, #8]
 # CHECK-NEXT:  1      6     0.33    *                   ldnp	s29, s28, [sp, #252]
 # CHECK-NEXT:  2      2     0.50           *            stnp	s27, s26, [sp, #-256]
 # CHECK-NEXT:  1      6     0.33    *                   ldnp	s1, s2, [x3, #44]
@@ -2481,7 +2481,7 @@ drps
 # CHECK-NEXT:  1      6     0.33    *                   ldnp	d2, d3, [x30, #-8]
 # CHECK-NEXT:  2      2     0.50           *            stnp	q3, q5, [sp]
 # CHECK-NEXT:  2      2     0.50           *            stnp	q17, q19, [sp, #1008]
-# CHECK-NEXT:  2      6     0.67    *                   ldnp	q23, q29, [x1, #-1024]
+# CHECK-NEXT:  1      6     0.67    *                   ldnp	q23, q29, [x1, #-1024]
 # CHECK-NEXT:  1      1     0.25                        mov	w3, #983055
 # CHECK-NEXT:  1      1     0.25                        mov	x10, #-6148914691236517206
 # CHECK-NEXT:  1      1     0.25                        and	w12, w23, w21
@@ -2502,12 +2502,12 @@ drps
 # CHECK-NEXT:  1      1     0.25                        orr	x8, x9, x10, lsl #12
 # CHECK-NEXT:  1      1     0.25                        orn	x3, x5, x7, asr #2
 # CHECK-NEXT:  1      1     0.25                        orn	w2, w5, w29
-# CHECK-NEXT:  1      2     0.50                        ands	w7, wzr, w9, lsl #1
-# CHECK-NEXT:  1      2     0.50                        ands	x3, x5, x20, ror #63
-# CHECK-NEXT:  1      2     0.50                        bics	w3, w5, w7
-# CHECK-NEXT:  1      2     0.50                        bics	x3, xzr, x3, lsl #1
-# CHECK-NEXT:  1      2     0.50                        tst	w3, w7, lsl #31
-# CHECK-NEXT:  1      2     0.50                        tst	x2, x20, asr #2
+# CHECK-NEXT:  2      2     0.50                        ands	w7, wzr, w9, lsl #1
+# CHECK-NEXT:  2      1     0.33                        ands	x3, x5, x20, ror #63
+# CHECK-NEXT:  2      1     0.33                        bics	w3, w5, w7
+# CHECK-NEXT:  2      2     0.50                        bics	x3, xzr, x3, lsl #1
+# CHECK-NEXT:  2      2     0.50                        tst	w3, w7, lsl #31
+# CHECK-NEXT:  2      2     0.50                        tst	x2, x20, asr #2
 # CHECK-NEXT:  1      1     0.25                        mov	x3, x6
 # CHECK-NEXT:  1      1     0.25                        mov	x3, xzr
 # CHECK-NEXT:  1      1     0.25                        mov	wzr, w2
@@ -2562,7 +2562,7 @@ drps
 
 # CHECK:      Resource pressure per iteration:
 # CHECK-NEXT: [0.0]  [0.1]  [1.0]  [1.1]  [2.0]  [2.1]  [2.2]  [3]    [4.0]  [4.1]  [5]    [6]    [7.0]  [7.1]  [8]    [9]    [10]   [11]
-# CHECK-NEXT: 11.00  11.00  33.00  33.00  45.33  45.33  45.33  96.33  162.33 162.33 306.50 205.50 139.00 139.00 167.50 44.50  51.50  9.50
+# CHECK-NEXT: 11.00  11.00  33.00  33.00  45.33  45.33  45.33  106.33 172.33 172.33 338.75 193.75 125.75 125.75 183.50 46.50  29.50  9.50
 
 # CHECK:      Resource pressure by instruction:
 # CHECK-NEXT: [0.0]  [0.1]  [1.0]  [1.1]  [2.0]  [2.1]  [2.2]  [3]    [4.0]  [4.1]  [5]    [6]    [7.0]  [7.1]  [8]    [9]    [10]   [11]   Instructions:
@@ -2581,16 +2581,16 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     sub	w4, w20, #546, lsl #12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     sub	sp, sp, #288
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     sub	wsp, w19, #16
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     adds	w13, w23, #291, lsl #12
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     adds	w13, w23, #291, lsl #12
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmn	w2, #4095
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     adds	w20, wsp, #0
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmn	x3, #1, lsl #12
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmp	sp, #20, lsl #12
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     cmn	x3, #1, lsl #12
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     cmp	sp, #20, lsl #12
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmp	x30, #4095
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     subs	x4, sp, #3822
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmn	w3, #291, lsl #12
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     cmn	w3, #291, lsl #12
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmn	wsp, #1365
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cmn	sp, #1092, lsl #12
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     cmn	sp, #1092, lsl #12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     mov	sp, x30
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     mov	wsp, w20
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     mov	x11, sp
@@ -2973,10 +2973,10 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     clz	x26, x4
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cls	w3, w5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     cls	x20, x5
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     5.00    -      -      -      -      -      -      -     udiv	w0, w7, w10
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     5.00    -      -      -      -      -      -      -     udiv	x9, x22, x4
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     5.00    -      -      -      -      -      -      -     sdiv	w12, w21, w0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     5.00    -      -      -      -      -      -      -     sdiv	x13, x2, x1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     12.00   -      -      -      -      -      -      -     udiv	w0, w7, w10
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     20.00   -      -      -      -      -      -      -     udiv	x9, x22, x4
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     12.00   -      -      -      -      -      -      -     sdiv	w12, w21, w0
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     20.00   -      -      -      -      -      -      -     sdiv	x13, x2, x1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     lsl	w11, w12, w13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     lsl	x14, x15, x16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     lsr	w17, w18, w19
@@ -3044,10 +3044,10 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     umull	x11, w13, w17
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     smnegl	x11, w13, w17
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     umnegl	x11, w13, w17
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.75   0.75   0.25   0.25    -      -      -      -     extr	w3, w5, w7, #0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.75   0.75   0.25   0.25    -      -      -      -     extr	w11, w13, w17, #31
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.75   0.75   0.25   0.25    -      -      -      -     extr	x3, x5, x7, #15
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.75   0.75   0.25   0.25    -      -      -      -     extr	x11, x13, x17, #63
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     extr	w3, w5, w7, #0
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     extr	w11, w13, w17, #31
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     extr	x3, x5, x7, #15
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     extr	x11, x13, x17, #63
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     ror	x19, x23, #24
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     ror	x29, xzr, #63
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     ror	w9, w13, #31
@@ -3080,7 +3080,7 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmov	s0, s1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fabs	s2, s3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fneg	s4, s5
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fsqrt	s6, s7
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fsqrt	s6, s7
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvt	d8, s9
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvt	h10, s11
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintn	s12, s13
@@ -3093,7 +3093,7 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmov	d0, d1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fabs	d2, d3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fneg	d4, d5
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fsqrt	d6, d7
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -     4.00    -     fsqrt	d6, d7
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvt	s8, d9
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvt	h10, d11
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintn	d12, d13
@@ -3106,7 +3106,7 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvt	s26, h27
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvt	d28, h29
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmul	s20, s19, s17
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fdiv	s1, s2, s3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.50    -     1.50    -     fdiv	s1, s2, s3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fadd	s4, s5, s6
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fsub	s7, s8, s9
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmax	s10, s11, s12
@@ -3131,42 +3131,42 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fnmadd	d3, d13, d0, d23
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fnmsub	s3, s5, s6, s31
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fnmsub	d3, d13, d0, d23
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	w3, h5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	wzr, h20, #13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	w19, h0, #32
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x3, h5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x12, h30, #45
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x19, h0, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	w3, s5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	wzr, s20, #13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	w19, s0, #32
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x3, s5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x12, s30, #45
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x19, s0, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	w3, d5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	wzr, d20, #13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	w19, d0, #32
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x3, d5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x12, d30, #45
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	x19, d0, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	w3, h5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	wzr, h20, #13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	w19, h0, #32
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x3, h5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x12, h30, #45
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x19, h0, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	w3, s5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	wzr, s20, #13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	w19, s0, #32
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x3, s5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x12, s30, #45
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x19, s0, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	w3, d5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	wzr, d20, #13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	w19, d0, #32
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x3, d5, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x12, d30, #45
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	x19, d0, #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	w3, h5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	wzr, h20, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	w19, h0, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x3, h5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x12, h30, #45
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x19, h0, #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	w3, s5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	wzr, s20, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	w19, s0, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x3, s5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x12, s30, #45
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x19, s0, #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	w3, d5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	wzr, d20, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	w19, d0, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x3, d5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x12, d30, #45
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	x19, d0, #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	w3, h5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	wzr, h20, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	w19, h0, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x3, h5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x12, h30, #45
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x19, h0, #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	w3, s5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	wzr, s20, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	w19, s0, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x3, s5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x12, s30, #45
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x19, s0, #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	w3, d5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	wzr, d20, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	w19, d0, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x3, d5, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x12, d30, #45
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	x19, d0, #64
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     scvtf	h23, w19, #1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     scvtf	h31, wzr, #20
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     scvtf	h14, w0, #32
@@ -3371,9 +3371,9 @@ drps
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	w19, [sp], #255
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	w20, [x30], #1
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	w21, [x12], #-256
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	xzr, [x9], #255
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	x2, [x3], #1
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	x19, [x12], #-256
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     str	xzr, [x9], #255
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     str	x2, [x3], #1
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     str	x19, [x12], #-256
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrb	w9, [x2], #255
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrb	w10, [x3], #1
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrb	w10, [x3], #-256
@@ -3401,18 +3401,18 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	wzr, [x9], #255
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	w2, [x3], #1
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	w19, [x12], #-256
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	b0, [x0], #255
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	b3, [x3], #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	b5, [sp], #-256
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	h10, [x10], #255
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	h13, [x23], #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	h15, [sp], #-256
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	s20, [x20], #255
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	s23, [x23], #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	s25, [x0], #-256
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	d20, [x20], #255
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	d23, [x23], #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	d25, [x0], #-256
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	b0, [x0], #255
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	b3, [x3], #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	b5, [sp], #-256
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	h10, [x10], #255
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	h13, [x23], #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	h15, [sp], #-256
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	s20, [x20], #255
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	s23, [x23], #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	s25, [x0], #-256
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d20, [x20], #255
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d23, [x23], #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d25, [x0], #-256
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	b0, [x0], #255
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	b3, [x3], #1
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	b5, [sp], #-256
@@ -3428,9 +3428,9 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q20, [x1], #255
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q23, [x9], #1
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q25, [x20], #-256
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q10, [x1], #255
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q22, [sp], #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q21, [x20], #-256
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q10, [x1], #255
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q22, [sp], #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q21, [x20], #-256
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	x3, [x4, #0]!
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     strb	w9, [x2, #255]!
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     strb	w10, [x3, #1]!
@@ -3441,9 +3441,9 @@ drps
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	w19, [sp, #255]!
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	w20, [x30, #1]!
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	w21, [x12, #-256]!
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	xzr, [x9, #255]!
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	x2, [x3, #1]!
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     str	x19, [x12, #-256]!
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     str	xzr, [x9, #255]!
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     str	x2, [x3, #1]!
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     str	x19, [x12, #-256]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrb	w9, [x2, #255]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrb	w10, [x3, #1]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrb	w10, [x3, #-256]!
@@ -3471,18 +3471,18 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	wzr, [x9, #255]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	w2, [x3, #1]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	w19, [x12, #-256]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	b0, [x0, #255]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	b3, [x3, #1]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	b5, [sp, #-256]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	h10, [x10, #255]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	h13, [x23, #1]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	h15, [sp, #-256]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	s20, [x20, #255]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	s23, [x23, #1]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	s25, [x0, #-256]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	d20, [x20, #255]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	d23, [x23, #1]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	d25, [x0, #-256]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	b0, [x0, #255]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	b3, [x3, #1]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	b5, [sp, #-256]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	h10, [x10, #255]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	h13, [x23, #1]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	h15, [sp, #-256]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	s20, [x20, #255]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	s23, [x23, #1]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	s25, [x0, #-256]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d20, [x20, #255]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d23, [x23, #1]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d25, [x0, #-256]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	b0, [x0, #255]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	b3, [x3, #1]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	b5, [sp, #-256]!
@@ -3498,9 +3498,9 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q20, [x1, #255]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q23, [x9, #1]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q25, [x20, #-256]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q10, [x1, #255]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q22, [sp, #1]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q21, [x20, #-256]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q10, [x1, #255]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q22, [sp, #1]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q21, [x20, #-256]!
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     sttrb	w9, [sp]
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     sttrh	wzr, [x12, #255]
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     sttr	w16, [x0, #-256]
@@ -3552,16 +3552,16 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrsb	x18, [x22, w10, sxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrsh	w3, [sp, x5]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrsh	w9, [x27, x6]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrh	w10, [x30, x7, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrh	w10, [x30, x7, lsl #1]
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     strh	w11, [x29, x3, sxtx]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrh	w12, [x28, xzr, sxtx]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrsh	x13, [x27, x5, sxtx #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	x13, [x27, x5, sxtx #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrh	w14, [x26, w6, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrh	w15, [x25, w7, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrsh	w16, [x24, w8, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldrsh	w16, [x24, w8, uxtw #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrh	w17, [x23, w9, sxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldrh	w18, [x22, w10, sxtw]
-# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     strh	w19, [x21, wzr, sxtw #1]
+# CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     strh	w19, [x21, wzr, sxtw #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	w3, [sp, x5]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	s9, [x27, x6]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	w10, [x30, x7, lsl #2]
@@ -3586,28 +3586,28 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	x17, [x23, w9, sxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	x18, [x22, w10, sxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	d19, [x21, wzr, sxtw #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q3, [sp, x5]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q9, [x27, x6]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	q3, [sp, x5]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	q9, [x27, x6]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q10, [x30, x7, lsl #4]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q11, [x29, x3, sxtx]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q12, [x28, xzr, sxtx]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q11, [x29, x3, sxtx]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q12, [x28, xzr, sxtx]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q13, [x27, x5, sxtx #4]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q14, [x26, w6, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q15, [x25, w7, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	q14, [x26, w6, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	q15, [x25, w7, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q16, [x24, w8, uxtw #4]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q17, [x23, w9, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     str	q18, [x22, w10, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldr	q17, [x23, w9, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     str	q18, [x22, w10, sxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldr	q19, [x21, wzr, sxtw #4]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldp	w3, w5, [sp]
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     stp	wzr, w9, [sp, #252]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldp	w2, wzr, [sp, #-256]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldp	w9, w10, [sp, #4]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [sp, #4]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [x2, #-256]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x20, x30, [sp, #252]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -      -      -      -      -     ldp	x21, x29, [x2, #504]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -      -      -      -      -     ldp	x22, x23, [x3, #-512]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -      -      -      -      -     ldp	x24, x25, [x4, #8]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [sp, #4]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [x2, #-256]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x20, x30, [sp, #252]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -      -      -      -      -     ldp	x21, x29, [x2, #504]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -      -      -      -      -     ldp	x22, x23, [x3, #-512]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -      -      -      -      -     ldp	x24, x25, [x4, #8]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldp	s29, s28, [sp, #252]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     stp	s27, s26, [sp, #-256]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldp	s1, s2, [x3, #44]
@@ -3621,47 +3621,47 @@ drps
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     stp	wzr, w9, [sp], #252
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	w2, wzr, [sp], #-256
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	w9, w10, [sp], #4
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.50   0.50   0.50   0.50    -      -      -      -     ldpsw	x9, x10, [sp], #4
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.50   0.50   0.50   0.50    -      -      -      -     ldpsw	x9, x10, [x2], #-256
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.50   0.50   0.50   0.50    -      -      -      -     ldpsw	x20, x30, [sp], #252
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x21, x29, [x2], #504
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x22, x23, [x3], #-512
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x24, x25, [x4], #8
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [sp], #4
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [x2], #-256
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x20, x30, [sp], #252
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x21, x29, [x2], #504
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x22, x23, [x3], #-512
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x24, x25, [x4], #8
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	s29, s28, [sp], #252
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	s27, s26, [sp], #-256
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	s1, s2, [x3], #44
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	d3, d5, [x9], #504
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	d7, d11, [x10], #-512
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	d2, d3, [x30], #-8
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	q3, q5, [sp], #0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	q17, q19, [sp], #1008
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00    -      -     stp	q3, q5, [sp], #0
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00    -      -     stp	q17, q19, [sp], #1008
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	q23, q29, [x1], #-1024
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	w3, w5, [sp, #0]!
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25    -      -      -      -     stp	wzr, w9, [sp, #252]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	w2, wzr, [sp, #-256]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	w9, w10, [sp, #4]!
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.50   0.50   0.50   0.50    -      -      -      -     ldpsw	x9, x10, [sp, #4]!
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.50   0.50   0.50   0.50    -      -      -      -     ldpsw	x9, x10, [x2, #-256]!
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.50   0.50   0.50   0.50    -      -      -      -     ldpsw	x20, x30, [sp, #252]!
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x21, x29, [x2, #504]!
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x22, x23, [x3, #-512]!
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x24, x25, [x4, #8]!
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [sp, #4]!
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x9, x10, [x2, #-256]!
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldpsw	x20, x30, [sp, #252]!
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x21, x29, [x2, #504]!
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x22, x23, [x3, #-512]!
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25    -      -      -      -     ldp	x24, x25, [x4, #8]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	s29, s28, [sp, #252]!
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	s27, s26, [sp, #-256]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	s1, s2, [x3, #44]!
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	d3, d5, [x9, #504]!
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	d7, d11, [x10, #-512]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25    -      -      -      -     ldp	d2, d3, [x30, #-8]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	q3, q5, [sp, #0]!
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   0.50   0.50    -      -     stp	q17, q19, [sp, #1008]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00    -      -     stp	q3, q5, [sp, #0]!
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00    -      -     stp	q17, q19, [sp, #1008]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ldp	q23, q29, [x1, #-1024]!
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldnp	w3, w5, [sp]
 # CHECK-NEXT:  -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     stnp	wzr, w9, [sp, #252]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldnp	w2, wzr, [sp, #-256]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldnp	w9, w10, [sp, #4]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -      -      -      -      -     ldnp	x21, x29, [x2, #504]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -      -      -      -      -     ldnp	x22, x23, [x3, #-512]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -      -      -      -      -     ldnp	x24, x25, [x4, #8]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -      -      -      -      -     ldnp	x21, x29, [x2, #504]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -      -      -      -      -     ldnp	x22, x23, [x3, #-512]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -      -      -      -      -     ldnp	x24, x25, [x4, #8]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldnp	s29, s28, [sp, #252]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.50   0.50    -      -     stnp	s27, s26, [sp, #-256]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ldnp	s1, s2, [x3, #44]
@@ -3692,8 +3692,8 @@ drps
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     orn	x3, x5, x7, asr #2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     orn	w2, w5, w29
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     ands	w7, wzr, w9, lsl #1
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     ands	x3, x5, x20, ror #63
-# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     bics	w3, w5, w7
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     ands	x3, x5, x20, ror #63
+# CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.25   0.25   0.25   0.25    -      -      -      -     bics	w3, w5, w7
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     bics	x3, xzr, x3, lsl #1
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     tst	w3, w7, lsl #31
 # CHECK-NEXT:  -      -      -      -     0.33   0.33   0.33    -      -      -     0.50   0.50    -      -      -      -      -      -     tst	x2, x20, asr #2
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s
index 4de37f9600052..4d099f5851437 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-forwarding.s
@@ -893,10 +893,10 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1203
-# CHECK-NEXT: Total uOps:        500
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.42
+# CHECK-NEXT: uOps Per Cycle:    0.33
 # CHECK-NEXT: IPC:               0.33
 # CHECK-NEXT: Block RThroughput: 2.0
 
@@ -931,10 +931,10 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1203
-# CHECK-NEXT: Total uOps:        500
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.42
+# CHECK-NEXT: uOps Per Cycle:    0.33
 # CHECK-NEXT: IPC:               0.33
 # CHECK-NEXT: Block RThroughput: 2.0
 
@@ -969,10 +969,10 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1403
-# CHECK-NEXT: Total uOps:        500
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: uOps Per Cycle:    0.29
 # CHECK-NEXT: IPC:               0.29
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -1007,10 +1007,10 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1203
-# CHECK-NEXT: Total uOps:        500
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.42
+# CHECK-NEXT: uOps Per Cycle:    0.33
 # CHECK-NEXT: IPC:               0.33
 # CHECK-NEXT: Block RThroughput: 2.0
 
@@ -1045,10 +1045,10 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1703
-# CHECK-NEXT: Total uOps:        800
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.47
+# CHECK-NEXT: uOps Per Cycle:    0.23
 # CHECK-NEXT: IPC:               0.23
 # CHECK-NEXT: Block RThroughput: 8.0
 
@@ -1063,7 +1063,7 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: [1,0]     D=================eeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT: [1,1]     D======================eeeeeER.    ..   mla	z0.d, p0/m, z1.d, z2.d
 # CHECK-NEXT: [1,2]     D========================eeeeeER   ..   mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     .D============================eeeeeER   mla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,3]     D=============================eeeeeER   mla	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1075,18 +1075,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: 0.     2     9.5    0.5    0.0       mul	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT: 1.     2     14.5   0.0    0.0       mla	z0.d, p0/m, z1.d, z2.d
 # CHECK-NEXT: 2.     2     16.5   0.0    0.0       mla	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: 3.     2     21.0   0.0    0.0       mla	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT:        2     15.4   0.1    0.0       <total>
+# CHECK-NEXT: 3.     2     21.5   0.0    0.0       mla	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT:        2     15.5   0.1    0.0       <total>
 
 # CHECK:      [22] Code Region - Z mad.d
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1703
-# CHECK-NEXT: Total uOps:        800
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.47
+# CHECK-NEXT: uOps Per Cycle:    0.23
 # CHECK-NEXT: IPC:               0.23
 # CHECK-NEXT: Block RThroughput: 8.0
 
@@ -1101,7 +1101,7 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: [1,0]     D=================eeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT: [1,1]     D======================eeeeeER.    ..   mad	z0.d, p0/m, z1.d, z2.d
 # CHECK-NEXT: [1,2]     D========================eeeeeER   ..   mad	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     .D============================eeeeeER   mad	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,3]     D=============================eeeeeER   mad	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1113,18 +1113,18 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: 0.     2     9.5    0.5    0.0       mul	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT: 1.     2     14.5   0.0    0.0       mad	z0.d, p0/m, z1.d, z2.d
 # CHECK-NEXT: 2.     2     16.5   0.0    0.0       mad	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: 3.     2     21.0   0.0    0.0       mad	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT:        2     15.4   0.1    0.0       <total>
+# CHECK-NEXT: 3.     2     21.5   0.0    0.0       mad	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT:        2     15.5   0.1    0.0       <total>
 
 # CHECK:      [23] Code Region - Z msb.d
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      400
 # CHECK-NEXT: Total Cycles:      1703
-# CHECK-NEXT: Total uOps:        800
+# CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.47
+# CHECK-NEXT: uOps Per Cycle:    0.23
 # CHECK-NEXT: IPC:               0.23
 # CHECK-NEXT: Block RThroughput: 8.0
 
@@ -1139,7 +1139,7 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: [1,0]     D=================eeeeeER.    .    ..   mul	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT: [1,1]     D======================eeeeeER.    ..   msb	z0.d, p0/m, z1.d, z2.d
 # CHECK-NEXT: [1,2]     D========================eeeeeER   ..   msb	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: [1,3]     .D============================eeeeeER   msb	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT: [1,3]     D=============================eeeeeER   msb	z0.d, p0/m, z0.d, z1.d
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1151,8 +1151,8 @@ bfmlalb z0.s, z0.h, z1.h
 # CHECK-NEXT: 0.     2     9.5    0.5    0.0       mul	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT: 1.     2     14.5   0.0    0.0       msb	z0.d, p0/m, z1.d, z2.d
 # CHECK-NEXT: 2.     2     16.5   0.0    0.0       msb	z0.d, p0/m, z1.d, z2.d
-# CHECK-NEXT: 3.     2     21.0   0.0    0.0       msb	z0.d, p0/m, z0.d, z1.d
-# CHECK-NEXT:        2     15.4   0.1    0.0       <total>
+# CHECK-NEXT: 3.     2     21.5   0.0    0.0       msb	z0.d, p0/m, z0.d, z1.d
+# CHECK-NEXT:        2     15.5   0.1    0.0       <total>
 
 # CHECK:      [24] Code Region - Z fcmla ZPmZZ
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-neon-instructions.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-neon-instructions.s
index 20e76ef27c470..bc7bc2cdb14b1 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-neon-instructions.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-neon-instructions.s
@@ -1248,17 +1248,17 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        addp	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  1      2     0.50                        addv	s0, v0.4s
 # CHECK-NEXT:  1      2     0.50                        addv	h0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        addv	h0, v0.8h
-# CHECK-NEXT:  2      4     0.50                        addv	b0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        addv	b0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        addv	h0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        addv	b0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        addv	b0, v0.16b
 # CHECK-NEXT:  1      2     0.25                        aesd	v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        aese	v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        aesimc	v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        aesmc	v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        and	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  1      3     0.50                        bfcvt	h0, s0
-# CHECK-NEXT:  1      4     0.50                        bfcvtn	v0.4h, v0.4s
-# CHECK-NEXT:  1      4     0.50                        bfcvtn2	v0.8h, v0.4s
+# CHECK-NEXT:  1      4     1.00                        bfcvtn	v0.4h, v0.4s
+# CHECK-NEXT:  1      4     1.00                        bfcvtn2	v0.8h, v0.4s
 # CHECK-NEXT:  1      4     0.25                        bfdot	v0.2s, v0.4h, v0.4h
 # CHECK-NEXT:  1      4     0.25                        bfdot	v0.4s, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.25                        bfmlalb	v0.4s, v0.8h, v0.8h
@@ -1374,113 +1374,113 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        fcmlt	s10, s11, #0.0
 # CHECK-NEXT:  1      2     0.25                        fcmlt	v0.4s, v0.4s, #0.0
 # CHECK-NEXT:  1      3     0.50                        fcvtas	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtas	s12, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtas	h12, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtas	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtas	h12, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtas	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtas	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtas	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtas	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtas	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtas	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtas	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtas	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtau	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtau	s12, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtau	h12, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtau	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtau	h12, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtau	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtau	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtau	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtau	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtau	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtau	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtau	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtau	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtl	v0.2d, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtl	v0.4s, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtl	v0.4s, v0.4h
 # CHECK-NEXT:  1      3     0.50                        fcvtl2	v0.2d, v0.4s
-# CHECK-NEXT:  2      4     1.00                        fcvtl2	v0.4s, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtl2	v0.4s, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtms	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtms	s22, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtms	h22, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtms	s22, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtms	h22, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtms	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtms	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtms	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtms	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtms	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtms	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtms	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtms	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtmu	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtmu	s12, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtmu	h12, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtmu	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtmu	h12, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtmu	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtmu	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtmu	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtmu	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtmu	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtmu	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtmu	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtmu	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtn	v0.2s, v0.2d
-# CHECK-NEXT:  2      4     1.00                        fcvtn	v0.4h, v0.4s
+# CHECK-NEXT:  1      4     1.00                        fcvtn	v0.4h, v0.4s
 # CHECK-NEXT:  1      3     0.50                        fcvtn2	v0.4s, v0.2d
-# CHECK-NEXT:  2      4     1.00                        fcvtn2	v0.8h, v0.4s
+# CHECK-NEXT:  1      4     1.00                        fcvtn2	v0.8h, v0.4s
 # CHECK-NEXT:  1      3     0.50                        fcvtns	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtns	s22, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtns	h22, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtns	s22, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtns	h22, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtns	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtns	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtns	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtns	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtns	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtns	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtns	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtns	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtnu	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtnu	s12, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtnu	h12, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtnu	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtnu	h12, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtnu	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtnu	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtnu	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtnu	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtnu	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtnu	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtnu	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtnu	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtps	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtps	s22, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtps	h22, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtps	s22, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtps	h22, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtps	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtps	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtps	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtps	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtps	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtps	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtps	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtps	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtpu	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtpu	s12, s13
-# CHECK-NEXT:  4      6     1.00                        fcvtpu	h12, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtpu	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtpu	h12, h13
 # CHECK-NEXT:  1      3     0.50                        fcvtpu	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtpu	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        fcvtpu	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtpu	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        fcvtpu	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtpu	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtpu	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        fcvtpu	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtxn	s22, d13
 # CHECK-NEXT:  1      3     0.50                        fcvtxn	v0.2s, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtxn2	v0.4s, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtzs	d21, d12, #1
 # CHECK-NEXT:  1      3     0.50                        fcvtzs	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtzs	s12, s13
-# CHECK-NEXT:  2      4     1.00                        fcvtzs	s21, s12, #1
-# CHECK-NEXT:  4      6     1.00                        fcvtzs	h21, h14
-# CHECK-NEXT:  4      6     1.00                        fcvtzs	h21, h12, #1
+# CHECK-NEXT:  1      3     0.50                        fcvtzs	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtzs	s21, s12, #1
+# CHECK-NEXT:  1      3     0.50                        fcvtzs	h21, h14
+# CHECK-NEXT:  1      3     0.50                        fcvtzs	h21, h12, #1
 # CHECK-NEXT:  1      3     0.50                        fcvtzs	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtzs	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      3     0.50                        fcvtzs	v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.50                        fcvtzs	v0.2s, v0.2s, #3
-# CHECK-NEXT:  2      4     1.00                        fcvtzs	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtzs	v0.4s, v0.4s
-# CHECK-NEXT:  2      4     1.00                        fcvtzs	v0.4s, v0.4s, #3
-# CHECK-NEXT:  4      6     1.00                        fcvtzs	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        fcvtzs	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtzs	v0.4s, v0.4s
+# CHECK-NEXT:  1      4     1.00                        fcvtzs	v0.4s, v0.4s, #3
+# CHECK-NEXT:  1      6     2.00                        fcvtzs	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        fcvtzu	d21, d12, #1
 # CHECK-NEXT:  1      3     0.50                        fcvtzu	d21, d14
-# CHECK-NEXT:  2      4     1.00                        fcvtzu	s12, s13
-# CHECK-NEXT:  2      4     1.00                        fcvtzu	s21, s12, #1
-# CHECK-NEXT:  4      6     1.00                        fcvtzu	h12, h13
-# CHECK-NEXT:  4      6     1.00                        fcvtzu	h21, h12, #1
+# CHECK-NEXT:  1      3     0.50                        fcvtzu	s12, s13
+# CHECK-NEXT:  1      3     0.50                        fcvtzu	s21, s12, #1
+# CHECK-NEXT:  1      3     0.50                        fcvtzu	h12, h13
+# CHECK-NEXT:  1      3     0.50                        fcvtzu	h21, h12, #1
 # CHECK-NEXT:  1      3     0.50                        fcvtzu	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        fcvtzu	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      3     0.50                        fcvtzu	v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.50                        fcvtzu	v0.2s, v0.2s, #3
-# CHECK-NEXT:  2      4     1.00                        fcvtzu	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        fcvtzu	v0.4s, v0.4s
-# CHECK-NEXT:  2      4     1.00                        fcvtzu	v0.4s, v0.4s, #3
-# CHECK-NEXT:  4      6     1.00                        fcvtzu	v0.8h, v0.8h
-# CHECK-NEXT:  1      15    3.50                        fdiv	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT:  1      10    3.50                        fdiv	v0.2s, v0.2s, v0.2s
+# CHECK-NEXT:  1      4     1.00                        fcvtzu	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        fcvtzu	v0.4s, v0.4s
+# CHECK-NEXT:  1      4     1.00                        fcvtzu	v0.4s, v0.4s, #3
+# CHECK-NEXT:  1      6     2.00                        fcvtzu	v0.8h, v0.8h
+# CHECK-NEXT:  1      15    7.00                        fdiv	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT:  1      10    2.50                        fdiv	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      7     3.50                        fdiv	v0.4h, v0.4h, v0.4h
-# CHECK-NEXT:  1      10    3.50                        fdiv	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT:  1      13    2.50                        fdiv	v0.8h, v0.8h, v0.8h
+# CHECK-NEXT:  1      10    4.50                        fdiv	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT:  1      13    6.50                        fdiv	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        fmax	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      2     0.25                        fmax	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        fmax	v0.4s, v0.4s, v0.4s
@@ -1493,9 +1493,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        fmaxp	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      2     0.25                        fmaxp	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        fmaxp	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT:  2      4     0.50                        fmaxv	h0, v0.4h
-# CHECK-NEXT:  3      6     0.75                        fmaxv	h0, v0.8h
-# CHECK-NEXT:  2      4     0.50                        fmaxv	s0, v0.4s
+# CHECK-NEXT:  1      4     0.50                        fmaxv	h0, v0.4h
+# CHECK-NEXT:  1      6     0.75                        fmaxv	h0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        fmaxv	s0, v0.4s
 # CHECK-NEXT:  1      2     0.25                        fmin	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      2     0.25                        fmin	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        fmin	v0.4s, v0.4s, v0.4s
@@ -1537,8 +1537,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.25                        fmul	s0, s1, v0.s[3]
 # CHECK-NEXT:  1      3     0.25                        fmul	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.25                        fmulx	d0, d4, v0.d[1]
-# CHECK-NEXT:  1      2     0.25                        fmulx	d23, d11, d1
-# CHECK-NEXT:  1      2     0.25                        fmulx	s20, s22, s15
+# CHECK-NEXT:  1      3     0.25                        fmulx	d23, d11, d1
+# CHECK-NEXT:  1      3     0.25                        fmulx	s20, s22, s15
 # CHECK-NEXT:  1      3     0.25                        fmulx	s3, s5, v0.s[3]
 # CHECK-NEXT:  1      3     0.25                        fmulx	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.25                        fmulx	v0.2s, v0.2s, v0.2s
@@ -1550,11 +1550,11 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        fneg	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frecpe	d13, d13
 # CHECK-NEXT:  1      3     0.50                        frecpe	s19, s14
-# CHECK-NEXT:  1      4     0.50                        frecpe	v0.2d, v0.2d
+# CHECK-NEXT:  1      4     1.00                        frecpe	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frecpe	v0.2s, v0.2s
-# CHECK-NEXT:  1      4     0.50                        frecpe	v0.4h, v0.4h
-# CHECK-NEXT:  1      4     0.50                        frecpe	v0.4s, v0.4s
-# CHECK-NEXT:  2      6     1.00                        frecpe	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frecpe	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frecpe	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frecpe	v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.25                        frecps	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      4     0.25                        frecps	d22, d30, d21
 # CHECK-NEXT:  1      4     0.25                        frecps	s21, s16, s13
@@ -1562,63 +1562,63 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frecpx	s18, s10
 # CHECK-NEXT:  1      3     0.50                        frinta	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frinta	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frinta	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frinta	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frinta	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frinta	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frinta	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frinta	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frinti	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frinti	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frinti	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frinti	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frinti	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frinti	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frinti	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frinti	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frintm	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frintm	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frintm	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frintm	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frintm	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frintm	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frintm	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frintm	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frintn	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frintn	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frintn	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frintn	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frintn	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frintn	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frintn	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frintn	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frintp	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frintp	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frintp	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frintp	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frintp	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frintp	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frintp	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frintp	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frintx	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frintx	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frintx	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frintx	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frintx	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frintx	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frintx	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frintx	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frintz	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frintz	v0.2s, v0.2s
-# CHECK-NEXT:  2      4     1.00                        frintz	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        frintz	v0.4s, v0.4s
-# CHECK-NEXT:  4      6     1.00                        frintz	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frintz	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frintz	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frintz	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.50                        frsqrte	d21, d12
 # CHECK-NEXT:  1      3     0.50                        frsqrte	s22, s13
-# CHECK-NEXT:  1      4     0.50                        frsqrte	v0.2d, v0.2d
+# CHECK-NEXT:  1      4     1.00                        frsqrte	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        frsqrte	v0.2s, v0.2s
-# CHECK-NEXT:  1      4     0.50                        frsqrte	v0.4h, v0.4h
-# CHECK-NEXT:  1      4     0.50                        frsqrte	v0.4s, v0.4s
-# CHECK-NEXT:  2      6     1.00                        frsqrte	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        frsqrte	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        frsqrte	v0.4s, v0.4s
+# CHECK-NEXT:  1      6     2.00                        frsqrte	v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.25                        frsqrts	d8, d22, d18
 # CHECK-NEXT:  1      4     0.25                        frsqrts	s21, s5, s12
 # CHECK-NEXT:  1      4     0.25                        frsqrts	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT:  1      16    3.50                        fsqrt	v0.2d, v0.2d
-# CHECK-NEXT:  1      10    3.50                        fsqrt	v0.2s, v0.2s
+# CHECK-NEXT:  1      16    7.50                        fsqrt	v0.2d, v0.2d
+# CHECK-NEXT:  1      10    2.50                        fsqrt	v0.2s, v0.2s
 # CHECK-NEXT:  1      7     3.50                        fsqrt	v0.4h, v0.4h
-# CHECK-NEXT:  1      10    3.50                        fsqrt	v0.4s, v0.4s
-# CHECK-NEXT:  1      13    5.50                        fsqrt	v0.8h, v0.8h
+# CHECK-NEXT:  1      10    4.50                        fsqrt	v0.4s, v0.4s
+# CHECK-NEXT:  1      13    6.50                        fsqrt	v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        fsub	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      6     0.33    *                   ld1	{ v0.16b }, [x0]
-# CHECK-NEXT:  3      6     0.67    *                   ld1	{ v0.8h, v1.8h }, [sp], #32
-# CHECK-NEXT:  4      6     1.00    *                   ld1	{ v0.4s, v1.4s, v2.4s }, [x0], #48
-# CHECK-NEXT:  4      7     1.33    *                   ld1	{ v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
+# CHECK-NEXT:  2      6     0.67    *                   ld1	{ v0.8h, v1.8h }, [sp], #32
+# CHECK-NEXT:  2      6     1.00    *                   ld1	{ v0.4s, v1.4s, v2.4s }, [x0], #48
+# CHECK-NEXT:  1      7     1.33    *                   ld1	{ v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
 # CHECK-NEXT:  2      6     0.33    *                   ld1	{ v0.1d }, [x15], x2
-# CHECK-NEXT:  2      6     0.67    *                   ld1	{ v0.2s, v1.2s }, [x15]
-# CHECK-NEXT:  3      6     1.00    *                   ld1	{ v0.4h, v1.4h, v2.4h }, [sp]
-# CHECK-NEXT:  3      6     0.67    *                   ld1	{ v0.8b, v1.8b, v2.8b, v3.8b }, [x0], x3
+# CHECK-NEXT:  1      6     0.67    *                   ld1	{ v0.2s, v1.2s }, [x15]
+# CHECK-NEXT:  1      6     1.00    *                   ld1	{ v0.4h, v1.4h, v2.4h }, [sp]
+# CHECK-NEXT:  2      6     0.67    *                   ld1	{ v0.8b, v1.8b, v2.8b, v3.8b }, [x0], x3
 # CHECK-NEXT:  2      8     0.33    *                   ld1	{ v0.b }[7], [x0]
 # CHECK-NEXT:  3      8     0.33    *                   ld1	{ v0.h }[3], [x0], #2
 # CHECK-NEXT:  2      8     0.33    *                   ld1	{ v0.s }[1], [x15]
@@ -1627,30 +1627,30 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  3      8     0.33    *                   ld1r	{ v0.8h }, [x0], #2
 # CHECK-NEXT:  2      8     0.33    *                   ld1r	{ v0.4s }, [x15]
 # CHECK-NEXT:  3      8     0.33    *                   ld1r	{ v0.2d }, [x15], x16
-# CHECK-NEXT:  4      8     0.67    *                   ld2	{ v0.16b, v1.16b }, [x0]
-# CHECK-NEXT:  4      8     0.50    *                   ld2	{ v0.8b, v1.8b }, [x0], #16
-# CHECK-NEXT:  3      8     0.50    *                   ld2	{ v0.h, v1.h }[7], [x15]
-# CHECK-NEXT:  4      8     0.50    *                   ld2	{ v0.h, v1.h }[7], [x15], x8
-# CHECK-NEXT:  3      8     0.50    *                   ld2r	{ v0.8b, v1.8b }, [x0]
-# CHECK-NEXT:  4      8     0.50    *                   ld2r	{ v0.4h, v1.4h }, [x0], #4
-# CHECK-NEXT:  3      8     0.50    *                   ld2r	{ v0.2s, v1.2s }, [sp]
-# CHECK-NEXT:  4      8     0.50    *                   ld2r	{ v0.1d, v1.1d }, [sp], x8
-# CHECK-NEXT:  5      8     0.75    *                   ld3	{ v0.4h, v1.4h, v2.4h }, [x15]
-# CHECK-NEXT:  7      8     1.00    *                   ld3	{ v0.8h, v1.8h, v2.8h }, [x15], #48
-# CHECK-NEXT:  5      8     0.75    *                   ld3	{ v0.s, v1.s, v2.s }[3], [sp]
-# CHECK-NEXT:  6      8     0.75    *                   ld3	{ v0.s, v1.s, v2.s }[3], [sp], x3
-# CHECK-NEXT:  5      8     0.75    *                   ld3r	{ v0.8b, v1.8b, v2.8b }, [x15]
-# CHECK-NEXT:  6      8     0.75    *                   ld3r	{ v0.4h, v1.4h, v2.4h }, [x15], #6
-# CHECK-NEXT:  5      8     0.75    *                   ld3r	{ v0.2s, v1.2s, v2.2s }, [x0]
-# CHECK-NEXT:  6      8     0.75    *                   ld3r	{ v0.1d, v1.1d, v2.1d }, [x0], x0
-# CHECK-NEXT:  7      8     1.00    *                   ld4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
-# CHECK-NEXT:  9      9     1.33    *                   ld4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
-# CHECK-NEXT:  7      8     1.00    *                   ld4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0]
-# CHECK-NEXT:  8      8     1.00    *                   ld4	{ v0.h, v1.h, v2.h, v3.h }[7], [x0], x0
-# CHECK-NEXT:  7      8     1.00    *                   ld4r	{ v0.1d, v1.1d, v2.1d, v3.1d }, [sp]
-# CHECK-NEXT:  7      8     1.00    *                   ld4r	{ v0.2d, v1.2d, v2.2d, v3.2d }, [sp]
-# CHECK-NEXT:  8      8     1.00    *                   ld4r	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp], #16
-# CHECK-NEXT:  8      8     1.00    *                   ld4r	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], x8
+# CHECK-NEXT:  2      8     0.67    *                   ld2	{ v0.16b, v1.16b }, [x0]
+# CHECK-NEXT:  3      8     0.33    *                   ld2	{ v0.8b, v1.8b }, [x0], #16
+# CHECK-NEXT:  2      8     0.67    *                   ld2	{ v0.h, v1.h }[7], [x15]
+# CHECK-NEXT:  3      8     0.67    *                   ld2	{ v0.h, v1.h }[7], [x15], x8
+# CHECK-NEXT:  2      8     0.67    *                   ld2r	{ v0.8b, v1.8b }, [x0]
+# CHECK-NEXT:  3      8     0.67    *                   ld2r	{ v0.4h, v1.4h }, [x0], #4
+# CHECK-NEXT:  2      8     0.67    *                   ld2r	{ v0.2s, v1.2s }, [sp]
+# CHECK-NEXT:  3      8     0.67    *                   ld2r	{ v0.1d, v1.1d }, [sp], x8
+# CHECK-NEXT:  2      8     1.00    *                   ld3	{ v0.4h, v1.4h, v2.4h }, [x15]
+# CHECK-NEXT:  3      8     1.00    *                   ld3	{ v0.8h, v1.8h, v2.8h }, [x15], #48
+# CHECK-NEXT:  2      8     1.00    *                   ld3	{ v0.s, v1.s, v2.s }[3], [sp]
+# CHECK-NEXT:  3      8     1.00    *                   ld3	{ v0.s, v1.s, v2.s }[3], [sp], x3
+# CHECK-NEXT:  2      8     1.00    *                   ld3r	{ v0.8b, v1.8b, v2.8b }, [x15]
+# CHECK-NEXT:  3      8     1.00    *                   ld3r	{ v0.4h, v1.4h, v2.4h }, [x15], #6
+# CHECK-NEXT:  2      8     1.00    *                   ld3r	{ v0.2s, v1.2s, v2.2s }, [x0]
+# CHECK-NEXT:  3      8     1.00    *                   ld3r	{ v0.1d, v1.1d, v2.1d }, [x0], x0
+# CHECK-NEXT:  2      8     1.00    *                   ld4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
+# CHECK-NEXT:  3      9     2.00    *                   ld4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
+# CHECK-NEXT:  2      8     1.00    *                   ld4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0]
+# CHECK-NEXT:  3      8     1.00    *                   ld4	{ v0.h, v1.h, v2.h, v3.h }[7], [x0], x0
+# CHECK-NEXT:  2      8     1.00    *                   ld4r	{ v0.1d, v1.1d, v2.1d, v3.1d }, [sp]
+# CHECK-NEXT:  2      8     1.00    *                   ld4r	{ v0.2d, v1.2d, v2.2d, v3.2d }, [sp]
+# CHECK-NEXT:  3      8     1.00    *                   ld4r	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp], #16
+# CHECK-NEXT:  3      8     1.00    *                   ld4r	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], x8
 # CHECK-NEXT:  1      4     0.50                        mla	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  1      4     0.50                        mls	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  1      2     0.25                        mov	b0, v0.b[15]
@@ -1759,9 +1759,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        saddlp	v0.8h, v0.16b
 # CHECK-NEXT:  1      2     0.50                        saddlv	d0, v0.4s
 # CHECK-NEXT:  1      2     0.50                        saddlv	s0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        saddlv	s0, v0.8h
-# CHECK-NEXT:  2      4     0.50                        saddlv	h0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        saddlv	h0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        saddlv	s0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        saddlv	h0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        saddlv	h0, v0.16b
 # CHECK-NEXT:  1      2     0.25                        saddw	v0.2d, v0.2d, v0.2s
 # CHECK-NEXT:  1      2     0.25                        saddw	v0.4s, v0.4s, v0.4h
 # CHECK-NEXT:  1      2     0.25                        saddw	v0.8h, v0.8h, v0.8b
@@ -1770,22 +1770,22 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        saddw2	v0.8h, v0.8h, v0.16b
 # CHECK-NEXT:  1      3     0.50                        scvtf	d21, d12
 # CHECK-NEXT:  1      3     0.50                        scvtf	d21, d12, #64
-# CHECK-NEXT:  2      4     1.00                        scvtf	s22, s13
-# CHECK-NEXT:  2      4     1.00                        scvtf	s22, s13, #32
+# CHECK-NEXT:  1      3     0.50                        scvtf	s22, s13
+# CHECK-NEXT:  1      3     0.50                        scvtf	s22, s13, #32
 # CHECK-NEXT:  1      3     0.50                        scvtf	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        scvtf	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      3     0.50                        scvtf	v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.50                        scvtf	v0.2s, v0.2s, #3
-# CHECK-NEXT:  2      4     1.00                        scvtf	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        scvtf	v0.4s, v0.4s
-# CHECK-NEXT:  2      4     1.00                        scvtf	v0.4s, v0.4s, #3
-# CHECK-NEXT:  4      6     1.00                        scvtf	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        scvtf	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        scvtf	v0.4s, v0.4s
+# CHECK-NEXT:  1      4     1.00                        scvtf	v0.4s, v0.4s, #3
+# CHECK-NEXT:  1      6     2.00                        scvtf	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.25                        sdot	v0.2s, v0.8b, v0.4b[2]
 # CHECK-NEXT:  1      3     0.25                        sdot	v0.2s, v0.8b, v0.8b
 # CHECK-NEXT:  1      3     0.25                        sdot	v0.4s, v0.16b, v0.16b
 # CHECK-NEXT:  1      3     0.25                        sdot	v0.4s, v0.16b, v0.4b[2]
 # CHECK-NEXT:  1      2     0.25                        shadd	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  1      2     0.25                        shl	d7, d10, #12
+# CHECK-NEXT:  1      2     0.50                        shl	d7, d10, #12
 # CHECK-NEXT:  1      2     0.50                        shl	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      2     0.50                        shl	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      2     0.50                        shl	v0.4h, v0.4h, #3
@@ -1810,7 +1810,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.50                        shrn2	v0.8h, v0.4s, #3
 # CHECK-NEXT:  1      2     0.25                        shsub	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        shsub	v0.4h, v0.4h, v0.4h
-# CHECK-NEXT:  1      2     0.25                        sli	d10, d14, #12
+# CHECK-NEXT:  1      2     0.50                        sli	d10, d14, #12
 # CHECK-NEXT:  1      2     0.50                        sli	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      2     0.50                        sli	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      2     0.50                        sli	v0.2s, v0.2s, #3
@@ -1824,10 +1824,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        smaxp	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        smaxp	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  1      2     0.25                        smaxp	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  2      4     0.50                        smaxv	b0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        smaxv	b0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        smaxv	b0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        smaxv	b0, v0.16b
 # CHECK-NEXT:  1      2     0.50                        smaxv	h0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        smaxv	h0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        smaxv	h0, v0.8h
 # CHECK-NEXT:  1      2     0.50                        smaxv	s0, v0.4s
 # CHECK-NEXT:  1      2     0.25                        smin	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        smin	v0.4s, v0.4s, v0.4s
@@ -1835,10 +1835,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        sminp	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        sminp	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      2     0.25                        sminp	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  2      4     0.50                        sminv	b0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        sminv	b0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        sminv	b0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        sminv	b0, v0.16b
 # CHECK-NEXT:  1      2     0.50                        sminv	h0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        sminv	h0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        sminv	h0, v0.8h
 # CHECK-NEXT:  1      2     0.50                        sminv	s0, v0.4s
 # CHECK-NEXT:  1      4     0.50                        smlal	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  1      4     0.50                        smlal	v0.4s, v0.4h, v0.4h
@@ -1896,9 +1896,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        sqdmulh	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      4     0.50                        sqdmulh	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      3     0.50                        sqdmull	d1, s1, v0.s[1]
-# CHECK-NEXT:  1      2     0.25                        sqdmull	d15, s22, s12
+# CHECK-NEXT:  1      3     0.50                        sqdmull	d15, s22, s12
 # CHECK-NEXT:  1      3     0.50                        sqdmull	s1, h1, v0.h[3]
-# CHECK-NEXT:  1      2     0.25                        sqdmull	s12, h22, h12
+# CHECK-NEXT:  1      3     0.50                        sqdmull	s12, h22, h12
 # CHECK-NEXT:  1      3     0.50                        sqdmull	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.50                        sqdmull	v0.4s, v0.4h, v0.4h
 # CHECK-NEXT:  1      3     0.50                        sqdmull2	v0.2d, v0.4s, v0.4s
@@ -1949,18 +1949,18 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        sqrshl	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      4     0.50                        sqrshl	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  1      4     0.50                        sqrshl	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  1      2     0.25                        sqrshrn	b10, h13, #2
-# CHECK-NEXT:  1      2     0.25                        sqrshrn	h15, s10, #6
-# CHECK-NEXT:  1      2     0.25                        sqrshrn	s15, d12, #9
+# CHECK-NEXT:  1      4     0.50                        sqrshrn	b10, h13, #2
+# CHECK-NEXT:  1      4     0.50                        sqrshrn	h15, s10, #6
+# CHECK-NEXT:  1      4     0.50                        sqrshrn	s15, d12, #9
 # CHECK-NEXT:  1      4     0.50                        sqrshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrn	v0.8b, v0.8h, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrn2	v0.16b, v0.8h, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrn2	v0.4s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrn2	v0.8h, v0.4s, #3
-# CHECK-NEXT:  1      2     0.25                        sqrshrun	b17, h10, #6
-# CHECK-NEXT:  1      2     0.25                        sqrshrun	h10, s13, #15
-# CHECK-NEXT:  1      2     0.25                        sqrshrun	s22, d16, #31
+# CHECK-NEXT:  1      4     0.50                        sqrshrun	b17, h10, #6
+# CHECK-NEXT:  1      4     0.50                        sqrshrun	h10, s13, #15
+# CHECK-NEXT:  1      4     0.50                        sqrshrun	s22, d16, #31
 # CHECK-NEXT:  1      4     0.50                        sqrshrun	v0.2s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrun	v0.4h, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        sqrshrun	v0.8b, v0.8h, #3
@@ -1994,24 +1994,24 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        sqshlu	v0.4s, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        sqshlu	v0.8b, v0.8b, #3
 # CHECK-NEXT:  1      4     0.50                        sqshlu	v0.8h, v0.8h, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrn	b10, h15, #5
-# CHECK-NEXT:  1      2     0.25                        sqshrn	h17, s10, #4
-# CHECK-NEXT:  1      2     0.25                        sqshrn	s18, d10, #31
+# CHECK-NEXT:  1      4     0.50                        sqshrn	b10, h15, #5
+# CHECK-NEXT:  1      4     0.50                        sqshrn	h17, s10, #4
+# CHECK-NEXT:  1      4     0.50                        sqshrn	s18, d10, #31
 # CHECK-NEXT:  1      4     0.50                        sqshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        sqshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        sqshrn	v0.8b, v0.8h, #3
 # CHECK-NEXT:  1      4     0.50                        sqshrn2	v0.16b, v0.8h, #3
 # CHECK-NEXT:  1      4     0.50                        sqshrn2	v0.4s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        sqshrn2	v0.8h, v0.4s, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun	b15, h10, #7
-# CHECK-NEXT:  1      2     0.25                        sqshrun	h20, s14, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun	s10, d15, #15
-# CHECK-NEXT:  1      2     0.25                        sqshrun	v0.2s, v0.2d, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun	v0.4h, v0.4s, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun	v0.8b, v0.8h, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun2	v0.16b, v0.8h, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun2	v0.4s, v0.2d, #3
-# CHECK-NEXT:  1      2     0.25                        sqshrun2	v0.8h, v0.4s, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun	b15, h10, #7
+# CHECK-NEXT:  1      4     0.50                        sqshrun	h20, s14, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun	s10, d15, #15
+# CHECK-NEXT:  1      4     0.50                        sqshrun	v0.2s, v0.2d, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun	v0.4h, v0.4s, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun	v0.8b, v0.8h, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun2	v0.16b, v0.8h, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun2	v0.4s, v0.2d, #3
+# CHECK-NEXT:  1      4     0.50                        sqshrun2	v0.8h, v0.4s, #3
 # CHECK-NEXT:  1      2     0.25                        sqsub	s20, s10, s7
 # CHECK-NEXT:  1      2     0.25                        sqsub	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      2     0.25                        sqsub	v0.4s, v0.4s, v0.4s
@@ -2037,7 +2037,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        srhadd	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        srhadd	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  1      2     0.25                        srhadd	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  1      2     0.25                        sri	d10, d12, #14
+# CHECK-NEXT:  1      2     0.50                        sri	d10, d12, #14
 # CHECK-NEXT:  1      2     0.50                        sri	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      2     0.50                        sri	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      2     0.50                        sri	v0.2s, v0.2s, #3
@@ -2049,7 +2049,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        srshl	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      4     0.50                        srshl	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  1      4     0.50                        srshl	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  1      2     0.25                        srshr	d19, d18, #7
+# CHECK-NEXT:  1      4     0.50                        srshr	d19, d18, #7
 # CHECK-NEXT:  1      4     0.50                        srshr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      4     0.50                        srshr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        srshr	v0.2s, v0.2s, #3
@@ -2057,7 +2057,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        srshr	v0.4s, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        srshr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  1      4     0.50                        srshr	v0.8h, v0.8h, #3
-# CHECK-NEXT:  1      2     0.25                        srsra	d15, d11, #19
+# CHECK-NEXT:  1      4     0.50                        srsra	d15, d11, #19
 # CHECK-NEXT:  1      4     0.50                        srsra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      4     0.50                        srsra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        srsra	v0.2s, v0.2s, #3
@@ -2072,7 +2072,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.50                        sshl	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  1      2     0.50                        sshll	v0.2d, v0.2s, #3
 # CHECK-NEXT:  1      2     0.50                        sshll2	v0.4s, v0.8h, #3
-# CHECK-NEXT:  1      2     0.25                        sshr	d15, d16, #12
+# CHECK-NEXT:  1      2     0.50                        sshr	d15, d16, #12
 # CHECK-NEXT:  1      2     0.50                        sshr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      2     0.50                        sshr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      2     0.50                        sshr	v0.2s, v0.2s, #3
@@ -2080,7 +2080,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.50                        sshr	v0.4s, v0.4s, #3
 # CHECK-NEXT:  1      2     0.50                        sshr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  1      2     0.50                        sshr	v0.8h, v0.8h, #3
-# CHECK-NEXT:  1      2     0.25                        ssra	d18, d12, #21
+# CHECK-NEXT:  1      4     0.50                        ssra	d18, d12, #21
 # CHECK-NEXT:  1      4     0.50                        ssra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      4     0.50                        ssra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        ssra	v0.2s, v0.2s, #3
@@ -2101,27 +2101,27 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        ssubw2	v0.4s, v0.4s, v0.8h
 # CHECK-NEXT:  1      2     0.25                        ssubw2	v0.8h, v0.8h, v0.16b
 # CHECK-NEXT:  2      2     0.50           *            st1	{ v0.16b }, [x0]
-# CHECK-NEXT:  5      2     1.00           *            st1	{ v0.4s, v1.4s }, [sp], #32
-# CHECK-NEXT:  7      2     1.50           *            st1	{ v0.2d, v1.2d, v2.2d }, [x0], #48
-# CHECK-NEXT:  8      2     2.00           *            st1	{ v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
+# CHECK-NEXT:  3      2     1.00           *            st1	{ v0.4s, v1.4s }, [sp], #32
+# CHECK-NEXT:  3      2     1.50           *            st1	{ v0.2d, v1.2d, v2.2d }, [x0], #48
+# CHECK-NEXT:  2      2     2.00           *            st1	{ v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
 # CHECK-NEXT:  3      2     0.50           *            st1	{ v0.8h }, [x15], x2
-# CHECK-NEXT:  4      2     1.00           *            st1	{ v0.8h, v1.8h }, [x15]
-# CHECK-NEXT:  6      2     1.50           *            st1	{ v0.4s, v1.4s, v2.4s }, [sp]
-# CHECK-NEXT:  5      2     1.00           *            st1	{ v0.8b, v1.8b, v2.8b, v3.8b }, [x0], x3
+# CHECK-NEXT:  2      2     1.00           *            st1	{ v0.8h, v1.8h }, [x15]
+# CHECK-NEXT:  2      2     1.50           *            st1	{ v0.4s, v1.4s, v2.4s }, [sp]
+# CHECK-NEXT:  3      2     1.00           *            st1	{ v0.8b, v1.8b, v2.8b, v3.8b }, [x0], x3
 # CHECK-NEXT:  2      4     0.50           *            st1	{ v0.d }[1], [x0]
 # CHECK-NEXT:  3      4     0.50           *            st1	{ v0.d }[1], [x0], #8
-# CHECK-NEXT:  5      4     1.00           *            st2	{ v0.16b, v1.16b }, [x0], x1
+# CHECK-NEXT:  3      4     1.00           *            st2	{ v0.16b, v1.16b }, [x0], x1
 # CHECK-NEXT:  2      4     0.50           *            st2	{ v0.8b, v1.8b }, [x0]
 # CHECK-NEXT:  2      4     0.50           *            st2	{ v0.s, v1.s }[3], [sp]
 # CHECK-NEXT:  3      4     0.50           *            st2	{ v0.s, v1.s }[3], [sp], #8
-# CHECK-NEXT:  4      4     1.00           *            st3	{ v0.4h, v1.4h, v2.4h }, [x15]
-# CHECK-NEXT:  7      5     1.50           *            st3	{ v0.8h, v1.8h, v2.8h }, [x15], x2
-# CHECK-NEXT:  4      4     1.00           *            st3	{ v0.h, v1.h, v2.h }[7], [x15]
-# CHECK-NEXT:  5      4     1.00           *            st3	{ v0.h, v1.h, v2.h }[7], [x15], #6
-# CHECK-NEXT:  6      6     1.50           *            st4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
-# CHECK-NEXT:  13     7     3.00           *            st4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
-# CHECK-NEXT:  6      6     1.00           *            st4	{ v0.b, v1.b, v2.b, v3.b }[15], [x0]
-# CHECK-NEXT:  5      4     1.00           *            st4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0], x5
+# CHECK-NEXT:  2      4     1.00           *            st3	{ v0.4h, v1.4h, v2.4h }, [x15]
+# CHECK-NEXT:  3      5     1.50           *            st3	{ v0.8h, v1.8h, v2.8h }, [x15], x2
+# CHECK-NEXT:  2      4     1.00           *            st3	{ v0.h, v1.h, v2.h }[7], [x15]
+# CHECK-NEXT:  3      4     1.00           *            st3	{ v0.h, v1.h, v2.h }[7], [x15], #6
+# CHECK-NEXT:  2      6     3.00           *            st4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
+# CHECK-NEXT:  3      7     6.00           *            st4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
+# CHECK-NEXT:  2      6     1.00           *            st4	{ v0.b, v1.b, v2.b, v3.b }[15], [x0]
+# CHECK-NEXT:  3      4     1.00           *            st4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0], x5
 # CHECK-NEXT:  1      2     0.25                        sub	d15, d5, d16
 # CHECK-NEXT:  1      2     0.25                        sub	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.25                        sudot	v0.2s, v0.8b, v0.4b[2]
@@ -2137,22 +2137,22 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        suqadd	v0.4s, v0.4s
 # CHECK-NEXT:  1      2     0.25                        suqadd	v0.8b, v0.8b
 # CHECK-NEXT:  1      2     0.25                        suqadd	v0.8h, v0.8h
-# CHECK-NEXT:  2      2     1.00                        tbl	v0.16b, { v0.16b }, v0.16b
-# CHECK-NEXT:  2      2     1.00                        tbl	v0.16b, { v0.16b, v1.16b }, v0.16b
-# CHECK-NEXT:  2      4     1.00                        tbl	v0.16b, { v0.16b, v1.16b, v2.16b }, v0.16b
-# CHECK-NEXT:  3      4     1.50                        tbl	v0.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.16b
-# CHECK-NEXT:  2      2     1.00                        tbl	v0.8b, { v0.16b }, v0.8b
-# CHECK-NEXT:  2      2     1.00                        tbl	v0.8b, { v0.16b, v1.16b }, v0.8b
-# CHECK-NEXT:  2      4     1.00                        tbl	v0.8b, { v0.16b, v1.16b, v2.16b }, v0.8b
-# CHECK-NEXT:  3      4     1.50                        tbl	v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.8b
-# CHECK-NEXT:  2      2     1.00                        tbx	v0.16b, { v0.16b }, v0.16b
-# CHECK-NEXT:  2      4     1.00                        tbx	v0.16b, { v0.16b, v1.16b }, v0.16b
-# CHECK-NEXT:  3      6     1.50                        tbx	v0.16b, { v0.16b, v1.16b, v2.16b }, v0.16b
-# CHECK-NEXT:  5      6     2.50                        tbx	v0.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.16b
-# CHECK-NEXT:  2      2     1.00                        tbx	v0.8b, { v0.16b }, v0.8b
-# CHECK-NEXT:  2      4     1.00                        tbx	v0.8b, { v0.16b, v1.16b }, v0.8b
-# CHECK-NEXT:  3      6     1.50                        tbx	v0.8b, { v0.16b, v1.16b, v2.16b }, v0.8b
-# CHECK-NEXT:  5      6     2.50                        tbx	v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.8b
+# CHECK-NEXT:  1      2     0.50                        tbl	v0.16b, { v0.16b }, v0.16b
+# CHECK-NEXT:  1      2     0.50                        tbl	v0.16b, { v0.16b, v1.16b }, v0.16b
+# CHECK-NEXT:  1      4     1.00                        tbl	v0.16b, { v0.16b, v1.16b, v2.16b }, v0.16b
+# CHECK-NEXT:  1      4     1.50                        tbl	v0.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.16b
+# CHECK-NEXT:  1      2     0.50                        tbl	v0.8b, { v0.16b }, v0.8b
+# CHECK-NEXT:  1      2     0.50                        tbl	v0.8b, { v0.16b, v1.16b }, v0.8b
+# CHECK-NEXT:  1      4     1.00                        tbl	v0.8b, { v0.16b, v1.16b, v2.16b }, v0.8b
+# CHECK-NEXT:  1      4     1.50                        tbl	v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.8b
+# CHECK-NEXT:  1      2     0.50                        tbx	v0.16b, { v0.16b }, v0.16b
+# CHECK-NEXT:  1      4     1.00                        tbx	v0.16b, { v0.16b, v1.16b }, v0.16b
+# CHECK-NEXT:  1      6     1.50                        tbx	v0.16b, { v0.16b, v1.16b, v2.16b }, v0.16b
+# CHECK-NEXT:  1      6     2.50                        tbx	v0.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.16b
+# CHECK-NEXT:  1      2     0.50                        tbx	v0.8b, { v0.16b }, v0.8b
+# CHECK-NEXT:  1      4     1.00                        tbx	v0.8b, { v0.16b, v1.16b }, v0.8b
+# CHECK-NEXT:  1      6     1.50                        tbx	v0.8b, { v0.16b, v1.16b, v2.16b }, v0.8b
+# CHECK-NEXT:  1      6     2.50                        tbx	v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.8b
 # CHECK-NEXT:  1      2     0.25                        trn1	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        trn1	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      2     0.25                        trn1	v0.2s, v0.2s, v0.2s
@@ -2201,9 +2201,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        uaddlp	v0.8h, v0.16b
 # CHECK-NEXT:  1      2     0.50                        uaddlv	d0, v0.4s
 # CHECK-NEXT:  1      2     0.50                        uaddlv	s0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        uaddlv	s0, v0.8h
-# CHECK-NEXT:  2      4     0.50                        uaddlv	h0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        uaddlv	h0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        uaddlv	s0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        uaddlv	h0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        uaddlv	h0, v0.16b
 # CHECK-NEXT:  1      2     0.25                        uaddw	v0.2d, v0.2d, v0.2s
 # CHECK-NEXT:  1      2     0.25                        uaddw	v0.4s, v0.4s, v0.4h
 # CHECK-NEXT:  1      2     0.25                        uaddw	v0.8h, v0.8h, v0.8b
@@ -2212,16 +2212,16 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        uaddw2	v0.8h, v0.8h, v0.16b
 # CHECK-NEXT:  1      3     0.50                        ucvtf	d21, d14
 # CHECK-NEXT:  1      3     0.50                        ucvtf	d21, d14, #64
-# CHECK-NEXT:  2      4     1.00                        ucvtf	s22, s13
-# CHECK-NEXT:  2      4     1.00                        ucvtf	s22, s13, #32
+# CHECK-NEXT:  1      3     0.50                        ucvtf	s22, s13
+# CHECK-NEXT:  1      3     0.50                        ucvtf	s22, s13, #32
 # CHECK-NEXT:  1      3     0.50                        ucvtf	v0.2d, v0.2d
 # CHECK-NEXT:  1      3     0.50                        ucvtf	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      3     0.50                        ucvtf	v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.50                        ucvtf	v0.2s, v0.2s, #3
-# CHECK-NEXT:  2      4     1.00                        ucvtf	v0.4h, v0.4h
-# CHECK-NEXT:  2      4     1.00                        ucvtf	v0.4s, v0.4s
-# CHECK-NEXT:  2      4     1.00                        ucvtf	v0.4s, v0.4s, #3
-# CHECK-NEXT:  4      6     1.00                        ucvtf	v0.8h, v0.8h
+# CHECK-NEXT:  1      4     1.00                        ucvtf	v0.4h, v0.4h
+# CHECK-NEXT:  1      4     1.00                        ucvtf	v0.4s, v0.4s
+# CHECK-NEXT:  1      4     1.00                        ucvtf	v0.4s, v0.4s, #3
+# CHECK-NEXT:  1      6     2.00                        ucvtf	v0.8h, v0.8h
 # CHECK-NEXT:  1      3     0.25                        udot	v0.2s, v0.8b, v0.4b[2]
 # CHECK-NEXT:  1      3     0.25                        udot	v0.2s, v0.8b, v0.8b
 # CHECK-NEXT:  1      3     0.25                        udot	v0.4s, v0.16b, v0.16b
@@ -2235,10 +2235,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        umaxp	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        umaxp	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      2     0.25                        umaxp	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  2      4     0.50                        umaxv	b0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        umaxv	b0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        umaxv	b0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        umaxv	b0, v0.16b
 # CHECK-NEXT:  1      2     0.50                        umaxv	h0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        umaxv	h0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        umaxv	h0, v0.8h
 # CHECK-NEXT:  1      2     0.50                        umaxv	s0, v0.4s
 # CHECK-NEXT:  1      2     0.25                        umin	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        umin	v0.4h, v0.4h, v0.4h
@@ -2246,10 +2246,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        uminp	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  1      2     0.25                        uminp	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  1      2     0.25                        uminp	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  2      4     0.50                        uminv	b0, v0.8b
-# CHECK-NEXT:  2      4     1.00                        uminv	b0, v0.16b
+# CHECK-NEXT:  1      4     0.50                        uminv	b0, v0.8b
+# CHECK-NEXT:  1      4     1.00                        uminv	b0, v0.16b
 # CHECK-NEXT:  1      2     0.50                        uminv	h0, v0.4h
-# CHECK-NEXT:  2      4     0.50                        uminv	h0, v0.8h
+# CHECK-NEXT:  1      4     0.50                        uminv	h0, v0.8h
 # CHECK-NEXT:  1      2     0.50                        uminv	s0, v0.4s
 # CHECK-NEXT:  1      4     0.50                        umlal	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  1      4     0.50                        umlal	v0.4s, v0.4h, v0.4h
@@ -2264,10 +2264,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        umlsl2	v0.4s, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        umlsl2	v0.8h, v0.16b, v0.16b
 # CHECK-NEXT:  1      3     0.25                        ummla	v0.4s, v0.16b, v0.16b
-# CHECK-NEXT:  1      2     0.25                        umov	w0, v0.b[1]
-# CHECK-NEXT:  1      2     0.25                        umov	w0, v0.h[1]
-# CHECK-NEXT:  1      2     0.25                        mov	w0, v0.s[1]
-# CHECK-NEXT:  1      2     0.25                        mov	x0, v0.d[1]
+# CHECK-NEXT:  1      2     1.00                        umov	w0, v0.b[1]
+# CHECK-NEXT:  1      2     1.00                        umov	w0, v0.h[1]
+# CHECK-NEXT:  1      2     1.00                        mov	w0, v0.s[1]
+# CHECK-NEXT:  1      2     1.00                        mov	x0, v0.d[1]
 # CHECK-NEXT:  1      3     0.50                        umull	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  1      3     0.50                        umull	v0.4s, v0.4h, v0.4h
 # CHECK-NEXT:  1      3     0.50                        umull	v0.8h, v0.8b, v0.8b
@@ -2282,9 +2282,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        uqrshl	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      4     0.50                        uqrshl	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      4     0.50                        uqrshl	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  1      2     0.25                        uqrshrn	b10, h12, #5
-# CHECK-NEXT:  1      2     0.25                        uqrshrn	h12, s10, #14
-# CHECK-NEXT:  1      2     0.25                        uqrshrn	s10, d10, #25
+# CHECK-NEXT:  1      4     0.50                        uqrshrn	b10, h12, #5
+# CHECK-NEXT:  1      4     0.50                        uqrshrn	h12, s10, #14
+# CHECK-NEXT:  1      4     0.50                        uqrshrn	s10, d10, #25
 # CHECK-NEXT:  1      4     0.50                        uqrshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        uqrshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        uqrshrn	v0.8b, v0.8h, #3
@@ -2308,9 +2308,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        uqshl	v0.8b, v0.8b, #3
 # CHECK-NEXT:  1      4     0.50                        uqshl	v0.8h, v0.8h, #3
 # CHECK-NEXT:  1      4     0.50                        uqshl	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  1      2     0.25                        uqshrn	b12, h10, #7
-# CHECK-NEXT:  1      2     0.25                        uqshrn	h10, s14, #5
-# CHECK-NEXT:  1      2     0.25                        uqshrn	s10, d12, #13
+# CHECK-NEXT:  1      4     0.50                        uqshrn	b12, h10, #7
+# CHECK-NEXT:  1      4     0.50                        uqshrn	h10, s14, #5
+# CHECK-NEXT:  1      4     0.50                        uqshrn	s10, d12, #13
 # CHECK-NEXT:  1      4     0.50                        uqshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        uqshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  1      4     0.50                        uqshrn	v0.8b, v0.8h, #3
@@ -2329,7 +2329,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        uqxtn2	v0.4s, v0.2d
 # CHECK-NEXT:  1      4     0.50                        uqxtn2	v0.8h, v0.4s
 # CHECK-NEXT:  1      3     0.50                        urecpe	v0.2s, v0.2s
-# CHECK-NEXT:  1      4     0.50                        urecpe	v0.4s, v0.4s
+# CHECK-NEXT:  1      4     1.00                        urecpe	v0.4s, v0.4s
 # CHECK-NEXT:  1      2     0.25                        urhadd	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  1      2     0.25                        urhadd	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      2     0.25                        urhadd	v0.8h, v0.8h, v0.8h
@@ -2338,7 +2338,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        urshl	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  1      4     0.50                        urshl	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  1      4     0.50                        urshl	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  1      2     0.25                        urshr	d20, d23, #31
+# CHECK-NEXT:  1      4     0.50                        urshr	d20, d23, #31
 # CHECK-NEXT:  1      4     0.50                        urshr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      4     0.50                        urshr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        urshr	v0.2s, v0.2s, #3
@@ -2347,8 +2347,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      4     0.50                        urshr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  1      4     0.50                        urshr	v0.8h, v0.8h, #3
 # CHECK-NEXT:  1      3     0.50                        ursqrte	v0.2s, v0.2s
-# CHECK-NEXT:  1      4     0.50                        ursqrte	v0.4s, v0.4s
-# CHECK-NEXT:  1      2     0.25                        ursra	d18, d10, #13
+# CHECK-NEXT:  1      4     1.00                        ursqrte	v0.4s, v0.4s
+# CHECK-NEXT:  1      4     0.50                        ursra	d18, d10, #13
 # CHECK-NEXT:  1      4     0.50                        ursra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      4     0.50                        ursra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        ursra	v0.2s, v0.2s, #3
@@ -2366,7 +2366,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.50                        ushl	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.50                        ushll	v0.4s, v0.4h, #3
 # CHECK-NEXT:  1      2     0.50                        ushll2	v0.8h, v0.16b, #3
-# CHECK-NEXT:  1      2     0.25                        ushr	d10, d17, #18
+# CHECK-NEXT:  1      2     0.50                        ushr	d10, d17, #18
 # CHECK-NEXT:  1      2     0.50                        ushr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      2     0.50                        ushr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      2     0.50                        ushr	v0.2s, v0.2s, #3
@@ -2375,11 +2375,11 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.50                        ushr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  1      2     0.50                        ushr	v0.8h, v0.8h, #3
 # CHECK-NEXT:  1      3     0.25                        usmmla	v0.4s, v0.16b, v0.16b
-# CHECK-NEXT:  1      2     0.25                        smov	w0, v0.b[1]
-# CHECK-NEXT:  1      2     0.25                        smov	w0, v0.h[1]
-# CHECK-NEXT:  1      2     0.25                        smov	x0, v0.b[1]
-# CHECK-NEXT:  1      2     0.25                        smov	x0, v0.h[1]
-# CHECK-NEXT:  1      2     0.25                        smov	x0, v0.s[1]
+# CHECK-NEXT:  1      2     1.00                        smov	w0, v0.b[1]
+# CHECK-NEXT:  1      2     1.00                        smov	w0, v0.h[1]
+# CHECK-NEXT:  1      2     1.00                        smov	x0, v0.b[1]
+# CHECK-NEXT:  1      2     1.00                        smov	x0, v0.h[1]
+# CHECK-NEXT:  1      2     1.00                        smov	x0, v0.s[1]
 # CHECK-NEXT:  1      2     0.25                        usqadd	b19, b14
 # CHECK-NEXT:  1      2     0.25                        usqadd	d18, d22
 # CHECK-NEXT:  1      2     0.25                        usqadd	h20, h15
@@ -2391,7 +2391,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  1      2     0.25                        usqadd	v0.4s, v0.4s
 # CHECK-NEXT:  1      2     0.25                        usqadd	v0.8b, v0.8b
 # CHECK-NEXT:  1      2     0.25                        usqadd	v0.8h, v0.8h
-# CHECK-NEXT:  1      2     0.25                        usra	d20, d13, #61
+# CHECK-NEXT:  1      4     0.50                        usra	d20, d13, #61
 # CHECK-NEXT:  1      4     0.50                        usra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  1      4     0.50                        usra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  1      4     0.50                        usra	v0.2s, v0.2s, #3
@@ -2468,7 +2468,7 @@ zip2 v0.8h, v0.8h, v0.8h
 
 # CHECK:      Resource pressure per iteration:
 # CHECK-NEXT: [0.0]  [0.1]  [1.0]  [1.1]  [2.0]  [2.1]  [2.2]  [3]    [4.0]  [4.1]  [5]    [6]    [7.0]  [7.1]  [8]    [9]    [10]   [11]
-# CHECK-NEXT:  -      -      -      -      -      -      -     26.67  49.17  49.17  18.75  7.75   7.75   7.75   431.00 356.50 385.50 311.00
+# CHECK-NEXT:  -      -      -      -      -      -      -     30.67  58.67  58.67  18.75  7.75   7.75   7.75   450.75 368.25 402.75 320.25
 
 # CHECK:      Resource pressure by instruction:
 # CHECK-NEXT: [0.0]  [0.1]  [1.0]  [1.1]  [2.0]  [2.1]  [2.2]  [3]    [4.0]  [4.1]  [5]    [6]    [7.0]  [7.1]  [8]    [9]    [10]   [11]   Instructions:
@@ -2492,8 +2492,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   addp	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   addv	s0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   addv	h0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   addv	h0, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   addv	b0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   addv	h0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   addv	b0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   addv	b0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   aesd	v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   aese	v0.16b, v0.16b
@@ -2501,8 +2501,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   aesmc	v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   and	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     bfcvt	h0, s0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     bfcvtn	v0.4h, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     bfcvtn2	v0.8h, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     bfcvtn	v0.4h, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     bfcvtn2	v0.8h, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   bfdot	v0.2s, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   bfdot	v0.4s, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   bfmlalb	v0.4s, v0.8h, v0.8h
@@ -2618,86 +2618,86 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fcmlt	s10, s11, #0.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fcmlt	v0.4s, v0.4s, #0.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtas	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtas	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtas	h12, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtas	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtas	h12, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtas	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtas	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtas	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtas	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtas	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtas	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtau	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtau	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtau	h12, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtau	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtau	h12, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtau	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtau	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtau	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtau	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtau	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtau	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtl	v0.2d, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtl	v0.4s, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtl2	v0.2d, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtl2	v0.4s, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtms	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtms	s22, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtms	h22, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtms	s22, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtms	h22, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtms	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtms	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtms	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtms	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtms	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtms	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtmu	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtmu	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtmu	h12, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtmu	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtmu	h12, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtmu	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtmu	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtmu	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtmu	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtmu	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtmu	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtn	v0.2s, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtn	v0.4h, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtn2	v0.4s, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtn2	v0.8h, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtns	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtns	s22, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtns	h22, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtns	s22, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtns	h22, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtns	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtns	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtns	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtns	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtns	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtns	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtnu	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtnu	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtnu	h12, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtnu	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtnu	h12, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtnu	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtnu	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtnu	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtnu	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtnu	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtnu	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtps	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtps	s22, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtps	h22, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtps	s22, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtps	h22, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtps	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtps	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtps	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtps	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtps	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtps	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtpu	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtpu	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtpu	h12, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtpu	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtpu	h12, h13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtpu	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtpu	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtpu	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtpu	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtpu	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtpu	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtxn	s22, d13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtxn	v0.2s, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtxn2	v0.4s, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	d21, d12, #1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	s21, s12, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	h21, h14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	h21, h12, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	s21, s12, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	h21, h14
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	h21, h12, #1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzs	v0.2s, v0.2s
@@ -2705,13 +2705,13 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	v0.4s, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzs	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtzs	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	d21, d12, #1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	d21, d14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	s12, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	s21, s12, #1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	h12, h13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	h21, h12, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	s12, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	s21, s12, #1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	h12, h13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	h21, h12, #1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     fcvtzu	v0.2s, v0.2s
@@ -2719,12 +2719,12 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	v0.4s, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     fcvtzu	v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fdiv	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fdiv	v0.2s, v0.2s, v0.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     fcvtzu	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -     7.00    -     fdiv	v0.2d, v0.2d, v0.2d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50    -     2.50    -     fdiv	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fdiv	v0.4h, v0.4h, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fdiv	v0.4s, v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50    -     2.50    -     fdiv	v0.8h, v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.50    -     4.50    -     fdiv	v0.4s, v0.4s, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     6.50    -     6.50    -     fdiv	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmax	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmax	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fmax	v0.4s, v0.4s, v0.4s
@@ -2794,11 +2794,11 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fneg	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frecpe	d13, d13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frecpe	s19, s14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frecpe	v0.2d, v0.2d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frecpe	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frecpe	v0.2s, v0.2s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frecpe	v0.4h, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frecpe	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frecpe	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frecpe	v0.4h, v0.4h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frecpe	v0.4s, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frecpe	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   frecps	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   frecps	d22, d30, d21
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   frecps	s21, s16, s13
@@ -2808,52 +2808,52 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frinta	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frinta	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frinta	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frinta	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frinta	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frinti	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frinti	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frinti	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frinti	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frinti	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frinti	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintm	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintm	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintm	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintm	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintm	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frintm	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintn	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintn	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintn	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintn	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintn	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frintn	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintp	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintp	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintp	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintp	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintp	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frintp	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintx	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintx	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintx	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintx	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintx	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frintx	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintz	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frintz	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintz	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintz	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frintz	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frintz	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frsqrte	d21, d12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frsqrte	s22, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frsqrte	v0.2d, v0.2d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frsqrte	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frsqrte	v0.2s, v0.2s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frsqrte	v0.4h, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     frsqrte	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frsqrte	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frsqrte	v0.4h, v0.4h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     frsqrte	v0.4s, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     frsqrte	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   frsqrts	d8, d22, d18
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   frsqrts	s21, s5, s12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   frsqrts	v0.2d, v0.2d, v0.2d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fsqrt	v0.2d, v0.2d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fsqrt	v0.2s, v0.2s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.50    -     7.50    -     fsqrt	v0.2d, v0.2d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50    -     2.50    -     fsqrt	v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fsqrt	v0.4h, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.50    -     3.50    -     fsqrt	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     5.50    -     5.50    -     fsqrt	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.50    -     4.50    -     fsqrt	v0.4s, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     6.50    -     6.50    -     fsqrt	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   fsub	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -      -      -      -      -     ld1	{ v0.16b }, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25    -      -      -      -     ld1	{ v0.8h, v1.8h }, [sp], #32
@@ -2872,29 +2872,29 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1r	{ v0.4s }, [x15]
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25   0.25   0.25   0.25   0.25   ld1r	{ v0.2d }, [x15], x16
 # CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld2	{ v0.16b, v1.16b }, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2	{ v0.8b, v1.8b }, [x0], #16
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.50   0.50   0.50   0.50   ld2	{ v0.h, v1.h }[7], [x15]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2	{ v0.h, v1.h }[7], [x15], x8
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.50   0.50   0.50   0.50   ld2r	{ v0.8b, v1.8b }, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2r	{ v0.4h, v1.4h }, [x0], #4
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.50   0.50   0.50   0.50   ld2r	{ v0.2s, v1.2s }, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2r	{ v0.1d, v1.1d }, [sp], x8
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.75   0.75   0.75   0.75   ld3	{ v0.4h, v1.4h, v2.4h }, [x15]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33   0.25   0.25   0.25   0.25   0.25   0.25   0.25   0.25   ld2	{ v0.8b, v1.8b }, [x0], #16
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld2	{ v0.h, v1.h }[7], [x15]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2	{ v0.h, v1.h }[7], [x15], x8
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld2r	{ v0.8b, v1.8b }, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2r	{ v0.4h, v1.4h }, [x0], #4
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld2r	{ v0.2s, v1.2s }, [sp]
+# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25   0.50   0.50   0.50   0.50   ld2r	{ v0.1d, v1.1d }, [sp], x8
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld3	{ v0.4h, v1.4h, v2.4h }, [x15]
 # CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3	{ v0.8h, v1.8h, v2.8h }, [x15], #48
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.75   0.75   0.75   0.75   ld3	{ v0.s, v1.s, v2.s }[3], [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3	{ v0.s, v1.s, v2.s }[3], [sp], x3
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.75   0.75   0.75   0.75   ld3r	{ v0.8b, v1.8b, v2.8b }, [x15]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3r	{ v0.4h, v1.4h, v2.4h }, [x15], #6
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.75   0.75   0.75   0.75   ld3r	{ v0.2s, v1.2s, v2.2s }, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3r	{ v0.1d, v1.1d, v2.1d }, [x0], x0
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     1.00   1.00   1.00   1.00   ld4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.33   1.33   1.33   0.25   0.25   0.25   0.25   1.00   1.00   1.00   1.00   ld4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     1.00   1.00   1.00   1.00   ld4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00   1.00   1.00   ld4	{ v0.h, v1.h, v2.h, v3.h }[7], [x0], x0
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     1.00   1.00   1.00   1.00   ld4r	{ v0.1d, v1.1d, v2.1d, v3.1d }, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     1.00   1.00   1.00   1.00   ld4r	{ v0.2d, v1.2d, v2.2d, v3.2d }, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00   1.00   1.00   ld4r	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp], #16
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00   1.00   1.00   ld4r	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], x8
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld3	{ v0.s, v1.s, v2.s }[3], [sp]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3	{ v0.s, v1.s, v2.s }[3], [sp], x3
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld3r	{ v0.8b, v1.8b, v2.8b }, [x15]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3r	{ v0.4h, v1.4h, v2.4h }, [x15], #6
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld3r	{ v0.2s, v1.2s, v2.2s }, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld3r	{ v0.1d, v1.1d, v2.1d }, [x0], x0
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00   0.25   0.25   0.25   0.25   1.50   1.50   1.50   1.50   ld4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld4	{ v0.h, v1.h, v2.h, v3.h }[7], [x0], x0
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld4r	{ v0.1d, v1.1d, v2.1d, v3.1d }, [sp]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   ld4r	{ v0.2d, v1.2d, v2.2d, v3.2d }, [sp]
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld4r	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp], #16
+# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00   0.25   0.25   0.25   0.25   0.75   0.75   0.75   0.75   ld4r	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], x8
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     mla	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     mls	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   mov	b0, v0.b[15]
@@ -3003,8 +3003,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   saddlp	v0.8h, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   saddlv	d0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   saddlv	s0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   saddlv	s0, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   saddlv	h0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   saddlv	s0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   saddlv	h0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   saddlv	h0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   saddw	v0.2d, v0.2d, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   saddw	v0.4s, v0.4s, v0.4h
@@ -3014,8 +3014,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   saddw2	v0.8h, v0.8h, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	d21, d12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	d21, d12, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     scvtf	s22, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     scvtf	s22, s13, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	s22, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	s22, s13, #32
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     scvtf	v0.2s, v0.2s
@@ -3023,13 +3023,13 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     scvtf	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     scvtf	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     scvtf	v0.4s, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     scvtf	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     scvtf	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sdot	v0.2s, v0.8b, v0.4b[2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sdot	v0.2s, v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sdot	v0.4s, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sdot	v0.4s, v0.16b, v0.4b[2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   shadd	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   shl	d7, d10, #12
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   shl	d7, d10, #12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   shl	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   shl	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   shl	v0.4h, v0.4h, #3
@@ -3054,7 +3054,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   shrn2	v0.8h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   shsub	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   shsub	v0.4h, v0.4h, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sli	d10, d14, #12
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sli	d10, d14, #12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sli	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sli	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sli	v0.2s, v0.2s, #3
@@ -3068,10 +3068,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smaxp	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smaxp	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smaxp	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   smaxv	b0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   smaxv	b0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   smaxv	b0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   smaxv	h0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   smaxv	h0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   smaxv	h0, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   smaxv	s0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smin	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smin	v0.4s, v0.4s, v0.4s
@@ -3079,10 +3079,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sminp	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sminp	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sminp	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   sminv	b0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sminv	b0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   sminv	b0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sminv	h0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   sminv	h0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sminv	h0, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sminv	s0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     smlal	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     smlal	v0.4s, v0.4h, v0.4h
@@ -3140,9 +3140,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmulh	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmulh	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull	d1, s1, v0.s[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqdmull	d15, s22, s12
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull	d15, s22, s12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull	s1, h1, v0.h[3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqdmull	s12, h22, h12
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull	s12, h22, h12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull	v0.4s, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     sqdmull2	v0.2d, v0.4s, v0.4s
@@ -3193,18 +3193,18 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshl	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshl	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshl	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqrshrn	b10, h13, #2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqrshrn	h15, s10, #6
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqrshrn	s15, d12, #9
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn	b10, h13, #2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn	h15, s10, #6
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn	s15, d12, #9
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn	v0.8b, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn2	v0.16b, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn2	v0.4s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrn2	v0.8h, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqrshrun	b17, h10, #6
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqrshrun	h10, s13, #15
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqrshrun	s22, d16, #31
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrun	b17, h10, #6
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrun	h10, s13, #15
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrun	s22, d16, #31
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrun	v0.2s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrun	v0.4h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqrshrun	v0.8b, v0.8h, #3
@@ -3238,24 +3238,24 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshlu	v0.4s, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshlu	v0.8b, v0.8b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshlu	v0.8h, v0.8h, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrn	b10, h15, #5
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrn	h17, s10, #4
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrn	s18, d10, #31
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn	b10, h15, #5
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn	h17, s10, #4
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn	s18, d10, #31
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn	v0.8b, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn2	v0.16b, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn2	v0.4s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrn2	v0.8h, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun	b15, h10, #7
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun	h20, s14, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun	s10, d15, #15
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun	v0.2s, v0.2d, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun	v0.4h, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun	v0.8b, v0.8h, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun2	v0.16b, v0.8h, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun2	v0.4s, v0.2d, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqshrun2	v0.8h, v0.4s, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun	b15, h10, #7
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun	h20, s14, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun	s10, d15, #15
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun	v0.2s, v0.2d, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun	v0.4h, v0.4s, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun	v0.8b, v0.8h, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun2	v0.16b, v0.8h, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun2	v0.4s, v0.2d, #3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sqshrun2	v0.8h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqsub	s20, s10, s7
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqsub	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sqsub	v0.4s, v0.4s, v0.4s
@@ -3281,7 +3281,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   srhadd	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   srhadd	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   srhadd	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sri	d10, d12, #14
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sri	d10, d12, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sri	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sri	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sri	v0.2s, v0.2s, #3
@@ -3293,7 +3293,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshl	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshl	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshl	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   srshr	d19, d18, #7
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	d19, d18, #7
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	v0.2s, v0.2s, #3
@@ -3301,7 +3301,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	v0.4s, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srshr	v0.8h, v0.8h, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   srsra	d15, d11, #19
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srsra	d15, d11, #19
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srsra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srsra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   srsra	v0.2s, v0.2s, #3
@@ -3316,7 +3316,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshl	v0.8b, v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshll	v0.2d, v0.2s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshll2	v0.4s, v0.8h, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sshr	d15, d16, #12
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	d15, d16, #12
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	v0.2s, v0.2s, #3
@@ -3324,7 +3324,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	v0.4s, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   sshr	v0.8h, v0.8h, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   ssra	d18, d12, #21
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ssra	d18, d12, #21
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ssra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ssra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ssra	v0.2s, v0.2s, #3
@@ -3362,9 +3362,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50   0.25   0.25   0.25   0.25   1.50   1.50    -      -     st3	{ v0.8h, v1.8h, v2.8h }, [x15], x2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     st3	{ v0.h, v1.h, v2.h }[7], [x15]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00    -      -     st3	{ v0.h, v1.h, v2.h }[7], [x15], #6
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     st4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00   0.25   0.25   0.25   0.25   3.00   3.00    -      -     st4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
-# CHECK-NEXT:  -      -      -      -      -      -      -     1.00   1.00   1.00    -      -      -      -     0.75   0.75   0.75   0.75   st4	{ v0.b, v1.b, v2.b, v3.b }[15], [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     st4	{ v0.2s, v1.2s, v2.2s, v3.2s }, [sp]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     6.00   6.00   0.25   0.25   0.25   0.25   6.00   6.00    -      -     st4	{ v0.4s, v1.4s, v2.4s, v3.4s }, [sp], #64
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     st4	{ v0.b, v1.b, v2.b, v3.b }[15], [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00   0.25   0.25   0.25   0.25   1.00   1.00    -      -     st4	{ v0.d, v1.d, v2.d, v3.d }[1], [x0], x5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sub	d15, d5, d16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sub	v0.2d, v0.2d, v0.2d
@@ -3381,19 +3381,19 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   suqadd	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   suqadd	v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   suqadd	v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbl	v0.16b, { v0.16b }, v0.16b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbl	v0.16b, { v0.16b, v1.16b }, v0.16b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     tbl	v0.16b, { v0.16b }, v0.16b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     tbl	v0.16b, { v0.16b, v1.16b }, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbl	v0.16b, { v0.16b, v1.16b, v2.16b }, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.50   1.50    -      -     tbl	v0.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.16b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbl	v0.8b, { v0.16b }, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbl	v0.8b, { v0.16b, v1.16b }, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     tbl	v0.8b, { v0.16b }, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     tbl	v0.8b, { v0.16b, v1.16b }, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbl	v0.8b, { v0.16b, v1.16b, v2.16b }, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.50   1.50    -      -     tbl	v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbx	v0.16b, { v0.16b }, v0.16b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     tbx	v0.16b, { v0.16b }, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbx	v0.16b, { v0.16b, v1.16b }, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.50   1.50    -      -     tbx	v0.16b, { v0.16b, v1.16b, v2.16b }, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     tbx	v0.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.16b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbx	v0.8b, { v0.16b }, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     tbx	v0.8b, { v0.16b }, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00    -      -     tbx	v0.8b, { v0.16b, v1.16b }, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.50   1.50    -      -     tbx	v0.8b, { v0.16b, v1.16b, v2.16b }, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     tbx	v0.8b, { v0.16b, v1.16b, v2.16b, v3.16b }, v0.8b
@@ -3445,8 +3445,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uaddlp	v0.8h, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uaddlv	d0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uaddlv	s0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   uaddlv	s0, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   uaddlv	h0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uaddlv	s0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uaddlv	h0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   uaddlv	h0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uaddw	v0.2d, v0.2d, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uaddw	v0.4s, v0.4s, v0.4h
@@ -3456,8 +3456,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uaddw2	v0.8h, v0.8h, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	d21, d14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	d21, d14, #64
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ucvtf	s22, s13
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ucvtf	s22, s13, #32
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	s22, s13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	s22, s13, #32
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ucvtf	v0.2s, v0.2s
@@ -3465,7 +3465,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ucvtf	v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ucvtf	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ucvtf	v0.4s, v0.4s, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ucvtf	v0.8h, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -     2.00    -     ucvtf	v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   udot	v0.2s, v0.8b, v0.4b[2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   udot	v0.2s, v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   udot	v0.4s, v0.16b, v0.16b
@@ -3479,10 +3479,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umaxp	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umaxp	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umaxp	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   umaxv	b0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   umaxv	b0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   umaxv	b0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   umaxv	h0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   umaxv	h0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   umaxv	h0, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   umaxv	s0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umin	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umin	v0.4h, v0.4h, v0.4h
@@ -3490,10 +3490,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uminp	v0.2s, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uminp	v0.4h, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uminp	v0.8b, v0.8b, v0.8b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   uminv	b0, v0.8b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uminv	b0, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00   uminv	b0, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uminv	h0, v0.4h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.75   0.25   0.75   uminv	h0, v0.8h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uminv	h0, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uminv	s0, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umlal	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umlal	v0.4s, v0.4h, v0.4h
@@ -3508,10 +3508,10 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umlsl2	v0.4s, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umlsl2	v0.8h, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   ummla	v0.4s, v0.16b, v0.16b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umov	w0, v0.b[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   umov	w0, v0.h[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   mov	w0, v0.s[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   mov	x0, v0.d[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   umov	w0, v0.b[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   umov	w0, v0.h[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   mov	w0, v0.s[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   mov	x0, v0.d[1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umull	v0.2d, v0.2s, v0.2s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umull	v0.4s, v0.4h, v0.4h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     umull	v0.8h, v0.8b, v0.8b
@@ -3526,9 +3526,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshl	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshl	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshl	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uqrshrn	b10, h12, #5
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uqrshrn	h12, s10, #14
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uqrshrn	s10, d10, #25
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshrn	b10, h12, #5
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshrn	h12, s10, #14
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshrn	s10, d10, #25
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqrshrn	v0.8b, v0.8h, #3
@@ -3552,9 +3552,9 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshl	v0.8b, v0.8b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshl	v0.8h, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshl	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uqshrn	b12, h10, #7
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uqshrn	h10, s14, #5
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   uqshrn	s10, d12, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshrn	b12, h10, #7
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshrn	h10, s14, #5
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshrn	s10, d12, #13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshrn	v0.2s, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshrn	v0.4h, v0.4s, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqshrn	v0.8b, v0.8h, #3
@@ -3573,7 +3573,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqxtn2	v0.4s, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   uqxtn2	v0.8h, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     urecpe	v0.2s, v0.2s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     urecpe	v0.4s, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     urecpe	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   urhadd	v0.16b, v0.16b, v0.16b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   urhadd	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   urhadd	v0.8h, v0.8h, v0.8h
@@ -3582,7 +3582,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshl	v0.2d, v0.2d, v0.2d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshl	v0.4s, v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshl	v0.8h, v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   urshr	d20, d23, #31
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshr	d20, d23, #31
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshr	v0.2s, v0.2s, #3
@@ -3591,8 +3591,8 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   urshr	v0.8h, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ursqrte	v0.2s, v0.2s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50    -     ursqrte	v0.4s, v0.4s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   ursra	d18, d10, #13
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -     1.00    -     ursqrte	v0.4s, v0.4s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ursra	d18, d10, #13
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ursra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ursra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ursra	v0.2s, v0.2s, #3
@@ -3610,7 +3610,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushl	v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushll	v0.4s, v0.4h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushll2	v0.8h, v0.16b, #3
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   ushr	d10, d17, #18
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushr	d10, d17, #18
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushr	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushr	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushr	v0.2s, v0.2s, #3
@@ -3619,11 +3619,11 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushr	v0.8b, v0.8b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   ushr	v0.8h, v0.8h, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usmmla	v0.4s, v0.16b, v0.16b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smov	w0, v0.b[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smov	w0, v0.h[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smov	x0, v0.b[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smov	x0, v0.h[1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   smov	x0, v0.s[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   smov	w0, v0.b[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   smov	w0, v0.h[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   smov	x0, v0.b[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   smov	x0, v0.h[1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00   1.00   1.00   1.00   smov	x0, v0.s[1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usqadd	b19, b14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usqadd	d18, d22
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usqadd	h20, h15
@@ -3635,7 +3635,7 @@ zip2 v0.8h, v0.8h, v0.8h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usqadd	v0.4s, v0.4s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usqadd	v0.8b, v0.8b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usqadd	v0.8h, v0.8h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usra	d20, d13, #61
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   usra	d20, d13, #61
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   usra	v0.16b, v0.16b, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   usra	v0.2d, v0.2d, #3
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50    -     0.50   usra	v0.2s, v0.2s, #3
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-scheduling-info.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-scheduling-info.s
new file mode 100644
index 0000000000000..9097ec650f2c0
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-scheduling-info.s
@@ -0,0 +1,7588 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=aarch64 -mcpu=neoverse-v1 -scheduling-info < %s | FileCheck %s
+
+  .text
+  .file	        "V1-scheduling-info.s"
+  .globl	test
+  .p2align	4
+  .type	test,@function
+test:
+  .cfi_startproc
+  abs D15, D11  /* ABS <V><d>, <V><n>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV */
+  abs V25.2S, V25.2S  // ABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  abs Z26.B, P6/M, Z27.B  // ABS <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adc W13, W6, W4  // ADC <Wd>, <Wn>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  adc X8, X12, X10  // ADC <Xd>, <Xn>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  adcs W29, W7, W30  // ADCS <Wd>, <Wn>, <Wm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adcs X11, X3, X5  // ADCS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  add WSP, WSP, W10  // ADD <Wd|WSP>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+  add WSP, WSP, W2, UXTB   // ADD <Wd|WSP>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+  add WSP, WSP, W13, UXTH #4  // ADD <Wd|WSP>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+  add WSP, WSP, W13, LSL #4  // ADD <Wd|WSP>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+  add X22, X2, X27  // ADD <Xd|SP>, <Xn|SP>, X<m>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  add X25, X9, W25, UXTB  // ADD <Xd|SP>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  add X4, X28, W3, UXTB #3  // ADD <Xd|SP>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, extend and shift  \\ 1 2  2  2.0 V1UnitM
+  add X0, X28, X26, LSL #3  // ADD <Xd|SP>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+  add WSP, WSP, #3765  // ADD <Wd|WSP>, <Wn|WSP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  add WSP, WSP, #3547, LSL #12  // ADD <Wd|WSP>, <Wn|WSP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  add X7, X30, #803  // ADD <Xd|SP>, <Xn|SP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  add X7, X2, #319, LSL #12  // ADD <Xd|SP>, <Xn|SP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  add Z13.D, Z13.D, #245  // ADD <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  add Z16.D, Z16.D, #233, LSL #8  // ADD <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  add W3, W2, W21, LSL #3  // ADD <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+  add W6, W21, W17, LSL #15  // ADD <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+  add W28, W30, W19, ASR #30  // ADD <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+  add X8, X3, X28, LSL #3  // ADD <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+  add X12, X13, X0, LSL #44  // ADD <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+  add X5, X20, X28, LSR #16  // ADD <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+  add D0, D23, D21  // ADD <V><d>, <V><n>, <V><m>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  add V19.4S, V24.4S, V15.4S  // ADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  add Z29.D, P5/M, Z29.D, Z29.D  // ADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  add Z10.H, Z22.H, Z13.H  // ADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  addhn V26.4H, V5.4S, V9.4S  // ADDHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  addhn2 V1.16B, V19.8H, V6.8H  // ADDHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  addp D1, V14.2D  // ADDP <V><d>, <Vn>.<T>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+  addp V7.2S, V1.2S, V2.2S  // ADDP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+  addpl X27, X6, #-6  // ADDPL <Xd|SP>, <Xn|SP>, #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  adds W17, WSP, W25  // ADDS <Wd>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds W6, WSP, W15, UXTH   // ADDS <Wd>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds W22, WSP, W30, UXTB #2  // ADDS <Wd>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds W12, WSP, W29, LSL #4  // ADDS <Wd>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds X14, X0, X10  // ADDS <Xd>, <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds X13, X23, W8, UXTB  // ADDS <Xd>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds X4, X26, W28, UXTB #1  // ADDS <Xd>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  adds X10, X3, X29, LSL #2  // ADDS <Xd>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  adds W23, WSP, #502  // ADDS <Wd>, <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds W2, WSP, #2980, LSL #12  // ADDS <Wd>, <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  adds X12, X4, #1345  // ADDS <Xd>, <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds X25, X18, #3037, LSL #12  // ADDS <Xd>, <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  adds W12, W13, W26  // ADDS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds W0, W23, W20, LSL #0  // ADDS <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds W13, W16, W12, LSL #28  // ADDS <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  adds W20, W19, W16, ASR #0  // ADDS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  adds X23, X12, X4  // ADDS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  adds X0, X13, X4, LSL #2  // ADDS <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  adds X4, X7, X6, LSL #31  // ADDS <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  adds X9, X8, X9, ASR #41  // ADDS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  addv B0, V28.8B  // ADDV B<d>, <Vn>.8B  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  addv B1, V26.16B  // ADDV B<d>, <Vn>.16B  \\ ASIMD arith, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  addv H18, V13.4H  // ADDV H<d>, <Vn>.4H  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  addv H29, V17.8H  // ADDV H<d>, <Vn>.8H  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  addv S22, V18.4S  // ADDV S<d>, <Vn>.4S  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  addvl X1, X27, #-8  // ADDVL <Xd|SP>, <Xn|SP>, #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  adr X3, test  // ADR <Xd>, <label>  \\ Address generation  \\ 1 1  1  4.0 V1UnitI
+  adr Z26.D, [Z1.D, Z8.D]  // ADR <Zd>.<T>, [<Zn>.<T>, <Zm>.<T>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adr Z22.S, [Z28.S, Z8.S, LSL #2]  // ADR <Zd>.<T>, [<Zn>.<T>, <Zm>.<T>, <mod> #<amount>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adr Z11.D, [Z2.D, Z29.D, SXTW ]  // ADR <Zd>.D, [<Zn>.D, <Zm>.D, SXTW ]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adr Z3.D, [Z9.D, Z9.D, SXTW #2]  // ADR <Zd>.D, [<Zn>.D, <Zm>.D, SXTW #<amount>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adr Z6.D, [Z7.D, Z13.D, UXTW ]  // ADR <Zd>.D, [<Zn>.D, <Zm>.D, UXTW ]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adr Z4.D, [Z24.D, Z22.D, UXTW #1]  // ADR <Zd>.D, [<Zn>.D, <Zm>.D, UXTW #<amount>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  adrp X0, test  // ADRP <Xd>, <label>  \\ Address generation  \\ 1 1  1  4.0 V1UnitI
+  and WSP, W16, #0xe00  // AND <Wd|WSP>, <Wn>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  and X2, X22, #0x1e00  // AND <Xd|SP>, <Xn>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  and Z1.B, Z1.B, #0x70  // AND <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  and Z7.H, Z7.H, #0x60  // AND <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  and Z7.S, Z7.S, #0x2  // AND <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  and Z7.D, Z7.D, #0x4  // AND <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  and P5.B, P1/Z, P6.B, P4.B  // AND <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  and W11, W14, W24  // AND <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  and W2, W21, W22, LSR #25  // AND <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  and X1, X20, X29  // AND <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  and X8, X11, X22, ASR #56  // AND <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  and V29.8B, V26.8B, V26.8B  // AND <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  and Z17.D, P6/M, Z17.D, Z12.D  // AND <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  and Z9.D, Z5.D, Z17.D  // AND <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  ands W14, W8, #0x70  // ANDS <Wd>, <Wn>, #<imms>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  ands X4, X10, #0x60  // ANDS <Xd>, <Xn>, #<immd>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  ands W29, W28, W12  // ANDS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  ands W7, W13, W23, ASR #3  // ANDS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift by immed, flagset, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  ands X21, X9, X6  // ANDS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  ands X10, X27, X7, ASR #20  // ANDS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, flagset  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  ands P5.B, P1/Z, P2.B, P7.B  // ANDS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  andv H7, P6, Z31.H  // ANDV <V><d>, <Pg>, <Zn>.<T>  \\ Reduction, logical   \\ 1 12  12  0.5 V1UnitV01[4]
+  asr W30, W14, #5  // ASR <Wd>, <Wn>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  asr X12, X21, #28  // ASR <Xd>, <Xn>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  asr Z7.B, P5/M, Z7.B, #3  // ASR <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z6.H, P6/M, Z6.H, #5  // ASR <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z28.S, P0/M, Z28.S, #11  // ASR <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z26.D, P5/M, Z26.D, #24  // ASR <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z10.B, Z14.B, #3  // ASR <Zd>.B, <Zn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z23.H, Z18.H, #6  // ASR <Zd>.H, <Zn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z29.S, Z11.S, #6  // ASR <Zd>.S, <Zn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z20.D, Z26.D, #29  // ASR <Zd>.D, <Zn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr W3, W0, W20  // ASR <Wd>, <Wn>, <Wm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+  asr X7, X5, X21  // ASR <Xd>, <Xn>, <Xm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+  asr Z3.S, P0/M, Z3.S, Z10.S  // ASR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z9.S, P2/M, Z9.S, Z8.D  // ASR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asr Z26.S, Z21.S, Z21.D  // ASR <Zd>.<T>, <Zn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asrd Z6.B, P4/M, Z6.B, #2  // ASRD <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+  asrd Z19.H, P3/M, Z19.H, #6  // ASRD <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+  asrd Z16.S, P3/M, Z16.S, #2  // ASRD <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+  asrd Z9.D, P6/M, Z9.D, #12  // ASRD <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+  asrr Z0.B, P0/M, Z0.B, Z19.B  // ASRR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  asrv W24, W28, W13  // ASRV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  asrv X3, X21, X24  // ASRV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  at s12e1r, X28  // AT <at_op>, <Xt>  \\ No description \\ No scheduling info
+  b test  // B <label>  \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.eq test // B.eq <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.none test // B.none <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.ne test // B.ne <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.any test // B.any <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.cs test // B.cs <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.hs test // B.hs <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.nlast test // B.nlast <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.cc test // B.cc <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.lo test // B.lo <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.last test // B.last <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.mi test // B.mi <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.first test // B.first <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.pl test // B.pl <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.nfrst test // B.nfrst <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.vs test // B.vs <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.vc test // B.vc <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.hi test // B.hi <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.pmore test // B.pmore <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.ls test // B.ls <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.plast test // B.plast <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.ge test // B.ge <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.tcont test // B.tcont <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.lt test // B.lt <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.tstop test // B.tstop <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.gt test // B.gt <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.le test // B.le <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.al test // B.al <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  b.nv test // B.nv <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+  bfcvt H6, S20  // BFCVT <Hd>, <Sn>  \\ Scalar convert, F32 to BF16  \\ 1 3  3  2.0 V1UnitV02
+  bfcvt Z16.H, P6/M, Z1.S  // BFCVT <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV0
+  bfcvtn V12.4H, V15.4S  // BFCVTN <Vd>.<Ta>, <Vn>.4S  \\ ASIMD convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV02[2]
+  bfcvtn2 V15.8H, V13.4S  // BFCVTN2 <Vd>.<Ta>, <Vn>.4S  \\ ASIMD convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV02[2]
+  bfcvtnt Z11.H, P7/M, Z24.S  // BFCVTNT <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV0
+  bfdot V0.2S, V24.4H, V14.2H[2]  // BFDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.2H[<index>]  \\ ASIMD dot product  \\ 1 4 2 4.0 V1UnitV
+  bfdot Z24.S, Z26.H, Z2.H[0]  // BFDOT <Zda>.S, <Zn>.H, <Zm>.H[<imm>]  \\ Dot product  \\ 1 4 2 2.0 V1UnitV01
+  bfdot V31.4S, V21.8H, V14.8H  // BFDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product  \\ 1 4 2 4.0 V1UnitV
+  bfdot Z15.S, Z3.H, Z7.H  // BFDOT <Zda>.S, <Zn>.H, <Zm>.H  \\ Dot product  \\ 1 4 2 2.0 V1UnitV01
+  bfi W10, W26, #31, #1  // BFI <Wd>, <Wn>, #<lsbs>, #<widths>  \\ Bit field insert/clear, unconditional  \\ 1 2  2  2.0 V1UnitM
+  bfi X25, X7, #8, #1  // BFI <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ Bit field insert/clear, unconditional  \\ 1 2  2  2.0 V1UnitM
+  bfm W30, W26, #14, #12  // BFM <Wd>, <Wn>, #<immrs>, #<immss>  \\ Bitfield move, insert  \\ 1 2  2  2.0 V1UnitM
+  bfm X15, X20, #0, #35  // BFM <Xd>, <Xn>, #<immrd>, #<immsd>  \\ Bitfield move, insert  \\ 1 2  2  2.0 V1UnitM
+  bfmlalb Z13.S, Z30.H, Z0.H[0]  // BFMLALB <Zda>.S, <Zn>.H, <Zm>.H[<imm>]  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+  bfmlalb Z3.S, Z14.H, Z13.H  // BFMLALB <Zda>.S, <Zn>.H, <Zm>.H  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+  bfmlalb V22.4S, V11.8H, V11.H[5]  // BFMLALB <Vd>.4S, <Vn>.8H, <Vm>.H[<index>]  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+  bfmlalt V17.4S, V4.8H, V11.H[7]  // BFMLALT <Vd>.4S, <Vn>.8H, <Vm>.H[<index>]  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+  bfmlalb V13.4S, V5.8H, V17.8H  // BFMLALB <Vd>.4S, <Vn>.8H, <Vm>.8H  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+  bfmlalt V10.4S, V16.8H, V1.8H  // BFMLALT <Vd>.4S, <Vn>.8H, <Vm>.8H  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+  bfmlalt Z23.S, Z3.H, Z2.H[2]  // BFMLALT <Zda>.S, <Zn>.H, <Zm>.H[<imm>]  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+  bfmlalt Z25.S, Z21.H, Z22.H  // BFMLALT <Zda>.S, <Zn>.H, <Zm>.H  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+  bfmmla V15.4S, V28.8H, V23.8H  // BFMMLA <Vd>.4S, <Vn>.8H, <Vm>.8H  \\ ASIMD matrix multiply accumulate  \\ 1 5 3 4.0 V1UnitV
+  bfmmla Z26.S, Z2.H, Z12.H  // BFMMLA <Zda>.S, <Zn>.H, <Zm>.H  \\ Matrix multiply accumulate  \\ 1 5 3 2.0 V1UnitV01
+  bfxil W27, W23, #14, #14  // BFXIL <Wd>, <Wn>, #<lsbs>, #<widths>  \\ No description \\ No scheduling info
+  bfxil X0, X5, #11, #22  // BFXIL <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ No description \\ No scheduling info
+  bic Z28.B, Z28.B, #0x70  // BIC <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  bic Z18.H, Z18.H, #0x60  // BIC <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  bic Z12.S, Z12.S, #0x2  // BIC <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  bic Z6.D, Z6.D, #0x4  // BIC <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  bic P4.B, P4/Z, P6.B, P0.B  // BIC <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  bic W0, W26, W22  // BIC <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  bic W23, W10, W7, LSL #11  // BIC <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  bic X21, X20, X14  // BIC <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  bic X21, X3, X17, LSR #35  // BIC <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  bic V6.4H, #217  // BIC <Vd>.<Th>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  bic V23.8H, #101, LSL #0  // BIC <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  bic V24.2S, #70  // BIC <Vd>.<T>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  bic V31.2S, #192, LSL #0  // BIC <Vd>.<T>, #<imm8>, LSL #<amount>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  bic V25.16B, V10.16B, V9.16B  // BIC <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  bic Z15.D, P4/M, Z15.D, Z25.D  // BIC <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  bic Z7.D, Z8.D, Z28.D  // BIC <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  bics W24, W1, W25  // BICS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  bics W21, W0, W24, LSL #11  // BICS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift by immed, flagset, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  bics X27, X25, X10  // BICS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  bics X22, X6, X27, LSL #62  // BICS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, flagset  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  bics P2.B, P4/Z, P1.B, P7.B  // BICS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  bif V0.8B, V25.8B, V4.8B  // BIF <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD bitwise insert  \\ 1 2  2  4.0 V1UnitV
+  bit V5.8B, V12.8B, V22.8B  // BIT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD bitwise insert  \\ 1 2  2  4.0 V1UnitV
+  bl test  // BL <label>  \\ Branch and link, immed  \\ 2 1  1  2.0 V1UnitB,V1UnitS
+  blr X11  // BLR <Xn>  \\ Branch and link, register   \\ 2 1  1  2.0 V1UnitB,V1UnitS
+  br X17  // BR <Xn>  \\ Branch, register  \\ 1 1  1  2.0 V1UnitB
+  brk #33813  // BRK #<imm>  \\ No description \\ No scheduling info
+  brka P7.B, P7/Z, P5.B  // BRKA <Pd>.B, <Pg>/<ZM>, <Pn>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+  brkas P6.B, P5/Z, P0.B  // BRKAS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+  brkb P5.B, P0/Z, P1.B  // BRKB <Pd>.B, <Pg>/<ZM>, <Pn>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+  brkbs P6.B, P1/Z, P4.B  // BRKBS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+  brkn P7.B, P0/Z, P6.B, P7.B  // BRKN <Pdm>.B, <Pg>/Z, <Pn>.B, <Pdm>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+  brkns P3.B, P1/Z, P7.B, P3.B  // BRKNS <Pdm>.B, <Pg>/Z, <Pn>.B, <Pdm>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+  brkpa P3.B, P5/Z, P0.B, P1.B  // BRKPA <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+  brkpas P2.B, P5/Z, P1.B, P3.B  // BRKPAS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+  brkpb P1.B, P0/Z, P7.B, P6.B  // BRKPB <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+  brkpbs P7.B, P1/Z, P6.B, P1.B  // BRKPBS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+  bsl V27.16B, V13.16B, V21.16B  // BSL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD bitwise insert  \\ 1 2  2  4.0 V1UnitV
+  cbnz W21, test  // CBNZ <Wt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  cbnz X26, test  // CBNZ <Xt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  cbz W6, test  // CBZ <Wt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  cbz X4, test  // CBZ <Xt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  ccmn W8, #14, #3, HS  // CCMN <Wn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmn X23, #17, #0, GT  // CCMN <Xn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmn W17, W18, #12, CS  // CCMN <Wn>, <Wm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmn X19, X29, #12, LAST  // CCMN <Xn>, <Xm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmp W24, #2, #5, NLAST  // CCMP <Wn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmp X12, #8, #2, LO  // CCMP <Xn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmp W2, W9, #3, TSTOP  // CCMP <Wn>, <Wm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  ccmp X11, X10, #13, LS  // CCMP <Xn>, <Xm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+  cinc W23, W5, TSTOP  // CINC <Wd>, <Wn>, <cond>  \\ No description \\ No scheduling info
+  cinc X2, X1, NFRST  // CINC <Xd>, <Xn>, <cond>  \\ No description \\ No scheduling info
+  cinv W9, W12, TCONT  // CINV <Wd>, <Wn>, <cond>  \\ No description \\ No scheduling info
+  cinv X9, X30, FIRST  // CINV <Xd>, <Xn>, <cond>  \\ No description \\ No scheduling info
+  clasta B11, P4, B11, Z21.B  // CLASTA <V><dn>, <Pg>, <V><dn>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+  clasta W8, P0, W8, Z6.B  // CLASTA <R><dn>, <Pg>, <R><dn>, <Zm>.<T>  \\ Conditional extract operations, scalar form  \\ 2 9  9  1.0 V1UnitM0,V1UnitV1
+  clasta Z25.S, P1, Z25.S, Z14.S  // CLASTA <Zdn>.<T>, <Pg>, <Zdn>.<T>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+  clastb D6, P7, D6, Z31.D  // CLASTB <V><dn>, <Pg>, <V><dn>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+  clastb W28, P6, W28, Z12.B  // CLASTB <R><dn>, <Pg>, <R><dn>, <Zm>.<T>  \\ Conditional extract operations, scalar form  \\ 2 9  9  1.0 V1UnitM0,V1UnitV1
+  clastb Z27.H, P6, Z27.H, Z22.H  // CLASTB <Zdn>.<T>, <Pg>, <Zdn>.<T>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+  clrex   // CLREX   \\ No description \\ No scheduling info
+  clrex #12  // CLREX #<imm>  \\ No description \\ No scheduling info
+  cls V5.8B, V22.8B  // CLS <Vd>.<T>, <Vn>.<T>  \\ ASIMD count  \\ 1 2  2  4.0 V1UnitV
+  cls W25, W0  // CLS <Wd>, <Wn>  \\ Count leading  \\ 1 1  1  4.0 V1UnitI
+  cls X22, X6  // CLS <Xd>, <Xn>  \\ Count leading  \\ 1 1  1  4.0 V1UnitI
+  cls Z28.D, P3/M, Z2.D  // CLS <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Count/reverse bits  \\ 1 2  2  2.0 V1UnitV01
+  clz V24.8H, V30.8H  // CLZ <Vd>.<T>, <Vn>.<T>  \\ ASIMD count  \\ 1 2  2  4.0 V1UnitV
+  clz W26, W27  // CLZ <Wd>, <Wn>  \\ Count leading zeros  \\ 1 1  1  4.0 V1UnitI
+  clz X4, X0  // CLZ <Xd>, <Xn>  \\ Count leading zeros  \\ 1 1  1  4.0 V1UnitI
+  clz Z3.S, P3/M, Z18.S  // CLZ <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Count/reverse bits  \\ 1 2  2  2.0 V1UnitV01
+  cmeq D26, D5, D25  // CMEQ <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmeq V9.8H, V16.8H, V24.8H  // CMEQ <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmeq D7, D26, #0  // CMEQ <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmeq V14.4H, V18.4H, #0  // CMEQ <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmge D26, D21, D28  // CMGE <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmge V22.8H, V16.8H, V3.8H  // CMGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmge D30, D12, #0  // CMGE <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmge V22.16B, V30.16B, #0  // CMGE <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmgt D23, D25, D12  // CMGT <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmgt V3.2D, V29.2D, V11.2D  // CMGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmgt D28, D14, #0  // CMGT <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmgt V22.2S, V10.2S, #0  // CMGT <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmhi D29, D16, D5  // CMHI <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmhi V28.4H, V25.4H, V21.4H  // CMHI <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmhs D5, D3, D12  // CMHS <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmhs V6.8B, V31.8B, V12.8B  // CMHS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmle D14, D21, #0  // CMLE <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmle V21.2S, V19.2S, #0  // CMLE <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmlt D21, D24, #0  // CMLT <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmlt V26.4H, V12.4H, #0  // CMLT <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmn WSP, W7  // CMN <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn WSP, W8, SXTB   // CMN <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn WSP, W3, UXTB #3  // CMN <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn WSP, W7, LSL #3  // CMN <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn X2, X28  // CMN <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn X3, W0, UXTB  // CMN <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn X0, W4, UXTB #3  // CMN <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmn X14, X26, LSL #2  // CMN <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  cmn WSP, #613  // CMN <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn WSP, #2991, LSL #12  // CMN <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmn X23, #3803  // CMN <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn X29, #3786, LSL #12  // CMN <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmn W12, W0  // CMN <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn W19, W27, LSL #1  // CMN <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn W2, W11, LSL #29  // CMN <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmn W0, W0, ASR #30  // CMN <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmn X23, X28  // CMN <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmn X6, X1, LSL #2  // CMN <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  cmn X28, X30, LSL #26  // CMN <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmn X25, X15, LSR #49  // CMN <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp WSP, W26  // CMP <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp WSP, W13, SXTH   // CMP <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp WSP, W12, SXTH #3  // CMP <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp WSP, W30, LSL #4  // CMP <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp X22, X18  // CMP <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp X16, W27, UXTB  // CMP <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp X16, W7, UXTB #4  // CMP <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp X21, X24, LSL #4  // CMP <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  cmp WSP, #2342  // CMP <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp WSP, #3664, LSL #12  // CMP <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp X5, #1482  // CMP <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp X4, #3684, LSL #12  // CMP <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp W14, W0, LSL #4  // CMP <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  cmp W0, W23, LSL #29  // CMP <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp W2, W28, LSR #20  // CMP <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp X27, X10, LSL #1  // CMP <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  cmp X18, X12, LSL #14  // CMP <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmp X6, X7, LSR #0  // CMP <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  cmpeq P2.H, P0/Z, Z26.H, #-8  // CMPEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpge P1.B, P4/Z, Z28.B, #-6  // CMPGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpgt P1.B, P0/Z, Z13.B, #14  // CMPGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmphi P1.D, P3/Z, Z23.D, #12  // CMPHI <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmphs P7.D, P5/Z, Z23.D, #114  // CMPHS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmple P5.B, P2/Z, Z9.B, #9  // CMPLE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmplo P3.S, P5/Z, Z18.S, #87  // CMPLO <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpls P6.D, P6/Z, Z31.D, #56  // CMPLS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmplt P0.H, P6/Z, Z29.H, #-13  // CMPLT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpne P5.S, P4/Z, Z18.S, #15  // CMPNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpeq P6.S, P5/Z, Z2.S, Z9.S  // CMPEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpge P7.S, P4/Z, Z15.S, Z15.S  // CMPGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpgt P2.H, P4/Z, Z26.H, Z11.H  // CMPGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmphi P0.S, P4/Z, Z8.S, Z4.S  // CMPHI <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmphs P1.D, P6/Z, Z26.D, Z15.D  // CMPHS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpne P4.B, P3/Z, Z21.B, Z16.B  // CMPNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpeq P2.D, P3/Z, Z13.D, Z18.D  // CMPEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpge P2.B, P3/Z, Z3.B, Z16.D  // CMPGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpgt P2.H, P2/Z, Z28.H, Z30.D  // CMPGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmphi P0.H, P5/Z, Z30.H, Z16.D  // CMPHI <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmphs P7.H, P2/Z, Z1.H, Z26.D  // CMPHS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmple P7.B, P7/Z, Z3.B, Z13.D  // CMPLE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmplo P6.D, P2/Z, Z16.D, Z16.D  // CMPLO <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpls P3.H, P2/Z, Z12.H, Z26.D  // CMPLS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmplt P0.D, P4/Z, Z29.D, Z26.D  // CMPLT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpne P0.S, P4/Z, Z30.S, Z8.D  // CMPNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmple P1.D, P3/Z, Z2.D, Z26.D  // CMPLE <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmplo P7.B, P0/Z, Z4.B, Z25.B  // CMPLO <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmpls P4.D, P4/Z, Z2.D, Z14.D  // CMPLS <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmplt P2.S, P2/Z, Z31.S, Z21.S  // CMPLT <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+  cmtst D10, D6, D5  // CMTST <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cmtst V13.2D, V13.2D, V13.2D  // CMTST <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+  cneg W3, W17, HI  // CNEG <Wd>, <Wn>, <cond>  \\ No description \\ No scheduling info
+  cneg X26, X8, LAST  // CNEG <Xd>, <Xn>, <cond>  \\ No description \\ No scheduling info
+  cnot Z7.S, P7/M, Z8.S  // CNOT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  cnt V12.16B, V14.16B  // CNT <Vd>.<T>, <Vn>.<T>  \\ ASIMD count  \\ 1 2  2  4.0 V1UnitV
+  cnt Z26.H, P0/M, Z27.H  // CNT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  cntb X18  // CNTB <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntb X9, VL128  // CNTB <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntb X28, VL8, MUL #13  // CNTB <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntd X20  // CNTD <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntd X27, VL7  // CNTD <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntd X8, VL7, MUL #2  // CNTD <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cnth X27  // CNTH <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cnth X0, VL1  // CNTH <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cnth X16, VL3, MUL #6  // CNTH <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntw X22  // CNTW <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntw X23, VL3  // CNTW <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntw X6, VL16, MUL #11  // CNTW <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  cntp X22, P1, P2.S  // CNTP <Xd>, <Pg>, <Pn>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  compact Z17.S, P1, Z18.S  // COMPACT <Zd>.<T>, <Pg>, <Zn>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+  cpy Z13.B, P0/M, B6  // CPY <Zd>.<T>, <Pg>/M, <V><n>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z3.B, P6/M, #-118  // CPY <Zd>.B, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z11.S, P5/M, #-62  // CPY <Zd>.<T>, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z0.H, P0/M, #-11, LSL #0  // CPY <Zd>.<T>, <Pg>/M, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z5.B, P1/Z, #-90  // CPY <Zd>.B, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z12.H, P1/Z, #-118  // CPY <Zd>.<T>, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z25.D, P3/Z, #-81, LSL #8  // CPY <Zd>.<T>, <Pg>/Z, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  cpy Z24.H, P0/M, W19  // CPY <Zd>.<T>, <Pg>/M, <R><n>  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+  cpy Z23.S, P2/M, WSP  // CPY <Zd>.<T>, <Pg>/M, <R2>SP  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+  crc32b W27, W12, W15  // CRC32B <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32h W3, W15, W21  // CRC32H <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32w W9, W18, W24  // CRC32W <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32x W19, W6, X25  // CRC32X <Wd>, <Wn>, <Xm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32cb W25, W28, W30  // CRC32CB <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32ch W25, W26, W16  // CRC32CH <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32cw W27, W12, W23  // CRC32CW <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  crc32cx W21, W28, X5  // CRC32CX <Wd>, <Wn>, <Xm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+  csdb  // CSDB  \\ No description \\ No scheduling info
+  csel W25, W16, W30, LS  // CSEL <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  csel X28, X1, X2, PL  // CSEL <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  cset W6, NE  // CSET <Wd>, <cond>  \\ No description \\ No scheduling info
+  cset X11, LT  // CSET <Xd>, <cond>  \\ No description \\ No scheduling info
+  csetm W3, HI  // CSETM <Wd>, <cond>  \\ No description \\ No scheduling info
+  csetm X6, NE  // CSETM <Xd>, <cond>  \\ No description \\ No scheduling info
+  csinc W9, W3, W14, LT  // CSINC <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  csinc X20, X11, X23, TCONT  // CSINC <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  csinv W1, W4, W3, NLAST  // CSINV <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  csinv X27, X21, X15, NE  // CSINV <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  csneg W5, W13, W4, HI  // CSNEG <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  csneg X8, X29, X29, PMORE  // CSNEG <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+  ctermeq X4, X11  // CTERMEQ <R><n>, <R><m>  \\ Loop terminate  \\ 1 1  1  1.0 V1UnitM0
+  ctermne X0, X16  // CTERMNE <R><n>, <R><m>  \\ Loop terminate  \\ 1 1  1  1.0 V1UnitM0
+  dc CSW, X16  // DC <dc_op>, <Xt>  \\ No description \\ No scheduling info
+  dcps1   // DCPS1   \\ No description \\ No scheduling info
+  dcps1 #4391  // DCPS1 #<imm>  \\ No description \\ No scheduling info
+  dcps2   // DCPS2   \\ No description \\ No scheduling info
+  dcps2 #26756  // DCPS2 #<imm>  \\ No description \\ No scheduling info
+  dcps3   // DCPS3   \\ No description \\ No scheduling info
+  dcps3 #47330  // DCPS3 #<imm>  \\ No description \\ No scheduling info
+  decb X22  // DECB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decb X5, VL256  // DECB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decb X21, VL256, MUL #7  // DECB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decd X11  // DECD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decd X19, ALL  // DECD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decd X24, VL2, MUL #10  // DECD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  dech X16  // DECH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  dech X20, MUL4  // DECH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  dech X0, MUL3, MUL #15  // DECH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decw X27  // DECW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decw X18, VL32  // DECW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decw X29, VL6, MUL #3  // DECW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  decd Z19.D  // DECD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  decd Z22.D, MUL3  // DECD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  decd Z1.D, VL128, MUL #11  // DECD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  dech Z23.H  // DECH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  dech Z29.H, VL5  // DECH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  dech Z28.H, VL64, MUL #16  // DECH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  decw Z8.S  // DECW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  decw Z4.S, VL64  // DECW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  decw Z27.S, VL4, MUL #10  // DECW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  decp X6, P6.B  // DECP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  decp Z22.H, P1  // DECP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+  dmb SY  // DMB <option>  \\ No description \\ No scheduling info
+  dmb #6  // DMB #<imm>  \\ No description \\ No scheduling info
+  drps  // DRPS  \\ No description \\ No scheduling info
+  dup B15, V25.B[12]  // DUP B<d>, <Vn>.B[<indexb>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup H2, V31.H[5]  // DUP H<d>, <Vn>.H[<indexh>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup S10, V2.S[1]  // DUP S<d>, <Vn>.S[<indexs>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup D24, V7.D[1]  // DUP D<d>, <Vn>.D[<indexd>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup V25.8B, V21.B[4]  // DUP <Vd>.<Tb>, <Vn>.B[<indexb>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup V28.8H, V29.H[1]  // DUP <Vd>.<Th>, <Vn>.H[<indexh>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup V24.4S, V9.S[3]  // DUP <Vd>.<Ts>, <Vn>.S[<indexs>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup V20.2D, V3.D[0]  // DUP <Vd>.<Td>, <Vn>.D[<indexd>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  dup V19.4S, W27  // DUP <Vd>.<T>, <R><n>  \\ ASIMD duplicate, gen reg  \\ 1 3  3  1.0 V1UnitM0
+  dup Z30.B, #16  // DUP <Zd>.B, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z15.H, #105  // DUP <Zd>.<T>, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z22.D, #-14, LSL #0  // DUP <Zd>.<T>, #<imm>, <shift>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z2.B, Z26.B[27]  // DUP <Zd>.B, <Zn>.B[<immb>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z23.H, Z22.H[2]  // DUP <Zd>.H, <Zn>.H[<immh>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z29.S, Z30.S[15]  // DUP <Zd>.S, <Zn>.S[<imms>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z4.D, Z7.D[0]  // DUP <Zd>.D, <Zn>.D[<immd>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  dup Z25.D, X28  // DUP <Zd>.<T>, <R><n>  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+  dup Z18.S, WSP  // DUP <Zd>.<T>, <R2>SP  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+  dupm Z18.B, #0x70  // DUPM <Zd>.B, #<constb>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  dupm Z12.H, #0x60  // DUPM <Zd>.H, #<consth>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  dupm Z16.S, #0x2  // DUPM <Zd>.S, #<consts>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  dupm Z16.D, #0x4  // DUPM <Zd>.D, #<constd>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  eon W29, W4, W19  // EON <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eon W14, W24, W28, ASR #14  // EON <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eon X19, X12, X2  // EON <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eon X23, X23, X23, ASR #41  // EON <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eon Z7.B, Z7.B, #0x70  // EON <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eon Z3.H, Z3.H, #0x60  // EON <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eon Z2.S, Z2.S, #0x2  // EON <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eon Z24.D, Z24.D, #0x4  // EON <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eor WSP, W4, #0xe00  // EOR <Wd|WSP>, <Wn>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  eor X27, X25, #0x1e00  // EOR <Xd|SP>, <Xn>, #<immd>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  eor Z19.B, Z19.B, #0x70  // EOR <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eor Z18.H, Z18.H, #0x60  // EOR <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eor Z10.S, Z10.S, #0x2  // EOR <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eor Z29.D, Z29.D, #0x4  // EOR <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eor P6.B, P7/Z, P3.B, P5.B  // EOR <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  eor W8, W27, W2  // EOR <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eor W8, W7, W29, ASR #30  // EOR <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eor X22, X16, X6  // EOR <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eor X0, X23, X30, LSL #11  // EOR <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  eor V8.16B, V10.16B, V19.16B  // EOR <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  eor Z8.H, P3/M, Z8.H, Z14.H  // EOR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eor Z30.D, Z26.D, Z20.D  // EOR <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  eors P1.B, P0/Z, P3.B, P1.B  // EORS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  eorv H17, P1, Z15.H  // EORV <V><d>, <Pg>, <Zn>.<T>  \\ Reduction, logical   \\ 1 12  12  0.5 V1UnitV01[4]
+  eret  // ERET  \\ No description \\ No scheduling info
+  esb  // ESB  \\ No description \\ No scheduling info
+  ext V12.8B, V22.8B, V31.8B, #6  // EXT <Vd>.8B, <Vn>.8B, <Vm>.8B, #<index8>  \\ ASIMD extract  \\ 1 2  2  4.0 V1UnitV
+  ext V17.16B, V18.16B, V8.16B, #10  // EXT <Vd>.16B, <Vn>.16B, <Vm>.16B, #<index16>  \\ ASIMD extract  \\ 1 2  2  4.0 V1UnitV
+  extr W19, W20, W20, #16  // EXTR <Wd>, <Wn>, <Wn>, #<lsbs>  \\ Bitfield extract, one reg  \\ 1 1  1  4.0 V1UnitI
+  extr W27, W4, W5, #23  // EXTR <Wd>, <Wn>, <Wm>, #<lsbs>  \\ Bitfield extract, two regs  \\ 1 3  3  2.0 V1UnitM
+  extr X25, X22, X22, #62  // EXTR <Xd>, <Xn>, <Xn>, #<lsbd>  \\ Bitfield extract, one reg  \\ 1 1  1  4.0 V1UnitI
+  extr X0, X12, X13, #17  // EXTR <Xd>, <Xn>, <Xm>, #<lsbd>  \\ Bitfield extract, two regs  \\ 1 3  3  2.0 V1UnitM
+  fabd H27, H20, H17  // FABD <Hd>, <Hn>, <Hm>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabd S16, S29, S6  // FABD <V><d>, <V><n>, <V><m>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabd V13.8H, V28.8H, V12.8H  // FABD <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabd V12.4S, V4.4S, V31.4S  // FABD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabd Z11.H, P6/M, Z11.H, Z5.H  // FABD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point absolute value/difference  \\ 1 2  2  2.0 V1UnitV01
+  fabs H25, H7  // FABS <Hd>, <Hn>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabs S17, S12  // FABS <Sd>, <Sn>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabs D30, D8  // FABS <Dd>, <Dn>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabs V16.4S, V31.4S  // FABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabs V17.2S, V28.2S  // FABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+  fabs Z26.S, P7/M, Z24.S  // FABS <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Floating point absolute value/difference  \\ 1 2  2  2.0 V1UnitV01
+  facge P0.H, P5/Z, Z15.H, Z18.H  // FACGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  facgt P7.S, P7/Z, Z10.S, Z4.S  // FACGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  facge H24, H26, H29  // FACGE <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facge D25, D24, D7  // FACGE <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facge V25.4H, V16.4H, V11.4H  // FACGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facge V19.2S, V24.2S, V5.2S  // FACGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facgt H0, H4, H10  // FACGT <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facgt S29, S3, S2  // FACGT <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facgt V22.8H, V14.8H, V31.8H  // FACGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facgt V22.4S, V8.4S, V2.4S  // FACGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  facle P7.H, P5/Z, Z22.H, Z27.H  // FACLE <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  faclt P5.H, P5/Z, Z31.H, Z16.H  // FACLT <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fadd Z4.H, P7/M, Z4.H, #1.0  // FADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fadd H23, H27, H22  // FADD <Hd>, <Hn>, <Hm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fadd S1, S23, S27  // FADD <Sd>, <Sn>, <Sm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fadd D16, D15, D21  // FADD <Dd>, <Dn>, <Dm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fadd V7.2D, V30.2D, V20.2D  // FADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fadd V16.2D, V13.2D, V11.2D  // FADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fadd Z26.H, P4/M, Z26.H, Z1.H  // FADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fadd Z23.S, Z7.S, Z16.S  // FADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fadda H8, P3, H8, Z28.H  // FADDA H<dn>, <Pg>, H<dn>, <Zm>.H  \\ Floating point associative add, F16  \\ 1 19  19  0.06 V1UnitV0[18]
+  fadda S11, P6, S11, Z1.S  // FADDA S<dn>, <Pg>, S<dn>, <Zm>.S  \\ Floating point associative add, F32  \\ 1 11  11  0.1 V1UnitV0[10]
+  fadda D27, P4, D27, Z27.D  // FADDA D<dn>, <Pg>, D<dn>, <Zm>.D  \\ Floating point associative add, F64  \\ 1 8  8  0.67 V1UnitV01[3]
+  faddp H10, V19.2H  // FADDP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  faddp D11, V28.2D  // FADDP <V><d>, <Vn>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  faddp V16.2D, V11.2D, V5.2D  // FADDP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  faddp V16.4S, V11.4S, V18.4S  // FADDP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  faddv H21, P2, Z3.H  // FADDV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+  faddv S16, P2, Z25.S  // FADDV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+  faddv D18, P4, Z7.D  // FADDV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+  fcadd Z29.H, P2/M, Z29.H, Z15.H, #270  // FCADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>, <const>  \\ Floating point complex add  \\ 1 3  3  2.0 V1UnitV01
+  fccmp H31, H3, #11, HS  // FCCMP <Hn>, <Hm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fccmp S5, S6, #0, CC  // FCCMP <Sn>, <Sm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fccmp D17, D15, #0, ANY  // FCCMP <Dn>, <Dm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fccmpe H6, H1, #12, ANY  // FCCMPE <Hn>, <Hm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fccmpe S16, S13, #10, VS  // FCCMPE <Sn>, <Sm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fccmpe D17, D14, #15, PLAST  // FCCMPE <Dn>, <Dm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmeq P7.D, P1/Z, Z23.D, Z21.D  // FCMEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmge P6.H, P1/Z, Z19.H, Z10.H  // FCMGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmgt P5.S, P2/Z, Z29.S, Z5.S  // FCMGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmne P5.D, P0/Z, Z22.D, Z15.D  // FCMNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmuo P0.D, P2/Z, Z15.D, Z23.D  // FCMUO <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmeq P4.D, P5/Z, Z19.D, #0.0  // FCMEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmge P0.D, P5/Z, Z10.D, #0.0  // FCMGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmgt P6.D, P1/Z, Z8.D, #0.0  // FCMGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmle P2.D, P4/Z, Z26.D, #0.0  // FCMLE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmlt P5.D, P5/Z, Z23.D, #0.0  // FCMLT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmne P2.H, P3/Z, Z7.H, #0.0  // FCMNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmeq H30, H6, H1  // FCMEQ <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq S17, S0, S21  // FCMEQ <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq V19.2S, V31.2S, V19.2S  // FCMEQ <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq V12.4S, V11.4S, V26.4S  // FCMEQ <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq H19, H23, #0.0  // FCMEQ <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq S25, S18, #0.0  // FCMEQ <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq V8.2S, V16.2S, #0.0  // FCMEQ <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmeq V18.2D, V17.2D, #0.0  // FCMEQ <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge H1, H16, H12  // FCMGE <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge D29, D9, D3  // FCMGE <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge V20.8H, V19.8H, V22.8H  // FCMGE <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge V17.2D, V11.2D, V13.2D  // FCMGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge H10, H23, #0.0  // FCMGE <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge D5, D17, #0.0  // FCMGE <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge V18.4H, V27.4H, #0.0  // FCMGE <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmge V17.2S, V11.2S, #0.0  // FCMGE <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt H4, H5, H0  // FCMGT <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt S13, S20, S3  // FCMGT <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt V24.8H, V24.8H, V28.8H  // FCMGT <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt V19.4S, V20.4S, V13.4S  // FCMGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt H0, H18, #0.0  // FCMGT <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt D30, D23, #0.0  // FCMGT <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt V0.8H, V11.8H, #0.0  // FCMGT <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmgt V19.2D, V31.2D, #0.0  // FCMGT <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmla Z20.H, Z12.H, Z4.H[1], #90  // FCMLA <Zda>.H, <Zn>.H, <Zmh>.H[<immh>], <const>  \\ Floating point complex multiply add   \\ 1 5 2 2.0 V1UnitV01
+  fcmla Z1.S, Z27.S, Z6.S[0], #90  // FCMLA <Zda>.S, <Zn>.S, <Zm>.S[<imm>], <const>  \\ Floating point complex multiply add   \\ 1 5 2 2.0 V1UnitV01
+  fcmla Z25.S, P3/M, Z13.S, Z23.S, #180  // FCMLA <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>, <const>  \\ Floating point complex multiply add   \\ 1 5 2 2.0 V1UnitV01
+  fcmle P5.S, P3/Z, Z28.S, Z12.S  // FCMLE <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmle H18, H28, #0.0  // FCMLE <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmle D18, D16, #0.0  // FCMLE <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmle V16.8H, V11.8H, #0.0  // FCMLE <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmle V22.4S, V30.4S, #0.0  // FCMLE <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmlt P1.S, P1/Z, Z13.S, Z24.S  // FCMLT <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmlt H23, H7, #0.0  // FCMLT <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmlt D22, D28, #0.0  // FCMLT <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmlt V8.4H, V2.4H, #0.0  // FCMLT <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmlt V7.2D, V16.2D, #0.0  // FCMLT <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+  fcmp H5, H21  // FCMP <Hn>, <Hm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmp H5, #0.0  // FCMP <Hn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmp S7, S0  // FCMP <Sn>, <Sm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmp S28, #0.0  // FCMP <Sn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmp D1, D27  // FCMP <Dn>, <Dm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmp D16, #0.0  // FCMP <Dn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmpe H22, H21  // FCMPE <Hn>, <Hm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmpe H13, #0.0  // FCMPE <Hn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmpe S11, S29  // FCMPE <Sn>, <Sm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmpe S15, #0.0  // FCMPE <Sn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmpe D27, D22  // FCMPE <Dn>, <Dm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcmpe D9, #0.0  // FCMPE <Dn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+  fcpy Z2.H, P7/M, #0.5  // FCPY <Zd>.<T>, <Pg>/M, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+  fcsel H26, H2, H11, NLAST  // FCSEL <Hd>, <Hn>, <Hm>, <cond>  \\ FP select  \\ 1 2  2  2.0 V1UnitV01
+  fcsel S5, S1, S4, VC  // FCSEL <Sd>, <Sn>, <Sm>, <cond>  \\ FP select  \\ 1 2  2  2.0 V1UnitV01
+  fcsel D14, D0, D19, NONE  // FCSEL <Dd>, <Dn>, <Dm>, <cond>  \\ FP select  \\ 1 2  2  2.0 V1UnitV01
+  fcvt S13, H13  // FCVT <Sd>, <Hn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+  fcvt D10, H6  // FCVT <Dd>, <Hn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+  fcvt H1, S1  // FCVT <Hd>, <Sn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+  fcvt D9, S23  // FCVT <Dd>, <Sn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+  fcvt H17, D16  // FCVT <Hd>, <Dn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+  fcvt S31, D27  // FCVT <Sd>, <Dn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+  fcvt Z0.S, P1/M, Z4.H  // FCVT <Zd>.S, <Pg>/M, <Zn>.H  \\ Floating point convert, long or narrow (F16 to F32 or F32 to F16)  \\ 1 4  4  0.5 V1UnitV0[2]
+  fcvt Z6.D, P0/M, Z17.H  // FCVT <Zd>.D, <Pg>/M, <Zn>.H  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+  fcvt Z7.H, P7/M, Z5.S  // FCVT <Zd>.H, <Pg>/M, <Zn>.S  \\ Floating point convert, long or narrow (F16 to F32 or F32 to F16)  \\ 1 4  4  0.5 V1UnitV0[2]
+  fcvt Z11.D, P2/M, Z18.S  // FCVT <Zd>.D, <Pg>/M, <Zn>.S  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+  fcvt Z26.H, P0/M, Z30.D  // FCVT <Zd>.H, <Pg>/M, <Zn>.D  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+  fcvt Z13.S, P2/M, Z3.D  // FCVT <Zd>.S, <Pg>/M, <Zn>.D  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas W23, H3  // FCVTAS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas X14, H29  // FCVTAS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas W0, S13  // FCVTAS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas X23, S15  // FCVTAS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas W1, D31  // FCVTAS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas X2, D3  // FCVTAS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtas H27, H24  // FCVTAS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtas S16, S0  // FCVTAS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtas D14, D7  // FCVTAS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtas V5.4H, V16.4H  // FCVTAS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtas V13.8H, V30.8H  // FCVTAS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtas V12.2S, V1.2S  // FCVTAS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtas V9.4S, V31.4S  // FCVTAS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtas V2.2D, V22.2D  // FCVTAS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtau W13, H27  // FCVTAU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtau X8, H12  // FCVTAU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtau W20, S10  // FCVTAU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtau X27, S22  // FCVTAU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtau W6, D26  // FCVTAU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtau X16, D13  // FCVTAU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtau H6, H29  // FCVTAU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtau S23, S7  // FCVTAU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtau D1, D26  // FCVTAU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtau V12.4H, V13.4H  // FCVTAU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtau V21.8H, V0.8H  // FCVTAU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtau V31.2S, V6.2S  // FCVTAU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtau V29.4S, V26.4S  // FCVTAU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtau V9.2D, V7.2D  // FCVTAU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtl V30.4S, V4.4H  // FCVTL <Vd>.4S, <Vn>.4H  \\ ASIMD FP convert, long (F16 to F32)  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtl V28.2D, V13.2S  // FCVTL <Vd>.2D, <Vn>.2S  \\ ASIMD FP convert, long (F32 to F64)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtl2 V14.4S, V29.8H  // FCVTL2 <Vd>.4S, <Vn>.8H  \\ ASIMD FP convert, long (F16 to F32)  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtl2 V0.2D, V9.4S  // FCVTL2 <Vd>.2D, <Vn>.4S  \\ ASIMD FP convert, long (F32 to F64)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtms W15, H1  // FCVTMS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtms X5, H2  // FCVTMS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtms W1, S16  // FCVTMS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtms X27, S22  // FCVTMS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtms W18, D21  // FCVTMS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtms X6, D26  // FCVTMS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtms H19, H29  // FCVTMS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtms S30, S14  // FCVTMS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtms D8, D20  // FCVTMS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtms V27.4H, V7.4H  // FCVTMS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtms V26.8H, V11.8H  // FCVTMS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtms V13.2S, V2.2S  // FCVTMS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtms V18.4S, V21.4S  // FCVTMS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtms V15.2D, V16.2D  // FCVTMS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtmu W20, H6  // FCVTMU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtmu X7, H18  // FCVTMU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtmu W24, S19  // FCVTMU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtmu X7, S15  // FCVTMU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtmu W16, D16  // FCVTMU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtmu X1, D18  // FCVTMU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtmu H20, H13  // FCVTMU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtmu S28, S25  // FCVTMU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtmu D3, D27  // FCVTMU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtmu V18.4H, V2.4H  // FCVTMU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtmu V10.8H, V11.8H  // FCVTMU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtmu V27.2S, V14.2S  // FCVTMU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtmu V31.4S, V4.4S  // FCVTMU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtmu V6.2D, V26.2D  // FCVTMU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtn V4.4H, V22.4S  // FCVTN <Vd>.4H, <Vn>.4S  \\ ASIMD FP convert, narrow (F32 to F16)  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtn V14.2S, V2.2D  // FCVTN <Vd>.2S, <Vn>.2D  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtn2 V0.8H, V30.4S  // FCVTN2 <Vd>.8H, <Vn>.4S  \\ ASIMD FP convert, narrow (F32 to F16)  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtn2 V21.4S, V13.2D  // FCVTN2 <Vd>.4S, <Vn>.2D  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtns W19, H15  // FCVTNS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtns X20, H0  // FCVTNS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtns W10, S5  // FCVTNS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtns X14, S12  // FCVTNS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtns W30, D2  // FCVTNS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtns X0, D12  // FCVTNS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtns H16, H25  // FCVTNS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtns S23, S19  // FCVTNS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtns D30, D1  // FCVTNS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtns V28.4H, V19.4H  // FCVTNS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtns V19.8H, V19.8H  // FCVTNS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtns V20.2S, V4.2S  // FCVTNS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtns V28.4S, V29.4S  // FCVTNS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtns V21.2D, V31.2D  // FCVTNS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtnu W12, H3  // FCVTNU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtnu X23, H27  // FCVTNU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtnu W4, S23  // FCVTNU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtnu X5, S28  // FCVTNU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtnu W4, D11  // FCVTNU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtnu X12, D8  // FCVTNU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtnu H24, H22  // FCVTNU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtnu S29, S22  // FCVTNU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtnu D18, D15  // FCVTNU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtnu V5.4H, V12.4H  // FCVTNU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtnu V26.8H, V20.8H  // FCVTNU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtnu V15.2S, V1.2S  // FCVTNU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtnu V7.4S, V16.4S  // FCVTNU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtnu V13.2D, V8.2D  // FCVTNU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtps W27, H14  // FCVTPS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtps X26, H20  // FCVTPS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtps W5, S27  // FCVTPS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtps X29, S6  // FCVTPS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtps W23, D25  // FCVTPS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtps X10, D16  // FCVTPS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtps H31, H22  // FCVTPS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtps S3, S3  // FCVTPS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtps D10, D26  // FCVTPS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtps V13.4H, V26.4H  // FCVTPS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtps V26.8H, V10.8H  // FCVTPS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtps V18.2S, V8.2S  // FCVTPS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtps V12.4S, V18.4S  // FCVTPS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtps V3.2D, V2.2D  // FCVTPS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtpu W25, H22  // FCVTPU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtpu X4, H24  // FCVTPU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtpu W13, S0  // FCVTPU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtpu X0, S17  // FCVTPU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtpu W16, D25  // FCVTPU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtpu X15, D12  // FCVTPU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtpu H1, H29  // FCVTPU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtpu S21, S30  // FCVTPU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtpu D16, D26  // FCVTPU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtpu V2.4H, V25.4H  // FCVTPU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtpu V24.8H, V26.8H  // FCVTPU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtpu V6.2S, V23.2S  // FCVTPU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtpu V10.4S, V6.4S  // FCVTPU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtpu V7.2D, V23.2D  // FCVTPU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtxn S29, D4  // FCVTXN <Vb><d>, <Va><n>  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtxn V25.2S, V15.2D  // FCVTXN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtxn2 V21.4S, V6.2D  // FCVTXN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs W28, H26, #26  // FCVTZS <Wd>, <Hn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs X22, H17, #58  // FCVTZS <Xd>, <Hn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs W17, S23, #22  // FCVTZS <Wd>, <Sn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs X15, S30, #2  // FCVTZS <Xd>, <Sn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs W13, D17, #17  // FCVTZS <Wd>, <Dn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs X14, D9, #24  // FCVTZS <Xd>, <Dn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs W15, H10  // FCVTZS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs X4, H21  // FCVTZS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs W1, S4  // FCVTZS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs X27, S27  // FCVTZS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs W24, D30  // FCVTZS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs X18, D21  // FCVTZS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs H29, H23, #16  // FCVTZS H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs S23, S15, #2  // FCVTZS S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs D20, D26, #57  // FCVTZS D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs V20.4H, V24.4H, #11  // FCVTZS <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzs V18.8H, V10.8H, #7  // FCVTZS <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtzs V16.2S, V2.2S, #11  // FCVTZS <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs V22.4S, V18.4S, #5  // FCVTZS <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzs V14.2D, V30.2D, #54  // FCVTZS <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs H16, H27  // FCVTZS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs S4, S5  // FCVTZS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs D4, D23  // FCVTZS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs V8.4H, V16.4H  // FCVTZS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzs V2.8H, V16.8H  // FCVTZS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtzs V27.2S, V28.2S  // FCVTZS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs V29.4S, V18.4S  // FCVTZS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzs V13.2D, V31.2D  // FCVTZS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzs Z1.H, P2/M, Z6.H  // FCVTZS <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+  fcvtzs Z19.S, P4/M, Z16.H  // FCVTZS <Zd>.S, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+  fcvtzs Z14.D, P0/M, Z6.H  // FCVTZS <Zd>.D, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+  fcvtzs Z25.S, P5/M, Z23.S  // FCVTZS <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+  fcvtzs Z3.D, P1/M, Z31.S  // FCVTZS <Zd>.D, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+  fcvtzs Z28.S, P5/M, Z23.D  // FCVTZS <Zd>.S, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzs Z22.D, P6/M, Z29.D  // FCVTZS <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu W12, H19, #20  // FCVTZU <Wd>, <Hn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu X17, H23, #12  // FCVTZU <Xd>, <Hn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu W16, S3, #12  // FCVTZU <Wd>, <Sn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu X27, S15, #8  // FCVTZU <Xd>, <Sn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu W21, D10, #23  // FCVTZU <Wd>, <Dn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu X26, D30, #27  // FCVTZU <Xd>, <Dn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu W26, H30  // FCVTZU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu X9, H11  // FCVTZU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu W20, S16  // FCVTZU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu X7, S21  // FCVTZU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu W25, D30  // FCVTZU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu X13, D8  // FCVTZU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu H19, H8, #12  // FCVTZU H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu S25, S27, #10  // FCVTZU S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu D30, D16, #42  // FCVTZU D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu V19.4H, V26.4H, #9  // FCVTZU <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzu V27.8H, V6.8H, #11  // FCVTZU <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtzu V30.2S, V4.2S, #19  // FCVTZU <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu V31.4S, V6.4S, #22  // FCVTZU <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzu V10.2D, V12.2D, #53  // FCVTZU <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu H25, H30  // FCVTZU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu S2, S19  // FCVTZU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu D4, D7  // FCVTZU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu V3.4H, V2.4H  // FCVTZU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzu V30.8H, V25.8H  // FCVTZU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  fcvtzu V25.2S, V25.2S  // FCVTZU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu V21.4S, V2.4S  // FCVTZU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  fcvtzu V23.2D, V15.2D  // FCVTZU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  fcvtzu Z15.H, P0/M, Z8.H  // FCVTZU <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+  fcvtzu Z8.S, P5/M, Z18.H  // FCVTZU <Zd>.S, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+  fcvtzu Z11.D, P4/M, Z24.H  // FCVTZU <Zd>.D, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+  fcvtzu Z13.S, P7/M, Z8.S  // FCVTZU <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+  fcvtzu Z20.D, P2/M, Z13.S  // FCVTZU <Zd>.D, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+  fcvtzu Z31.S, P3/M, Z20.D  // FCVTZU <Zd>.S, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+  fcvtzu Z4.D, P1/M, Z25.D  // FCVTZU <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+  fdiv H1, H26, H23  // FDIV <Hd>, <Hn>, <Hm>  \\ FP divide, H-form  \\ 1 7  7  1.0 V1UnitV02[2]
+  fdiv S31, S18, S12  // FDIV <Sd>, <Sn>, <Sm>  \\ FP divide, S-form  \\ 1 10 10 0.67 V1UnitV02[3]
+  fdiv D6, D3, D0  // FDIV <Dd>, <Dn>, <Dm>  \\ FP divide, D-form  \\ 1 15 15 0.29 V1UnitV02[7]
+  fdiv V21.4H, V15.4H, V22.4H  // FDIV <Vd>.4H, <Vn>.4H, <Vm>.4H  \\ ASIMD FP divide, D-form, F16  \\ 1 7  7  0.29 V1UnitV02[7]
+  fdiv V31.8H, V12.8H, V15.8H  // FDIV <Vd>.8H, <Vn>.8H, <Vm>.8H  \\ ASIMD FP divide, Q-form, F16  \\ 1 13 13 0.15 V1UnitV02[13]
+  fdiv V15.2S, V23.2S, V2.2S  // FDIV <Vd>.2S, <Vn>.2S, <Vm>.2S  \\ ASIMD FP divide, D-form, F32  \\ 1 10 10 0.4 V1UnitV02[5]
+  fdiv V7.4S, V27.4S, V22.4S  // FDIV <Vd>.4S, <Vn>.4S, <Vm>.4S  \\ ASIMD FP divide, Q-form, F32  \\ 1 10 10 0.22 V1UnitV02[9]
+  fdiv V31.2D, V25.2D, V8.2D  // FDIV <Vd>.2D, <Vn>.2D, <Vm>.2D  \\ ASIMD FP divide, Q-form, F64  \\ 1 15 15 0.14 V1UnitV02[14]
+  fdiv Z21.H, P7/M, Z21.H, Z15.H  // FDIV <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Floating point divide, F16  \\ 1 13 13 0.08 V1UnitV0[12]
+  fdiv Z17.S, P4/M, Z17.S, Z20.S  // FDIV <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Floating point divide, F32  \\ 1 10 10 0.11 V1UnitV0[9]
+  fdiv Z13.D, P3/M, Z13.D, Z28.D  // FDIV <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Floating point divide, F64  \\ 1 15 15 0.07 V1UnitV0[14]
+  fdivr Z29.H, P4/M, Z29.H, Z1.H  // FDIVR <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Floating point divide, F16  \\ 1 13 13 0.08 V1UnitV0[12]
+  fdivr Z13.S, P0/M, Z13.S, Z29.S  // FDIVR <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Floating point divide, F32  \\ 1 10 10 0.11 V1UnitV0[9]
+  fdivr Z14.D, P3/M, Z14.D, Z31.D  // FDIVR <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Floating point divide, F64  \\ 1 15 15 0.07 V1UnitV0[14]
+  fdup Z19.S, #0.5  // FDUP <Zd>.<T>, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+  fexpa Z6.H, Z3.H  // FEXPA <Zd>.<T>, <Zn>.<T>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+  fmad Z9.S, P5/M, Z9.S, Z7.S  // FMAD <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmadd H27, H0, H6, H28  // FMADD <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmadd S13, S24, S15, S5  // FMADD <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmadd D19, D4, D2, D17  // FMADD <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmax Z25.D, P2/M, Z25.D, #0.0  // FMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fmax H8, H7, H11  // FMAX <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmax S9, S21, S2  // FMAX <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmax D4, D26, D26  // FMAX <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmax V0.4S, V13.4S, V21.4S  // FMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmax V12.4S, V27.4S, V11.4S  // FMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmax Z16.S, P5/M, Z16.S, Z12.S  // FMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fmaxnm Z25.D, P5/M, Z25.D, #1.0  // FMAXNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fmaxnm H29, H13, H14  // FMAXNM <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmaxnm S25, S20, S0  // FMAXNM <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmaxnm D29, D25, D16  // FMAXNM <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmaxnm V6.4S, V3.4S, V3.4S  // FMAXNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmaxnm V9.2D, V15.2D, V11.2D  // FMAXNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmaxnm Z6.S, P5/M, Z6.S, Z17.S  // FMAXNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fmaxnmp H25, V19.2H  // FMAXNMP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxnmp D17, V29.2D  // FMAXNMP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxnmp V31.4S, V4.4S, V2.4S  // FMAXNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxnmp V23.4S, V15.4S, V1.4S  // FMAXNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxnmv H0, V13.4H  // FMAXNMV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fmaxnmv H12, V11.8H  // FMAXNMV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+  fmaxnmv S28, V31.4S  // FMAXNMV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fmaxnmv H9, P3, Z2.H  // FMAXNMV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+  fmaxnmv S26, P6, Z0.S  // FMAXNMV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+  fmaxnmv D7, P1, Z29.D  // FMAXNMV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+  fmaxp H15, V25.2H  // FMAXP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxp S6, V2.2S  // FMAXP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxp V21.2S, V17.2S, V13.2S  // FMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxp V10.4S, V5.4S, V25.4S  // FMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fmaxv H23, V4.4H  // FMAXV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fmaxv H25, V15.8H  // FMAXV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+  fmaxv S23, V2.4S  // FMAXV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fmaxv H12, P0, Z22.H  // FMAXV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+  fmaxv S24, P5, Z12.S  // FMAXV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+  fmaxv D1, P6, Z25.D  // FMAXV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+  fmin Z24.D, P4/M, Z24.D, #0.0  // FMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fmin H4, H13, H17  // FMIN <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmin S1, S14, S22  // FMIN <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmin D18, D19, D22  // FMIN <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmin V6.4S, V25.4S, V27.4S  // FMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmin V12.2S, V30.2S, V25.2S  // FMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fmin Z11.H, P3/M, Z11.H, Z16.H  // FMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fminnm Z19.H, P4/M, Z19.H, #0.0  // FMINNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fminnm H29, H23, H17  // FMINNM <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fminnm S24, S14, S30  // FMINNM <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fminnm D0, D26, D8  // FMINNM <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fminnm V16.2S, V23.2S, V27.2S  // FMINNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fminnm V23.4S, V19.4S, V22.4S  // FMINNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+  fminnm Z24.S, P3/M, Z24.S, Z13.S  // FMINNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+  fminnmp H20, V14.2H  // FMINNMP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminnmp D15, V8.2D  // FMINNMP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminnmp V27.2D, V27.2D, V16.2D  // FMINNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminnmp V2.4S, V14.4S, V14.4S  // FMINNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminnmv H19, V25.4H  // FMINNMV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fminnmv H23, V17.8H  // FMINNMV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+  fminnmv S29, V17.4S  // FMINNMV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fminnmv H24, P3, Z1.H  // FMINNMV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+  fminnmv S30, P3, Z9.S  // FMINNMV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+  fminnmv D18, P5, Z8.D  // FMINNMV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+  fminp H7, V10.2H  // FMINP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminp S17, V7.2S  // FMINP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminp V25.4S, V2.4S, V15.4S  // FMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminp V14.2S, V28.2S, V15.2S  // FMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+  fminv H3, V30.4H  // FMINV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fminv H29, V12.8H  // FMINV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+  fminv S16, V19.4S  // FMINV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+  fminv H15, P2, Z25.H  // FMINV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+  fminv S4, P0, Z6.S  // FMINV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+  fminv D20, P1, Z5.D  // FMINV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+  fmla H23, H24, V15.H[4]  // FMLA <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla S9, S20, V28.S[2]  // FMLA S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla D12, D20, V7.D[1]  // FMLA D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla V29.8H, V15.8H, V10.H[4]  // FMLA <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla V2.2S, V16.2S, V28.S[0]  // FMLA <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla V14.4S, V14.4S, V5.S[3]  // FMLA <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla V10.2D, V14.2D, V21.D[1]  // FMLA <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla Z2.H, Z4.H, Z7.H[0]  // FMLA <Zda>.H, <Zn>.H, <Zmhs>.H[<immh>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmla Z22.S, Z15.S, Z1.S[3]  // FMLA <Zda>.S, <Zn>.S, <Zmhs>.S[<imms>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmla Z1.D, Z30.D, Z11.D[1]  // FMLA <Zda>.D, <Zn>.D, <Zmd>.D[<immd>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmla V1.4S, V24.4S, V12.4S  // FMLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla V30.2D, V16.2D, V6.2D  // FMLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmla Z6.S, P1/M, Z24.S, Z24.S  // FMLA <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmls H8, H14, V7.H[4]  // FMLS <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls S20, S17, V5.S[2]  // FMLS S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls D11, D24, V29.D[0]  // FMLS D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls V30.8H, V18.8H, V4.H[6]  // FMLS <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls V10.2S, V27.2S, V0.S[0]  // FMLS <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls V27.4S, V7.4S, V24.S[0]  // FMLS <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls V10.2D, V22.2D, V29.D[0]  // FMLS <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls Z3.H, Z31.H, Z0.H[6]  // FMLS <Zda>.H, <Zn>.H, <Zmhs>.H[<immh>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmls Z30.S, Z8.S, Z0.S[2]  // FMLS <Zda>.S, <Zn>.S, <Zmhs>.S[<imms>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmls Z10.D, Z20.D, Z0.D[1]  // FMLS <Zda>.D, <Zn>.D, <Zmd>.D[<immd>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmls V6.2S, V3.2S, V12.2S  // FMLS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls V6.8H, V15.8H, V23.8H  // FMLS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmls Z26.S, P5/M, Z28.S, Z26.S  // FMLS <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmov W15, H31  // FMOV <Wd>, <Hn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+  fmov X21, H14  // FMOV <Xd>, <Hn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+  fmov H6, W5  // FMOV <Hd>, <Wn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+  fmov S22, W0  // FMOV <Sd>, <Wn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+  fmov W23, S30  // FMOV <Wd>, <Sn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+  fmov H16, X27  // FMOV <Hd>, <Xn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+  fmov D22, X12  // FMOV <Dd>, <Xn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+  fmov V7.D[1], X8  // FMOV <Vd>.D[1], <Xn>  \\ FP transfer, from gen to high half of vec reg  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  fmov X26, D29  // FMOV <Xd>, <Dn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+  fmov X4, V26.D[1]  // FMOV <Xd>, <Vn>.D[1]  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+  fmov Z2.S, P0/M, #0.5  // FMOV <Zd>.<T>, <Pg>/M, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+  fmov Z14.S, #0.5  // FMOV <Zd>.<T>, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+  fmov H18, H28  // FMOV <Hd>, <Hn>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov S13, S23  // FMOV <Sd>, <Sn>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov D27, D17  // FMOV <Dd>, <Dn>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov H29, #0.5  // FMOV <Hd>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov S22, #0.5  // FMOV <Sd>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov D18, #0.5  // FMOV <Dd>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov V12.2S, #0.5  // FMOV <Vd>.<T>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov V10.2S, #0.5  // FMOV <Vd>.<T>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov V0.2D, #0.5  // FMOV <Vd>.2D, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+  fmov Z2.D, P2/M, #0.0  // FMOV <Zd>.<T>, <Pg>/M, #0.0  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+  fmov Z5.S, #0.0  // FMOV <Zd>.<T>, #0.0  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+  fmsb Z25.S, P5/M, Z25.S, Z29.S  // FMSB <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fmsub H25, H28, H12, H24  // FMSUB <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmsub S31, S0, S23, S24  // FMSUB <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmsub D12, D10, D20, D16  // FMSUB <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fmul H18, H4, V7.H[3]  // FMUL <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul S17, S23, V30.S[2]  // FMUL S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul D27, D8, V10.D[1]  // FMUL D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul V10.4H, V2.4H, V7.H[5]  // FMUL <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul V5.2S, V12.2S, V9.S[0]  // FMUL <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul V15.4S, V30.4S, V2.S[3]  // FMUL <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul V11.2D, V31.2D, V24.D[1]  // FMUL <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul Z17.H, P5/M, Z17.H, #2.0  // FMUL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fmul Z27.H, Z30.H, Z0.H[0]  // FMUL <Zd>.H, <Zn>.H, <Zmhs>.H[<immh>]  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fmul Z6.S, Z16.S, Z1.S[0]  // FMUL <Zd>.S, <Zn>.S, <Zmhs>.S[<imms>]  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fmul Z4.D, Z30.D, Z2.D[0]  // FMUL <Zd>.D, <Zn>.D, <Zmd>.D[<immd>]  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fmul H28, H14, H3  // FMUL <Hd>, <Hn>, <Hm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul S28, S16, S24  // FMUL <Sd>, <Sn>, <Sm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul D19, D19, D0  // FMUL <Dd>, <Dn>, <Dm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul V0.2D, V14.2D, V20.2D  // FMUL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul V9.2D, V29.2D, V7.2D  // FMUL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmul Z22.D, P1/M, Z22.D, Z3.D  // FMUL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fmul Z19.S, Z14.S, Z26.S  // FMUL <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fmulx H18, H17, V7.H[1]  // FMULX <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx S23, S3, V3.S[2]  // FMULX S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx D3, D13, V30.D[0]  // FMULX D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx V28.4H, V25.4H, V15.H[1]  // FMULX <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx V3.2S, V22.2S, V23.S[3]  // FMULX <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx V5.4S, V28.4S, V15.S[3]  // FMULX <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx V22.2D, V18.2D, V25.D[1]  // FMULX <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx H20, H25, H0  // FMULX <Hd>, <Hn>, <Hm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx D18, D19, D22  // FMULX <V><d>, <V><n>, <V><m>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx V22.2D, V18.2D, V4.2D  // FMULX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx V16.2S, V4.2S, V27.2S  // FMULX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fmulx Z7.H, P5/M, Z7.H, Z21.H  // FMULX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fneg H2, H9  // FNEG <Hd>, <Hn>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+  fneg S11, S19  // FNEG <Sd>, <Sn>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+  fneg D5, D16  // FNEG <Dd>, <Dn>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+  fneg V26.2D, V2.2D  // FNEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+  fneg V14.2S, V24.2S  // FNEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+  fneg Z16.S, P0/M, Z25.S  // FNEG <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fnmad Z6.H, P2/M, Z14.H, Z21.H  // FNMAD <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fnmadd H3, H18, H31, H24  // FNMADD <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fnmadd S8, S18, S2, S14  // FNMADD <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fnmadd D19, D29, D28, D30  // FNMADD <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fnmla Z15.D, P0/M, Z8.D, Z29.D  // FNMLA <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fnmls Z13.D, P0/M, Z8.D, Z12.D  // FNMLS <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fnmsb Z30.D, P7/M, Z8.D, Z9.D  // FNMSB <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+  fnmsub H3, H29, H24, H17  // FNMSUB <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fnmsub S29, S26, S17, S4  // FNMSUB <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fnmsub D7, D13, D13, D4  // FNMSUB <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+  fnmul H3, H15, H7  // FNMUL <Hd>, <Hn>, <Hm>  \\ FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fnmul S16, S11, S2  // FNMUL <Sd>, <Sn>, <Sm>  \\ FP multiply  \\ 1 3  3  4.0 V1UnitV
+  fnmul D12, D22, D14  // FNMUL <Dd>, <Dn>, <Dm>  \\ FP multiply  \\ 1 3  3  4.0 V1UnitV
+  frecpe H20, H8  // FRECPE <Hd>, <Hn>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frecpe S27, S7  // FRECPE S<d>, S<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frecpe D2, D1  // FRECPE D<d>, D<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frecpe V28.4H, V27.4H  // FRECPE <Vd>.4H, <Vn>.4H  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+  frecpe V9.8H, V6.8H  // FRECPE <Vd>.8H, <Vn>.8H  \\ ASIMD reciprocal and square root estimate, Q-form F16  \\ 1  6   6  0.5 V1UnitV02[4]
+  frecpe V25.2S, V28.2S  // FRECPE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frecpe V21.4S, V18.4S  // FRECPE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+  frecpe V10.2D, V26.2D  // FRECPE <Vd>.2D, <Vn>.2D  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+  frecpe Z14.H, Z0.H  // FRECPE <Zd>.H, <Zn>.H  \\ Floating point reciprocal estimate, F16  \\ 1 6  6  1.0 V1UnitV0
+  frecpe Z5.S, Z16.S  // FRECPE <Zd>.S, <Zn>.S  \\ Floating point reciprocal estimate, F32  \\ 1 4  4  1.0 V1UnitV0
+  frecpe Z27.D, Z11.D  // FRECPE <Zd>.D, <Zn>.D  \\ Floating point reciprocal estimate, F64  \\ 1 3  3  1.0 V1UnitV0
+  frecps H29, H19, H8  // FRECPS <Hd>, <Hn>, <Hm>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frecps D25, D17, D12  // FRECPS <V><d>, <V><n>, <V><m>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frecps V12.8H, V25.8H, V4.8H  // FRECPS <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frecps V7.2D, V29.2D, V18.2D  // FRECPS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frecps Z11.S, Z31.S, Z1.S  // FRECPS <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point reciprocal step  \\ 1 4  4  2.0 V1UnitV01
+  frecpx H18, H11  // FRECPX <Hd>, <Hn>  \\ ASIMD reciprocal exponent  \\ 1 3  3  2.0 V1UnitV02
+  frecpx S13, S30  // FRECPX <V><d>, <V><n>  \\ ASIMD reciprocal exponent  \\ 1 3  3  2.0 V1UnitV02
+  frecpx Z15.S, P4/M, Z12.S  // FRECPX <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Floating point  reciprocal exponent  \\ 1 3  3  1.0 V1UnitV0
+  frintn Z30.H, P3/M, Z31.H  // FRINTN <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frintn Z17.S, P4/M, Z23.S  // FRINTN <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frintn Z28.D, P1/M, Z25.D  // FRINTN <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frinta Z10.H, P6/M, Z17.H  // FRINTA <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frinta Z7.S, P4/M, Z27.S  // FRINTA <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frinta Z17.D, P4/M, Z17.D  // FRINTA <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frintm Z26.H, P7/M, Z0.H  // FRINTM <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frintm Z6.S, P0/M, Z28.S  // FRINTM <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frintm Z29.D, P4/M, Z3.D  // FRINTM <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frintp Z20.H, P4/M, Z12.H  // FRINTP <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frintp Z3.S, P7/M, Z18.S  // FRINTP <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frintp Z28.D, P7/M, Z4.D  // FRINTP <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frintz Z27.H, P2/M, Z12.H  // FRINTZ <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frintz Z12.S, P6/M, Z3.S  // FRINTZ <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frintz Z12.D, P2/M, Z31.D  // FRINTZ <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frinti Z16.H, P4/M, Z9.H  // FRINTI <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frinti Z18.S, P6/M, Z27.S  // FRINTI <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frinti Z26.D, P2/M, Z12.D  // FRINTI <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frintx Z17.H, P0/M, Z9.H  // FRINTX <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+  frintx Z27.S, P7/M, Z16.S  // FRINTX <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+  frintx Z21.D, P4/M, Z23.D  // FRINTX <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+  frinta H22, H10  // FRINTA <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frinta S15, S7  // FRINTA <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frinta D30, D10  // FRINTA <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frinta V24.4H, V10.4H  // FRINTA <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frinta V5.8H, V3.8H  // FRINTA <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frinta V23.2S, V22.2S  // FRINTA <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frinta V28.4S, V28.4S  // FRINTA <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frinta V3.2D, V13.2D  // FRINTA <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frinti H31, H14  // FRINTI <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frinti S23, S9  // FRINTI <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frinti D8, D12  // FRINTI <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frinti V6.4H, V10.4H  // FRINTI <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frinti V22.8H, V7.8H  // FRINTI <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frinti V9.2S, V25.2S  // FRINTI <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frinti V23.4S, V7.4S  // FRINTI <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frinti V28.2D, V5.2D  // FRINTI <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintm H0, H21  // FRINTM <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintm S22, S10  // FRINTM <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintm D5, D30  // FRINTM <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintm V3.4H, V8.4H  // FRINTM <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintm V19.8H, V26.8H  // FRINTM <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frintm V15.2S, V8.2S  // FRINTM <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintm V20.4S, V26.4S  // FRINTM <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintm V20.2D, V11.2D  // FRINTM <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintn H12, H3  // FRINTN <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintn S27, S14  // FRINTN <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintn D30, D17  // FRINTN <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintn V27.4H, V4.4H  // FRINTN <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintn V17.8H, V19.8H  // FRINTN <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frintn V23.2S, V23.2S  // FRINTN <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintn V2.4S, V4.4S  // FRINTN <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintn V24.2D, V12.2D  // FRINTN <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintp H17, H31  // FRINTP <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintp S14, S10  // FRINTP <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintp D25, D13  // FRINTP <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintp V22.4H, V25.4H  // FRINTP <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintp V18.8H, V11.8H  // FRINTP <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frintp V31.2S, V5.2S  // FRINTP <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintp V0.4S, V24.4S  // FRINTP <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintp V1.2D, V3.2D  // FRINTP <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintx H4, H5  // FRINTX <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintx S10, S28  // FRINTX <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintx D17, D19  // FRINTX <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintx V24.4H, V25.4H  // FRINTX <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintx V1.8H, V27.8H  // FRINTX <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frintx V2.2S, V14.2S  // FRINTX <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintx V27.4S, V31.4S  // FRINTX <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintx V24.2D, V20.2D  // FRINTX <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintz H10, H29  // FRINTZ <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintz S11, S23  // FRINTZ <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintz D6, D11  // FRINTZ <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+  frintz V13.4H, V5.4H  // FRINTZ <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintz V20.8H, V21.8H  // FRINTZ <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  frintz V15.2S, V19.2S  // FRINTZ <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frintz V11.4S, V18.4S  // FRINTZ <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  frintz V12.2D, V22.2D  // FRINTZ <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  frsqrte H23, H26  // FRSQRTE <Hd>, <Hn>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frsqrte S23, S5  // FRSQRTE S<d>, S<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frsqrte D3, D11  // FRSQRTE D<d>, D<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frsqrte V16.4H, V15.4H  // FRSQRTE <Vd>.4H, <Vn>.4H  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+  frsqrte V14.8H, V0.8H  // FRSQRTE <Vd>.8H, <Vn>.8H  \\ ASIMD reciprocal and square root estimate, Q-form F16  \\ 1  6   6  0.5 V1UnitV02[4]
+  frsqrte V6.2S, V8.2S  // FRSQRTE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+  frsqrte V30.4S, V21.4S  // FRSQRTE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+  frsqrte V15.2D, V14.2D  // FRSQRTE <Vd>.2D, <Vn>.2D  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+  frsqrte Z6.H, Z30.H  // FRSQRTE <Zd>.H, <Zn>.H  \\ Floating point reciprocal estimate, F16  \\ 1 6  6  1.0 V1UnitV0
+  frsqrte Z27.S, Z15.S  // FRSQRTE <Zd>.S, <Zn>.S  \\ Floating point reciprocal estimate, F32  \\ 1 4  4  1.0 V1UnitV0
+  frsqrte Z6.D, Z17.D  // FRSQRTE <Zd>.D, <Zn>.D  \\ Floating point reciprocal estimate, F64  \\ 1 3  3  1.0 V1UnitV0
+  frsqrts H28, H26, H1  // FRSQRTS <Hd>, <Hn>, <Hm>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frsqrts S28, S1, S11  // FRSQRTS <V><d>, <V><n>, <V><m>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frsqrts V8.4H, V9.4H, V30.4H  // FRSQRTS <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frsqrts V20.4S, V26.4S, V27.4S  // FRSQRTS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+  frsqrts Z10.H, Z25.H, Z22.H  // FRSQRTS <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point reciprocal step  \\ 1 4  4  2.0 V1UnitV01
+  fscale Z2.H, P0/M, Z2.H, Z21.H  // FSCALE <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+  fsqrt H13, H24  // FSQRT <Hd>, <Hn>  \\ FP square root, H-form  \\ 1 7  7  1.0 V1UnitV02[2]
+  fsqrt S20, S15  // FSQRT <Sd>, <Sn>  \\ FP square root, S-form  \\ 1 9 9 1.0 V1UnitV02[2]
+  fsqrt D25, D21  // FSQRT <Dd>, <Dn>  \\ FP square root, D-form  \\ 1 16 16 0.25 V1UnitV02[8]
+  fsqrt V24.4H, V14.4H  // FSQRT <Vd>.4H, <Vn>.4H  \\ ASIMD FP square root, D-form, F16  \\ 1 7  7  0.29 V1UnitV02[7]
+  fsqrt V12.8H, V3.8H  // FSQRT <Vd>.8H, <Vn>.8H  \\ ASIMD FP square root, Q-form, F16  \\ 1 13 13 0.15 V1UnitV02[13]
+  fsqrt V30.2S, V20.2S  // FSQRT <Vd>.2S, <Vn>.2S  \\ ASIMD FP square root, D-form, F32  \\ 1 10 10 0.4 V1UnitV02[5]
+  fsqrt V2.4S, V24.4S  // FSQRT <Vd>.4S, <Vn>.4S  \\ ASIMD FP square root, Q-form, F32  \\ 1 10 10 0.22 V1UnitV02[9]
+  fsqrt V28.2D, V25.2D  // FSQRT <Vd>.2D, <Vn>.2D  \\ ASIMD FP square root, Q-form, F64  \\ 1 16 16 0.13 V1UnitV02[15]
+  fsqrt Z13.H, P3/M, Z11.H  // FSQRT <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point square root, F16  \\ 1 13 13 0.08 V1UnitV0[12]
+  fsqrt Z2.S, P7/M, Z0.S  // FSQRT <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point square root, F32  \\ 1 10 10 0.11 V1UnitV0[9]
+  fsqrt Z17.D, P6/M, Z17.D  // FSQRT <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point square root F64  \\ 1 16 16 0.07 V1UnitV0[14]
+  fsub Z12.D, P6/M, Z12.D, #1.0  // FSUB <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fsub H20, H11, H18  // FSUB <Hd>, <Hn>, <Hm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fsub S15, S4, S24  // FSUB <Sd>, <Sn>, <Sm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fsub D25, D26, D4  // FSUB <Dd>, <Dn>, <Dm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fsub V13.8H, V15.8H, V17.8H  // FSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fsub V1.2S, V31.2S, V27.2S  // FSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+  fsub Z24.S, P4/M, Z24.S, Z10.S  // FSUB <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fsub Z19.H, Z8.H, Z29.H  // FSUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fsubr Z22.H, P7/M, Z22.H, #0.5  // FSUBR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  fsubr Z13.S, P2/M, Z13.S, Z4.S  // FSUBR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+  ftmad Z19.D, Z19.D, Z6.D, #3  // FTMAD <Zdn>.<T>, <Zdn>.<T>, <Zm>.<T>, #<imm>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+  ftsmul Z21.S, Z0.S, Z10.S  // FTSMUL <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+  ftssel Z5.D, Z0.D, Z15.D  // FTSSEL <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+  hint #9  // HINT #<imm>  \\ No description \\ No scheduling info
+  hlt #31335  // HLT #<imm>  \\ No description \\ No scheduling info
+  hvc #60601  // HVC #<imm>  \\ No description \\ No scheduling info
+  ic IALLUIS // IC <ic_op> \\ No description \\ No scheduling info
+  ic IVAU, X6  // IC <ic_op2>, <Xt>  \\ No description \\ No scheduling info
+  incb X18  // INCB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incb X17, VL3  // INCB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incb X17, MUL3, MUL #7  // INCB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incd X19  // INCD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incd X17, VL3  // INCD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incd X11, VL64, MUL #7  // INCD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  inch X24  // INCH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  inch X23, ALL  // INCH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  inch X22, VL1, MUL #8  // INCH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incw X29  // INCW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incw X2, VL64  // INCW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incw X2, VL8, MUL #1  // INCW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  incd Z24.D  // INCD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  incd Z23.D, VL8  // INCD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  incd Z20.D, VL2, MUL #11  // INCD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  inch Z29.H  // INCH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  inch Z28.H, VL16  // INCH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  inch Z29.H, VL16, MUL #13  // INCH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  incw Z17.S  // INCW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  incw Z31.S, MUL3  // INCW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  incw Z12.S, VL4, MUL #5  // INCW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  incp X7, P0.H  // INCP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  incp Z2.D, P6  // INCP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+  index Z8.B, #15, W14  // INDEX <Zd>.B, #<imm>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z14.H, #11, W10  // INDEX <Zd>.H, #<imm>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z17.S, #14, W21  // INDEX <Zd>.S, #<imm>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z5.D, #11, X15  // INDEX <Zd>.D, #<imm>, X<m>  \\ Horizontal operations, D form, scalar, imm/ scalar/ imm, scalar  \\ 2 8  8  0.5 V1UnitM0[2],V1UnitV0[2]
+  index Z16.B, #-2, #0  // INDEX <Zd>.B, #<imm1>, #<imm2>  \\ Horizontal operations, B, H, S form, imm, imm  \\ 1 4  4  1.0 V1UnitV0
+  index Z13.H, #13, #2  // INDEX <Zd>.H, #<imm1>, #<imm2>  \\ Horizontal operations, B, H, S form, imm, imm  \\ 1 4  4  1.0 V1UnitV0
+  index Z20.S, #6, #1  // INDEX <Zd>.S, #<imm1>, #<imm2>  \\ Horizontal operations, B, H, S form, imm, imm  \\ 1 4  4  1.0 V1UnitV0
+  index Z13.D, #-15, #0  // INDEX <Zd>.D, #<imm1>, #<imm2>  \\ Horizontal operations, D form, imm, imm  \\ 1 5  5  0.5 V1UnitV0[2]
+  index Z28.B, W27, #1  // INDEX <Zd>.B, W<n>, #<imm>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z13.H, W28, #-5  // INDEX <Zd>.H, W<n>, #<imm>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z22.S, W7, #8  // INDEX <Zd>.S, W<n>, #<imm>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z0.D, X25, #-8  // INDEX <Zd>.D, X<n>, #<imm>  \\ Horizontal operations, D form, scalar, imm/ scalar/ imm, scalar  \\ 2 8  8  0.5 V1UnitM0[2],V1UnitV0[2]
+  index Z6.B, W24, W8  // INDEX <Zd>.B, W<n>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z20.H, W4, W7  // INDEX <Zd>.H, W<n>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z10.S, W2, W19  // INDEX <Zd>.S, W<n>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+  index Z2.D, X23, X7  // INDEX <Zd>.D, X<n>, X<m>  \\ Horizontal operations, D form, scalar, imm/ scalar/ imm, scalar  \\ 2 8  8  0.5 V1UnitM0[2],V1UnitV0[2]
+  ins V15.B[7], V6.B[15]  // INS <Vd>.B[<index1b>], <Vn>.B[<index2b>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  ins V17.H[1], V3.H[2]  // INS <Vd>.H[<index1h>], <Vn>.H[<index2h>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  ins V4.S[1], V7.S[0]  // INS <Vd>.S[<index1s>], <Vn>.S[<index2s>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  ins V22.D[1], V25.D[1]  // INS <Vd>.D[<index1d>], <Vn>.D[<index2d>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  ins V14.B[3], W12  // INS <Vd>.B[<indexb>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  ins V25.H[2], W14  // INS <Vd>.H[<indexh>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  ins V14.S[1], W29  // INS <Vd>.S[<indexs>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  ins V19.D[1], X27  // INS <Vd>.D[<indexd>], X<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  insr Z4.D, D0  // INSR <Zdn>.<T>, <V><m>  \\ Extract/insert operation, SIMD and FP scalar form  \\ 1 3  3  1.0 V1UnitV1
+  insr Z4.D, X14  // INSR <Zdn>.<T>, <R><m>  \\ Extract/insert operation, scalar  \\ 2 6  6  1.0 V1UnitV1,V1UnitM0
+  isb  // ISB  \\ No description \\ No scheduling info
+  isb SY  // ISB <option>  \\ No description \\ No scheduling info
+  isb #1  // ISB #<imm>  \\ No description \\ No scheduling info
+  lasta B3, P1, Z3.B  // LASTA <V><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, SIMD and FP scalar form  \\ 1 3  3  1.0 V1UnitV1
+  lasta W16, P0, Z10.B  // LASTA <R><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, scalar  \\ 2 6  6  1.0 V1UnitV1,V1UnitM0
+  lastb D3, P1, Z17.D  // LASTB <V><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, SIMD and FP scalar form  \\ 1 3  3  1.0 V1UnitV1
+  lastb X4, P3, Z31.D  // LASTB <R><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, scalar  \\ 2 6  6  1.0 V1UnitV1,V1UnitM0
+  ld1 { V23.8B }, [X11]  // LD1 { <Vt>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V25.8B }, [X30], #8  // LD1 { <Vt>.8B }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V14.8B }, [X1], X26  // LD1 { <Vt>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V12.16B }, [X19]  // LD1 { <Vt>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V24.16B }, [X28], #16  // LD1 { <Vt>.16B }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V21.16B }, [X25], X28  // LD1 { <Vt>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V8.4H }, [X30]  // LD1 { <Vt>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V4.4H }, [X10], #8  // LD1 { <Vt>.4H }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V17.4H }, [X12], X16  // LD1 { <Vt>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V24.8H }, [X27]  // LD1 { <Vt>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V21.8H }, [X24], #16  // LD1 { <Vt>.8H }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V9.8H }, [X9], X27  // LD1 { <Vt>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V4.2S }, [X2]  // LD1 { <Vt>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V19.2S }, [X27], #8  // LD1 { <Vt>.2S }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V25.2S }, [X13], X19  // LD1 { <Vt>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V3.4S }, [X4]  // LD1 { <Vt>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V24.4S }, [X20], #16  // LD1 { <Vt>.4S }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V29.4S }, [X25], X23  // LD1 { <Vt>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V24.1D }, [X9]  // LD1 { <Vt>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V23.1D }, [X3], #8  // LD1 { <Vt>.1D }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V19.1D }, [X10], X19  // LD1 { <Vt>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V3.2D }, [X28]  // LD1 { <Vt>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+  ld1 { V8.2D }, [X16], #16  // LD1 { <Vt>.2D }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V5.2D }, [X1], X29  // LD1 { <Vt>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ld1 { V24.8B, V25.8B }, [X6]  // LD1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V17.8B, V18.8B }, [X18], #16  // LD1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V18.8B, V19.8B }, [X6], X11  // LD1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V0.16B, V1.16B }, [X14]  // LD1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V20.16B, V21.16B }, [X2], #32  // LD1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V5.16B, V6.16B }, [X17], X25  // LD1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V25.4H, V26.4H }, [X3]  // LD1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V10.4H, V11.4H }, [X14], #16  // LD1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V0.4H, V1.4H }, [X24], X15  // LD1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V1.8H, V2.8H }, [X27]  // LD1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V22.8H, V23.8H }, [X13], #32  // LD1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V9.8H, V10.8H }, [X4], X13  // LD1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V6.2S, V7.2S }, [X29]  // LD1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V23.2S, V24.2S }, [X10], #16  // LD1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V26.2S, V27.2S }, [X21], X29  // LD1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V11.4S, V12.4S }, [X30]  // LD1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V23.4S, V24.4S }, [X14], #32  // LD1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V12.4S, V13.4S }, [X27], X22  // LD1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V27.1D, V28.1D }, [X7]  // LD1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V13.1D, V14.1D }, [X29], #16  // LD1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V1.1D, V2.1D }, [X7], X20  // LD1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V13.2D, V14.2D }, [X13]  // LD1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V13.2D, V14.2D }, [X10], #32  // LD1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V20.2D, V21.2D }, [X29], X28  // LD1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V7.8B, V8.8B, V9.8B }, [X12]  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V13.8B, V14.8B, V15.8B }, [X10], #24  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V28.8B, V29.8B, V30.8B }, [X2], X21  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V19.16B, V20.16B, V21.16B }, [X10]  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V8.16B, V9.16B, V10.16B }, [X29], #48  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V14.16B, V15.16B, V16.16B }, [X5], X17  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V10.4H, V11.4H, V12.4H }, [X28]  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V22.4H, V23.4H, V24.4H }, [X6], #24  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V11.4H, V12.4H, V13.4H }, [X13], X23  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V21.8H, V22.8H, V23.8H }, [X22]  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V26.8H, V27.8H, V28.8H }, [X2], #48  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V6.8H, V7.8H, V8.8H }, [X22], X6  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V16.2S, V17.2S, V18.2S }, [X27]  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V3.2S, V4.2S, V5.2S }, [X30], #24  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V14.2S, V15.2S, V16.2S }, [X11], X28  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V0.4S, V1.4S, V2.4S }, [X24]  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V17.4S, V18.4S, V19.4S }, [X28], #48  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V5.4S, V6.4S, V7.4S }, [X20], X13  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V14.1D, V15.1D, V16.1D }, [X3]  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V21.1D, V22.1D, V23.1D }, [X24], #24  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V25.1D, V26.1D, V27.1D }, [X18], X14  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V12.2D, V13.2D, V14.2D }, [X15]  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+  ld1 { V13.2D, V14.2D, V15.2D }, [X4], #48  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V15.2D, V16.2D, V17.2D }, [X10], X6  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+  ld1 { V4.8B, V5.8B, V6.8B, V7.8B }, [X13]  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V8.8B, V9.8B, V10.8B, V11.8B }, [X30], #32  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V4.8B, V5.8B, V6.8B, V7.8B }, [X20], X3  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V13.16B, V14.16B, V15.16B, V16.16B }, [X9]  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+  ld1 { V3.16B, V4.16B, V5.16B, V6.16B }, [X17], #64  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V10.16B, V11.16B, V12.16B, V13.16B }, [X19], X29  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V20.4H, V21.4H, V22.4H, V23.4H }, [X15]  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V4.4H, V5.4H, V6.4H, V7.4H }, [X12], #32  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V24.4H, V25.4H, V26.4H, V27.4H }, [X25], X0  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V0.8H, V1.8H, V2.8H, V3.8H }, [X21]  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+  ld1 { V12.8H, V13.8H, V14.8H, V15.8H }, [X21], #64  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V14.8H, V15.8H, V16.8H, V17.8H }, [X12], X23  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V21.2S, V22.2S, V23.2S, V24.2S }, [X21]  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V27.2S, V28.2S, V29.2S, V30.2S }, [X11], #32  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V24.2S, V25.2S, V26.2S, V27.2S }, [X1], X22  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V15.4S, V16.4S, V17.4S, V18.4S }, [X28]  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+  ld1 { V14.4S, V15.4S, V16.4S, V17.4S }, [X8], #64  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V11.4S, V12.4S, V13.4S, V14.4S }, [X2], X28  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V22.1D, V23.1D, V24.1D, V25.1D }, [X4]  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ld1 { V3.1D, V4.1D, V5.1D, V6.1D }, [X23], #32  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V22.1D, V23.1D, V24.1D, V25.1D }, [X9], X22  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ld1 { V18.2D, V19.2D, V20.2D, V21.2D }, [X6]  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+  ld1 { V3.2D, V4.2D, V5.2D, V6.2D }, [X3], #64  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V6.2D, V7.2D, V8.2D, V9.2D }, [X17], X18  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+  ld1 { V18.B }[3], [X23]  // LD1 { <Vt>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1 { V18.H }[3], [X1]  // LD1 { <Vt>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1 { V8.S }[0], [X24]  // LD1 { <Vt>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1 { V11.D }[0], [X13]  // LD1 { <Vt>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, D  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1 { V23.B }[1], [X13], #1  // LD1 { <Vt>.B }[<indexb>], [<Xn|SP>], #1  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V10.B }[9], [X25], X14  // LD1 { <Vt>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V6.H }[2], [X26], #2  // LD1 { <Vt>.H }[<indexh>], [<Xn|SP>], #2  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V30.H }[6], [X27], X3  // LD1 { <Vt>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V5.S }[1], [X10], #4  // LD1 { <Vt>.S }[<indexs>], [<Xn|SP>], #4  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V13.S }[3], [X6], X24  // LD1 { <Vt>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V26.D }[1], [X28], #8  // LD1 { <Vt>.D }[<indexd>], [<Xn|SP>], #8  \\ ASIMD load, 1 element, one lane, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1 { V1.D }[1], [X20], X30  // LD1 { <Vt>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1b { Z20.B }, P1/Z, [X25]  // LD1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z10.B }, P1/Z, [X16, #-1, MUL VL]  // LD1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z31.H }, P1/Z, [X4]  // LD1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z5.H }, P5/Z, [X8, #6, MUL VL]  // LD1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z1.S }, P3/Z, [X12]  // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z24.S }, P2/Z, [X28, #1, MUL VL]  // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z25.D }, P5/Z, [X2]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z0.D }, P6/Z, [X22, #5, MUL VL]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z7.B }, P0/Z, [X24, X11]  // LD1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z26.H }, P5/Z, [X5, X21]  // LD1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z22.S }, P3/Z, [X16, X12]  // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z7.D }, P5/Z, [X18, X12]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1b { Z2.D }, P0/Z, [X15, Z18.D, UXTW]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1b { Z20.S }, P6/Z, [X2, Z0.S, SXTW]  // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1b { Z15.D }, P4/Z, [X23, Z9.D]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1b { Z8.S }, P4/Z, [Z25.S, #22]  // LD1B { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1b { Z13.D }, P2/Z, [Z3.D, #30]  // LD1B { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1d { Z21.D }, P1/Z, [X24, Z31.D, SXTW #3]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1d { Z7.D }, P0/Z, [X13, Z15.D, SXTW]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1d { Z14.D }, P1/Z, [X26, Z27.D, LSL #3]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1d { Z30.D }, P7/Z, [X14, Z16.D]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1d { Z22.D }, P1/Z, [Z15.D]  // LD1D { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1d { Z8.D }, P4/Z, [Z12.D, #200]  // LD1D { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1h { Z3.H }, P2/Z, [X21]  // LD1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z15.H }, P0/Z, [X25, #-3, MUL VL]  // LD1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z9.S }, P1/Z, [X17]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z1.S }, P3/Z, [X14, #5, MUL VL]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z10.D }, P3/Z, [X9]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z2.D }, P7/Z, [X1, #4, MUL VL]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z26.H }, P5/Z, [X10, X19, LSL #1]  // LD1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z29.S }, P7/Z, [X23, X11, LSL #1]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z2.D }, P5/Z, [X30, X9, LSL #1]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1h { Z14.S }, P7/Z, [X14, Z28.S, SXTW #1]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1h { Z28.D }, P7/Z, [X8, Z9.D, SXTW #1]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1h { Z16.D }, P5/Z, [X7, Z9.D, UXTW]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1h { Z27.S }, P4/Z, [X4, Z7.S, UXTW]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1h { Z6.D }, P7/Z, [X30, Z26.D, LSL #1]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1h { Z11.D }, P2/Z, [X20, Z25.D]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1h { Z6.S }, P7/Z, [Z31.S]  // LD1H { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1h { Z1.S }, P3/Z, [Z12.S, #8]  // LD1H { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1h { Z7.D }, P7/Z, [Z9.D]  // LD1H { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1h { Z13.D }, P3/Z, [Z5.D, #8]  // LD1H { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1r { V8.8B }, [X23]  // LD1R { <Vt>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V4.8B }, [X25], #1  // LD1R { <Vt>.8B }, [<Xn|SP>], #1  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V14.8B }, [X24], X14  // LD1R { <Vt>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V8.16B }, [X24]  // LD1R { <Vt>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V21.16B }, [X30], #1  // LD1R { <Vt>.16B }, [<Xn|SP>], #1  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V1.16B }, [X3], X9  // LD1R { <Vt>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V28.4H }, [X9]  // LD1R { <Vt>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V10.4H }, [X27], #2  // LD1R { <Vt>.4H }, [<Xn|SP>], #2  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V12.4H }, [X8], X20  // LD1R { <Vt>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V3.8H }, [X16]  // LD1R { <Vt>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V27.8H }, [X18], #2  // LD1R { <Vt>.8H }, [<Xn|SP>], #2  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V20.8H }, [X20], X4  // LD1R { <Vt>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V10.2S }, [X20]  // LD1R { <Vt>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V28.2S }, [X8], #4  // LD1R { <Vt>.2S }, [<Xn|SP>], #4  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V4.2S }, [X0], X12  // LD1R { <Vt>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V11.4S }, [X3]  // LD1R { <Vt>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V18.4S }, [X3], #4  // LD1R { <Vt>.4S }, [<Xn|SP>], #4  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V2.4S }, [X4], X1  // LD1R { <Vt>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V3.1D }, [X15]  // LD1R { <Vt>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, D  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V16.1D }, [X2], #8  // LD1R { <Vt>.1D }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, all lanes, D-form, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V24.1D }, [X21], X3  // LD1R { <Vt>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V18.2D }, [X0]  // LD1R { <Vt>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld1r { V8.2D }, [X18], #8  // LD1R { <Vt>.2D }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1r { V8.2D }, [X16], X28  // LD1R { <Vt>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld1rb { Z13.B }, P0/Z, [X9]  // LD1RB { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z30.B }, P6/Z, [X21, #28]  // LD1RB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z10.H }, P1/Z, [X9]  // LD1RB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z25.H }, P3/Z, [X26, #6]  // LD1RB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z24.S }, P2/Z, [X19]  // LD1RB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z16.S }, P1/Z, [X8, #54]  // LD1RB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z17.D }, P7/Z, [X4]  // LD1RB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rb { Z4.D }, P7/Z, [X20, #18]  // LD1RB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rd { Z12.D }, P7/Z, [X20]  // LD1RD { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rd { Z19.D }, P5/Z, [X13, #384]  // LD1RD { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rh { Z13.H }, P7/Z, [X0]  // LD1RH { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rh { Z23.H }, P0/Z, [X18, #56]  // LD1RH { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rh { Z24.S }, P6/Z, [X27]  // LD1RH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rh { Z6.S }, P7/Z, [X1, #84]  // LD1RH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rh { Z3.D }, P4/Z, [X25]  // LD1RH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rh { Z25.D }, P5/Z, [X5, #108]  // LD1RH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqb { Z31.B }, P1/Z, [X6]  // LD1RQB { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqb { Z21.B }, P7/Z, [X29, #112]  // LD1RQB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqb { Z7.B }, P6/Z, [X26, X26]  // LD1RQB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load broadcast, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqd { Z10.D }, P0/Z, [X28]  // LD1RQD { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqd { Z29.D }, P5/Z, [X6, #-16]  // LD1RQD { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqd { Z5.D }, P6/Z, [X7, X8, LSL #3]  // LD1RQD { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous load broadcast, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqh { Z29.H }, P3/Z, [X3]  // LD1RQH { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqh { Z29.H }, P4/Z, [X30, #112]  // LD1RQH { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqh { Z9.H }, P0/Z, [X23, X11, LSL #1]  // LD1RQH { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load broadcast, scalar + scalar + S \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1rqw { Z11.S }, P0/Z, [X26]  // LD1RQW { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqw { Z7.S }, P3/Z, [X16, #-80]  // LD1RQW { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rqw { Z2.S }, P0/Z, [X21, X23, LSL #2]  // LD1RQW { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous load broadcast, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsb { Z6.H }, P6/Z, [X23]  // LD1RSB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsb { Z28.H }, P3/Z, [X21, #43]  // LD1RSB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsb { Z13.S }, P5/Z, [X14]  // LD1RSB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsb { Z26.S }, P3/Z, [X15, #4]  // LD1RSB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsb { Z23.D }, P2/Z, [X21]  // LD1RSB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsb { Z29.D }, P6/Z, [X14, #25]  // LD1RSB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsh { Z25.S }, P2/Z, [X4]  // LD1RSH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsh { Z30.S }, P5/Z, [X6, #124]  // LD1RSH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsh { Z24.D }, P4/Z, [X6]  // LD1RSH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsh { Z14.D }, P3/Z, [X20, #98]  // LD1RSH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsw { Z2.D }, P0/Z, [X23]  // LD1RSW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rsw { Z18.D }, P7/Z, [X11, #0]  // LD1RSW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rw { Z12.S }, P7/Z, [X9]  // LD1RW { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rw { Z25.S }, P7/Z, [X17, #60]  // LD1RW { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rw { Z22.D }, P5/Z, [X1]  // LD1RW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1rw { Z2.D }, P3/Z, [X3, #36]  // LD1RW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z28.H }, P6/Z, [X9]  // LD1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z22.H }, P2/Z, [X19, #7, MUL VL]  // LD1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z22.S }, P3/Z, [X23]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z2.S }, P6/Z, [X22, #-2, MUL VL]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z31.D }, P6/Z, [X10]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z23.D }, P5/Z, [X2, #-4, MUL VL]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z3.H }, P5/Z, [X10, X23]  // LD1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z16.S }, P7/Z, [X27, X16]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z13.D }, P7/Z, [X28, X18]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1sb { Z30.D }, P6/Z, [X22, Z27.D, UXTW]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sb { Z23.S }, P5/Z, [X17, Z10.S, UXTW]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sb { Z23.D }, P2/Z, [X28, Z10.D]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sb { Z14.S }, P4/Z, [Z18.S, #24]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sb { Z5.D }, P0/Z, [Z25.D, #31]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sh { Z8.S }, P3/Z, [X21]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sh { Z29.S }, P4/Z, [X11, #-4, MUL VL]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sh { Z13.D }, P6/Z, [X18]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sh { Z19.D }, P2/Z, [X29, #-3, MUL VL]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sh { Z28.S }, P0/Z, [X6, X28, LSL #1]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1sh { Z26.D }, P0/Z, [X7, X12, LSL #1]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ld1sh { Z22.S }, P3/Z, [X7, Z1.S, UXTW #1]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sh { Z3.D }, P6/Z, [X11, Z14.D, SXTW #1]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sh { Z27.D }, P3/Z, [X19, Z23.D, SXTW]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sh { Z12.S }, P5/Z, [X27, Z13.S, SXTW]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sh { Z9.D }, P0/Z, [X22, Z8.D, LSL #1]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sh { Z22.D }, P0/Z, [X27, Z12.D]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sh { Z1.S }, P2/Z, [Z9.S, #44]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sh { Z11.D }, P5/Z, [Z30.D, #34]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sw { Z7.D }, P1/Z, [X19]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sw { Z28.D }, P1/Z, [X26, #4, MUL VL]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ld1sw { Z26.D }, P4/Z, [X20, X17, LSL #2]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+  ld1sw { Z22.D }, P1/Z, [X14, Z23.D, SXTW #2]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sw { Z4.D }, P3/Z, [X20, Z15.D, SXTW]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sw { Z1.D }, P4/Z, [X20, Z23.D, LSL #2]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1sw { Z2.D }, P7/Z, [X4, Z0.D]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sw { Z12.D }, P7/Z, [Z21.D]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1sw { Z27.D }, P3/Z, [Z10.D, #24]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1w { Z9.S }, P0/Z, [X18, Z9.S, SXTW #2]  // LD1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1w { Z14.D }, P5/Z, [X26, Z2.D, UXTW #2]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1w { Z31.D }, P6/Z, [X17, Z2.D, UXTW]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1w { Z14.S }, P2/Z, [X18, Z28.S, SXTW]  // LD1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1w { Z13.D }, P3/Z, [X5, Z11.D, LSL #2]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1w { Z24.D }, P3/Z, [X2, Z17.D]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1w { Z4.S }, P0/Z, [Z1.S]  // LD1W { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1w { Z17.S }, P6/Z, [Z26.S, #60]  // LD1W { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ld1w { Z31.D }, P7/Z, [Z22.D]  // LD1W { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld1w { Z2.D }, P3/Z, [Z6.D, #116]  // LD1W { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld2 { V13.8B, V14.8B }, [X4]  // LD2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld2 { V20.8B, V21.8B }, [X11], #16  // LD2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld2 { V13.8B, V14.8B }, [X4], X7  // LD2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld2 { V26.16B, V27.16B }, [X16]  // LD2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V15.16B, V16.16B }, [X3], #32  // LD2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V24.16B, V25.16B }, [X7], X30  // LD2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V0.4H, V1.4H }, [X21]  // LD2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld2 { V5.4H, V6.4H }, [X30], #16  // LD2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld2 { V5.4H, V6.4H }, [X22], X1  // LD2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld2 { V8.8H, V9.8H }, [X28]  // LD2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V14.8H, V15.8H }, [X19], #32  // LD2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V28.8H, V29.8H }, [X26], X7  // LD2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V2.2S, V3.2S }, [X16]  // LD2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+  ld2 { V23.2S, V24.2S }, [X5], #16  // LD2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld2 { V22.2S, V23.2S }, [X11], X12  // LD2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+  ld2 { V22.4S, V23.4S }, [X4]  // LD2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V27.4S, V28.4S }, [X18], #32  // LD2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V22.4S, V23.4S }, [X26], X29  // LD2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V22.2D, V23.2D }, [X17]  // LD2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, D  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V12.2D, V13.2D }, [X19], #32  // LD2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V6.2D, V7.2D }, [X11], X24  // LD2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V29.B, V30.B }[3], [X1]  // LD2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, B/H  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V23.H, V24.H }[7], [X14]  // LD2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, B/H  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V26.S, V27.S }[1], [X17]  // LD2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V1.D, V2.D }[0], [X10]  // LD2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, D  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2 { V20.B, V21.B }[9], [X24], #2  // LD2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], #2  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V29.B, V30.B }[6], [X18], X19  // LD2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V2.H, V3.H }[3], [X12], #4  // LD2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], #4  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V11.H, V12.H }[3], [X18], X17  // LD2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V15.S, V16.S }[1], [X7], #8  // LD2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], #8  \\ ASIMD load, 2 element, one lane, S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V29.S, V30.S }[1], [X12], X0  // LD2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V1.D, V2.D }[1], [X3], #16  // LD2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], #16  \\ ASIMD load, 2 element, one lane, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2 { V10.D, V11.D }[1], [X18], X27  // LD2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2b { Z9.B, Z10.B }, P2/Z, [X22]  // LD2B { <Zt1>.B, <Zt2>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2b { Z28.B, Z29.B }, P3/Z, [X22, #4, MUL VL]  // LD2B { <Zt1>.B, <Zt2>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2b { Z26.B, Z27.B }, P1/Z, [X3, X12]  // LD2B { <Zt1>.B, <Zt2>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 2 9  9  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2d { Z12.D, Z13.D }, P5/Z, [X24]  // LD2D { <Zt1>.D, <Zt2>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2d { Z22.D, Z23.D }, P2/Z, [X21, #-2, MUL VL]  // LD2D { <Zt1>.D, <Zt2>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2d { Z22.D, Z23.D }, P6/Z, [X14, X4, LSL #3]  // LD2D { <Zt1>.D, <Zt2>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 2 9  9  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2h { Z5.H, Z6.H }, P5/Z, [X20]  // LD2H { <Zt1>.H, <Zt2>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2h { Z27.H, Z28.H }, P7/Z, [X11, #14, MUL VL]  // LD2H { <Zt1>.H, <Zt2>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2h { Z18.H, Z19.H }, P3/Z, [X9, X17, LSL #1]  // LD2H { <Zt1>.H, <Zt2>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 3 10  10  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitS[2]
+  ld2r { V10.8B, V11.8B }, [X20]  // LD2R { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V18.8B, V19.8B }, [X11], #2  // LD2R { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #2  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V28.8B, V29.8B }, [X30], X14  // LD2R { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V10.16B, V11.16B }, [X23]  // LD2R { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V24.16B, V25.16B }, [X1], #2  // LD2R { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #2  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V20.16B, V21.16B }, [X11], X7  // LD2R { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V25.4H, V26.4H }, [X11]  // LD2R { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V28.4H, V29.4H }, [X18], #4  // LD2R { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #4  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V21.4H, V22.4H }, [X2], X17  // LD2R { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V23.8H, V24.8H }, [X10]  // LD2R { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V19.8H, V20.8H }, [X29], #4  // LD2R { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #4  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V13.8H, V14.8H }, [X13], X5  // LD2R { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V25.2S, V26.2S }, [X19]  // LD2R { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V5.2S, V6.2S }, [X28], #8  // LD2R { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #8  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V4.2S, V5.2S }, [X14], X19  // LD2R { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V8.4S, V9.4S }, [X17]  // LD2R { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V22.4S, V23.4S }, [X5], #8  // LD2R { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #8  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V29.4S, V30.4S }, [X4], X18  // LD2R { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V9.1D, V10.1D }, [X25]  // LD2R { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, D  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V15.1D, V16.1D }, [X26], #16  // LD2R { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, all lanes, D-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V10.1D, V11.1D }, [X28], X26  // LD2R { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V26.2D, V27.2D }, [X8]  // LD2R { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+  ld2r { V14.2D, V15.2D }, [X3], #16  // LD2R { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2r { V24.2D, V25.2D }, [X6], X14  // LD2R { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+  ld2w { Z21.S, Z22.S }, P4/Z, [X12]  // LD2W { <Zt1>.S, <Zt2>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2w { Z29.S, Z30.S }, P2/Z, [X19, #6, MUL VL]  // LD2W { <Zt1>.S, <Zt2>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld2w { Z18.S, Z19.S }, P6/Z, [X22, X22, LSL #2]  // LD2W { <Zt1>.S, <Zt2>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 2 9  9  1.0 V1UnitV01[2],V1UnitL01[2]
+  ld3 { V8.8B, V9.8B, V10.8B }, [X0]  // LD3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V6.8B, V7.8B, V8.8B }, [X26], #24  // LD3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V20.8B, V21.8B, V22.8B }, [X25], X24  // LD3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V15.16B, V16.16B, V17.16B }, [X5]  // LD3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V19.16B, V20.16B, V21.16B }, [X3], #48  // LD3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V26.16B, V27.16B, V28.16B }, [X8], X29  // LD3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V15.4H, V16.4H, V17.4H }, [X8]  // LD3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V4.4H, V5.4H, V6.4H }, [X5], #24  // LD3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V24.4H, V25.4H, V26.4H }, [X25], X0  // LD3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V7.8H, V8.8H, V9.8H }, [X21]  // LD3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V4.8H, V5.8H, V6.8H }, [X26], #48  // LD3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V12.8H, V13.8H, V14.8H }, [X0], X25  // LD3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V16.2S, V17.2S, V18.2S }, [X0]  // LD3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V9.2S, V10.2S, V11.2S }, [X1], #24  // LD3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V27.2S, V28.2S, V29.2S }, [X23], X4  // LD3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V12.4S, V13.4S, V14.4S }, [X25]  // LD3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V12.4S, V13.4S, V14.4S }, [X27], #48  // LD3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V2.4S, V3.4S, V4.4S }, [X22], X21  // LD3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V10.2D, V11.2D, V12.2D }, [X18]  // LD3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V25.2D, V26.2D, V27.2D }, [X4], #48  // LD3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V6.2D, V7.2D, V8.2D }, [X10], X24  // LD3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V17.B, V18.B, V19.B }[2], [X27]  // LD3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V18.H, V19.H, V20.H }[5], [X16]  // LD3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V1.S, V2.S, V3.S }[3], [X14]  // LD3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V5.D, V6.D, V7.D }[1], [X14]  // LD3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3 { V16.B, V17.B, V18.B }[3], [X15], #3  // LD3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], #3  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V14.B, V15.B, V16.B }[4], [X23], X6  // LD3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V11.H, V12.H, V13.H }[1], [X28], #6  // LD3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], #6  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V4.H, V5.H, V6.H }[2], [X5], X15  // LD3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V26.S, V27.S, V28.S }[0], [X14], #12  // LD3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], #12  \\ ASIMD load, 3 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V1.S, V2.S, V3.S }[0], [X26], X20  // LD3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V14.D, V15.D, V16.D }[1], [X30], #24  // LD3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], #24  \\ ASIMD load, 3 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3 { V23.D, V24.D, V25.D }[0], [X24], X14  // LD3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3b { Z29.B, Z30.B, Z31.B }, P3/Z, [X17]  // LD3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3b { Z23.B, Z24.B, Z25.B }, P7/Z, [X12, #18, MUL VL]  // LD3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3b { Z23.B, Z24.B, Z25.B }, P3/Z, [X12, X12]  // LD3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+  ld3d { Z20.D, Z21.D, Z22.D }, P2/Z, [X6]  // LD3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3d { Z1.D, Z2.D, Z3.D }, P2/Z, [X9, #-15, MUL VL]  // LD3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3d { Z13.D, Z14.D, Z15.D }, P6/Z, [X27, X30, LSL #3]  // LD3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+  ld3h { Z26.H, Z27.H, Z28.H }, P1/Z, [X29]  // LD3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3h { Z14.H, Z15.H, Z16.H }, P3/Z, [X18, #9, MUL VL]  // LD3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3h { Z5.H, Z6.H, Z7.H }, P3/Z, [X6, X21, LSL #1]  // LD3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+  ld3r { V24.8B, V25.8B, V26.8B }, [X10]  // LD3R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V14.8B, V15.8B, V16.8B }, [X11], #3  // LD3R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #3  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V22.8B, V23.8B, V24.8B }, [X0], X11  // LD3R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V17.16B, V18.16B, V19.16B }, [X3]  // LD3R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V7.16B, V8.16B, V9.16B }, [X29], #3  // LD3R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #3  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V3.16B, V4.16B, V5.16B }, [X20], X5  // LD3R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V3.4H, V4.4H, V5.4H }, [X1]  // LD3R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V8.4H, V9.4H, V10.4H }, [X3], #6  // LD3R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #6  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V4.4H, V5.4H, V6.4H }, [X0], X28  // LD3R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V6.8H, V7.8H, V8.8H }, [X28]  // LD3R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V4.8H, V5.8H, V6.8H }, [X11], #6  // LD3R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #6  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V3.8H, V4.8H, V5.8H }, [X17], X0  // LD3R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V18.2S, V19.2S, V20.2S }, [X24]  // LD3R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V8.2S, V9.2S, V10.2S }, [X22], #12  // LD3R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #12  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V12.2S, V13.2S, V14.2S }, [X0], X14  // LD3R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V28.4S, V29.4S, V30.4S }, [X2]  // LD3R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V21.4S, V22.4S, V23.4S }, [X22], #12  // LD3R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #12  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V28.4S, V29.4S, V30.4S }, [X13], X25  // LD3R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V1.1D, V2.1D, V3.1D }, [X28]  // LD3R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V0.1D, V1.1D, V2.1D }, [X7], #24  // LD3R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V22.1D, V23.1D, V24.1D }, [X9], X15  // LD3R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V8.2D, V9.2D, V10.2D }, [X3]  // LD3R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld3r { V3.2D, V4.2D, V5.2D }, [X25], #24  // LD3R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3r { V8.2D, V9.2D, V10.2D }, [X18], X13  // LD3R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld3w { Z23.S, Z24.S, Z25.S }, P1/Z, [X8]  // LD3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3w { Z6.S, Z7.S, Z8.S }, P4/Z, [X0, #18, MUL VL]  // LD3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+  ld3w { Z27.S, Z28.S, Z29.S }, P3/Z, [X3, X6, LSL #2]  // LD3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+  ld4 { V6.8B, V7.8B, V8.8B, V9.8B }, [X27]  // LD4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V20.8B, V21.8B, V22.8B, V23.8B }, [X10], #32  // LD4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V18.8B, V19.8B, V20.8B, V21.8B }, [X24], X11  // LD4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V11.16B, V12.16B, V13.16B, V14.16B }, [X5]  // LD4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld4 { V10.16B, V11.16B, V12.16B, V13.16B }, [X12], #64  // LD4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V12.16B, V13.16B, V14.16B, V15.16B }, [X4], X17  // LD4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V21.4H, V22.4H, V23.4H, V24.4H }, [X14]  // LD4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V10.4H, V11.4H, V12.4H, V13.4H }, [X19], #32  // LD4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V5.4H, V6.4H, V7.4H, V8.4H }, [X15], X17  // LD4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V9.8H, V10.8H, V11.8H, V12.8H }, [X1]  // LD4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld4 { V2.8H, V3.8H, V4.8H, V5.8H }, [X0], #64  // LD4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V4.8H, V5.8H, V6.8H, V7.8H }, [X17], X17  // LD4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V23.2S, V24.2S, V25.2S, V26.2S }, [X24]  // LD4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V25.2S, V26.2S, V27.2S, V28.2S }, [X3], #32  // LD4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V22.2S, V23.2S, V24.2S, V25.2S }, [X14], X15  // LD4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V17.4S, V18.4S, V19.4S, V20.4S }, [X4]  // LD4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld4 { V25.4S, V26.4S, V27.4S, V28.4S }, [X19], #64  // LD4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V4.4S, V5.4S, V6.4S, V7.4S }, [X28], X3  // LD4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V2.2D, V3.2D, V4.2D, V5.2D }, [X24]  // LD4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, D  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ld4 { V18.2D, V19.2D, V20.2D, V21.2D }, [X0], #64  // LD4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, D  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V27.2D, V28.2D, V29.2D, V30.2D }, [X27], X4  // LD4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, D  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+  ld4 { V4.B, V5.B, V6.B, V7.B }[12], [X27]  // LD4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V5.H, V6.H, V7.H, V8.H }[0], [X4]  // LD4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V0.S, V1.S, V2.S, V3.S }[0], [X26]  // LD4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V2.D, V3.D, V4.D, V5.D }[0], [X29]  // LD4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4 { V26.B, V27.B, V28.B, V29.B }[4], [X13], #4  // LD4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], #4  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V10.B, V11.B, V12.B, V13.B }[11], [X24], X21  // LD4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V8.H, V9.H, V10.H, V11.H }[0], [X17], #8  // LD4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], #8  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V21.H, V22.H, V23.H, V24.H }[2], [X21], X24  // LD4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V1.S, V2.S, V3.S, V4.S }[1], [X28], #16  // LD4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], #16  \\ ASIMD load, 4 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V20.S, V21.S, V22.S, V23.S }[1], [X27], X16  // LD4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V18.D, V19.D, V20.D, V21.D }[1], [X26], #32  // LD4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], #32  \\ ASIMD load, 4 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4 { V8.D, V9.D, V10.D, V11.D }[0], [X23], X0  // LD4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4b { Z16.B, Z17.B, Z18.B, Z19.B }, P3/Z, [X23]  // LD4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4b { Z7.B, Z8.B, Z9.B, Z10.B }, P5/Z, [X3, #12, MUL VL]  // LD4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4b { Z7.B, Z8.B, Z9.B, Z10.B }, P4/Z, [X20, X12]  // LD4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+  ld4d { Z26.D, Z27.D, Z28.D, Z29.D }, P7/Z, [X10]  // LD4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4d { Z27.D, Z28.D, Z29.D, Z30.D }, P0/Z, [X6, #24, MUL VL]  // LD4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4d { Z7.D, Z8.D, Z9.D, Z10.D }, P4/Z, [X25, X8, LSL #3]  // LD4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+  ld4h { Z4.H, Z5.H, Z6.H, Z7.H }, P4/Z, [X19]  // LD4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4h { Z4.H, Z5.H, Z6.H, Z7.H }, P1/Z, [X16, #-8, MUL VL]  // LD4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4h { Z10.H, Z11.H, Z12.H, Z13.H }, P2/Z, [X8, X28, LSL #1]  // LD4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+  ld4r { V20.8B, V21.8B, V22.8B, V23.8B }, [X23]  // LD4R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V24.8B, V25.8B, V26.8B, V27.8B }, [X15], #4  // LD4R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #4  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V4.8B, V5.8B, V6.8B, V7.8B }, [X26], X6  // LD4R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V1.16B, V2.16B, V3.16B, V4.16B }, [X25]  // LD4R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V1.16B, V2.16B, V3.16B, V4.16B }, [X14], #4  // LD4R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #4  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V0.16B, V1.16B, V2.16B, V3.16B }, [X29], X11  // LD4R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V16.4H, V17.4H, V18.4H, V19.4H }, [X6]  // LD4R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V14.4H, V15.4H, V16.4H, V17.4H }, [X0], #8  // LD4R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #8  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V21.4H, V22.4H, V23.4H, V24.4H }, [X25], X22  // LD4R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V4.8H, V5.8H, V6.8H, V7.8H }, [X23]  // LD4R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V25.8H, V26.8H, V27.8H, V28.8H }, [X7], #8  // LD4R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #8  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V13.8H, V14.8H, V15.8H, V16.8H }, [X19], X27  // LD4R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V0.2S, V1.2S, V2.2S, V3.2S }, [X30]  // LD4R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V23.2S, V24.2S, V25.2S, V26.2S }, [X29], #16  // LD4R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #16  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V19.2S, V20.2S, V21.2S, V22.2S }, [X9], X0  // LD4R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V7.4S, V8.4S, V9.4S, V10.4S }, [X23]  // LD4R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V9.4S, V10.4S, V11.4S, V12.4S }, [X3], #16  // LD4R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #16  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V3.4S, V4.4S, V5.4S, V6.4S }, [X10], X22  // LD4R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V7.1D, V8.1D, V9.1D, V10.1D }, [X26]  // LD4R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V11.1D, V12.1D, V13.1D, V14.1D }, [X5], #32  // LD4R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V12.1D, V13.1D, V14.1D, V15.1D }, [X30], X17  // LD4R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V7.2D, V8.2D, V9.2D, V10.2D }, [X8]  // LD4R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+  ld4r { V12.2D, V13.2D, V14.2D, V15.2D }, [X2], #32  // LD4R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4r { V17.2D, V18.2D, V19.2D, V20.2D }, [X21], X13  // LD4R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+  ld4w { Z18.S, Z19.S, Z20.S, Z21.S }, P6/Z, [X4]  // LD4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4w { Z21.S, Z22.S, Z23.S, Z24.S }, P5/Z, [X16, #-8, MUL VL]  // LD4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+  ld4w { Z25.S, Z26.S, Z27.S, Z28.S }, P2/Z, [X23, X8, LSL #2]  // LD4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+  ldapur W7, [X24]  // LDAPUR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapur W25, [X29, #68]  // LDAPUR <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapur X20, [X13]  // LDAPUR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapur X29, [X4, #-199]  // LDAPUR <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapurb W13, [X17]  // LDAPURB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapurb W20, [X19, #124]  // LDAPURB <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapurh W3, [X22]  // LDAPURH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapurh W1, [X6, #113]  // LDAPURH <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapursb W7, [X8]  // LDAPURSB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapursb W29, [X22, #-76]  // LDAPURSB <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapursb X29, [X7]  // LDAPURSB <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapursb X6, [X0, #-254]  // LDAPURSB <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapursh W17, [X19]  // LDAPURSH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapursh W26, [X18, #-114]  // LDAPURSH <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapursh X3, [X3]  // LDAPURSH <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapursh X13, [X25, #30]  // LDAPURSH <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldapursw X3, [X18]  // LDAPURSW <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldapursw X21, [X25, #0]  // LDAPURSW <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  ldar W9, [X20]  // LDAR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldar W15, [X0, #0]  // LDAR <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldar X5, [X25]  // LDAR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldar X11, [X2, #0]  // LDAR <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldarb W16, [X21]  // LDARB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldarb W14, [X30, #0]  // LDARB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldarh W26, [X25]  // LDARH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldarh W21, [X2, #0]  // LDARH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldaxp W13, W22, [X28]  // LDAXP <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldaxp W11, W19, [X20, #0]  // LDAXP <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldaxp X25, X8, [X16]  // LDAXP <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldaxp X28, X17, [X25, #0]  // LDAXP <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldaxr W4, [X5]  // LDAXR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldaxr W10, [X7, #0]  // LDAXR <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldaxr X22, [X21]  // LDAXR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldaxr X7, [X1, #0]  // LDAXR <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldaxrb W12, [X30]  // LDAXRB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldaxrb W27, [X2, #0]  // LDAXRB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldaxrh W30, [X16]  // LDAXRH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldaxrh W14, [X3, #0]  // LDAXRH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldff1b { Z10.B }, P3/Z, [X10]  // LDFF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z2.B }, P5/Z, [X28, X2]  // LDFF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z2.H }, P0/Z, [X14]  // LDFF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z30.H }, P3/Z, [X25, X18]  // LDFF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z17.S }, P5/Z, [X24]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z17.S }, P7/Z, [X11, X15]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z9.D }, P2/Z, [X3]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z5.D }, P2/Z, [X6, X8]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1b { Z7.D }, P3/Z, [X27, Z19.D, SXTW]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1b { Z13.S }, P3/Z, [X24, Z25.S, SXTW]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1b { Z27.D }, P0/Z, [X13, Z16.D]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1b { Z7.S }, P7/Z, [Z16.S]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1b { Z11.S }, P5/Z, [Z8.S, #25]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1b { Z2.D }, P7/Z, [Z19.D]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1b { Z3.D }, P5/Z, [Z0.D, #11]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1d { Z21.D }, P2/Z, [X20]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1d { Z9.D }, P3/Z, [X28, X30, LSL #3]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1d { Z21.D }, P4/Z, [X11, Z12.D, SXTW #3]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1d { Z6.D }, P4/Z, [X15, Z1.D, UXTW]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1d { Z12.D }, P7/Z, [X11, Z28.D, LSL #3]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1d { Z26.D }, P4/Z, [X30, Z5.D]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1d { Z10.D }, P5/Z, [Z10.D]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1d { Z21.D }, P6/Z, [Z3.D, #48]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1h { Z14.H }, P3/Z, [X22]  // LDFF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1h { Z15.H }, P2/Z, [X24, X8, LSL #1]  // LDFF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1h { Z23.S }, P0/Z, [X12]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1h { Z18.S }, P0/Z, [X7, X25, LSL #1]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1h { Z16.D }, P0/Z, [X11]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1h { Z25.D }, P3/Z, [X24, X19, LSL #1]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1h { Z9.S }, P2/Z, [X3, Z24.S, SXTW #1]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1h { Z7.D }, P0/Z, [X8, Z17.D, UXTW #1]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1h { Z9.D }, P5/Z, [X4, Z10.D, SXTW]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1h { Z4.S }, P4/Z, [X6, Z27.S, UXTW]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1h { Z25.D }, P1/Z, [X29, Z6.D, LSL #1]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1h { Z10.D }, P7/Z, [X1, Z26.D]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1h { Z4.S }, P1/Z, [Z27.S]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1h { Z5.S }, P3/Z, [Z8.S, #62]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1h { Z16.D }, P5/Z, [Z10.D]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1h { Z15.D }, P2/Z, [Z19.D, #34]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sb { Z0.H }, P2/Z, [X2]  // LDFF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sb { Z29.H }, P1/Z, [X16, X21]  // LDFF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sb { Z20.S }, P7/Z, [X8]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sb { Z8.S }, P2/Z, [X4, X14]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sb { Z11.D }, P4/Z, [X6]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sb { Z17.D }, P4/Z, [X16, X10]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sb { Z13.D }, P2/Z, [X28, Z8.D, SXTW]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sb { Z3.S }, P2/Z, [X26, Z24.S, SXTW]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sb { Z10.D }, P7/Z, [X20, Z6.D]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sb { Z18.S }, P3/Z, [Z9.S]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sb { Z25.S }, P2/Z, [Z29.S, #25]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sb { Z8.D }, P0/Z, [Z24.D]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sb { Z7.D }, P0/Z, [Z4.D, #9]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sh { Z2.S }, P2/Z, [X6]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1sh { Z9.S }, P3/Z, [X30, X16, LSL #1]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1sh { Z7.D }, P4/Z, [X30]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1sh { Z1.D }, P0/Z, [X29, X0, LSL #1]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldff1sh { Z25.S }, P4/Z, [X5, Z9.S, SXTW #1]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sh { Z17.D }, P3/Z, [X0, Z25.D, SXTW #1]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sh { Z12.D }, P7/Z, [X5, Z15.D, SXTW]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sh { Z8.S }, P5/Z, [X3, Z21.S, UXTW]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sh { Z14.D }, P6/Z, [X17, Z27.D, LSL #1]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sh { Z23.D }, P4/Z, [X22, Z0.D]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sh { Z6.S }, P4/Z, [Z6.S]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sh { Z3.S }, P7/Z, [Z26.S, #16]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sh { Z25.D }, P3/Z, [Z17.D]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sh { Z2.D }, P3/Z, [Z31.D, #26]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sw { Z16.D }, P2/Z, [X8]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sw { Z27.D }, P1/Z, [X6, X11, LSL #2]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1sw { Z27.D }, P3/Z, [X5, Z20.D, UXTW #2]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sw { Z15.D }, P1/Z, [X13, Z26.D, SXTW]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sw { Z24.D }, P2/Z, [X7, Z23.D, LSL #2]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1sw { Z8.D }, P3/Z, [X5, Z22.D]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sw { Z16.D }, P6/Z, [Z12.D]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1sw { Z3.D }, P1/Z, [Z13.D, #60]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1w { Z2.S }, P5/Z, [X13]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1w { Z9.S }, P3/Z, [X16, X19, LSL #2]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1w { Z31.D }, P6/Z, [X3]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1w { Z30.D }, P4/Z, [X25, X12, LSL #2]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldff1w { Z27.S }, P6/Z, [X10, Z17.S, UXTW #2]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1w { Z8.D }, P4/Z, [X28, Z31.D, SXTW #2]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1w { Z1.D }, P0/Z, [X23, Z14.D, UXTW]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1w { Z17.S }, P5/Z, [X8, Z6.S, UXTW]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1w { Z19.D }, P3/Z, [X7, Z18.D, LSL #2]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1w { Z23.D }, P2/Z, [X16, Z4.D]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1w { Z24.S }, P6/Z, [Z24.S]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1w { Z20.S }, P0/Z, [Z6.S, #36]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+  ldff1w { Z21.D }, P5/Z, [Z12.D]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldff1w { Z29.D }, P2/Z, [Z11.D, #40]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+  ldnf1b { Z17.B }, P5/Z, [X20]  // LDNF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z8.B }, P5/Z, [X26, #1, MUL VL]  // LDNF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z4.H }, P3/Z, [X25]  // LDNF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z31.H }, P3/Z, [X7, #0, MUL VL]  // LDNF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z2.S }, P7/Z, [X25]  // LDNF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z17.S }, P5/Z, [X29, #2, MUL VL]  // LDNF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z6.D }, P5/Z, [X26]  // LDNF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1b { Z18.D }, P4/Z, [X20, #5, MUL VL]  // LDNF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1d { Z5.D }, P6/Z, [X6]  // LDNF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1d { Z19.D }, P0/Z, [X15, #-1, MUL VL]  // LDNF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1h { Z7.H }, P5/Z, [X22]  // LDNF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1h { Z27.H }, P1/Z, [X2, #6, MUL VL]  // LDNF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1h { Z18.S }, P2/Z, [X13]  // LDNF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1h { Z8.S }, P2/Z, [X29, #-8, MUL VL]  // LDNF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1h { Z26.D }, P5/Z, [X5]  // LDNF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1h { Z20.D }, P0/Z, [X29, #-6, MUL VL]  // LDNF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sb { Z17.H }, P0/Z, [X23]  // LDNF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sb { Z14.H }, P0/Z, [X18, #-5, MUL VL]  // LDNF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sb { Z23.S }, P0/Z, [X3]  // LDNF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sb { Z13.S }, P7/Z, [X15, #-8, MUL VL]  // LDNF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sb { Z14.D }, P4/Z, [X7]  // LDNF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sb { Z13.D }, P7/Z, [X25, #6, MUL VL]  // LDNF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sh { Z28.S }, P4/Z, [X9]  // LDNF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sh { Z3.S }, P1/Z, [X14, #-2, MUL VL]  // LDNF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sh { Z1.D }, P2/Z, [X0]  // LDNF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sh { Z14.D }, P3/Z, [X8, #3, MUL VL]  // LDNF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sw { Z8.D }, P4/Z, [X9]  // LDNF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1sw { Z28.D }, P4/Z, [X13, #-7, MUL VL]  // LDNF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1w { Z15.S }, P5/Z, [X27]  // LDNF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1w { Z28.S }, P0/Z, [X28, #-1, MUL VL]  // LDNF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1w { Z28.D }, P5/Z, [X13]  // LDNF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnf1w { Z4.D }, P0/Z, [X12, #2, MUL VL]  // LDNF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnp S1, S13, [X4]  // LDNP <St1>, <St2>, [<Xn|SP>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldnp S30, S5, [X11, #-184]  // LDNP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldnp D3, D12, [X21]  // LDNP <Dt1>, <Dt2>, [<Xn|SP>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldnp D12, D5, [X7, #-424]  // LDNP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldnp Q0, Q14, [X24]  // LDNP <Qt1>, <Qt2>, [<Xn|SP>]  \\ Load vector pair, immed offset, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ldnp Q4, Q1, [X27, #80]  // LDNP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Load vector pair, immed offset, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ldnp W4, W20, [X25]  // LDNP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+  ldnp W30, W4, [X21, #-196]  // LDNP <Wt1>, <Wt2>, [<Xn|SP>, #<imm32>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+  ldnp X7, X30, [X18]  // LDNP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+  ldnp X5, X19, [X1, #-240]  // LDNP <Xt1>, <Xt2>, [<Xn|SP>, #<imm64>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+  ldnt1b { Z9.B }, P2/Z, [X21]  // LDNT1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1b { Z30.B }, P5/Z, [X30, #-3, MUL VL]  // LDNT1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1b { Z10.B }, P5/Z, [X12, X17]  // LDNT1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Non temporal load, scalar + scalar  \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldnt1d { Z27.D }, P2/Z, [X12]  // LDNT1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1d { Z5.D }, P7/Z, [X22, #6, MUL VL]  // LDNT1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1d { Z28.D }, P2/Z, [X14, X0, LSL #3]  // LDNT1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Non temporal load, scalar + scalar  \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldnt1h { Z11.H }, P0/Z, [X21]  // LDNT1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1h { Z19.H }, P1/Z, [X24, #-5, MUL VL]  // LDNT1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1h { Z27.H }, P0/Z, [X22, X24, LSL #1]  // LDNT1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Non temporal load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+  ldnt1w { Z27.S }, P4/Z, [X19]  // LDNT1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1w { Z15.S }, P0/Z, [X22, #3, MUL VL]  // LDNT1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+  ldnt1w { Z25.S }, P4/Z, [X12, X21, LSL #2]  // LDNT1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Non temporal load, scalar + scalar  \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+  ldp S19, S15, [X24], #-64  // LDP <St1>, <St2>, [<Xn|SP>], #<imm32>  \\ Load vector pair, immed post-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+  ldp D9, D1, [X20], #296  // LDP <Dt1>, <Dt2>, [<Xn|SP>], #<imm64>  \\ Load vector pair, immed post-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+  ldp Q18, Q24, [X11], #144  // LDP <Qt1>, <Qt2>, [<Xn|SP>], #<imm128>  \\ Load vector pair, immed post-index, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ldp S10, S30, [X0, #-4]!  // LDP <St1>, <St2>, [<Xn|SP>, #<imm32>]!  \\ Load vector pair, immed pre-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+  ldp D26, D11, [X16, #-304]!  // LDP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]!  \\ Load vector pair, immed pre-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+  ldp Q18, Q12, [X25, #960]!  // LDP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]!  \\ Load vector pair, immed pre-index, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+  ldp S12, S31, [X20, #-192]  // LDP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldp D26, D6, [X22, #-144]  // LDP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldp Q5, Q19, [X9, #-448]  // LDP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Load vector pair, immed offset, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+  ldp W10, W18, [X16], #-96  // LDP <Wt1>, <Wt2>, [<Xn|SP>], #<imm32>  \\ Load pair, immed post-index or immed pre-index, normal, W-form  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldp X13, X16, [X11], #288  // LDP <Xt1>, <Xt2>, [<Xn|SP>], #<imm64>  \\ Load pair, immed post-index or immed pre-index, normal, X-form  \\ 2 4  4  1.0 V1UnitL[3],V1UnitI
+  ldp W7, W16, [X13, #-116]!  // LDP <Wt1>, <Wt2>, [<Xn|SP>, #<imm32>]!  \\ Load pair, immed post-index or immed pre-index, normal, W-form  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldp X26, X3, [X14, #16]!  // LDP <Xt1>, <Xt2>, [<Xn|SP>, #<imm64>]!  \\ Load pair, immed post-index or immed pre-index, normal, X-form  \\ 2 4  4  1.0 V1UnitL[3],V1UnitI
+  ldp W25, W23, [X22]  // LDP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+  ldp W3, W21, [X17, #40]  // LDP <Wt1>, <Wt2>, [<Xn|SP>, #<imm32>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+  ldp X6, X25, [X17]  // LDP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+  ldp X9, X21, [X3, #104]  // LDP <Xt1>, <Xt2>, [<Xn|SP>, #<imm64>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+  ldpsw X23, X26, [X30], #-160  // LDPSW <Xt1>, <Xt2>, [<Xn|SP>], #<imm>  \\ Load pair, immed post-index or immed pre-index, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+  ldpsw X19, X28, [X21, #-248]!  // LDPSW <Xt1>, <Xt2>, [<Xn|SP>, #<imm>]!  \\ Load pair, immed post-index or immed pre-index, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+  ldpsw X13, X20, [X15]  // LDPSW <Xt1>, <Xt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+  ldpsw X9, X27, [X8, #80]  // LDPSW <Xt1>, <Xt2>, [<Xn|SP>, #<imm>]  \\ Load pair, signed immed offset, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+  ldr W13, [X2], #-22  // LDR <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldr X6, [X9], #248  // LDR <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldr W20, [X10, #13]!  // LDR <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldr X23, [X20, #-24]!  // LDR <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldr W19, [X15, #11620]  // LDR <Wt>, [<Xn|SP>, #<pimm32>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldr X2, [X13, #18528]  // LDR <Xt>, [<Xn|SP>, #<pimm64>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldr B0, [X15], #-18  // LDR <Bt>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr H25, [X4], #-156  // LDR <Ht>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr S28, [X6], #162  // LDR <St>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr D23, [X8], #-176  // LDR <Dt>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr Q5, [X18], #70  // LDR <Qt>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr B9, [X0, #-104]!  // LDR <Bt>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr H24, [X10, #34]!  // LDR <Ht>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr S29, [X5, #168]!  // LDR <St>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr D22, [X9, #-1]!  // LDR <Dt>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr Q27, [X20, #-204]!  // LDR <Qt>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+  ldr B23, [X0, #349]  // LDR <Bt>, [<Xn|SP>, #<pimmb>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+  ldr H1, [X15, #3540]  // LDR <Ht>, [<Xn|SP>, #<pimmh>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+  ldr S14, [X7, #16208]  // LDR <St>, [<Xn|SP>, #<pimms>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+  ldr D4, [X17, #7368]  // LDR <Dt>, [<Xn|SP>, #<pimmd>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+  ldr Q14, [X6, #4624]  // LDR <Qt>, [<Xn|SP>, #<pimmq>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+  ldr W15, test  // LDR <Wt>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+  ldr X26, test  // LDR <Xt>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+  ldr S17, test  // LDR <St>, <label>  \\ Load vector reg, literal, S/D/Q forms  \\ 1 6  6  3.0 V1UnitL
+  ldr D10, test  // LDR <Dt>, <label>  \\ Load vector reg, literal, S/D/Q forms  \\ 1 6  6  3.0 V1UnitL
+  ldr Q22, test  // LDR <Qt>, <label>  \\ Load vector reg, literal, S/D/Q forms  \\ 1 6  6  3.0 V1UnitL
+  ldr P0, [X28]  // LDR <Pt>, [<Xn|SP>]  \\ Load predicate  \\ 2 6  6  2.0 V1UnitL,V1UnitM
+  ldr P1, [X6, #-53, MUL VL]  // LDR <Pt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Load predicate  \\ 2 6  6  2.0 V1UnitL,V1UnitM
+  ldr W30, [X10, X0]  // LDR <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldr X13, [X4, X21]  // LDR <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldr W25, [X18, W26, UXTW]  // LDR <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldr X20, [X29, W26, UXTW]  // LDR <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldr W26, [X12, W0, UXTW #2]  // LDR <Wt>, [<Xn|SP>, <Wm>, UXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr X13, [X2, W10, UXTW #3]  // LDR <Xt>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr W13, [X18, W19, SXTW]  // LDR <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldr X5, [X26, W12, SXTW]  // LDR <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldr W16, [X9, W24, SXTW #2]  // LDR <Wt>, [<Xn|SP>, <Wm>, SXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr X21, [X29, W4, SXTW #3]  // LDR <Xt>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr W19, [X15, X1, SXTX]  // LDR <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldr X25, [X4, X20, SXTX]  // LDR <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldr W3, [X1, X17, SXTX #2]  // LDR <Wt>, [<Xn|SP>, <Xm>, SXTX #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr X2, [X13, X26, SXTX #3]  // LDR <Xt>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr W1, [X18, X17, LSL #2]  // LDR <Wt>, [<Xn|SP>, <Xm>, LSL #2]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr X22, [X17, X3, LSL #3]  // LDR <Xt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldr B8, [X30, X10]  // LDR <Bt>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+  ldr B25, [X21, W8, UXTW]  // LDR <Bt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr B7, [X9, W29, SXTW]  // LDR <Bt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr B31, [X17, X6, SXTX]  // LDR <Bt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr H11, [X13, X9]  // LDR <Ht>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+  ldr H6, [X4, W4, UXTW]  // LDR <Ht>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr H28, [X3, W28, SXTW]  // LDR <Ht>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr H3, [X15, X19, SXTX]  // LDR <Ht>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr H24, [X27, W5, UXTW #1]  // LDR <Ht>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr H22, [X28, W11, SXTW #1]  // LDR <Ht>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr H3, [X18, X26, SXTX #1]  // LDR <Ht>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr H8, [X23, X19, LSL #1]  // LDR <Ht>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load vector reg, register offset, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr S21, [X1, X29]  // LDR <St>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+  ldr S12, [X30, W5, UXTW]  // LDR <St>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr S15, [X2, W20, SXTW]  // LDR <St>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr S11, [X25, X20, SXTX]  // LDR <St>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr S9, [X24, W27, UXTW #2]  // LDR <St>, [<Xn|SP>, <Wm>, UXTW #2]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr S7, [X2, W5, SXTW #2]  // LDR <St>, [<Xn|SP>, <Wm>, SXTW #2]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr S13, [X19, X28, SXTX #2]  // LDR <St>, [<Xn|SP>, <Xm>, SXTX #2]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr S21, [X10, X4, LSL #2]  // LDR <St>, [<Xn|SP>, <Xm>, LSL #2]  \\ Load vector reg, register offset, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr D10, [X23, X10]  // LDR <Dt>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+  ldr D24, [X26, W7, UXTW]  // LDR <Dt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr D28, [X12, W2, SXTW]  // LDR <Dt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr D0, [X7, X29, SXTX]  // LDR <Dt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr D24, [X9, W27, UXTW #3]  // LDR <Dt>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr D5, [X17, W2, SXTW #3]  // LDR <Dt>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr D2, [X5, X16, SXTX #3]  // LDR <Dt>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr D2, [X29, X18, LSL #3]  // LDR <Dt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load vector reg, register offset, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+  ldr Q9, [X13, X16]  // LDR <Qt>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+  ldr Q16, [X16, W1, UXTW]  // LDR <Qt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr Q1, [X17, W5, SXTW]  // LDR <Qt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr Q1, [X8, X9, SXTX]  // LDR <Qt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+  ldr Q23, [X26, W23, UXTW #4]  // LDR <Qt>, [<Xn|SP>, <Wm>, UXTW #4]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr Q3, [X18, W23, SXTW #4]  // LDR <Qt>, [<Xn|SP>, <Wm>, SXTW #4]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr Q2, [X28, X30, SXTX #4]  // LDR <Qt>, [<Xn|SP>, <Xm>, SXTX #4]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr Q21, [X23, X27, LSL #4]  // LDR <Qt>, [<Xn|SP>, <Xm>, LSL #4]  \\ Load vector reg, register offset, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+  ldr Z26, [X4]  // LDR <Zt>, [<Xn|SP>]  \\ Load vector  \\ 1 6  6  2.0 V1UnitL01
+  ldr Z18, [X27, #16, MUL VL]  // LDR <Zt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Load vector  \\ 1 6  6  2.0 V1UnitL01
+  ldrb W4, [X17], #0  // LDRB <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrb W27, [X23, #114]!  // LDRB <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrb W26, [X19]  // LDRB <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrb W29, [X18, #3179]  // LDRB <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrb W16, [X25, X9]  // LDRB <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrb W9, [X15, W19, UXTW]  // LDRB <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrb W25, [X7, W0, SXTW]  // LDRB <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrb W0, [X18, X21, SXTX]  // LDRB <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrh W9, [X1], #-2  // LDRH <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrh W12, [X29, #-41]!  // LDRH <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrh W28, [X3]  // LDRH <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrh W27, [X19, #3156]  // LDRH <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrh W20, [X25, X15]  // LDRH <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrh W22, [X0, W24, UXTW]  // LDRH <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrh W6, [X17, W18, SXTW]  // LDRH <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrh W21, [X13, X30, SXTX]  // LDRH <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrh W14, [X21, W21, UXTW #1]  // LDRH <Wt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrh W0, [X29, W13, SXTW #1]  // LDRH <Wt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrh W11, [X20, X0, SXTX #1]  // LDRH <Wt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrh W12, [X17, X27, LSL #1]  // LDRH <Wt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load register, register offset, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsb W12, [X13], #-250  // LDRSB <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsb X10, [X2], #-229  // LDRSB <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsb W5, [X2, #-169]!  // LDRSB <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsb X28, [X12, #-46]!  // LDRSB <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsb W5, [X26]  // LDRSB <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsb W24, [X0, #3862]  // LDRSB <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsb X6, [X0]  // LDRSB <Xt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsb X20, [X0, #653]  // LDRSB <Xt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsb W30, [X22, X21]  // LDRSB <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrsb W24, [X2, W14, UXTW]  // LDRSB <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsb W7, [X1, W8, SXTW]  // LDRSB <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsb W4, [X8, X25, SXTX]  // LDRSB <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsb X12, [X28, X27]  // LDRSB <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrsb X10, [X5, W9, UXTW]  // LDRSB <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsb X19, [X23, W24, SXTW]  // LDRSB <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsb X20, [X10, X13, SXTX]  // LDRSB <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W5, [X0], #-115  // LDRSH <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsh X30, [X18], #-50  // LDRSH <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsh W27, [X15, #-45]!  // LDRSH <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsh X14, [X24, #27]!  // LDRSH <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsh W18, [X13]  // LDRSH <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W11, [X27, #4094]  // LDRSH <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsh X19, [X26]  // LDRSH <Xt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsh X19, [X9, #6652]  // LDRSH <Xt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W18, [X30, X24]  // LDRSH <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W13, [X25, W7, UXTW]  // LDRSH <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W3, [X16, W28, SXTW]  // LDRSH <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W0, [X13, X14, SXTX]  // LDRSH <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh W0, [X5, W21, UXTW #1]  // LDRSH <Wt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh W26, [X6, W29, SXTW #1]  // LDRSH <Wt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh W22, [X26, X15, SXTX #1]  // LDRSH <Wt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh W26, [X20, X21, LSL #1]  // LDRSH <Wt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load register, register offset, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh X4, [X9, X24]  // LDRSH <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrsh X25, [X8, W13, UXTW]  // LDRSH <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh X25, [X20, W10, SXTW]  // LDRSH <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh X6, [X13, X10, SXTX]  // LDRSH <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsh X15, [X0, W28, UXTW #1]  // LDRSH <Xt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh X19, [X9, W15, SXTW #1]  // LDRSH <Xt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh X1, [X17, X26, SXTX #1]  // LDRSH <Xt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsh X7, [X29, X17, LSL #1]  // LDRSH <Xt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load register, register offset, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+  ldrsw X4, [X21], #-93  // LDRSW <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsw X6, [X28, #96]!  // LDRSW <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+  ldrsw X1, [X23]  // LDRSW <Xt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X6, [X19, #4552]  // LDRSW <Xt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X20, test  // LDRSW <Xt>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X21, [X25, X7]  // LDRSW <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X12, [X28, W12, UXTW]  // LDRSW <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X22, [X26, W21, SXTW]  // LDRSW <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X0, [X21, X19, SXTX]  // LDRSW <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X23, [X17, W19, UXTW #2]  // LDRSW <Xt>, [<Xn|SP>, <Wm>, UXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X23, [X30, W11, SXTW #2]  // LDRSW <Xt>, [<Xn|SP>, <Wm>, SXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X29, [X12, X5, SXTX #2]  // LDRSW <Xt>, [<Xn|SP>, <Xm>, SXTX #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldrsw X3, [X1, X17, LSL #2]  // LDRSW <Xt>, [<Xn|SP>, <Xm>, LSL #2]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  ldtr W12, [X9]  // LDTR <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtr W9, [X3, #-55]  // LDTR <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtr X9, [X9]  // LDTR <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtr X25, [X1, #103]  // LDTR <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrb W27, [X7]  // LDTRB <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrb W8, [X1, #-90]  // LDTRB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrh W13, [X21]  // LDTRH <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrh W10, [X15, #-67]  // LDTRH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsb W15, [X19]  // LDTRSB <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsb W28, [X19, #-202]  // LDTRSB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsb X17, [X6]  // LDTRSB <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsb X0, [X11, #180]  // LDTRSB <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsh W19, [X26]  // LDTRSH <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsh W16, [X28, #-233]  // LDTRSH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsh X26, [X22]  // LDTRSH <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsh X27, [X19, #-76]  // LDTRSH <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsw X23, [X28]  // LDTRSW <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldtrsw X26, [X21, #45]  // LDTRSW <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+  ldur B24, [X3]  // LDUR <Bt>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur B9, [X25, #240]  // LDUR <Bt>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur H29, [X21]  // LDUR <Ht>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur H5, [X23, #-5]  // LDUR <Ht>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur S12, [X14]  // LDUR <St>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur S22, [X10, #108]  // LDUR <St>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur D16, [X14]  // LDUR <Dt>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur D22, [X24, #-198]  // LDUR <Dt>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur Q25, [X9]  // LDUR <Qt>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur Q5, [X24, #233]  // LDUR <Qt>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+  ldur W19, [X30]  // LDUR <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldur W24, [X12, #202]  // LDUR <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldur X0, [X3]  // LDUR <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldur X14, [X14, #17]  // LDUR <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldurb W9, [X24]  // LDURB <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldurb W12, [X5, #92]  // LDURB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldurh W27, [X14]  // LDURH <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldurh W13, [X30, #-173]  // LDURH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursb W5, [X8]  // LDURSB <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursb W21, [X10, #172]  // LDURSB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursb X19, [X15]  // LDURSB <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursb X16, [X11, #-173]  // LDURSB <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursh W21, [X12]  // LDURSH <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursh W16, [X18, #203]  // LDURSH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursh X4, [X28]  // LDURSH <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursh X5, [X3, #-133]  // LDURSH <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursw X21, [X7]  // LDURSW <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldursw X11, [X16, #169]  // LDURSW <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  ldxp W23, W14, [X17]  // LDXP <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldxp W2, W8, [X21, #0]  // LDXP <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldxp X5, X6, [X30]  // LDXP <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldxp X10, X26, [X6, #0]  // LDXP <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldxr W4, [X9]  // LDXR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldxr W7, [X3, #0]  // LDXR <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldxr X6, [X27]  // LDXR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldxr X3, [X4, #0]  // LDXR <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldxrb W17, [X21]  // LDXRB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldxrb W14, [X3, #0]  // LDXRB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  ldxrh W14, [X1]  // LDXRH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  ldxrh W24, [X11, #0]  // LDXRH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  lsl W25, W0, #22  // LSL <Wd>, <Wn>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  lsl X27, X7, #56  // LSL <Xd>, <Xn>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  lsl Z1.B, P1/M, Z1.B, #3  // LSL <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z7.H, P3/M, Z7.H, #5  // LSL <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z10.S, P3/M, Z10.S, #7  // LSL <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z21.D, P7/M, Z21.D, #28  // LSL <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z13.B, Z4.B, #2  // LSL <Zd>.B, <Zn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z11.H, Z16.H, #1  // LSL <Zd>.H, <Zn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z16.S, Z11.S, #6  // LSL <Zd>.S, <Zn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z18.D, Z4.D, #26  // LSL <Zd>.D, <Zn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl W4, W9, W12  // LSL <Wd>, <Wn>, <Wm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+  lsl X7, X29, X22  // LSL <Xd>, <Xn>, <Xm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+  lsl Z3.D, P2/M, Z3.D, Z15.D  // LSL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z3.S, P6/M, Z3.S, Z8.D  // LSL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsl Z19.S, Z25.S, Z25.D  // LSL <Zd>.<T>, <Zn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lslr Z3.H, P5/M, Z3.H, Z23.H  // LSLR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lslv W6, W8, W2  // LSLV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  lslv X7, X26, X21  // LSLV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  lsr W0, W0, #30  // LSR <Wd>, <Wn>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  lsr X23, X24, #23  // LSR <Xd>, <Xn>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  lsr Z21.B, P5/M, Z21.B, #3  // LSR <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z1.H, P4/M, Z1.H, #5  // LSR <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z24.S, P7/M, Z24.S, #9  // LSR <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z13.D, P3/M, Z13.D, #4  // LSR <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z3.B, Z11.B, #3  // LSR <Zd>.B, <Zn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z5.H, Z12.H, #2  // LSR <Zd>.H, <Zn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z21.S, Z16.S, #15  // LSR <Zd>.S, <Zn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z21.D, Z15.D, #8  // LSR <Zd>.D, <Zn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr W17, W20, W15  // LSR <Wd>, <Wn>, <Wm>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  lsr X24, X4, X20  // LSR <Xd>, <Xn>, <Xm>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  lsr Z30.D, P3/M, Z30.D, Z28.D  // LSR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z18.H, P3/M, Z18.H, Z29.D  // LSR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsr Z7.H, Z30.H, Z11.D  // LSR <Zd>.<T>, <Zn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsrr Z14.B, P1/M, Z14.B, Z16.B  // LSRR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+  lsrv W0, W28, W19  // LSRV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  lsrv X16, X22, X19  // LSRV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  mad Z17.B, P7/M, Z4.B, Z5.B  // MAD <Zdn>.B, <Pg>/M, <Zm>.B, <Za>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mad Z29.H, P4/M, Z31.H, Z18.H  // MAD <Zdn>.H, <Pg>/M, <Zm>.H, <Za>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mad Z7.S, P4/M, Z5.S, Z29.S  // MAD <Zdn>.S, <Pg>/M, <Zm>.S, <Za>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mad Z28.D, P7/M, Z18.D, Z2.D  // MAD <Zdn>.D, <Pg>/M, <Zm>.D, <Za>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+  madd W15, W9, W9, W29  // MADD <Wd>, <Wn>, <Wm>, <Wa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+  madd X29, X22, X21, X21  // MADD <Xd>, <Xn>, <Xm>, <Xa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+  mla V15.8H, V22.8H, V4.H[3]  // MLA <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+  mla V28.2S, V10.2S, V2.S[0]  // MLA <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+  mla V31.4S, V18.4S, V27.4S  // MLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+  mla Z1.B, P0/M, Z3.B, Z3.B  // MLA <Zda>.B, <Pg>/M, <Zn>.B, <Zm>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mla Z21.H, P2/M, Z31.H, Z30.H  // MLA <Zda>.H, <Pg>/M, <Zn>.H, <Zm>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mla Z24.S, P3/M, Z11.S, Z9.S  // MLA <Zda>.S, <Pg>/M, <Zn>.S, <Zm>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mla Z2.D, P0/M, Z12.D, Z5.D  // MLA <Zda>.D, <Pg>/M, <Zn>.D, <Zm>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+  mls V25.8H, V29.8H, V0.H[4]  // MLS <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+  mls V22.2S, V29.2S, V0.S[3]  // MLS <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+  mls V26.4S, V5.4S, V28.4S  // MLS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+  mls Z11.B, P1/M, Z28.B, Z6.B  // MLS <Zda>.B, <Pg>/M, <Zn>.B, <Zm>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mls Z31.H, P0/M, Z25.H, Z24.H  // MLS <Zda>.H, <Pg>/M, <Zn>.H, <Zm>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mls Z1.S, P5/M, Z7.S, Z13.S  // MLS <Zda>.S, <Pg>/M, <Zn>.S, <Zm>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  mls Z2.D, P1/M, Z17.D, Z10.D  // MLS <Zda>.D, <Pg>/M, <Zn>.D, <Zm>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+  mneg W14, W30, W30  // MNEG <Wd>, <Wn>, <Wm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+  mneg X21, X3, X9  // MNEG <Xd>, <Xn>, <Xm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+  mov Z9.S, P2/M, S10  // MOV <Zd>.<T>, <Pg>/M, <V><n>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z17.B, Z29.B[38]  // MOV <Zd>.B, <Zn>.B[<immb>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z26.H, Z7.H[16]  // MOV <Zd>.H, <Zn>.H[<immh>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z14.S, Z21.S[13]  // MOV <Zd>.S, <Zn>.S[<imms>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z22.D, Z14.D[2]  // MOV <Zd>.D, <Zn>.D[<immd>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z21.S, S25  // MOV <Zd>.<T>, <V><n>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov WSP, #0xe00  // MOV <Wd|WSP>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  mov X3, #0x1e00  // MOV <Xd|SP>, #<immd>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  mov V30.B[12], V17.B[14]  // MOV <Vd>.B[<index1b>], <Vn>.B[<index2b>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  mov V10.H[3], V17.H[5]  // MOV <Vd>.H[<index1h>], <Vn>.H[<index2h>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  mov V19.S[2], V2.S[1]  // MOV <Vd>.S[<index1s>], <Vn>.S[<index2s>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  mov V21.D[1], V16.D[0]  // MOV <Vd>.D[<index1d>], <Vn>.D[<index2d>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+  mov V5.B[12], W23  // MOV <Vd>.B[<indexb>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  mov V27.H[6], W6  // MOV <Vd>.H[<indexh>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  mov V21.S[0], W21  // MOV <Vd>.S[<indexs>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  mov V13.D[0], X10  // MOV <Vd>.D[<indexd>], X<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+  mov Z30.B, P7/M, #77  // MOV <Zd>.B, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z30.D, P7/M, #-89  // MOV <Zd>.<T>, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z10.H, P5/M, #72, LSL #0  // MOV <Zd>.<T>, <Pg>/M, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z19.B, P6/Z, #0  // MOV <Zd>.B, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z6.D, P1/Z, #-109  // MOV <Zd>.<T>, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z12.D, P7/Z, #40, LSL #8  // MOV <Zd>.<T>, <Pg>/Z, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+  mov Z30.B, #-31  // MOV <Zd>.B, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z2.H, #-56  // MOV <Zd>.<T>, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z20.H, #82, LSL #8  // MOV <Zd>.<T>, #<imm>, <shift>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+  mov W24, #0xe00  // MOV <Wd>, #<imms>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  mov X15, #0xe00  // MOV <Xd>, #<immd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  mov P0.B, P0/M, P6.B  // MOV <Pd>.B, <Pg>/M, <Pn>.B  \\ Predicate select  \\ 1 1  1  1.0 V1UnitM0
+  mov P3.B, P7/Z, P2.B  // MOV <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  mov W21, W11  // MOV <Wd>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  mov X14, X0  // MOV <Xd>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  mov B15, V21.B[8]  // MOV B<d>, <Vn>.B[<indexb>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  mov H13, V17.H[3]  // MOV H<d>, <Vn>.H[<indexh>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  mov S7, V11.S[0]  // MOV S<d>, <Vn>.S[<indexs>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  mov D27, V24.D[1]  // MOV D<d>, <Vn>.D[<indexd>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+  mov Z12.D, P5/M, X24  // MOV <Zd>.<T>, <Pg>/M, <R><n>  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+  mov Z31.D, P6/M, SP  // MOV <Zd>.<T>, <Pg>/M, <R2>SP  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+  mov Z19.B, W27  // MOV <Zd>.<T>, <R><n>  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+  mov Z17.H, WSP  // MOV <Zd>.<T>, <R2>SP  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+  mov W13, V12.S[2]  // MOV <Wd>, <Vn>.S[<indexs>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  mov X30, V18.D[0]  // MOV <Xd>, <Vn>.D[<indexd>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  mov WSP, WSP  // MOV <Wd|WSP>, <Wn|WSP>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  mov X1, X11  // MOV <Xd|SP>, <Xn|SP>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  mov V12.16B, V6.16B  // MOV <Vd>.<T>, <Vn>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  mov Z1.D, P3/M, Z6.D  // MOV <Zd>.<T>, <Pv>/M, <Zn>.<T>  \\ Select, vector form  \\ 1 2  2  2.0 V1UnitV01
+  mov Z24.D, Z25.D  // MOV <Zd>.D, <Zn>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  mov W30, #0xe00  // MOV <Wd>, #<imms>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  mov X4, #0xe00  // MOV <Xd>, #<immd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  mov Z14.B, #0x70  // MOV <Zd>.B, #<constb>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  mov Z8.H, #0x60  // MOV <Zd>.H, #<consth>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  mov Z2.S, #0x2  // MOV <Zd>.S, #<consts>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  mov Z6.D, #0x4  // MOV <Zd>.D, #<constd>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+  mov P2.B, P5.B  // MOV <Pd>.B, <Pn>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  movi V7.16B, #177  // MOVI <Vd>.<Tb>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi V14.8H, #174  // MOVI <Vd>.<Th>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi V13.4H, #74, LSL #8  // MOVI <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi V19.2S, #226  // MOVI <Vd>.<Ts>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi V0.2S, #137, LSL #24  // MOVI <Vd>.<Ts>, #<imm8>, LSL #<amounts>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi V1.4S, #122, MSL #8  // MOVI <Vd>.<Ts>, #<imm8>, MSL #<amountones>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi D16, #0  // MOVI <Dd>, #<imm>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movi V13.2D, #0xff00ff00ff00ff00  // MOVI <Vd>.2D, #<imm>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  movk W8, #57951  // MOVK <Wd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movk W6, #34540, LSL #0  // MOVK <Wd>, #<imm>, LSL #<shifts>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movk X1, #56641  // MOVK <Xd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movk X23, #3111, LSL #48  // MOVK <Xd>, #<imm>, LSL #<shiftd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movn W16, #52526  // MOVN <Wd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movn W27, #47742, LSL #0  // MOVN <Wd>, #<imm>, LSL #<shifts>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movn X10, #63431  // MOVN <Xd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movn X0, #58015, LSL #48  // MOVN <Xd>, #<imm>, LSL #<shiftd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movprfx Z22.B, P0/M, Z4.B  // MOVPRFX <Zd>.<T>, <Pg>/<ZM>, <Zn>.<T>  \\ Move prefix  \\ 1 2  2  2.0 V1UnitV01
+  mla Z22.B, P0/M, Z19.B, Z25.B // Ignore
+  movprfx Z3, Z26  // MOVPRFX <Zd>, <Zn>  \\ Move prefix  \\ 1 2  2  2.0 V1UnitV01
+  fmla Z3.D, P0/M, Z8.D, Z19.D // Ignore
+  movs P0.B, P7/Z, P3.B  // MOVS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  movs P4.B, P0.B  // MOVS <Pd>.B, <Pn>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  movz W3, #9629  // MOVZ <Wd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movz W23, #10835, LSL #16  // MOVZ <Wd>, #<imm>, LSL #<shifts>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movz X0, #22630  // MOVZ <Xd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  movz X11, #20464, LSL #48  // MOVZ <Xd>, #<imm>, LSL #<shiftd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+  mrs X4, ACTLR_EL1  // MRS <Xt>, <systemreg>  \\ No description \\ No scheduling info
+  mrs X14, S2_4_C0_C5_4  // MRS <Xt>, S<op0>_<op1>_<Cn>_<Cm>_<op2>  \\ No description \\ No scheduling info
+  msb Z18.B, P1/M, Z27.B, Z0.B  // MSB <Zdn>.B, <Pg>/M, <Zm>.B, <Za>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  msb Z27.H, P5/M, Z23.H, Z1.H  // MSB <Zdn>.H, <Pg>/M, <Zm>.H, <Za>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  msb Z26.S, P2/M, Z0.S, Z2.S  // MSB <Zdn>.S, <Pg>/M, <Zm>.S, <Za>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+  msb Z1.D, P6/M, Z12.D, Z12.D  // MSB <Zdn>.D, <Pg>/M, <Zm>.D, <Za>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+  msr DAIFSet, #0  // MSR <pstatefield1>, #<imm1>  \\ No description \\ No scheduling info
+  msr SPSel, #0  // MSR <pstatefield2>, #<imm2>  \\ No description \\ No scheduling info
+  msr ACTLR_EL3, X18  // MSR <systemreg>, <Xt>  \\ No description \\ No scheduling info
+  msr S3_6_C8_C12_1, X23  // MSR S<op0>_<op1>_<Cn>_<Cm>_<op2>, <Xt>  \\ No description \\ No scheduling info
+  msub W6, W26, W13, W13  // MSUB <Wd>, <Wn>, <Wm>, <Wa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+  msub X14, X28, X9, X3  // MSUB <Xd>, <Xn>, <Xm>, <Xa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+  mul V26.4H, V20.4H, V14.H[5]  // MUL <Vd>.4H, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  mul V5.8H, V21.8H, V3.H[7]  // MUL <Vd>.8H, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  mul V29.2S, V10.2S, V3.S[1]  // MUL <Vd>.2S, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  mul V30.4S, V11.4S, V4.S[0]  // MUL <Vd>.4S, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  mul Z16.B, Z16.B, #-118  // MUL <Zdn>.B, <Zdn>.B, #<imm>  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  mul Z9.H, Z9.H, #-56  // MUL <Zdn>.H, <Zdn>.H, #<imm>  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  mul Z23.S, Z23.S, #74  // MUL <Zdn>.S, <Zdn>.S, #<imm>  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  mul Z15.D, Z15.D, #20  // MUL <Zdn>.D, <Zdn>.D, #<imm>  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+  mul V3.8H, V9.8H, V8.8H  // MUL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  mul Z17.B, P6/M, Z17.B, Z9.B  // MUL <Zdn>.B, <Pg>/M, <Zdn>.B, <Zm>.B  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  mul Z18.H, P7/M, Z18.H, Z15.H  // MUL <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  mul Z29.S, P6/M, Z29.S, Z8.S  // MUL <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  mul Z25.D, P1/M, Z25.D, Z25.D  // MUL <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+  mul W8, W13, W20  // MUL <Wd>, <Wn>, <Wm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+  mul X12, X8, X25  // MUL <Xd>, <Xn>, <Xm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+  mvn W0, W18  // MVN <Wd>, <Wm>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+  mvn W25, W27, ASR #6  // MVN <Wd>, <Wm>, <shift> #<wamount>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+  mvn X1, X21  // MVN <Xd>, <Xm>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+  mvn X9, X23, ASR #39  // MVN <Xd>, <Xm>, <shift> #<amount>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+  mvn V16.16B, V24.16B  // MVN <Vd>.<T>, <Vn>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  mvni V9.4H, #237  // MVNI <Vd>.<Th>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  mvni V8.8H, #171, LSL #8  // MVNI <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  mvni V7.2S, #81  // MVNI <Vd>.<Ts>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  mvni V22.4S, #15, LSL #8  // MVNI <Vd>.<Ts>, #<imm8>, LSL #<amounts>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  mvni V12.4S, #141, MSL #8  // MVNI <Vd>.<Ts>, #<imm8>, MSL #<amountones>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+  nand P5.B, P4/Z, P5.B, P5.B  // NAND <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  nands P6.B, P3/Z, P4.B, P5.B  // NANDS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  neg W25, W20, LSL #4  // NEG <Wd>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+  neg W0, W29, LSL #9  // NEG <Wd>, <Wm>, LSL #<wamounth>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+  neg W7, W28, ASR #24  // NEG <Wd>, <Wm>, <shift> #<wamount>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+  neg X29, X11, LSL #3  // NEG <Xd>, <Xm>, LSL #<amountl>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+  neg X24, X10, LSL #54  // NEG <Xd>, <Xm>, LSL #<amounth>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+  neg X0, X16, LSR #2  // NEG <Xd>, <Xm>, <shift> #<amount>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+  neg D18, D20  // NEG <V><d>, <V><n>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  neg V16.2D, V14.2D  // NEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  neg Z16.B, P2/M, Z15.B  // NEG <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  negs W30, W22, LSL #2  // NEGS <Wd>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  negs W8, W8, LSL #15  // NEGS <Wd>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  negs W12, W21, ASR #15  // NEGS <Wd>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  negs X24, X23, LSL #1  // NEGS <Xd>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  negs X20, X13, LSL #20  // NEGS <Xd>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  negs X1, X22, LSR #30  // NEGS <Xd>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  ngc W11, W9  // NGC <Wd>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  ngc X30, X4  // NGC <Xd>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  ngcs W13, W22  // NGCS <Wd>, <Wm>  \\ No description \\ No scheduling info
+  ngcs X15, X1  // NGCS <Xd>, <Xm>  \\ No description \\ No scheduling info
+  nop  // NOP  \\ No description \\ No scheduling info
+  nor P4.B, P4/Z, P0.B, P4.B  // NOR <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  nors P1.B, P0/Z, P7.B, P6.B  // NORS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  not P7.B, P2/Z, P6.B  // NOT <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  not Z29.S, P4/M, Z9.S  // NOT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  not V15.8B, V29.8B  // NOT <Vd>.<T>, <Vn>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  nots P7.B, P3/Z, P1.B  // NOTS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  orn Z5.B, Z5.B, #0x70  // ORN <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orn Z14.H, Z14.H, #0x60  // ORN <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orn Z14.S, Z14.S, #0x2  // ORN <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orn Z27.D, Z27.D, #0x4  // ORN <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orn P1.B, P2/Z, P3.B, P5.B  // ORN <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  orn W2, W27, W7  // ORN <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orn W6, W28, W14, LSL #19  // ORN <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orn X22, X12, X3  // ORN <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orn X19, X17, X0, LSL #58  // ORN <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orn V29.8B, V19.8B, V16.8B  // ORN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  orns P3.B, P3/Z, P0.B, P3.B  // ORNS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  orr WSP, W27, #0xe00  // ORR <Wd|WSP>, <Wn>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  orr X27, X6, #0x1e00  // ORR <Xd|SP>, <Xn>, #<immd>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  orr Z4.B, Z4.B, #0x70  // ORR <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orr Z26.H, Z26.H, #0x60  // ORR <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orr Z3.S, Z3.S, #0x2  // ORR <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orr Z30.D, Z30.D, #0x4  // ORR <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orr P6.B, P4/Z, P4.B, P3.B  // ORR <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+  orr W14, W1, W23  // ORR <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orr W25, W22, W0, ASR #20  // ORR <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orr X11, X6, X13  // ORR <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orr X26, X26, X7, LSL #62  // ORR <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+  orr V9.4H, #18  // ORR <Vd>.<Th>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  orr V20.8H, #175, LSL #0  // ORR <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  orr V4.4S, #0  // ORR <Vd>.<T>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  orr V17.4S, #119, LSL #24  // ORR <Vd>.<T>, #<imm8>, LSL #<amount>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  orr V12.16B, V9.16B, V1.16B  // ORR <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+  orr Z28.H, P3/M, Z28.H, Z7.H  // ORR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orr Z8.D, Z14.D, Z19.D  // ORR <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+  orrs P7.B, P7/Z, P6.B, P5.B  // ORRS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+  orv D19, P6, Z31.D  // ORV <V><d>, <Pg>, <Zn>.<T>  \\ Reduction, logical   \\ 1 12  12  0.5 V1UnitV01[4]
+  pfalse P6.B  // PFALSE <Pd>.B  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  pfirst P0.B, P5, P0.B  // PFIRST <Pdn>.B, <Pg>, <Pdn>.B  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  pmul V30.8B, V0.8B, V27.8B  // PMUL <Vd>.8B, <Vn>.8B, <Vm>.8B  \\ ASIMD multiply/multiply long (8x8) polynomial, D-form  \\ 1 3  3  2.0 V1UnitV01
+  pmul V7.16B, V20.16B, V18.16B  // PMUL <Vd>.16B, <Vn>.16B, <Vm>.16B  \\ ASIMD multiply/multiply long (8x8) polynomial, Q-form  \\ 1 3  3  2.0 V1UnitV01
+  pnext P5.S, P5, P5.S  // PNEXT <Pdn>.<T>, <Pv>, <Pdn>.<T>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  prfb #14, P5, [X21]  // PRFB #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfb #14, P3, [X28, #-24, MUL VL]  // PRFB #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfb PSTL1STRM, P7, [X5]  // PRFB <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfb PLDL2KEEP, P1, [X12, #11, MUL VL]  // PRFB <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfb PLDL1KEEP, P7, [X4, X9]  // PRFB <prfop>, <Pg>, [<Xn|SP>, <Xm>]  \\ No description \\ No scheduling info
+  prfb PLDL3STRM, P4, [X3, Z15.S, UXTW]  // PRFB <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ No description \\ No scheduling info
+  prfb PLDL1STRM, P7, [X28, Z4.D, UXTW]  // PRFB <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ No description \\ No scheduling info
+  prfb PSTL3KEEP, P2, [X18, Z19.D]  // PRFB <prfop>, <Pg>, [<Xn|SP>, <Zm>.D]  \\ No description \\ No scheduling info
+  prfb #12, P1, [Z28.S]  // PRFB #<imm4>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfb #8, P0, [Z22.S, #21]  // PRFB #<imm4>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfb PSTL1STRM, P2, [Z25.S]  // PRFB <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfb PSTL2STRM, P1, [Z31.S, #18]  // PRFB <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfb #11, P5, [Z25.D]  // PRFB #<imm4>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfb #2, P2, [Z4.D, #10]  // PRFB #<imm4>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  prfb PSTL2KEEP, P5, [Z5.D]  // PRFB <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfb PLDL1KEEP, P1, [Z31.D, #17]  // PRFB <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  prfd #13, P3, [X21]  // PRFD #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfd #4, P5, [X3, #-7, MUL VL]  // PRFD #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfd PSTL3KEEP, P0, [X29]  // PRFD <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfd PLDL1STRM, P3, [X15, #-16, MUL VL]  // PRFD <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfd PSTL2KEEP, P3, [X24, X24, LSL #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ No description \\ No scheduling info
+  prfd PSTL1STRM, P3, [X27, Z27.S, SXTW #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #3]  \\ No description \\ No scheduling info
+  prfd PSTL1KEEP, P0, [X21, Z2.D, UXTW #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ No description \\ No scheduling info
+  prfd PLDL1STRM, P7, [X22, Z22.D, LSL #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, LSL #3]  \\ No description \\ No scheduling info
+  prfd #3, P1, [Z2.S]  // PRFD #<imm4>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfd #8, P7, [Z10.S, #72]  // PRFD #<imm4>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfd PSTL1KEEP, P3, [Z19.S]  // PRFD <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfd PSTL2STRM, P4, [Z26.S, #248]  // PRFD <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfd #15, P1, [Z17.D]  // PRFD #<imm4>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfd #3, P0, [Z6.D, #24]  // PRFD #<imm4>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  prfd PSTL1KEEP, P3, [Z31.D]  // PRFD <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfd PSTL1STRM, P7, [Z10.D, #40]  // PRFD <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  prfh #3, P3, [X17]  // PRFH #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfh #6, P3, [X6, #19, MUL VL]  // PRFH #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfh PLDL3KEEP, P6, [X2]  // PRFH <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfh PLDL2KEEP, P6, [X18, #-4, MUL VL]  // PRFH <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfh PSTL2KEEP, P1, [X28, X9, LSL #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ No description \\ No scheduling info
+  prfh PLDL1STRM, P6, [X0, Z10.S, UXTW #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ No description \\ No scheduling info
+  prfh PLDL3KEEP, P7, [X24, Z21.D, UXTW #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ No description \\ No scheduling info
+  prfh PSTL1STRM, P5, [X10, Z6.D, LSL #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, LSL #1]  \\ No description \\ No scheduling info
+  prfh PLDL3STRM, P6, [Z0.S]  // PRFH <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfh PSTL3STRM, P0, [Z30.S, #12]  // PRFH <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfh PSTL2KEEP, P2, [Z21.D]  // PRFH <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfh PSTL2KEEP, P1, [Z8.D, #14]  // PRFH <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  prfm PLDL1STRM, [X5]  // PRFM <prfop>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  prfm PSTL3KEEP, [X19, #10160]  // PRFM <prfop>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  prfm #25, [X28]  // PRFM #<imm5>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  prfm #7, [X15, #6776]  // PRFM #<imm5>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+  prfm PLDL3STRM, test  // PRFM <prfop>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+  prfm #0, test  // PRFM #<imm5>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+  prfm PLDL1KEEP, [X25, X16]  // PRFM <prfop>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  prfm #24, [X1, X18]  // PRFM #<imm5>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+  prfm PLDL1KEEP, [X14, W8, UXTW]  // PRFM <prfop>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  prfm #12, [X8, W5, UXTW]  // PRFM #<imm5>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  prfm PLDL2KEEP, [X16, W16, SXTW]  // PRFM <prfop>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  prfm #11, [X25, W11, SXTW]  // PRFM #<imm5>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  prfm PSTL2STRM, [X3, X24, SXTX]  // PRFM <prfop>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  prfm #25, [X5, X2, SXTX]  // PRFM #<imm5>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+  prfm PLDL2KEEP, [X10, W29, UXTW #3]  // PRFM <prfop>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm #17, [X9, W27, UXTW #3]  // PRFM #<imm5>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm PLDL1KEEP, [X24, W0, SXTW #3]  // PRFM <prfop>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm #4, [X30, W25, SXTW #3]  // PRFM #<imm5>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm PSTL1STRM, [X18, X20, SXTX #3]  // PRFM <prfop>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm #19, [X29, X25, SXTX #3]  // PRFM #<imm5>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm PSTL3KEEP, [X2, X5, LSL #3]  // PRFM <prfop>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfm #8, [X22, X3, LSL #3]  // PRFM #<imm5>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+  prfum PSTL1KEEP, [X7]  // PRFUM <prfop>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  prfum PLDL2KEEP, [X7, #-37]  // PRFUM <prfop>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  prfum #20, [X21]  // PRFUM #<imm5>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  prfum #23, [X6, #-131]  // PRFUM #<imm5>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+  prfw #3, P2, [X4]  // PRFW #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfw #6, P4, [X7, #6, MUL VL]  // PRFW #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfw PLDL3KEEP, P3, [X2]  // PRFW <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  prfw PSTL1KEEP, P7, [X2, #-31, MUL VL]  // PRFW <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+  prfw PSTL1KEEP, P4, [X18, X21, LSL #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ No description \\ No scheduling info
+  prfw PLDL2STRM, P0, [X15, Z6.S, UXTW #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ No description \\ No scheduling info
+  prfw PSTL2KEEP, P0, [X27, Z18.D, SXTW #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ No description \\ No scheduling info
+  prfw PSTL2KEEP, P3, [X19, Z8.D, LSL #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, LSL #2]  \\ No description \\ No scheduling info
+  prfw #7, P7, [Z27.S]  // PRFW #<imm4>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfw #9, P5, [Z16.S, #72]  // PRFW #<imm4>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfw PLDL3KEEP, P4, [Z2.S]  // PRFW <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+  prfw PSTL3KEEP, P2, [Z0.S, #40]  // PRFW <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+  prfw #7, P1, [Z20.D]  // PRFW #<imm4>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfw #7, P2, [Z10.D, #108]  // PRFW #<imm4>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  prfw PSTL1KEEP, P6, [Z12.D]  // PRFW <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+  prfw PSTL2STRM, P0, [Z18.D, #60]  // PRFW <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+  psb CSYNC  // PSB CSYNC  \\ No description \\ No scheduling info
+  pssbb  // PSSBB  \\ No description \\ No scheduling info
+  ptest P0, P5.B  // PTEST <Pg>, <Pn>.B  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  ptrue P2.B  // PTRUE <Pd>.<T>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  ptrue P3.D, POW2  // PTRUE <Pd>.<T>, <pattern>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  ptrue P0.H  // PTRUE <Pd>.<T>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  ptrue P4.S, #21  // PTRUE <Pd>.<T>, #<uimm5>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+  ptrues P3.H  // PTRUES <Pd>.<T>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+  ptrues P3.D, VL32  // PTRUES <Pd>.<T>, <pattern>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+  ptrues P0.B  // PTRUES <Pd>.<T>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+  ptrues P2.D, #12  // PTRUES <Pd>.<T>, #<uimm5>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+  punpkhi P4.H, P4.B  // PUNPKHI <Pd>.H, <Pn>.B  \\ Predicate unpack and widen  \\ 1 2  2  1.0 V1UnitM0
+  punpklo P1.H, P4.B  // PUNPKLO <Pd>.H, <Pn>.B  \\ Predicate unpack and widen  \\ 1 2  2  1.0 V1UnitM0
+  raddhn V17.2S, V22.2D, V5.2D  // RADDHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  raddhn2 V21.4S, V11.2D, V1.2D  // RADDHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  rbit V16.16B, V21.16B  // RBIT <Vd>.<T>, <Vn>.<T>  \\ ASIMD bit reverse  \\ 1 2  2  4.0 V1UnitV
+  rbit W27, W10  // RBIT <Wd>, <Wn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rbit X30, X0  // RBIT <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rbit Z23.S, P3/M, Z10.S  // RBIT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Count/reverse bits  \\ 1 2  2  2.0 V1UnitV01
+  rdffr P2.B, P1/Z  // RDFFR <Pd>.B, <Pg>/Z  \\ Read first fault register, predicated  \\ 1 3  3  0.5 V1UnitM0[2]
+  rdffr P5.B  // RDFFR <Pd>.B  \\ Read first fault register, unpredicated  \\ 1 2  2  1.0 V1UnitM0
+  rdffrs P7.B, P2/Z  // RDFFRS <Pd>.B, <Pg>/Z  \\ Read first fault register and set flags  \\ 1 4  4  0.33 V1UnitM[6]
+  rdvl X20, #-20  // RDVL <Xd>, #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  ret  // RET  \\ Branch, register  \\ 1 1  1  2.0 V1UnitB
+  ret X14  // RET {<Xn>}  \\ Branch, register  \\ 1 1  1  2.0 V1UnitB
+  rev P1.H, P2.H  // REV <Pd>.<T>, <Pn>.<T>  \\ Predicate reverse  \\ 1 2  2  1.0 V1UnitM0
+  rev Z11.D, Z24.D  // REV <Zd>.<T>, <Zn>.<T>  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+  rev W19, W20  // REV <Wd>, <Wn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rev X30, X15  // REV <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rev16 V5.16B, V26.16B  // REV16 <Vd>.<T>, <Vn>.<T>  \\ ASIMD reverse  \\ 1 2  2  4.0 V1UnitV
+  rev16 W1, W25  // REV16 <Wd>, <Wn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rev16 X27, X11  // REV16 <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rev32 V22.8H, V4.8H  // REV32 <Vd>.<T>, <Vn>.<T>  \\ ASIMD reverse  \\ 1 2  2  4.0 V1UnitV
+  rev32 X30, X6  // REV32 <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rev64 X5, X2  // REV64 <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+  rev64 V0.2S, V19.2S  // REV64 <Vd>.<T>, <Vn>.<T>  \\ ASIMD reverse  \\ 1 2  2  4.0 V1UnitV
+  revb Z3.D, P2/M, Z21.D  // REVB <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+  revh Z1.D, P5/M, Z19.D  // REVH <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+  revw Z16.D, P1/M, Z3.D  // REVW <Zd>.D, <Pg>/M, <Zn>.D  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+  ror W20, W13, #21  // ROR <Wd>, <Ws>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  ror X5, X8, #7  // ROR <Xd>, <Xs>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+  ror W29, W26, W0  // ROR <Wd>, <Wn>, <Wm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+  ror X4, X13, X3  // ROR <Xd>, <Xn>, <Xm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+  rorv W26, W0, W28  // RORV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  rorv X21, X29, X17  // RORV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+  rshrn V24.8B, V0.8H, #4  // RSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  rshrn V8.4H, V24.4S, #16  // RSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  rshrn V12.2S, V12.2D, #28  // RSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  rshrn2 V1.16B, V16.8H, #6  // RSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  rshrn2 V1.8H, V28.4S, #3  // RSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  rshrn2 V20.4S, V19.2D, #14  // RSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  rsubhn V3.8B, V9.8H, V16.8H  // RSUBHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  rsubhn2 V31.4S, V12.2D, V15.2D  // RSUBHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  saba V8.16B, V27.16B, V13.16B  // SABA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff accum  \\ 1 4 1 2.0 V1UnitV13
+  sabal V2.2D, V5.2S, V31.2S  // SABAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+  sabal2 V21.2D, V15.4S, V13.4S  // SABAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+  sabd V12.2S, V11.2S, V27.2S  // SABD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff  \\ 1 2  2  4.0 V1UnitV
+  sabd Z14.S, P1/M, Z14.S, Z23.S  // SABD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sabdl V28.2D, V4.2S, V19.2S  // SABDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+  sabdl2 V10.8H, V30.16B, V4.16B  // SABDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+  sadalp V3.4H, V5.8B  // SADALP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD pairwise add and accumulate long  \\ 1 4 1 2.0 V1UnitV13
+  saddl V7.8H, V3.8B, V23.8B  // SADDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  saddl2 V21.4S, V5.8H, V10.8H  // SADDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  saddlp V13.8H, V29.16B  // SADDLP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+  saddlv H18, V28.8B  // SADDLV H<d>, <Vn>.8B  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  saddlv H30, V4.16B  // SADDLV H<d>, <Vn>.16B  \\ ASIMD arith, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  saddlv S24, V29.4H  // SADDLV S<d>, <Vn>.4H  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  saddlv S22, V23.8H  // SADDLV S<d>, <Vn>.8H  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  saddlv D2, V27.4S  // SADDLV D<d>, <Vn>.4S  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  saddv D19, P6, Z1.B  // SADDV <Dd>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+  saddv D7, P2, Z14.H  // SADDV <Dd>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+  saddv D4, P7, Z27.S  // SADDV <Dd>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+  saddw V8.4S, V0.4S, V1.4H  // SADDW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  saddw2 V24.8H, V10.8H, V30.16B  // SADDW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  sbc W0, W16, W1  // SBC <Wd>, <Wn>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sbc X19, X3, X9  // SBC <Xd>, <Xn>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sbcs W26, W28, W0  // SBCS <Wd>, <Wn>, <Wm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  sbcs X8, X26, X29  // SBCS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  sbfiz W14, W5, #21, #8  // SBFIZ <Wd>, <Wn>, #<lsbs>, #<widths>  \\ No description \\ No scheduling info
+  sbfiz X14, X1, #56, #2  // SBFIZ <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ No description \\ No scheduling info
+  sbfm W24, W11, #27, #19  // SBFM <Wd>, <Wn>, #<immrs>, #<immss>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+  sbfm X14, X1, #36, #55  // SBFM <Xd>, <Xn>, #<immrd>, #<immsd>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+  sbfx W16, W16, #31, #1  // SBFX <Wd>, <Wn>, #<lsbs>, #<widths>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+  sbfx X14, X28, #53, #8  // SBFX <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+  scvtf H18, W17, #30  // SCVTF <Hd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf S14, W9, #19  // SCVTF <Sd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf D16, W3, #13  // SCVTF <Dd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf H28, X25, #23  // SCVTF <Hd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf S27, X19, #5  // SCVTF <Sd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf D15, X22, #32  // SCVTF <Dd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf H22, W7  // SCVTF <Hd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf S22, W10  // SCVTF <Sd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf D23, W6  // SCVTF <Dd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf H21, X12  // SCVTF <Hd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf S25, X28  // SCVTF <Sd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf D12, X0  // SCVTF <Dd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  scvtf H4, H8, #9  // SCVTF H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf S29, S12, #1  // SCVTF S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf D1, D12, #26  // SCVTF D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf V25.4H, V13.4H, #8  // SCVTF <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  scvtf V4.8H, V8.8H, #10  // SCVTF <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  scvtf V5.2S, V2.2S, #26  // SCVTF <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf V2.4S, V24.4S, #10  // SCVTF <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  scvtf V11.2D, V2.2D, #42  // SCVTF <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf H5, H14  // SCVTF <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf S5, S16  // SCVTF S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf D12, D11  // SCVTF D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf V22.4H, V10.4H  // SCVTF <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  scvtf V16.8H, V13.8H  // SCVTF <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  scvtf V9.2S, V31.2S  // SCVTF <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf V2.4S, V7.4S  // SCVTF <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  scvtf V18.2D, V11.2D  // SCVTF <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  scvtf Z3.H, P3/M, Z29.H  // SCVTF <Zd>.H, <Pg>/M, <Zn>.H  \\ Convert to floating point, 16b to half  \\ 1 6  6  0.25 V1UnitV0[4]
+  scvtf Z1.H, P5/M, Z27.S  // SCVTF <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+  scvtf Z30.S, P4/M, Z29.S  // SCVTF <Zd>.S, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+  scvtf Z18.D, P3/M, Z16.S  // SCVTF <Zd>.D, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+  scvtf Z18.H, P1/M, Z14.D  // SCVTF <Zd>.H, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+  scvtf Z10.S, P1/M, Z11.D  // SCVTF <Zd>.S, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+  scvtf Z3.D, P2/M, Z27.D  // SCVTF <Zd>.D, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+  sdiv W6, W28, W24  // SDIV <Wd>, <Wn>, <Wm>  \\ Divide, W-form  \\ 1 12 12 0.08 V1UnitM0[12]
+  sdiv X19, X2, X14  // SDIV <Xd>, <Xn>, <Xm>  \\ Divide, X-form  \\ 1 20 20 0.05 V1UnitM0[20]
+  sdiv Z24.S, P1/M, Z24.S, Z14.S  // SDIV <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+  sdiv Z7.D, P6/M, Z7.D, Z20.D  // SDIV <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+  sdivr Z10.S, P2/M, Z10.S, Z7.S  // SDIVR <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+  sdivr Z0.D, P3/M, Z0.D, Z9.D  // SDIVR <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+  sdot Z6.S, Z29.B, Z0.B[2]  // SDOT <Zda>.S, <Zn>.B, <Zmb>.B[<imms>]  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+  sdot Z0.D, Z18.H, Z10.H[1]  // SDOT <Zda>.D, <Zn>.H, <Zmh>.H[<immd>]  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+  sdot Z28.S, Z30.B, Z14.B  // SDOT <Zda>.S, <Zn>.B, <Zm>.B  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+  sdot Z19.D, Z5.H, Z8.H  // SDOT <Zda>.D, <Zn>.H, <Zm>.H  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+  sdot V2.4S, V27.16B, V5.4B[0]  // SDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<indexs>]  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+  sdot V3.2S, V20.8B, V10.8B  // SDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+  sel P1.B, P7, P5.B, P4.B  // SEL <Pd>.B, <Pg>, <Pn>.B, <Pm>.B  \\ Predicate select  \\ 1 1  1  1.0 V1UnitM0
+  sel Z0.H, P7, Z13.H, Z13.H  // SEL <Zd>.<T>, <Pv>, <Zn>.<T>, <Zm>.<T>  \\ Select, vector form  \\ 1 2  2  2.0 V1UnitV01
+  setffr  // SETFFR  \\ Set first fault register  \\ 1 2  2  1.0 V1UnitM0
+  sev  // SEV  \\ No description \\ No scheduling info
+  sevl  // SEVL  \\ No description \\ No scheduling info
+  shadd V25.16B, V1.16B, V10.16B  // SHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  shl D17, D3, #16  // SHL <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shl V23.8B, V18.8B, #6  // SHL <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shl V0.8H, V23.8H, #10  // SHL <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shl V0.4S, V18.4S, #30  // SHL <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shl V20.2D, V28.2D, #40  // SHL <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shll V3.8H, V13.8B, #8  // SHLL <Vd>.8H, <Vn>.8B, #8  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shll V26.4S, V18.4H, #16  // SHLL <Vd>.4S, <Vn>.4H, #16  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shll V4.2D, V25.2S, #32  // SHLL <Vd>.2D, <Vn>.2S, #32  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shll2 V12.8H, V28.16B, #8  // SHLL2 <Vd>.8H, <Vn>.16B, #8  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shll2 V11.4S, V22.8H, #16  // SHLL2 <Vd>.4S, <Vn>.8H, #16  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shll2 V2.2D, V29.4S, #32  // SHLL2 <Vd>.2D, <Vn>.4S, #32  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shrn V27.8B, V23.8H, #3  // SHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shrn V17.4H, V1.4S, #13  // SHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shrn V13.2S, V0.2D, #12  // SHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shrn2 V4.16B, V29.8H, #8  // SHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shrn2 V9.8H, V18.4S, #10  // SHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shrn2 V5.4S, V12.2D, #16  // SHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  shsub V15.8H, V5.8H, V27.8H  // SHSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  sli D7, D19, #53  // SLI <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sli V16.16B, V26.16B, #7  // SLI <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sli V14.4H, V10.4H, #15  // SLI <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sli V29.2S, V14.2S, #13  // SLI <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sli V25.2D, V21.2D, #41  // SLI <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  smaddl X17, W27, W30, X3  // SMADDL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+  smax Z3.S, Z3.S, #-39  // SMAX <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  smax Z0.B, P5/M, Z0.B, Z20.B  // SMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  smax V30.16B, V3.16B, V30.16B  // SMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  smaxp V21.8H, V16.8H, V7.8H  // SMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  smaxv B4, V30.8B  // SMAXV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  smaxv B15, V16.16B  // SMAXV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  smaxv H28, V14.4H  // SMAXV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  smaxv H6, V19.8H  // SMAXV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  smaxv S3, V14.4S  // SMAXV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  smaxv B19, P4, Z14.B  // SMAXV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+  smaxv H0, P6, Z20.H  // SMAXV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+  smaxv S11, P2, Z28.S  // SMAXV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+  smaxv D24, P5, Z24.D  // SMAXV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+  smc #32343  // SMC #<imm>  \\ No description \\ No scheduling info
+  smin Z21.S, Z21.S, #59  // SMIN <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  smin Z22.S, P0/M, Z22.S, Z30.S  // SMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  smin V29.4S, V24.4S, V24.4S  // SMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  sminp V7.8H, V27.8H, V7.8H  // SMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  sminv B6, V11.8B  // SMINV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  sminv B24, V8.16B  // SMINV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  sminv H24, V23.4H  // SMINV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  sminv H2, V9.8H  // SMINV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  sminv S16, V15.4S  // SMINV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  sminv B4, P2, Z10.B  // SMINV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+  sminv H15, P7, Z10.H  // SMINV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+  sminv S29, P0, Z27.S  // SMINV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+  sminv D17, P2, Z18.D  // SMINV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+  smlal V16.4S, V9.4H, V11.H[4]  // SMLAL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlal V0.2D, V25.2S, V1.S[1]  // SMLAL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlal2 V1.4S, V9.8H, V0.H[6]  // SMLAL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlal2 V30.2D, V22.4S, V7.S[2]  // SMLAL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlal V25.8H, V24.8B, V28.8B  // SMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlal2 V30.4S, V31.8H, V13.8H  // SMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlsl V14.4S, V23.4H, V12.H[7]  // SMLSL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlsl V25.2D, V27.2S, V1.S[1]  // SMLSL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlsl2 V12.4S, V11.8H, V12.H[0]  // SMLSL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlsl2 V11.2D, V28.4S, V7.S[2]  // SMLSL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlsl V11.4S, V14.4H, V15.4H  // SMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smlsl2 V21.4S, V27.8H, V16.8H  // SMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  smmla V0.4S, V17.16B, V31.16B  // SMMLA <Vd>.4S, <Vn>.16B, <Vm>.16B  \\ ASIMD matrix multiply-accumulate  \\ 1 3 1 4.0 V1UnitV
+  smnegl X3, W23, W18  // SMNEGL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+  smov W15, V22.B[0]  // SMOV <Wd>, <Vn>.B[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov W6, V28.B[9]  // SMOV <Wd>, <Vn>.B[<indexb>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov W26, V27.H[0]  // SMOV <Wd>, <Vn>.H[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov W18, V29.H[6]  // SMOV <Wd>, <Vn>.H[<indexh>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov X21, V0.B[0]  // SMOV <Xd>, <Vn>.B[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov X16, V29.B[8]  // SMOV <Xd>, <Vn>.B[<indexb>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov X9, V27.H[0]  // SMOV <Xd>, <Vn>.H[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov X4, V21.H[2]  // SMOV <Xd>, <Vn>.H[<indexh>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov X15, V3.S[0]  // SMOV <Xd>, <Vn>.S[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smov X5, V29.S[1]  // SMOV <Xd>, <Vn>.S[<indexs>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  smsubl X8, W24, W13, X6  // SMSUBL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+  smulh Z11.B, P5/M, Z11.B, Z17.B  // SMULH <Zdn>.B, <Pg>/M, <Zdn>.B, <Zm>.B  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  smulh Z8.H, P0/M, Z8.H, Z4.H  // SMULH <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  smulh Z27.S, P7/M, Z27.S, Z30.S  // SMULH <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  smulh Z4.D, P7/M, Z4.D, Z28.D  // SMULH <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+  smulh X8, X29, X17  // SMULH <Xd>, <Xn>, <Xm>  \\ Multiply high  \\ 1 3  3  2.0 V1UnitM
+  smull X19, W0, W6  // SMULL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+  smull V3.4S, V26.4H, V1.H[5]  // SMULL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  smull V31.2D, V23.2S, V6.S[2]  // SMULL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  smull2 V13.4S, V18.8H, V0.H[3]  // SMULL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  smull2 V11.2D, V1.4S, V7.S[0]  // SMULL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  smull V28.2D, V26.2S, V20.2S  // SMULL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  smull2 V7.2D, V14.4S, V15.4S  // SMULL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqabs D15, D26  // SQABS <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqabs V25.8H, V24.8H  // SQABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqadd Z1.B, Z1.B, #164  // SQADD <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqadd Z18.H, Z18.H, #166  // SQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqadd Z3.D, Z3.D, #158, LSL #0  // SQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqadd Z19.D, Z27.D, Z28.D  // SQADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqadd H12, H18, H10  // SQADD <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqadd V15.2S, V13.2S, V28.2S  // SQADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqdecb X26, W26  // SQDECB <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecb X16, W16, VL64  // SQDECB <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecb X4, W4, VL1, MUL #16  // SQDECB <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecb X4  // SQDECB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecb X28, VL6  // SQDECB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecb X20, VL7, MUL #4  // SQDECB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd X1, W1  // SQDECD <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd X11, W11, MUL3  // SQDECD <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd X14, W14, VL2, MUL #16  // SQDECD <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd X18  // SQDECD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd X11, VL5  // SQDECD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd X21, ALL, MUL #13  // SQDECD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecd Z27.D  // SQDECD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdecd Z2.D, VL128  // SQDECD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdecd Z23.D, VL1, MUL #16  // SQDECD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdech X7, W7  // SQDECH <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdech X10, W10, VL128  // SQDECH <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdech X16, W16, VL6, MUL #11  // SQDECH <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdech X6  // SQDECH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdech X17, VL128  // SQDECH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdech X27, VL128, MUL #4  // SQDECH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdech Z16.H  // SQDECH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdech Z21.H, VL6  // SQDECH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdech Z7.H, MUL3, MUL #7  // SQDECH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdecp X1, P4.B, W1  // SQDECP <Xdn>, <Pm>.<T>, <Wdn>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  sqdecp X26, P6.D  // SQDECP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  sqdecp Z10.D, P3  // SQDECP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+  sqdecw X13, W13  // SQDECW <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecw X2, W2, POW2  // SQDECW <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecw X26, W26, VL8, MUL #10  // SQDECW <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecw X10  // SQDECW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecw X17, VL128  // SQDECW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecw X13, MUL4, MUL #3  // SQDECW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqdecw Z7.S  // SQDECW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdecw Z10.S, POW2  // SQDECW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdecw Z28.S, VL2, MUL #15  // SQDECW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqdmlal S23, H16, V4.H[7]  // SQDMLAL S<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal D12, S18, V3.S[0]  // SQDMLAL D<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal V20.4S, V30.4H, V12.H[3]  // SQDMLAL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal V11.2D, V24.2S, V0.S[3]  // SQDMLAL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal2 V2.4S, V17.8H, V5.H[6]  // SQDMLAL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal2 V23.2D, V30.4S, V6.S[0]  // SQDMLAL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal D16, S12, S15  // SQDMLAL <Va><d>, <Vb><n>, <Vb><m>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal V8.4S, V24.4H, V31.4H  // SQDMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlal2 V29.4S, V11.8H, V13.8H  // SQDMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl S26, H21, V11.H[1]  // SQDMLSL S<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl D6, S16, V3.S[1]  // SQDMLSL D<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl V4.4S, V22.4H, V13.H[2]  // SQDMLSL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl V26.2D, V7.2S, V3.S[0]  // SQDMLSL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl2 V2.4S, V28.8H, V4.H[6]  // SQDMLSL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl2 V4.2D, V3.4S, V3.S[2]  // SQDMLSL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl D13, S21, S8  // SQDMLSL <Va><d>, <Vb><n>, <Vb><m>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl V11.4S, V19.4H, V5.4H  // SQDMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmlsl2 V27.4S, V8.8H, V22.8H  // SQDMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+  sqdmulh H14, H17, V6.H[6]  // SQDMULH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqdmulh S19, S6, V6.S[3]  // SQDMULH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqdmulh V8.4H, V16.4H, V5.H[4]  // SQDMULH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqdmulh V16.2S, V24.2S, V7.S[2]  // SQDMULH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqdmulh H26, H21, H17  // SQDMULH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqdmulh V20.2S, V11.2S, V29.2S  // SQDMULH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqdmull S25, H5, V1.H[3]  // SQDMULL S<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull D29, S23, V0.S[2]  // SQDMULL D<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull V8.4S, V19.4H, V1.H[2]  // SQDMULL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull V20.2D, V10.2S, V6.S[2]  // SQDMULL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull2 V10.4S, V25.8H, V0.H[7]  // SQDMULL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull2 V4.2D, V29.4S, V2.S[3]  // SQDMULL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull D19, S2, S0  // SQDMULL <Va><d>, <Vb><n>, <Vb><m>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull V14.2D, V23.2S, V13.2S  // SQDMULL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqdmull2 V12.4S, V11.8H, V1.8H  // SQDMULL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  sqincb X12, W12  // SQINCB <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincb X1, W1, VL8  // SQINCB <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincb X16, W16, VL2, MUL #16  // SQINCB <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincb X5  // SQINCB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincb X4, VL6  // SQINCB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincb X30, ALL, MUL #7  // SQINCB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd X28, W28  // SQINCD <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd X16, W16, VL8  // SQINCD <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd X22, W22, VL6, MUL #16  // SQINCD <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd X10  // SQINCD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd X17, VL5  // SQINCD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd X13, VL64, MUL #1  // SQINCD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincd Z24.D  // SQINCD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqincd Z10.D, VL128  // SQINCD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqincd Z29.D, VL128, MUL #12  // SQINCD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqinch X28, W28  // SQINCH <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqinch X30, W30, VL1  // SQINCH <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqinch X16, W16, VL4, MUL #2  // SQINCH <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqinch X23  // SQINCH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqinch X10, VL64  // SQINCH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqinch X16, POW2, MUL #2  // SQINCH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqinch Z3.H  // SQINCH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqinch Z23.H, VL4  // SQINCH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqinch Z6.H, VL128, MUL #3  // SQINCH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqincp X13, P2.H, W13  // SQINCP <Xdn>, <Pm>.<T>, <Wdn>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  sqincp X0, P7.H  // SQINCP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  sqincp Z9.H, P1  // SQINCP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+  sqincw X24, W24  // SQINCW <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincw X16, W16, MUL4  // SQINCW <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincw X27, W27, VL32, MUL #15  // SQINCW <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincw X29  // SQINCW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincw X25, VL7  // SQINCW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincw X21, VL8, MUL #3  // SQINCW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  sqincw Z30.S  // SQINCW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqincw Z8.S, MUL3  // SQINCW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqincw Z0.S, VL5, MUL #9  // SQINCW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  sqneg D24, D22  // SQNEG <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqneg V30.16B, V15.16B  // SQNEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqrdmlah H14, H4, V6.H[7]  // SQRDMLAH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlah S24, S17, V6.S[2]  // SQRDMLAH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlah V17.4H, V18.4H, V4.H[7]  // SQRDMLAH <Vd>.4H, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlah V10.2S, V17.2S, V3.S[3]  // SQRDMLAH <Vd>.2S, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlah S3, S3, S5  // SQRDMLAH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlah V16.8H, V30.8H, V28.8H  // SQRDMLAH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh H13, H26, V4.H[2]  // SQRDMLSH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh S26, S29, V7.S[0]  // SQRDMLSH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh V1.8H, V21.8H, V8.H[1]  // SQRDMLSH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh V8.4H, V11.4H, V1.H[3]  // SQRDMLSH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh V20.2S, V29.2S, V4.S[3]  // SQRDMLSH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh V21.4S, V9.4S, V1.S[0]  // SQRDMLSH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh S30, S20, S13  // SQRDMLSH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmlsh V20.4H, V2.4H, V23.4H  // SQRDMLSH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmulh H3, H25, V2.H[1]  // SQRDMULH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmulh S9, S24, V4.S[3]  // SQRDMULH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmulh V0.8H, V15.8H, V0.H[5]  // SQRDMULH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmulh V6.2S, V29.2S, V4.S[2]  // SQRDMULH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmulh H5, H2, H20  // SQRDMULH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqrdmulh V31.2S, V17.2S, V4.2S  // SQRDMULH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+  sqrshl D6, D1, D30  // SQRSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshl V15.8B, V26.8B, V21.8B  // SQRSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn B6, H24, #3  // SQRSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn H11, S22, #8  // SQRSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn S4, D9, #13  // SQRSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn V31.8B, V31.8H, #2  // SQRSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn V27.4H, V11.4S, #8  // SQRSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn V4.2S, V30.2D, #10  // SQRSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn2 V11.16B, V30.8H, #7  // SQRSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn2 V14.8H, V3.4S, #12  // SQRSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrn2 V13.4S, V28.2D, #24  // SQRSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun B5, H0, #3  // SQRSHRUN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun H25, S11, #7  // SQRSHRUN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun S15, D18, #2  // SQRSHRUN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun V0.8B, V3.8H, #7  // SQRSHRUN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun V5.4H, V8.4S, #7  // SQRSHRUN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun V7.2S, V8.2D, #13  // SQRSHRUN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun2 V14.16B, V14.8H, #3  // SQRSHRUN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun2 V9.8H, V16.4S, #10  // SQRSHRUN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqrshrun2 V12.4S, V23.2D, #30  // SQRSHRUN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl B15, B3, #4  // SQSHL B<d>, B<n>, #<shiftb>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl H21, H0, #5  // SQSHL H<d>, H<n>, #<shifth>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl S26, S9, #24  // SQSHL S<d>, S<n>, #<shifts>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl D8, D23, #17  // SQSHL D<d>, D<n>, #<shiftd>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl V25.16B, V26.16B, #5  // SQSHL <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl V29.4H, V1.4H, #7  // SQSHL <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl V0.2S, V5.2S, #1  // SQSHL <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl V11.2D, V2.2D, #23  // SQSHL <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl S17, S4, S23  // SQSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshl V23.16B, V23.16B, V23.16B  // SQSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshlu B3, B27, #5  // SQSHLU B<d>, B<n>, #<shiftb>  \\ No description \\ No scheduling info
+  sqshlu H23, H4, #6  // SQSHLU H<d>, H<n>, #<shifth>  \\ No description \\ No scheduling info
+  sqshlu S29, S29, #30  // SQSHLU S<d>, S<n>, #<shifts>  \\ No description \\ No scheduling info
+  sqshlu D14, D5, #22  // SQSHLU D<d>, D<n>, #<shiftd>  \\ No description \\ No scheduling info
+  sqshlu V11.8B, V17.8B, #6  // SQSHLU <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ No description \\ No scheduling info
+  sqshlu V18.8H, V8.8H, #14  // SQSHLU <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ No description \\ No scheduling info
+  sqshlu V25.4S, V7.4S, #13  // SQSHLU <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ No description \\ No scheduling info
+  sqshlu V19.2D, V14.2D, #39  // SQSHLU <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ No description \\ No scheduling info
+  sqshrn B17, H30, #7  // SQSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn H30, S15, #5  // SQSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn S16, D0, #20  // SQSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn V3.8B, V25.8H, #1  // SQSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn V23.4H, V14.4S, #6  // SQSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn V6.2S, V29.2D, #10  // SQSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn2 V31.16B, V31.8H, #8  // SQSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn2 V13.8H, V6.4S, #13  // SQSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrn2 V30.4S, V0.2D, #1  // SQSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun B3, H16, #3  // SQSHRUN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun H11, S10, #7  // SQSHRUN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun S18, D1, #13  // SQSHRUN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun V21.8B, V27.8H, #5  // SQSHRUN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun V18.4H, V19.4S, #2  // SQSHRUN <Vd>.4H, <Vn>.4S, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun V2.2S, V14.2D, #3  // SQSHRUN <Vd>.2S, <Vn>.2D, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun2 V10.16B, V28.8H, #5  // SQSHRUN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun2 V4.8H, V28.4S, #12  // SQSHRUN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqshrun2 V7.4S, V18.2D, #16  // SQSHRUN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  sqsub Z13.B, Z13.B, #114  // SQSUB <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqsub Z28.H, Z28.H, #139  // SQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqsub Z11.S, Z11.S, #14, LSL #0  // SQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqsub Z28.S, Z9.S, Z12.S  // SQSUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sqsub B3, B13, B12  // SQSUB <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqsub V20.8H, V18.8H, V12.8H  // SQSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sqxtn B11, H22  // SQXTN <Vb><d>, <Va><n>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  sqxtn V3.2S, V17.2D  // SQXTN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  sqxtn2 V17.8H, V27.4S  // SQXTN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  sqxtun B30, H18  // SQXTUN <Vb><d>, <Va><n>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  sqxtun V26.8B, V21.8H  // SQXTUN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  sqxtun2 V22.16B, V6.8H  // SQXTUN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  srhadd V29.8B, V3.8B, V8.8B  // SRHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  sri D30, D17, #61  // SRI <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sri V23.16B, V30.16B, #2  // SRI <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sri V1.4H, V0.4H, #4  // SRI <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sri V28.2S, V6.2S, #16  // SRI <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  sri V8.2D, V19.2D, #40  // SRI <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+  srshl D30, D8, D8  // SRSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  srshl V20.8B, V23.8B, V27.8B  // SRSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  srshr D20, D18, #27  // SRSHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  srshr V20.8B, V0.8B, #7  // SRSHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  srshr V27.8H, V19.8H, #9  // SRSHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  srshr V8.2S, V20.2S, #31  // SRSHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  srshr V31.2D, V17.2D, #33  // SRSHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  srsra D13, D10, #25  // SRSRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  srsra V31.16B, V15.16B, #5  // SRSRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  srsra V14.4H, V27.4H, #7  // SRSRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  srsra V17.2S, V8.2S, #8  // SRSRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  srsra V22.2D, V4.2D, #12  // SRSRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ssbb  // SSBB  \\ No description \\ No scheduling info
+  sshl D29, D30, D9  // SSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshl V13.2D, V7.2D, V27.2D  // SSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshll V9.8H, V2.8B, #0  // SSHLL <Vd>.8H, <Vn>.8B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshll V12.4S, V3.4H, #4  // SSHLL <Vd>.4S, <Vn>.4H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshll V17.2D, V6.2S, #22  // SSHLL <Vd>.2D, <Vn>.2S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshll2 V28.8H, V12.16B, #7  // SSHLL2 <Vd>.8H, <Vn>.16B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshll2 V29.4S, V22.8H, #7  // SSHLL2 <Vd>.4S, <Vn>.8H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshll2 V17.2D, V13.4S, #22  // SSHLL2 <Vd>.2D, <Vn>.4S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshr D3, D18, #10  // SSHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshr V20.8B, V28.8B, #2  // SSHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshr V20.4H, V23.4H, #10  // SSHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshr V13.2S, V23.2S, #2  // SSHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sshr V3.2D, V8.2D, #61  // SSHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ssra D28, D30, #51  // SSRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ssra V9.8B, V18.8B, #2  // SSRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ssra V21.4H, V24.4H, #3  // SSRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ssra V28.2S, V17.2S, #6  // SSRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ssra V0.2D, V23.2D, #35  // SSRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ssubl V13.4S, V9.4H, V5.4H  // SSUBL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  ssubl2 V18.4S, V29.8H, V17.8H  // SSUBL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  ssubw V5.2D, V13.2D, V4.2S  // SSUBW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  ssubw2 V4.4S, V26.4S, V31.8H  // SSUBW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  st1 { V18.8B }, [X15]  // ST1 { <Vt>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V31.16B }, [X29]  // ST1 { <Vt>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V19.4H }, [X7]  // ST1 { <Vt>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V27.8H }, [X17]  // ST1 { <Vt>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V25.2S }, [X6]  // ST1 { <Vt>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V22.4S }, [X19]  // ST1 { <Vt>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V20.1D }, [X10]  // ST1 { <Vt>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V8.2D }, [X15]  // ST1 { <Vt>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V16.8B }, [X14], #8  // ST1 { <Vt>.8B }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V10.16B }, [X8], #16  // ST1 { <Vt>.16B }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V29.4H }, [X17], #8  // ST1 { <Vt>.4H }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V14.8H }, [X28], #16  // ST1 { <Vt>.8H }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V18.2S }, [X20], #8  // ST1 { <Vt>.2S }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V28.4S }, [X1], #16  // ST1 { <Vt>.4S }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V17.1D }, [X27], #8  // ST1 { <Vt>.1D }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V30.2D }, [X4], #16  // ST1 { <Vt>.2D }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V13.8B }, [X8], X7  // ST1 { <Vt>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V4.16B }, [X7], X26  // ST1 { <Vt>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V17.4H }, [X10], X4  // ST1 { <Vt>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V18.8H }, [X15], X1  // ST1 { <Vt>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V6.2S }, [X17], X24  // ST1 { <Vt>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V26.4S }, [X20], X29  // ST1 { <Vt>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V13.1D }, [X3], X20  // ST1 { <Vt>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V15.2D }, [X21], X11  // ST1 { <Vt>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V8.8B, V9.8B }, [X18]  // ST1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V1.16B, V2.16B }, [X4]  // ST1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V22.4H, V23.4H }, [X22]  // ST1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V18.8H, V19.8H }, [X2]  // ST1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V13.2S, V14.2S }, [X9]  // ST1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V15.4S, V16.4S }, [X12]  // ST1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V21.1D, V22.1D }, [X29]  // ST1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  st1 { V26.2D, V27.2D }, [X28]  // ST1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V23.8B, V24.8B }, [X4], #16  // ST1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V15.16B, V16.16B }, [X16], #32  // ST1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V7.4H, V8.4H }, [X7], #16  // ST1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V8.8H, V9.8H }, [X1], #32  // ST1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V23.2S, V24.2S }, [X7], #16  // ST1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V8.4S, V9.4S }, [X15], #32  // ST1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V14.1D, V15.1D }, [X11], #16  // ST1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V12.2D, V13.2D }, [X2], #32  // ST1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V3.8B, V4.8B }, [X28], X14  // ST1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V19.16B, V20.16B }, [X13], X7  // ST1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V28.4H, V29.4H }, [X14], X5  // ST1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V9.8H, V10.8H }, [X28], X9  // ST1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V10.2S, V11.2S }, [X10], X2  // ST1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V13.4S, V14.4S }, [X8], X15  // ST1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V5.1D, V6.1D }, [X9], X14  // ST1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V14.2D, V15.2D }, [X24], X1  // ST1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V15.8B, V16.8B, V17.8B }, [X0]  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V27.16B, V28.16B, V29.16B }, [X18]  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+  st1 { V13.4H, V14.4H, V15.4H }, [X7]  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V8.8H, V9.8H, V10.8H }, [X16]  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+  st1 { V12.2S, V13.2S, V14.2S }, [X3]  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V19.4S, V20.4S, V21.4S }, [X7]  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+  st1 { V5.1D, V6.1D, V7.1D }, [X3]  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V13.2D, V14.2D, V15.2D }, [X27]  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+  st1 { V3.8B, V4.8B, V5.8B }, [X21], #24  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V25.16B, V26.16B, V27.16B }, [X4], #48  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V24.4H, V25.4H, V26.4H }, [X9], #24  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V0.8H, V1.8H, V2.8H }, [X7], #48  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V3.2S, V4.2S, V5.2S }, [X4], #24  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V25.4S, V26.4S, V27.4S }, [X14], #48  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V7.1D, V8.1D, V9.1D }, [X13], #24  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V19.2D, V20.2D, V21.2D }, [X5], #48  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V5.8B, V6.8B, V7.8B }, [X17], X25  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V12.16B, V13.16B, V14.16B }, [X29], X23  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V18.4H, V19.4H, V20.4H }, [X0], X14  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V16.8H, V17.8H, V18.8H }, [X1], X18  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V1.2S, V2.2S, V3.2S }, [X15], X29  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V2.4S, V3.4S, V4.4S }, [X29], X6  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V8.1D, V9.1D, V10.1D }, [X13], X27  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V8.2D, V9.2D, V10.2D }, [X18], X19  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+  st1 { V21.8B, V22.8B, V23.8B, V24.8B }, [X14]  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V18.16B, V19.16B, V20.16B, V21.16B }, [X29]  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+  st1 { V23.4H, V24.4H, V25.4H, V26.4H }, [X24]  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V7.8H, V8.8H, V9.8H, V10.8H }, [X19]  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+  st1 { V6.2S, V7.2S, V8.2S, V9.2S }, [X13]  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V26.4S, V27.4S, V28.4S, V29.4S }, [X12]  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+  st1 { V0.1D, V1.1D, V2.1D, V3.1D }, [X10]  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+  st1 { V25.2D, V26.2D, V27.2D, V28.2D }, [X19]  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+  st1 { V27.8B, V28.8B, V29.8B, V30.8B }, [X17], #32  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V26.16B, V27.16B, V28.16B, V29.16B }, [X0], #64  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V18.4H, V19.4H, V20.4H, V21.4H }, [X22], #32  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V12.8H, V13.8H, V14.8H, V15.8H }, [X13], #64  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V13.2S, V14.2S, V15.2S, V16.2S }, [X25], #32  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V4.4S, V5.4S, V6.4S, V7.4S }, [X11], #64  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V7.1D, V8.1D, V9.1D, V10.1D }, [X13], #32  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V12.2D, V13.2D, V14.2D, V15.2D }, [X25], #64  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V21.8B, V22.8B, V23.8B, V24.8B }, [X25], X28  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V26.16B, V27.16B, V28.16B, V29.16B }, [X24], X5  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V20.4H, V21.4H, V22.4H, V23.4H }, [X25], X19  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V20.8H, V21.8H, V22.8H, V23.8H }, [X18], X0  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V4.2S, V5.2S, V6.2S, V7.2S }, [X9], X5  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V7.4S, V8.4S, V9.4S, V10.4S }, [X12], X30  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V23.1D, V24.1D, V25.1D, V26.1D }, [X23], X4  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+  st1 { V20.2D, V21.2D, V22.2D, V23.2D }, [X7], X14  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+  st1 { V1.B }[5], [X1]  // ST1 { <Vt>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+  st1 { V0.H }[2], [X1]  // ST1 { <Vt>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+  st1 { V31.S }[1], [X16]  // ST1 { <Vt>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+  st1 { V15.D }[1], [X8]  // ST1 { <Vt>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, D  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+  st1 { V15.B }[1], [X12], #1  // ST1 { <Vt>.B }[<indexb>], [<Xn|SP>], #1  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V16.B }[3], [X0], X2  // ST1 { <Vt>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V29.H }[2], [X27], #2  // ST1 { <Vt>.H }[<indexh>], [<Xn|SP>], #2  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V15.H }[4], [X30], X9  // ST1 { <Vt>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V3.S }[1], [X24], #4  // ST1 { <Vt>.S }[<indexs>], [<Xn|SP>], #4  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V26.S }[0], [X2], X30  // ST1 { <Vt>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V19.D }[1], [X9], #8  // ST1 { <Vt>.D }[<indexd>], [<Xn|SP>], #8  \\ ASIMD store, 1 element, one lane, D  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1 { V29.D }[0], [X26], X22  // ST1 { <Vt>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, D  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+  st1b { Z7.H }, P2, [X14]  // ST1B { <Zt>.<T> }, <Pg>, [<Xn|SP>]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  st1b { Z16.S }, P4, [X20, #3, MUL VL]  // ST1B { <Zt>.<T> }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  st1b { Z17.S }, P3, [X20, X0]  // ST1B { <Zt>.<T> }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  st1b { Z0.D }, P4, [X11, Z13.D, UXTW]  // ST1B { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1b { Z16.S }, P4, [X19, Z25.S, SXTW]  // ST1B { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ Scatter store, 32-bit unscaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1b { Z10.D }, P3, [X12, Z21.D]  // ST1B { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1b { Z17.S }, P7, [Z28.S]  // ST1B { <Zt>.S }, <Pg>, [<Zn>.S]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1b { Z16.S }, P0, [Z25.S, #7]  // ST1B { <Zt>.S }, <Pg>, [<Zn>.S, #<imm>]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1b { Z15.D }, P6, [Z27.D]  // ST1B { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1b { Z2.D }, P0, [Z21.D, #24]  // ST1B { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1d { Z10.D }, P2, [X26, Z5.D, SXTW #3]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ Scatter store, 32-bit unpacked scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1d { Z18.D }, P2, [X7, Z1.D, UXTW]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1d { Z9.D }, P6, [X6, Z12.D, LSL #3]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, LSL #3]  \\ Scatter store, 64-bit scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1d { Z3.D }, P3, [X1, Z30.D]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1d { Z18.D }, P0, [Z7.D]  // ST1D { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1d { Z4.D }, P2, [Z2.D, #136]  // ST1D { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1h { Z28.S }, P3, [X18]  // ST1H { <Zt>.<T> }, <Pg>, [<Xn|SP>]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  st1h { Z23.H }, P1, [X14, #-8, MUL VL]  // ST1H { <Zt>.<T> }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  st1h { Z25.S }, P3, [X17, X8, LSL #1]  // ST1H { <Zt>.<T> }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store, scalar + scalar   \\ 3 2  2  2.0 V1UnitL01,V1UnitS,V1UnitV
+  st1h { Z12.S }, P3, [X24, Z30.S, SXTW #1]  // ST1H { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Scatter store, 32-bit scaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1h { Z26.D }, P5, [X9, Z17.D, UXTW #1]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Scatter store, 32-bit unpacked scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1h { Z23.D }, P1, [X5, Z25.D, SXTW]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1h { Z14.S }, P4, [X22, Z17.S, SXTW]  // ST1H { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ Scatter store, 32-bit unscaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1h { Z23.D }, P3, [X25, Z11.D, LSL #1]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Scatter store, 64-bit scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1h { Z0.D }, P4, [X21, Z21.D]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1h { Z29.S }, P5, [Z9.S]  // ST1H { <Zt>.S }, <Pg>, [<Zn>.S]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1h { Z4.S }, P7, [Z23.S, #40]  // ST1H { <Zt>.S }, <Pg>, [<Zn>.S, #<imm>]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1h { Z27.D }, P2, [Z3.D]  // ST1H { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1h { Z11.D }, P6, [Z7.D, #38]  // ST1H { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1w { Z25.S }, P1, [X9, Z28.S, SXTW #2]  // ST1W { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ Scatter store, 32-bit scaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1w { Z13.D }, P3, [X16, Z9.D, SXTW #2]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Scatter store, 32-bit unpacked scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1w { Z21.D }, P1, [X24, Z23.D, SXTW]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1w { Z17.S }, P1, [X5, Z22.S, UXTW]  // ST1W { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ Scatter store, 32-bit unscaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1w { Z28.D }, P1, [X5, Z8.D, LSL #2]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Scatter store, 64-bit scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1w { Z26.D }, P3, [X3, Z0.D]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1w { Z28.S }, P6, [Z21.S]  // ST1W { <Zt>.S }, <Pg>, [<Zn>.S]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1w { Z26.S }, P3, [Z24.S, #120]  // ST1W { <Zt>.S }, <Pg>, [<Zn>.S, #<imm>]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+  st1w { Z3.D }, P0, [Z12.D]  // ST1W { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st1w { Z17.D }, P2, [Z1.D, #80]  // ST1W { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+  st2 { V14.8B, V15.8B }, [X2]  // ST2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V6.16B, V7.16B }, [X23]  // ST2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st2 { V10.4H, V11.4H }, [X18]  // ST2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V10.8H, V11.8H }, [X18]  // ST2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st2 { V25.2S, V26.2S }, [X29]  // ST2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V26.4S, V27.4S }, [X14]  // ST2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st2 { V10.2D, V11.2D }, [X1]  // ST2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, D  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st2 { V21.8B, V22.8B }, [X22], #16  // ST2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V26.16B, V27.16B }, [X2], #32  // ST2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V19.4H, V20.4H }, [X27], #16  // ST2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V28.8H, V29.8H }, [X22], #32  // ST2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V1.2S, V2.2S }, [X26], #16  // ST2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V19.4S, V20.4S }, [X7], #32  // ST2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V22.2D, V23.2D }, [X18], #32  // ST2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V29.8B, V30.8B }, [X9], X2  // ST2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V17.16B, V18.16B }, [X4], X0  // ST2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V9.4H, V10.4H }, [X7], X25  // ST2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V8.8H, V9.8H }, [X11], X8  // ST2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V17.2S, V18.2S }, [X2], X8  // ST2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V9.4S, V10.4S }, [X23], X12  // ST2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V29.2D, V30.2D }, [X25], X11  // ST2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st2 { V21.B, V22.B }[15], [X15]  // ST2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V28.H, V29.H }[2], [X6]  // ST2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V14.S, V15.S }[1], [X25]  // ST2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V17.D, V18.D }[1], [X1]  // ST2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, D  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+  st2 { V9.B, V10.B }[15], [X12], #2  // ST2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], #2  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V19.B, V20.B }[9], [X27], X28  // ST2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V18.H, V19.H }[3], [X30], #4  // ST2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], #4  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V13.H, V14.H }[5], [X23], X24  // ST2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V23.S, V24.S }[1], [X22], #8  // ST2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], #8  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V16.S, V17.S }[3], [X12], X16  // ST2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V27.D, V28.D }[0], [X16], #16  // ST2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], #16  \\ ASIMD store, 2 element, one lane, D  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2 { V6.D, V7.D }[1], [X14], X5  // ST2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, D  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+  st2b { Z19.B, Z20.B }, P1, [X18]  // ST2B { <Zt1>.B, <Zt2>.B }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2b { Z26.B, Z27.B }, P7, [X15, #-6, MUL VL]  // ST2B { <Zt1>.B, <Zt2>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2b { Z19.B, Z20.B }, P1, [X23, X27]  // ST2B { <Zt1>.B, <Zt2>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2d { Z29.D, Z30.D }, P4, [X8]  // ST2D { <Zt1>.D, <Zt2>.D }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2d { Z16.D, Z17.D }, P3, [X20, #14, MUL VL]  // ST2D { <Zt1>.D, <Zt2>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2d { Z17.D, Z18.D }, P7, [X2, X28, LSL #3]  // ST2D { <Zt1>.D, <Zt2>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2h { Z5.H, Z6.H }, P7, [X23]  // ST2H { <Zt1>.H, <Zt2>.H }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2h { Z11.H, Z12.H }, P6, [X4, #10, MUL VL]  // ST2H { <Zt1>.H, <Zt2>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2h { Z3.H, Z4.H }, P3, [X22, X16, LSL #1]  // ST2H { <Zt1>.H, <Zt2>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 3 4  4  1.0 V1UnitL01[2],V1UnitS[2],V1UnitV[2]
+  st2w { Z14.S, Z15.S }, P4, [X17]  // ST2W { <Zt1>.S, <Zt2>.S }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2w { Z9.S, Z10.S }, P5, [X19, #-8, MUL VL]  // ST2W { <Zt1>.S, <Zt2>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st2w { Z5.S, Z6.S }, P3, [X23, X13, LSL #2]  // ST2W { <Zt1>.S, <Zt2>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+  st3 { V10.8B, V11.8B, V12.8B }, [X18]  // ST3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V26.16B, V27.16B, V28.16B }, [X4]  // ST3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+  st3 { V25.4H, V26.4H, V27.4H }, [X11]  // ST3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V0.8H, V1.8H, V2.8H }, [X0]  // ST3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+  st3 { V19.2S, V20.2S, V21.2S }, [X30]  // ST3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V24.4S, V25.4S, V26.4S }, [X8]  // ST3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+  st3 { V24.2D, V25.2D, V26.2D }, [X25]  // ST3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, D  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+  st3 { V25.8B, V26.8B, V27.8B }, [X23], #24  // ST3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V9.16B, V10.16B, V11.16B }, [X26], #48  // ST3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V24.4H, V25.4H, V26.4H }, [X3], #24  // ST3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V23.8H, V24.8H, V25.8H }, [X22], #48  // ST3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V7.2S, V8.2S, V9.2S }, [X8], #24  // ST3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V11.4S, V12.4S, V13.4S }, [X15], #48  // ST3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V1.2D, V2.2D, V3.2D }, [X4], #48  // ST3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, D  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V16.8B, V17.8B, V18.8B }, [X26], X2  // ST3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V9.16B, V10.16B, V11.16B }, [X3], X18  // ST3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V2.4H, V3.4H, V4.4H }, [X4], X4  // ST3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V27.8H, V28.8H, V29.8H }, [X27], X8  // ST3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V26.2S, V27.2S, V28.2S }, [X2], X25  // ST3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V5.4S, V6.4S, V7.4S }, [X18], X29  // ST3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V26.2D, V27.2D, V28.2D }, [X14], X5  // ST3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, D  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+  st3 { V8.B, V9.B, V10.B }[4], [X18]  // ST3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, B/H  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V11.H, V12.H, V13.H }[4], [X0]  // ST3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, B/H  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V9.S, V10.S, V11.S }[2], [X20]  // ST3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V16.D, V17.D, V18.D }[0], [X13]  // ST3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, D  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st3 { V26.B, V27.B, V28.B }[1], [X12], #3  // ST3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], #3  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V27.B, V28.B, V29.B }[15], [X19], X23  // ST3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V24.H, V25.H, V26.H }[2], [X14], #6  // ST3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], #6  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V1.H, V2.H, V3.H }[2], [X0], X23  // ST3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V25.S, V26.S, V27.S }[2], [X10], #12  // ST3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], #12  \\ ASIMD store, 3 element, one lane, S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V8.S, V9.S, V10.S }[0], [X11], X20  // ST3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V19.D, V20.D, V21.D }[1], [X5], #24  // ST3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], #24  \\ ASIMD store, 3 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3 { V10.D, V11.D, V12.D }[0], [X12], X11  // ST3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st3b { Z0.B, Z1.B, Z2.B }, P6, [X26]  // ST3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3b { Z22.B, Z23.B, Z24.B }, P6, [X25, #3, MUL VL]  // ST3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3b { Z14.B, Z15.B, Z16.B }, P2, [X29, X27]  // ST3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+  st3d { Z6.D, Z7.D, Z8.D }, P2, [X12]  // ST3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3d { Z20.D, Z21.D, Z22.D }, P5, [X15, #9, MUL VL]  // ST3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3d { Z15.D, Z16.D, Z17.D }, P7, [X0, X9, LSL #3]  // ST3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+  st3h { Z17.H, Z18.H, Z19.H }, P3, [X14]  // ST3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3h { Z21.H, Z22.H, Z23.H }, P0, [X15, #6, MUL VL]  // ST3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3h { Z2.H, Z3.H, Z4.H }, P3, [X21, X9, LSL #1]  // ST3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+  st3w { Z9.S, Z10.S, Z11.S }, P3, [X29]  // ST3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3w { Z11.S, Z12.S, Z13.S }, P4, [X13, #15, MUL VL]  // ST3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+  st3w { Z19.S, Z20.S, Z21.S }, P2, [X22, X28, LSL #2]  // ST3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+  st4 { V17.8B, V18.8B, V19.8B, V20.8B }, [X8]  // ST4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 2 6  6  0.33 V1UnitV01[6],V1UnitL01[6]
+  st4 { V7.16B, V8.16B, V9.16B, V10.16B }, [X15]  // ST4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 2 7  7  0.17 V1UnitV01[12],V1UnitL01[12]
+  st4 { V5.4H, V6.4H, V7.4H, V8.4H }, [X13]  // ST4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 2 6  6  0.33 V1UnitV01[6],V1UnitL01[6]
+  st4 { V11.8H, V12.8H, V13.8H, V14.8H }, [X1]  // ST4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 2 7  7  0.17 V1UnitV01[12],V1UnitL01[12]
+  st4 { V15.2S, V16.2S, V17.2S, V18.2S }, [X18]  // ST4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 2 6  6  0.33 V1UnitV01[6],V1UnitL01[6]
+  st4 { V21.4S, V22.4S, V23.4S, V24.4S }, [X6]  // ST4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 2 7  7  0.17 V1UnitV01[12],V1UnitL01[12]
+  st4 { V25.2D, V26.2D, V27.2D, V28.2D }, [X16]  // ST4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, D  \\ 2 4  4  0.25 V1UnitV01[8],V1UnitL01[8]
+  st4 { V16.8B, V17.8B, V18.8B, V19.8B }, [X24], #32  // ST4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+  st4 { V2.16B, V3.16B, V4.16B, V5.16B }, [X13], #64  // ST4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+  st4 { V17.4H, V18.4H, V19.4H, V20.4H }, [X3], #32  // ST4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+  st4 { V18.8H, V19.8H, V20.8H, V21.8H }, [X5], #64  // ST4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+  st4 { V26.2S, V27.2S, V28.2S, V29.2S }, [X17], #32  // ST4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+  st4 { V21.4S, V22.4S, V23.4S, V24.4S }, [X7], #64  // ST4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+  st4 { V27.2D, V28.2D, V29.2D, V30.2D }, [X25], #64  // ST4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, D  \\ 3 4  4  0.25 V1UnitV01[8],V1UnitL01[8],V1UnitI
+  st4 { V24.8B, V25.8B, V26.8B, V27.8B }, [X24], X8  // ST4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+  st4 { V2.16B, V3.16B, V4.16B, V5.16B }, [X21], X21  // ST4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+  st4 { V11.4H, V12.4H, V13.4H, V14.4H }, [X29], X3  // ST4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+  st4 { V16.8H, V17.8H, V18.8H, V19.8H }, [X13], X3  // ST4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+  st4 { V13.2S, V14.2S, V15.2S, V16.2S }, [X0], X0  // ST4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+  st4 { V26.4S, V27.4S, V28.4S, V29.4S }, [X1], X22  // ST4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+  st4 { V18.2D, V19.2D, V20.2D, V21.2D }, [X10], X28  // ST4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, D  \\ 3 4  4  0.25 V1UnitV01[8],V1UnitL01[8],V1UnitI
+  st4 { V10.B, V11.B, V12.B, V13.B }[3], [X5]  // ST4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, B/H  \\ 2 6  6  1.0 V1UnitV01[2],V1UnitL01[2]
+  st4 { V5.H, V6.H, V7.H, V8.H }[4], [X13]  // ST4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, B/H  \\ 2 6  6  1.0 V1UnitV01[2],V1UnitL01[2]
+  st4 { V22.S, V23.S, V24.S, V25.S }[0], [X7]  // ST4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, S  \\ 2 6  6  1.0 V1UnitV01[2],V1UnitL01[2]
+  st4 { V23.D, V24.D, V25.D, V26.D }[1], [X5]  // ST4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, D  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+  st4 { V22.B, V23.B, V24.B, V25.B }[0], [X29], #4  // ST4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], #4  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V6.B, V7.B, V8.B, V9.B }[9], [X26], X21  // ST4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V19.H, V20.H, V21.H, V22.H }[2], [X18], #8  // ST4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], #8  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V6.H, V7.H, V8.H, V9.H }[4], [X9], X9  // ST4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V19.S, V20.S, V21.S, V22.S }[2], [X27], #16  // ST4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], #16  \\ ASIMD store, 4 element, one lane, S  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V22.S, V23.S, V24.S, V25.S }[0], [X29], X21  // ST4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, S  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V10.D, V11.D, V12.D, V13.D }[0], [X16], #32  // ST4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], #32  \\ ASIMD store, 4 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4 { V10.D, V11.D, V12.D, V13.D }[0], [X12], X11  // ST4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+  st4b { Z22.B, Z23.B, Z24.B, Z25.B }, P0, [X0]  // ST4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4b { Z1.B, Z2.B, Z3.B, Z4.B }, P7, [X1, #20, MUL VL]  // ST4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4b { Z28.B, Z29.B, Z30.B, Z31.B }, P4, [X27, X20]  // ST4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+  st4d { Z19.D, Z20.D, Z21.D, Z22.D }, P1, [X11]  // ST4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4d { Z0.D, Z1.D, Z2.D, Z3.D }, P6, [X7, #-24, MUL VL]  // ST4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4d { Z28.D, Z29.D, Z30.D, Z31.D }, P5, [X19, X20, LSL #3]  // ST4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+  st4h { Z14.H, Z15.H, Z16.H, Z17.H }, P1, [X24]  // ST4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4h { Z27.H, Z28.H, Z29.H, Z30.H }, P3, [X26, #16, MUL VL]  // ST4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4h { Z2.H, Z3.H, Z4.H, Z5.H }, P5, [X30, X17, LSL #1]  // ST4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+  st4w { Z3.S, Z4.S, Z5.S, Z6.S }, P0, [X0]  // ST4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4w { Z5.S, Z6.S, Z7.S, Z8.S }, P2, [X0, #-20, MUL VL]  // ST4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+  st4w { Z21.S, Z22.S, Z23.S, Z24.S }, P5, [X5, X18, LSL #2]  // ST4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+  stlrb W19, [X26]  // STLRB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlrb W9, [X19, #0]  // STLRB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlrh W4, [X7]  // STLRH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlrh W20, [X5, #0]  // STLRH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlur W3, [X27]  // STLUR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlur W0, [X15, #-14]  // STLUR <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  stlur X23, [X25]  // STLUR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlur X18, [X6, #101]  // STLUR <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  stlurb W30, [X17]  // STLURB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlurb W25, [X21, #-8]  // STLURB <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  stlurh W9, [X29]  // STLURH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlurh W6, [X27, #-224]  // STLURH <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+  stlxp W26, W11, W12, [X7]  // STLXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlxp W24, W10, W16, [X8, #0]  // STLXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlxp W1, X25, X26, [X10]  // STLXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlxp W10, X7, X20, [X22, #0]  // STLXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlxr W23, W8, [X6]  // STLXR <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlxr W29, W28, [X26, #0]  // STLXR <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlxr W23, X8, [X7]  // STLXR <Ws>, <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlxr W14, X18, [X23, #0]  // STLXR <Ws>, <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlxrb W2, W7, [X10]  // STLXRB <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlxrb W0, W1, [X20, #0]  // STLXRB <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stlxrh W16, W17, [X21]  // STLXRH <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stlxrh W12, W26, [X23, #0]  // STLXRH <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stnp S29, S16, [X11]  // STNP <St1>, <St2>, [<Xn|SP>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stnp S17, S19, [X27, #-40]  // STNP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stnp D4, D3, [X30]  // STNP <Dt1>, <Dt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stnp D25, D31, [X28, #328]  // STNP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stnp Q28, Q22, [X3]  // STNP <Qt1>, <Qt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stnp Q17, Q15, [X16, #656]  // STNP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stnp W29, W25, [X5]  // STNP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stnp W16, W18, [X27, #-232]  // STNP <Wt1>, <Wt2>, [<Xn|SP>, #<imms>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stnp X20, X16, [X8]  // STNP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stnp X6, X20, [X15, #-120]  // STNP <Xt1>, <Xt2>, [<Xn|SP>, #<immd>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stnt1b { Z18.B }, P7, [X21]  // STNT1B { <Zt>.B }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1b { Z9.B }, P6, [X26, #-7, MUL VL]  // STNT1B { <Zt>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1b { Z18.B }, P1, [X1, X20]  // STNT1B { <Zt>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Non temporal store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1d { Z16.D }, P3, [X3]  // STNT1D { <Zt>.D }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1d { Z27.D }, P4, [X16, #-6, MUL VL]  // STNT1D { <Zt>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1d { Z11.D }, P0, [X18, X22, LSL #3]  // STNT1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Non temporal store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1h { Z27.H }, P5, [X16]  // STNT1H { <Zt>.H }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1h { Z2.H }, P2, [X30, #-8, MUL VL]  // STNT1H { <Zt>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1h { Z0.H }, P1, [X7, X1, LSL #1]  // STNT1H { <Zt>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Non temporal store, scalar + scalar  \\ 3 2  2  2.0 V1UnitL01,V1UnitS,V1UnitV
+  stnt1w { Z9.S }, P3, [X20]  // STNT1W { <Zt>.S }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1w { Z12.S }, P4, [X11, #-6, MUL VL]  // STNT1W { <Zt>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stnt1w { Z28.S }, P6, [X6, X0, LSL #2]  // STNT1W { <Zt>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Non temporal store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  stp S10, S19, [X13], #76  // STP <St1>, <St2>, [<Xn|SP>], #<imm32>  \\ Store vector pair, immed post-index, S-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  stp D19, D20, [X30], #-144  // STP <Dt1>, <Dt2>, [<Xn|SP>], #<imm64>  \\ Store vector pair, immed post-index, D-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  stp Q3, Q17, [X14], #-976  // STP <Qt1>, <Qt2>, [<Xn|SP>], #<imm128>  \\ Store vector pair, immed post-index, Q-form  \\ 3 2  2  1.0 V1UnitI,V1UnitL01[2],V1UnitV01[2]
+  stp S19, S24, [X27, #-224]!  // STP <St1>, <St2>, [<Xn|SP>, #<imm32>]!  \\ Store vector pair, immed pre-index, S-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  stp D16, D21, [X28, #168]!  // STP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]!  \\ Store vector pair, immed pre-index, D-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  stp Q10, Q31, [X0, #608]!  // STP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]!  \\ Store vector pair, immed pre-index, Q-form  \\ 3 2  2  1.0 V1UnitI,V1UnitL01[2],V1UnitV01[2]
+  stp S27, S11, [X30]  // STP <St1>, <St2>, [<Xn|SP>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stp D30, D19, [X25]  // STP <Dt1>, <Dt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stp Q25, Q3, [X27]  // STP <Qt1>, <Qt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stp S29, S13, [X0, #-44]  // STP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stp D15, D12, [X20, #-72]  // STP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stp Q13, Q16, [X3, #320]  // STP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stp W18, W8, [X6], #196  // STP <Wt1>, <Wt2>, [<Xn|SP>], #<imms>  \\ Store pair, immed post-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  stp X10, X17, [X7], #-328  // STP <Xt1>, <Xt2>, [<Xn|SP>], #<immd>  \\ Store pair, immed post-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  stp W4, W3, [X0, #-36]!  // STP <Wt1>, <Wt2>, [<Xn|SP>, #<imms>]!  \\ Store pair, immed pre-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  stp X14, X13, [X24, #-272]!  // STP <Xt1>, <Xt2>, [<Xn|SP>, #<immd>]!  \\ Store pair, immed pre-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  stp W27, W30, [X20]  // STP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stp X3, X6, [X16]  // STP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stp W9, W14, [X10, #-24]  // STP <Wt1>, <Wt2>, [<Xn|SP>, #<imms>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stp X27, X4, [X14, #-448]  // STP <Xt1>, <Xt2>, [<Xn|SP>, #<immd>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W14, [X2], #-72  // STR <Wt>, [<Xn|SP>], #<simm>  \\ Store, immed post-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  str X28, [X14], #-130  // STR <Xt>, [<Xn|SP>], #<simm>  \\ Store register, immed post-index  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W9, [X29, #-227]!  // STR <Wt>, [<Xn|SP>, #<simm>]!  \\ Store, immed pre-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  str X13, [X5, #233]!  // STR <Xt>, [<Xn|SP>, #<simm>]!  \\ Store register, immed pre-index   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W2, [X30]  // STR <Wt>, [<Xn|SP>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W28, [X2, #1796]  // STR <Wt>, [<Xn|SP>, #<pimm32>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X22, [X29]  // STR <Xt>, [<Xn|SP>]  \\ Store register, unsigned immed  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X2, [X10, #9472]  // STR <Xt>, [<Xn|SP>, #<pimm64>]  \\ Store register, unsigned immed  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str B21, [X28], #-62  // STR <Bt>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H13, [X10], #-194  // STR <Ht>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S14, [X8], #166  // STR <St>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D24, [X10], #134  // STR <Dt>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q20, [X30], #-108  // STR <Qt>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str B9, [X24, #242]!  // STR <Bt>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H0, [X4, #-193]!  // STR <Ht>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S19, [X23, #115]!  // STR <St>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D20, [X2, #-30]!  // STR <Dt>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q24, [X20, #62]!  // STR <Qt>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str B5, [X11]  // STR <Bt>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str B20, [X23, #2409]  // STR <Bt>, [<Xn|SP>, #<pimm8>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H23, [X15]  // STR <Ht>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H24, [X6, #492]  // STR <Ht>, [<Xn|SP>, #<pimm16>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S25, [X19]  // STR <St>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S2, [X14, #984]  // STR <St>, [<Xn|SP>, #<pimm32>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D15, [X2]  // STR <Dt>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D27, [X7, #25704]  // STR <Dt>, [<Xn|SP>, #<pimm64>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q13, [X16]  // STR <Qt>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q4, [X7, #96]  // STR <Qt>, [<Xn|SP>, #<pimm128>]  \\ Store vector reg, immed pre-index, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str P4, [X5]  // STR <Pt>, [<Xn|SP>]  \\ Store from predicate reg  \\ 1 1  1  2.0 V1UnitL01
+  str P3, [X21, #-78, MUL VL]  // STR <Pt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Store from predicate reg  \\ 1 1  1  2.0 V1UnitL01
+  str W14, [X9, X17]  // STR <Wt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X5, [X0, X22]  // STR <Xt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W24, [X21, W29, UXTW]  // STR <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X27, [X26, W24, UXTW]  // STR <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W28, [X29, W29, SXTW]  // STR <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X25, [X1, W24, SXTW]  // STR <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W2, [X24, X12, SXTX]  // STR <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X3, [X24, X27, SXTX]  // STR <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W29, [X30, W30, UXTW #2] // STR <Wt>, [<Xn|SP>, <Wm>, UXTW #2] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X5, [X13, W8, UXTW #3] // STR <Xt>, [<Xn|SP>, <Wm>, UXTW #3] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W28, [X7, W24, SXTW #2] // STR <Wt>, [<Xn|SP>, <Wm>, SXTW #2] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X23, [X2, W26, SXTW #3] // STR <Xt>, [<Xn|SP>, <Wm>, SXTW #3] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W11, [X8, X30, SXTX #2] // STR <Wt>, [<Xn|SP>, <Xm>, SXTX #2] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X20, [X4, X2, SXTX #3] // STR <Xt>, [<Xn|SP>, <Xm>, SXTX #3] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str W8, [X11, X10, LSL #2]  // STR <Wt>, [<Xn|SP>, <Xm>, LSL #2]  \\ Store register, register offset, scaled by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str X27, [X2, X11, LSL #3]  // STR <Xt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Store register, register offset, scaled by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  str B14, [X13, X25]  // STR <Bt>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str B30, [X16, W26, UXTW]  // STR <Bt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str B20, [X19, W3, SXTW]  // STR <Bt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str B13, [X29, X19, SXTX]  // STR <Bt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H16, [X5, X24]  // STR <Ht>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H15, [X15, W15, UXTW]  // STR <Ht>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H3, [X6, W15, SXTW]  // STR <Ht>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H2, [X1, X28, SXTX]  // STR <Ht>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str H30, [X29, W30, UXTW #1] // STR <Ht>, [<Xn|SP>, <Wm>, UXTW #1] \\ Store vector reg, register offset, extend, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str H10, [X21, W11, SXTW #1] // STR <Ht>, [<Xn|SP>, <Wm>, SXTW #1] \\ Store vector reg, register offset, extend, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str H0, [X15, X9, SXTX #1] // STR <Ht>, [<Xn|SP>, <Xm>, SXTX #1] \\ Store vector reg, register offset, extend, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str H13, [X0, X26, LSL #1]  // STR <Ht>, [<Xn|SP>, <Xm>, LSL #1]  \\ Store vector reg, register offset, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str S2, [X16, X17]  // STR <St>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S20, [X24, W10, UXTW]  // STR <St>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S4, [X9, W14, SXTW]  // STR <St>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S3, [X23, X26, SXTX]  // STR <St>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S27, [X17, W9, UXTW #2] // STR <St>, [<Xn|SP>, <Wm>, UXTW #2] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S0, [X11, W20, SXTW #2] // STR <St>, [<Xn|SP>, <Wm>, SXTW #2] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S20, [X17, X14, SXTX #2] // STR <St>, [<Xn|SP>, <Xm>, SXTX #2] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str S0, [X15, X28, LSL #2]  // STR <St>, [<Xn|SP>, <Xm>, LSL #2]  \\ Store vector reg, register offset, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D5, [X26, X6]  // STR <Dt>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D11, [X9, W5, UXTW]  // STR <Dt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D16, [X20, W8, SXTW]  // STR <Dt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D0, [X12, X9, SXTX]  // STR <Dt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D4, [X21, W25, UXTW #3] // STR <Dt>, [<Xn|SP>, <Wm>, UXTW #3] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D28, [X20, W4, SXTW #3] // STR <Dt>, [<Xn|SP>, <Wm>, SXTW #3] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D20, [X13, X23, SXTX #3] // STR <Dt>, [<Xn|SP>, <Xm>, SXTX #3] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str D31, [X19, X28, LSL #3]  // STR <Dt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Store vector reg, register offset, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q13, [X24, X1]  // STR <Qt>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q1, [X25, W9, UXTW]  // STR <Qt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q25, [X20, W15, SXTW]  // STR <Qt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q25, [X0, X15, SXTX]  // STR <Qt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  str Q6, [X13, W0, UXTW #4] // STR <Qt>, [<Xn|SP>, <Wm>, UXTW #4] \\ Store vector reg, register offset, extend, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str Q27, [X4, W15, SXTW #4] // STR <Qt>, [<Xn|SP>, <Wm>, SXTW #4] \\ Store vector reg, register offset, extend, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str Q3, [X23, X0, SXTX #4] // STR <Qt>, [<Xn|SP>, <Xm>, SXTX #4] \\ Store vector reg, register offset, extend, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str Q27, [X1, X28, LSL #4]  // STR <Qt>, [<Xn|SP>, <Xm>, LSL #4]  \\ Store vector reg, register offset, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+  str Z3, [X0]  // STR <Zt>, [<Xn|SP>]  \\ Store from vector reg  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  str Z8, [X6, #188, MUL VL]  // STR <Zt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Store from vector reg  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+  strb W23, [X11], #34  // STRB <Wt>, [<Xn|SP>], #<simm>  \\ Store, immed post-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  strb W5, [X19, #-175]!  // STRB <Wt>, [<Xn|SP>, #<simm>]!  \\ Store, immed pre-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  strb W18, [X30]  // STRB <Wt>, [<Xn|SP>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strb W12, [X9, #2315]  // STRB <Wt>, [<Xn|SP>, #<pimm>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strb W5, [X26, W7, UXTW]  // STRB <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strb W18, [X2, W28, SXTW]  // STRB <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strb W21, [X21, X7, SXTX]  // STRB <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strb W9, [X6, X21]  // STRB <Wt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W21, [X8], #192  // STRH <Wt>, [<Xn|SP>], #<simm>  \\ Store, immed post-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  strh W8, [X26, #-204]!  // STRH <Wt>, [<Xn|SP>, #<simm>]!  \\ Store, immed pre-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+  strh W6, [X7]  // STRH <Wt>, [<Xn|SP>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W0, [X19, #7514]  // STRH <Wt>, [<Xn|SP>, #<pimm>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W12, [X0, X11]  // STRH <Wt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W5, [X18, W8, UXTW]  // STRH <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W28, [X29, W0, SXTW]  // STRH <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W7, [X17, X0, SXTX]  // STRH <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  strh W7, [X2, W14, UXTW #1]  // STRH <Wt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Store register, register offset, extend, scale by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+  strh W7, [X16, W29, SXTW #1]  // STRH <Wt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Store register, register offset, extend, scale by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+  strh W5, [X1, X13, SXTX #1]  // STRH <Wt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Store register, register offset, extend, scale by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+  strh W14, [X28, X2, LSL #1]  // STRH <Wt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Store register, register offset, scaled by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+  sttr W17, [X20]  // STTR <Wt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttr W14, [X30, #-35]  // STTR <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttr X10, [X16]  // STTR <Xt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttr X16, [X8, #-25]  // STTR <Xt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttrb W13, [X2]  // STTRB <Wt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttrb W0, [X20, #-114]  // STTRB <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttrh W26, [X11]  // STTRH <Wt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sttrh W11, [X30, #-78]  // STTRH <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stur B29, [X8]  // STUR <Bt>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur B5, [X0, #80]  // STUR <Bt>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur H10, [X15]  // STUR <Ht>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur H10, [X12, #-227]  // STUR <Ht>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur S10, [X4]  // STUR <St>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur S9, [X14, #21]  // STUR <St>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur D1, [X28]  // STUR <Dt>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur D6, [X6, #188]  // STUR <Dt>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur Q6, [X16]  // STUR <Qt>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur Q5, [X13, #-253]  // STUR <Qt>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+  stur W29, [X27]  // STUR <Wt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stur W14, [X2, #-34]  // STUR <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stur X29, [X10]  // STUR <Xt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stur X30, [X25, #127]  // STUR <Xt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sturb W21, [X5]  // STURB <Wt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sturb W25, [X26, #-117]  // STURB <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sturh W0, [X11]  // STURH <Wt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  sturh W7, [X10, #-209]  // STURH <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+  stxp W29, W24, W6, [X9]  // STXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stxp W26, W19, W22, [X11, #0]  // STXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stxp W30, X6, X3, [X1]  // STXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stxp W7, X2, X10, [X25, #0]  // STXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stxr W19, W21, [X9]  // STXR <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stxr W25, W1, [X24, #0]  // STXR <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stxr W25, X30, [X28]  // STXR <Ws>, <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stxr W30, X20, [X23, #0]  // STXR <Ws>, <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stxrb W0, W26, [X10]  // STXRB <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stxrb W10, W16, [X25, #0]  // STXRB <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  stxrh W0, W20, [X8]  // STXRH <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+  stxrh W12, W14, [X1, #0]  // STXRH <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+  sub W13, WSP, W10  // SUB <Wd>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+  sub W22, WSP, W13, UXTB   // SUB <Wd>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+  sub W18, WSP, W23, SXTB #1  // SUB <Wd>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+  sub W13, WSP, W8, LSL #4  // SUB <Wd>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+  sub X6, X8, X22  // SUB <Xd>, <Xn|SP>, X<m>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sub X16, X2, W19, UXTB  // SUB <Xd>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sub X16, X3, W27, UXTB #2  // SUB <Xd>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, extend and shift  \\ 1 2  2  2.0 V1UnitM
+  sub X4, X13, X16, LSL #3  // SUB <Xd>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+  sub WSP, WSP, #50  // SUB <Wd|WSP>, <Wn|WSP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sub WSP, WSP, #84, LSL #12  // SUB <Wd|WSP>, <Wn|WSP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sub X18, X22, #36  // SUB <Xd|SP>, <Xn|SP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sub X17, X20, #184, LSL #0  // SUB <Xd|SP>, <Xn|SP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+  sub Z18.B, Z18.B, #117  // SUB <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sub Z22.S, Z22.S, #4  // SUB <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sub Z15.H, Z15.H, #196, LSL #8  // SUB <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sub W0, W21, W2, LSL #4  // SUB <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+  sub W22, W7, W13, LSL #19  // SUB <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+  sub W1, W18, W16, ASR #4  // SUB <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+  sub X27, X29, X16, LSL #1  // SUB <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+  sub X24, X10, X15, LSL #35  // SUB <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+  sub X24, X19, X13, LSR #20  // SUB <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+  sub D18, D25, D0  // SUB <V><d>, <V><n>, <V><m>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  sub V15.2S, V14.2S, V11.2S  // SUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  sub Z18.H, P4/M, Z18.H, Z7.H  // SUB <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  sub Z29.B, Z19.B, Z8.B  // SUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  subhn V7.4H, V10.4S, V13.4S  // SUBHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  subhn2 V24.4S, V24.2D, V8.2D  // SUBHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  subr Z13.B, Z13.B, #229  // SUBR <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  subr Z17.S, Z17.S, #140  // SUBR <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  subr Z15.D, Z15.D, #100, LSL #0  // SUBR <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  subr Z21.D, P7/M, Z21.D, Z24.D  // SUBR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  subs W25, WSP, W13  // SUBS <Wd>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs W10, WSP, W9, UXTH   // SUBS <Wd>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs W20, WSP, W3, SXTH #2  // SUBS <Wd>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs W12, WSP, W27, LSL #4  // SUBS <Wd>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs X16, X20, X21  // SUBS <Xd>, <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs X15, X2, W11, UXTB  // SUBS <Xd>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs X13, X15, X14, SXTX #1  // SUBS <Xd>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  subs X30, X1, X26, LSL #3  // SUBS <Xd>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  subs W25, WSP, #239  // SUBS <Wd>, <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs W13, WSP, #75, LSL #12  // SUBS <Wd>, <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  subs X9, X3, #173  // SUBS <Xd>, <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs X30, X25, #82, LSL #12  // SUBS <Xd>, <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  subs W16, W27, W25  // SUBS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs W0, W30, W27, LSL #4  // SUBS <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs W17, W27, W3, LSL #20  // SUBS <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  subs W27, W7, W27, ASR #5  // SUBS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  subs X21, X22, X17  // SUBS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  subs X18, X1, X5, LSL #0  // SUBS <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+  subs X28, X26, X4, LSL #49  // SUBS <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  subs X26, X14, X30, LSR #35  // SUBS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  sudot V4.2S, V20.8B, V18.4B[2]  // SUDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product using signed and unsigned integers  \\ 1 3 1 4.0 V1UnitV
+  sudot Z5.S, Z30.B, Z3.B[1]  // SUDOT <Zda>.S, <Zn>.B, <Zm>.B[<imm>]  \\ Dot product, 8 bit, using signed and unsigned integers  \\ 1 3 1 2.0 V1UnitV[2]
+  sunpkhi Z22.D, Z16.S  // SUNPKHI <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+  sunpklo Z10.H, Z0.B  // SUNPKLO <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+  suqadd B15, B21  // SUQADD <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  suqadd V26.16B, V27.16B  // SUQADD <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  svc #35275  // SVC #<imm>  \\ No description \\ No scheduling info
+  sxtb W7, W20  // SXTB <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  sxtb X18, W14  // SXTB <Xd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  sxtb Z16.H, P5/M, Z15.H  // SXTB <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+  sxth Z4.S, P7/M, Z11.S  // SXTH <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+  sxtw Z12.D, P1/M, Z16.D  // SXTW <Zd>.D, <Pg>/M, <Zn>.D  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+  sxth W23, W2  // SXTH <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  sxth X22, W17  // SXTH <Xd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  sxtl V4.8H, V21.8B  // SXTL <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sxtl2 V20.2D, V30.4S  // SXTL2 <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  sxtw X18, W22  // SXTW <Xd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  sys #6, C6, C0, #3 // SYS #<op1>, <Cn>, <Cm>, #<op2> \\ No description \\ No scheduling info
+  sys #7, C12, C5, #3, X8  // SYS #<op1>, <Cn>, <Cm>, #<op2>, <Xt>  \\ No description \\ No scheduling info
+  sysl X16, #5, C11, C8, #5  // SYSL <Xt>, #<op1>, <Cn>, <Cm>, #<op2>  \\ No description \\ No scheduling info
+  tbl V7.8B, { V2.16B, V3.16B }, V17.8B  // TBL <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 1 or 2 table regs  \\ 1 2  2  2.0 V1UnitV01
+  tbl V3.16B, { V10.16B, V11.16B, V12.16B }, V29.16B  // TBL <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 3 table regs  \\ 1 4  4  1.0 V1UnitV01[2]
+  tbl V9.8B, { V22.16B, V23.16B, V24.16B, V25.16B }, V14.8B  // TBL <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B, <Vn+3>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 4 table regs  \\ 1 4  4  0.67 V1UnitV01[3]
+  tbl V29.16B, { V3.16B }, V17.16B  // TBL <Vd>.<Ta>, { <Vn>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 1 or 2 table regs  \\ 1 2  2  2.0 V1UnitV01
+  tbnz W3, #28, test  // TBNZ W<t>, #<imms>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  tbnz X30, #48, test  // TBNZ X<t>, #<immd>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  tbx V25.8B, { V13.16B, V14.16B }, V30.8B  // TBX <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 2 table reg  \\ 1 4  4  1.0 V1UnitV01[2]
+  tbx V22.16B, { V3.16B, V4.16B, V5.16B }, V25.16B  // TBX <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 3 table reg  \\ 1 6  6  0.67 V1UnitV01[3]
+  tbx V23.16B, { V0.16B, V1.16B, V2.16B, V3.16B }, V26.16B  // TBX <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B, <Vn+3>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 4 table reg  \\ 1 6  6  0.4 V1UnitV01[5]
+  tbx V16.8B, { V21.16B }, V18.8B  // TBX <Vd>.<Ta>, { <Vn>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 1 table reg  \\ 1 2  2  2.0 V1UnitV01
+  tbz W17, #16, test  // TBZ W<t>, #<imms>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  tbz X22, #41, test  // TBZ X<t>, #<immd>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+  tlbi VMALLE1 // TLBI <tlbi_op> \\ No description \\ No scheduling info
+  tlbi IPAS2E1IS, X7 // TLBI <tlbi_op2>, <Xt> \\ No description \\ No scheduling info
+  trn1 V30.2S, V21.2S, V25.2S  // TRN1 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD transpose  \\ 1 2  2  4.0 V1UnitV
+  trn1 P1.S, P4.S, P0.S  // TRN1 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate transpose  \\ 1 2  2  1.0 V1UnitM0
+  trn2 P0.H, P5.H, P7.H  // TRN2 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate transpose  \\ 1 2  2  1.0 V1UnitM0
+  trn2 V27.2D, V29.2D, V10.2D  // TRN2 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD transpose  \\ 1 2  2  4.0 V1UnitV
+  tst W25, #0xe00  // TST <Wn>, #<imms>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  tst X3, #0x1e00  // TST <Xn>, #<immd>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  tst W9, W14  // TST <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  tst W10, W3, ASR #16  // TST <Wn>, <Wm>, <shift> #<wamount>  \\ Test/Compare, shift by immed  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  tst X11, X28  // TST <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+  tst X9, X7, ASR #33  // TST <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, flagset  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+  uaba V13.16B, V14.16B, V19.16B  // UABA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff accum  \\ 1 4 1 2.0 V1UnitV13
+  uabal V13.2D, V16.2S, V11.2S  // UABAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+  uabal2 V17.4S, V0.8H, V1.8H  // UABAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+  uabd V23.4S, V4.4S, V30.4S  // UABD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff  \\ 1 2  2  4.0 V1UnitV
+  uabd Z5.B, P5/M, Z5.B, Z10.B  // UABD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uabdl V13.4S, V26.4H, V7.4H  // UABDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+  uabdl2 V15.2D, V9.4S, V10.4S  // UABDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+  uadalp V31.1D, V14.2S  // UADALP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD pairwise add and accumulate long  \\ 1 4 1 2.0 V1UnitV13
+  uaddl V29.8H, V8.8B, V31.8B  // UADDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  uaddl2 V15.4S, V22.8H, V14.8H  // UADDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  uaddlp V15.1D, V5.2S  // UADDLP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+  uaddlv H24, V24.8B  // UADDLV H<d>, <Vn>.8B  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  uaddlv H19, V31.16B  // UADDLV H<d>, <Vn>.16B  \\ ASIMD arith, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  uaddlv S12, V24.4H  // UADDLV S<d>, <Vn>.4H  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  uaddlv S30, V0.8H  // UADDLV S<d>, <Vn>.8H  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  uaddlv D6, V19.4S  // UADDLV D<d>, <Vn>.4S  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  uaddv D9, P5, Z1.B  // UADDV <Dd>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+  uaddv D26, P0, Z25.H  // UADDV <Dd>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+  uaddv D4, P1, Z1.S  // UADDV <Dd>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+  uaddv D28, P6, Z6.D  // UADDV <Dd>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+  uaddw V17.2D, V9.2D, V12.2S  // UADDW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  uaddw2 V15.4S, V13.4S, V4.8H  // UADDW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  ubfiz W11, W6, #30, #1  // UBFIZ <Wd>, <Wn>, #<lsbs>, #<widths>  \\ No description \\ No scheduling info
+  ubfiz X27, X15, #49, #9  // UBFIZ <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ No description \\ No scheduling info
+  ubfm W19, W16, #25, #24  // UBFM <Wd>, <Wn>, #<immrs>, #<immss>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+  ubfm X4, X30, #59, #50  // UBFM <Xd>, <Xn>, #<immrd>, #<immsd>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+  ubfx W13, W18, #25, #3  // UBFX <Wd>, <Wn>, #<lsbs>, #<widths>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+  ubfx X23, X26, #59, #5  // UBFX <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+  ucvtf H8, W24, #16  // UCVTF <Hd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf S7, W16, #29  // UCVTF <Sd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf D5, W17, #23  // UCVTF <Dd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf H13, X17, #12  // UCVTF <Hd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf S25, X2, #37  // UCVTF <Sd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf D20, X11, #43  // UCVTF <Dd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf H30, W4  // UCVTF <Hd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf S22, W8  // UCVTF <Sd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf D8, W15  // UCVTF <Dd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf H17, X12  // UCVTF <Hd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf S8, X0  // UCVTF <Sd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf D22, X17  // UCVTF <Dd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+  ucvtf H22, H16, #11  // UCVTF H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf S17, S18, #18  // UCVTF S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf D19, D1, #2  // UCVTF D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf V18.4H, V11.4H, #7  // UCVTF <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  ucvtf V22.8H, V20.8H, #10  // UCVTF <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  ucvtf V16.2S, V17.2S, #11  // UCVTF <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf V17.4S, V23.4S, #2  // UCVTF <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  ucvtf V18.2D, V20.2D, #60  // UCVTF <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf H7, H21  // UCVTF <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf S25, S7  // UCVTF S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf D30, D29  // UCVTF D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf V9.4H, V25.4H  // UCVTF <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  ucvtf V24.8H, V31.8H  // UCVTF <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+  ucvtf V14.2S, V2.2S  // UCVTF <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf V20.4S, V0.4S  // UCVTF <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+  ucvtf V27.2D, V3.2D  // UCVTF <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+  ucvtf Z31.H, P5/M, Z30.H  // UCVTF <Zd>.H, <Pg>/M, <Zn>.H  \\ Convert to floating point, 16b to half  \\ 1 6  6  0.25 V1UnitV0[4]
+  ucvtf Z23.H, P7/M, Z9.S  // UCVTF <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+  ucvtf Z1.S, P1/M, Z10.S  // UCVTF <Zd>.S, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+  ucvtf Z24.D, P5/M, Z9.S  // UCVTF <Zd>.D, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+  ucvtf Z30.H, P2/M, Z24.D  // UCVTF <Zd>.H, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+  ucvtf Z9.S, P5/M, Z9.D  // UCVTF <Zd>.S, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+  ucvtf Z18.D, P6/M, Z19.D  // UCVTF <Zd>.D, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+  udiv W12, W17, W22  // UDIV <Wd>, <Wn>, <Wm>  \\ Divide, W-form  \\ 1 12 12 0.08 V1UnitM0[12]
+  udiv X7, X2, X23  // UDIV <Xd>, <Xn>, <Xm>  \\ Divide, X-form  \\ 1 20 20 0.05 V1UnitM0[20]
+  udiv Z30.S, P5/M, Z30.S, Z10.S  // UDIV <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+  udiv Z31.D, P5/M, Z31.D, Z29.D  // UDIV <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+  udivr Z19.S, P4/M, Z19.S, Z8.S  // UDIVR <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+  udivr Z3.D, P5/M, Z3.D, Z8.D  // UDIVR <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+  udot Z0.S, Z5.B, Z4.B[1]  // UDOT <Zda>.S, <Zn>.B, <Zms>.B[<imms>]  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+  udot Z19.D, Z1.H, Z13.H[1]  // UDOT <Zda>.D, <Zn>.H, <Zmd>.H[<immd>]  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+  udot Z22.S, Z29.B, Z4.B  // UDOT <Zda>.S, <Zn>.B, <Zm>.B  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+  udot Z9.D, Z1.H, Z11.H  // UDOT <Zda>.D, <Zn>.H, <Zm>.H  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+  udot V10.2S, V11.8B, V21.4B[3]  // UDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+  udot V7.4S, V21.16B, V6.4B[3]  // UDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+  udot V19.2S, V31.8B, V17.8B  // UDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+  uhadd V10.8H, V7.8H, V7.8H  // UHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  uhsub V12.4H, V16.4H, V28.4H  // UHSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  umaddl X9, W28, W9, X19  // UMADDL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+  umax Z8.B, Z8.B, #12  // UMAX <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  umax Z27.B, P1/M, Z27.B, Z13.B  // UMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  umax V7.16B, V11.16B, V7.16B  // UMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  umaxp V15.8H, V8.8H, V12.8H  // UMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  umaxv B19, V7.8B  // UMAXV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  umaxv B12, V10.16B  // UMAXV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  umaxv H27, V5.4H  // UMAXV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  umaxv H11, V22.8H  // UMAXV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  umaxv S5, V25.4S  // UMAXV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  umaxv B9, P7, Z19.B  // UMAXV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+  umaxv H8, P7, Z26.H  // UMAXV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+  umaxv S15, P2, Z28.S  // UMAXV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+  umaxv D11, P4, Z11.D  // UMAXV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+  umin Z21.S, Z21.S, #139  // UMIN <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  umin Z31.S, P2/M, Z31.S, Z4.S  // UMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  umin V0.16B, V26.16B, V2.16B  // UMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  uminp V28.4S, V16.4S, V15.4S  // UMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+  uminv B23, V21.8B  // UMINV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  uminv B3, V10.16B  // UMINV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+  uminv H6, V22.4H  // UMINV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  uminv H23, V3.8H  // UMINV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+  uminv S29, V19.4S  // UMINV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+  uminv B2, P5, Z8.B  // UMINV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+  uminv H28, P0, Z0.H  // UMINV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+  uminv S10, P1, Z29.S  // UMINV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+  uminv D24, P5, Z29.D  // UMINV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+  umlal V22.4S, V14.4H, V0.H[6]  // UMLAL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlal V28.2D, V31.2S, V0.S[1]  // UMLAL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlal2 V31.4S, V7.8H, V15.H[5]  // UMLAL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlal2 V10.2D, V4.4S, V3.S[2]  // UMLAL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlal V29.4S, V20.4H, V30.4H  // UMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlal2 V10.2D, V28.4S, V19.4S  // UMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlsl V21.4S, V12.4H, V7.H[5]  // UMLSL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlsl V20.2D, V20.2S, V2.S[0]  // UMLSL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlsl2 V27.4S, V28.8H, V6.H[4]  // UMLSL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlsl2 V30.2D, V23.4S, V1.S[2]  // UMLSL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlsl V11.2D, V23.2S, V1.2S  // UMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  umlsl2 V11.8H, V20.16B, V2.16B  // UMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+  ummla V14.4S, V17.16B, V25.16B  // UMMLA <Vd>.4S, <Vn>.16B, <Vm>.16B  \\ ASIMD matrix multiply-accumulate  \\ 1 3 1 4.0 V1UnitV
+  umnegl X23, W5, W23  // UMNEGL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+  umov W6, V22.B[0]  // UMOV <Wd>, <Vn>.B[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov W29, V0.B[11]  // UMOV <Wd>, <Vn>.B[<indexb>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov W10, V25.H[0]  // UMOV <Wd>, <Vn>.H[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov W6, V7.H[3]  // UMOV <Wd>, <Vn>.H[<indexh>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov W8, V8.S[0]  // UMOV <Wd>, <Vn>.S[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov W20, V1.S[3]  // UMOV <Wd>, <Vn>.S[<indexs>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov X20, V11.D[0]  // UMOV <Xd>, <Vn>.D[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umov X29, V7.D[1]  // UMOV <Xd>, <Vn>.D[<indexd>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+  umsubl X21, W16, W28, X6  // UMSUBL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+  umulh Z20.B, P4/M, Z20.B, Z6.B  // UMULH <Zdn>.B, <Pg>/M, <Zdn>.B, <Zm>.B  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  umulh Z30.H, P6/M, Z30.H, Z15.H  // UMULH <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  umulh Z11.S, P7/M, Z11.S, Z8.S  // UMULH <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+  umulh Z3.D, P3/M, Z3.D, Z2.D  // UMULH <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+  umulh X23, X22, X19  // UMULH <Xd>, <Xn>, <Xm>  \\ Multiply high  \\ 1 3  3  2.0 V1UnitM
+  umull X5, W17, W23  // UMULL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+  umull V27.4S, V1.4H, V8.H[6]  // UMULL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  umull V22.2D, V28.2S, V6.S[1]  // UMULL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  umull2 V18.4S, V26.8H, V10.H[1]  // UMULL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  umull2 V28.2D, V21.4S, V1.S[0]  // UMULL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  umull V23.4S, V26.4H, V19.4H  // UMULL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  umull2 V11.8H, V29.16B, V29.16B  // UMULL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+  uqadd Z18.B, Z18.B, #14  // UQADD <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqadd Z2.S, Z2.S, #14  // UQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqadd Z24.S, Z24.S, #56, LSL #0  // UQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqadd Z6.H, Z28.H, Z5.H  // UQADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqadd S0, S24, S30  // UQADD <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  uqadd V14.2D, V22.2D, V20.2D  // UQADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  uqdecb W10  // UQDECB <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecb W8, VL3  // UQDECB <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecb W3, VL32, MUL #1  // UQDECB <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecb X8  // UQDECB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecb X3, VL5  // UQDECB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecb X22, MUL3, MUL #2  // UQDECB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd W11  // UQDECD <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd W27, VL256  // UQDECD <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd W6, VL32, MUL #10  // UQDECD <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd X1  // UQDECD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd X12, VL8  // UQDECD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd X10, VL64, MUL #10  // UQDECD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecd Z0.D  // UQDECD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdecd Z8.D, VL3  // UQDECD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdecd Z27.D, VL16, MUL #2  // UQDECD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdech W30  // UQDECH <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdech W28, MUL3  // UQDECH <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdech W5, VL5, MUL #8  // UQDECH <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdech X2  // UQDECH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdech X15, VL7  // UQDECH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdech X17, VL256, MUL #10  // UQDECH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdech Z5.H  // UQDECH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdech Z16.H, VL128  // UQDECH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdech Z27.H, VL128, MUL #15  // UQDECH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdecp W19, P5.H  // UQDECP <Wdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  uqdecp X1, P1.B  // UQDECP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  uqdecp Z20.S, P0  // UQDECP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+  uqdecw W17  // UQDECW <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecw W11, VL256  // UQDECW <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecw W13, MUL4, MUL #13  // UQDECW <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecw X7  // UQDECW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecw X28, VL32  // UQDECW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecw X0, VL256, MUL #3  // UQDECW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqdecw Z29.S  // UQDECW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdecw Z22.S, VL2  // UQDECW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqdecw Z20.S, VL2, MUL #10  // UQDECW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqincb W2  // UQINCB <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincb W21, VL128  // UQINCB <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincb W0, ALL, MUL #13  // UQINCB <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincb X24  // UQINCB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincb X18, VL7  // UQINCB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincb X13, VL256, MUL #13  // UQINCB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd W23  // UQINCD <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd W27, VL4  // UQINCD <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd W7, VL32, MUL #16  // UQINCD <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd X0  // UQINCD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd X29, MUL4  // UQINCD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd X20, POW2, MUL #3  // UQINCD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincd Z29.D  // UQINCD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqincd Z4.D, VL64  // UQINCD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqincd Z12.D, VL6, MUL #13  // UQINCD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqinch W4  // UQINCH <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqinch W23, MUL3  // UQINCH <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqinch W27, VL7, MUL #3  // UQINCH <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqinch X8  // UQINCH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqinch X13, MUL3  // UQINCH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqinch X5, MUL4, MUL #9  // UQINCH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqinch Z21.H  // UQINCH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqinch Z1.H, VL8  // UQINCH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqinch Z7.H, VL7, MUL #12  // UQINCH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqincp W4, P5.D  // UQINCP <Wdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  uqincp X13, P5.D  // UQINCP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+  uqincp Z1.S, P0  // UQINCP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+  uqincw W13  // UQINCW <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincw W26, VL8  // UQINCW <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincw W3, VL16, MUL #13  // UQINCW <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincw X26  // UQINCW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincw X13, VL256  // UQINCW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincw X29, VL7, MUL #6  // UQINCW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+  uqincw Z26.S  // UQINCW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqincw Z31.S, VL5  // UQINCW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqincw Z12.S, VL7, MUL #4  // UQINCW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+  uqrshl S17, S5, S8  // UQRSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshl V25.8B, V13.8B, V23.8B  // UQRSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn B12, H9, #4  // UQRSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn H1, S28, #2  // UQRSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn S1, D4, #12  // UQRSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn V17.8B, V24.8H, #4  // UQRSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn V29.4H, V25.4S, #10  // UQRSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn V16.2S, V0.2D, #10  // UQRSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn2 V5.16B, V28.8H, #6  // UQRSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn2 V28.8H, V22.4S, #15  // UQRSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqrshrn2 V20.4S, V13.2D, #4  // UQRSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl B16, B25, #3  // UQSHL B<d>, B<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl H22, H27, #3  // UQSHL H<d>, H<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl S9, S5, #2  // UQSHL S<d>, S<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl D25, D1, #30  // UQSHL D<d>, D<n>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl V25.16B, V0.16B, #7  // UQSHL <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl V1.4H, V12.4H, #15  // UQSHL <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl V23.2S, V4.2S, #17  // UQSHL <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl V28.2D, V23.2D, #48  // UQSHL <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl B22, B26, B2  // UQSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshl V8.4H, V17.4H, V13.4H  // UQSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn B16, H27, #6  // UQSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn H4, S2, #15  // UQSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn S0, D15, #22  // UQSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn V19.8B, V26.8H, #3  // UQSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn V31.4H, V17.4S, #8  // UQSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn V1.2S, V11.2D, #9  // UQSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn2 V23.16B, V16.8H, #1  // UQSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn2 V1.8H, V12.4S, #2  // UQSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqshrn2 V30.4S, V29.2D, #32  // UQSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  uqsub Z26.B, Z26.B, #174  // UQSUB <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqsub Z19.S, Z19.S, #228  // UQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqsub Z15.H, Z15.H, #104, LSL #8  // UQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqsub Z25.D, Z13.D, Z19.D  // UQSUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+  uqsub S16, S21, S6  // UQSUB <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  uqsub V19.4S, V0.4S, V5.4S  // UQSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  uqxtn S3, D27  // UQXTN <Vb><d>, <Va><n>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  uqxtn V26.2S, V5.2D  // UQXTN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  uqxtn2 V15.16B, V22.8H  // UQXTN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+  urecpe V10.2S, V8.2S  // URECPE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form U32  \\ 1  3   3  2.0 V1UnitV02
+  urecpe V1.4S, V23.4S  // URECPE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, Q-form U32  \\ 1  4   4  1.0 V1UnitV02[2]
+  urhadd V16.2S, V19.2S, V2.2S  // URHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  urshl D24, D22, D29  // URSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  urshl V31.8B, V5.8B, V3.8B  // URSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+  urshr D23, D19, #62  // URSHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  urshr V23.16B, V14.16B, #2  // URSHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  urshr V16.4H, V13.4H, #7  // URSHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  urshr V10.4S, V10.4S, #21  // URSHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  urshr V2.2D, V16.2D, #30  // URSHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+  ursqrte V15.2S, V20.2S  // URSQRTE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form U32  \\ 1  3   3  2.0 V1UnitV02
+  ursqrte V31.4S, V14.4S  // URSQRTE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, Q-form U32  \\ 1  4   4  1.0 V1UnitV02[2]
+  ursra D24, D24, #48  // URSRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ursra V14.8B, V18.8B, #1  // URSRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ursra V9.4H, V9.4H, #16  // URSRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ursra V25.2S, V17.2S, #9  // URSRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  ursra V17.2D, V16.2D, #61  // URSRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  usdot V0.2S, V18.8B, V10.4B[3]  // USDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product using signed and unsigned integers  \\ 1 3 1 4.0 V1UnitV
+  usdot Z5.S, Z25.B, Z2.B[1]  // USDOT <Zda>.S, <Zn>.B, <Zm>.B[<imm>]  \\ Dot product, 8 bit, using signed and unsigned integers  \\ 1 3 1 2.0 V1UnitV[2]
+  usdot V17.2S, V0.8B, V29.8B  // USDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product using signed and unsigned integers  \\ 1 3 1 4.0 V1UnitV
+  usdot Z8.S, Z6.B, Z18.B  // USDOT <Zda>.S, <Zn>.B, <Zm>.B  \\ Dot product, 8 bit, using signed and unsigned integers  \\ 1 3 1 2.0 V1UnitV[2]
+  ushl D7, D17, D3  // USHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushl V6.8B, V26.8B, V6.8B  // USHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushll V18.8H, V24.8B, #4  // USHLL <Vd>.8H, <Vn>.8B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushll V12.4S, V10.4H, #3  // USHLL <Vd>.4S, <Vn>.4H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushll V16.2D, V16.2S, #31  // USHLL <Vd>.2D, <Vn>.2S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushll2 V14.8H, V3.16B, #3  // USHLL2 <Vd>.8H, <Vn>.16B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushll2 V18.4S, V22.8H, #13  // USHLL2 <Vd>.4S, <Vn>.8H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushll2 V31.2D, V12.4S, #11  // USHLL2 <Vd>.2D, <Vn>.4S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushr D23, D22, #58  // USHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushr V24.8B, V0.8B, #2  // USHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushr V21.8H, V31.8H, #11  // USHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushr V27.2S, V24.2S, #14  // USHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  ushr V0.2D, V27.2D, #48  // USHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  usmmla V25.4S, V10.16B, V11.16B  // USMMLA <Vd>.4S, <Vn>.16B, <Vm>.16B  \\ ASIMD matrix multiply-accumulate  \\ 1 3 1 4.0 V1UnitV
+  usqadd H14, H13  // USQADD <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  usqadd V18.2D, V23.2D  // USQADD <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+  usra D22, D24, #9  // USRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  usra V16.16B, V5.16B, #5  // USRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  usra V18.4H, V22.4H, #11  // USRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  usra V13.2S, V12.2S, #24  // USRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  usra V30.2D, V30.2D, #41  // USRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+  usubl V22.4S, V18.4H, V3.4H  // USUBL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  usubl2 V12.8H, V23.16B, V15.16B  // USUBL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  usubw V30.8H, V12.8H, V20.8B  // USUBW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  usubw2 V2.4S, V0.4S, V30.8H  // USUBW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+  uunpkhi Z26.D, Z26.S  // UUNPKHI <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+  uunpklo Z10.S, Z11.H  // UUNPKLO <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+  uxtb W2, W23  // UXTB <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  uxtb Z1.D, P2/M, Z11.D  // UXTB <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+  uxth Z6.S, P3/M, Z18.S  // UXTH <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+  uxtw Z23.D, P4/M, Z3.D  // UXTW <Zd>.D, <Pg>/M, <Zn>.D  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+  uxth W7, W14  // UXTH <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+  uxtl V1.4S, V22.4H  // UXTL <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  uxtl2 V14.8H, V3.16B  // UXTL2 <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+  uzp1 V9.2S, V29.2S, V20.2S  // UZP1 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+  uzp1 P5.D, P3.D, P5.D  // UZP1 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+  uzp2 P6.S, P0.S, P6.S  // UZP2 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+  uzp2 V18.4S, V12.4S, V31.4S  // UZP2 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+  wfe  // WFE  \\ No description \\ No scheduling info
+  wfi  // WFI  \\ No description \\ No scheduling info
+  whilele P6.H, X28, X30  // WHILELE <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+  whilelo P3.B, X9, X7  // WHILELO <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+  whilels P4.B, W4, W20  // WHILELS <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+  whilelt P7.S, X20, X6  // WHILELT <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+  wrffr P7.B  // WRFFR <Pn>.B  \\ Write to first fault register  \\ 1 2  2  1.0 V1UnitM0
+  xtn V20.8B, V17.8H  // XTN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow  \\ 1 2  2  4.0 V1UnitV
+  xtn2 V31.16B, V26.8H  // XTN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow  \\ 1 2  2  4.0 V1UnitV
+  yield  // YIELD  \\ No description \\ No scheduling info
+  zip1 V21.2D, V4.2D, V11.2D  // ZIP1 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+  zip1 P0.D, P1.D, P4.D  // ZIP1 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+  zip2 P3.S, P5.S, P4.S  // ZIP2 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+  zip2 V2.4S, V20.4S, V5.4S  // ZIP2 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+
+.Lfunc_end0:
+  .size	test, .Lfunc_end0-test
+  .cfi_endproc
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      376600
+# CHECK-NEXT: Total Cycles:      292826
+# CHECK-NEXT: Total uOps:        532700
+
+# CHECK:      Dispatch Width:    15
+# CHECK-NEXT: uOps Per Cycle:    1.82
+# CHECK-NEXT: IPC:               1.29
+# CHECK-NEXT: Block RThroughput: 854.0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - V1UnitB:2
+# CHECK-NEXT: [1]   - V1UnitD:2
+# CHECK-NEXT: [2]   - V1UnitFlg:3
+# CHECK-NEXT: [3]   - V1UnitI:4   V1UnitS, V1UnitS, V1UnitM0, V1UnitM1
+# CHECK-NEXT: [4]   - V1UnitL:3   V1UnitL01, V1UnitL01, V1UnitL2
+# CHECK-NEXT: [5]   - V1UnitL2:1
+# CHECK-NEXT: [6]   - V1UnitL01:2
+# CHECK-NEXT: [7]   - V1UnitM:2   V1UnitM0, V1UnitM1
+# CHECK-NEXT: [8]   - V1UnitM0:1
+# CHECK-NEXT: [9]   - V1UnitM1:1
+# CHECK-NEXT: [10]  - V1UnitS:2
+# CHECK-NEXT: [11]  - V1UnitV:4   V1UnitV0, V1UnitV1, V1UnitV2, V1UnitV3
+# CHECK-NEXT: [12]  - V1UnitV0:1
+# CHECK-NEXT: [13]  - V1UnitV1:1
+# CHECK-NEXT: [14]  - V1UnitV2:1
+# CHECK-NEXT: [15]  - V1UnitV3:1
+# CHECK-NEXT: [16]  - V1UnitV01:2 V1UnitV0, V1UnitV1
+# CHECK-NEXT: [17]  - V1UnitV02:2 V1UnitV0, V1UnitV2
+# CHECK-NEXT: [18]  - V1UnitV13:2 V1UnitV1, V1UnitV3
+
+# CHECK:      Scheduling Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: Bypass Latency
+# CHECK-NEXT: [4]: Throughput
+# CHECK-NEXT: [5]: Resources
+# CHECK-NEXT: [6]: LLVM OpcodeName
+# CHECK-NEXT: [7]: Instruction
+# CHECK-NEXT: [8]: Comment if any
+# CHECK-NEXT:  [1]    [2]  [3]   [4]      [5]                                                                [6]                [7]                                 [8]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ABSv1i64         | abs	d15, d11                       /* ABS <V><d>, <V><n>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV */
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ABSv2i32         | abs	v25.2s, v25.2s                 // ABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ABS_ZPmZ_B       | abs	z26.b, p6/m, z27.b             // ABS <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADCWr            | adc	w13, w6, w4                    // ADC <Wd>, <Wn>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADCXr            | adc	x8, x12, x10                   // ADC <Xd>, <Xn>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADCSWr           | adcs	w29, w7, w30                   // ADCS <Wd>, <Wn>, <Wm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADCSXr           | adcs	x11, x3, x5                    // ADCS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWrx           | add	wsp, wsp, w10                  // ADD <Wd|WSP>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWrx           | add	wsp, wsp, w2, uxtb             // ADD <Wd|WSP>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWrx           | add	wsp, wsp, w13, uxth #4         // ADD <Wd|WSP>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWrx           | add	wsp, wsp, w13, lsl #4          // ADD <Wd|WSP>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDXrs           | add	x22, x2, x27                   // ADD <Xd|SP>, <Xn|SP>, X<m>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDXrx           | add	x25, x9, w25, uxtb             // ADD <Xd|SP>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | ADDXrx           | add	x4, x28, w3, uxtb #3           // ADD <Xd|SP>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, extend and shift  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDXrs           | add	x0, x28, x26, lsl #3           // ADD <Xd|SP>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWri           | add	wsp, wsp, #3765                // ADD <Wd|WSP>, <Wn|WSP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWri           | add	wsp, wsp, #3547, lsl #12       // ADD <Wd|WSP>, <Wn|WSP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDXri           | add	x7, x30, #803                  // ADD <Xd|SP>, <Xn|SP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDXri           | add	x7, x2, #319, lsl #12          // ADD <Xd|SP>, <Xn|SP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADD_ZI_D         | add	z13.d, z13.d, #245             // ADD <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADD_ZI_D         | add	z16.d, z16.d, #59648           // ADD <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWrs           | add	w3, w2, w21, lsl #3            // ADD <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | ADDWrs           | add	w6, w21, w17, lsl #15          // ADD <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | ADDWrs           | add	w28, w30, w19, asr #30         // ADD <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDXrs           | add	x8, x3, x28, lsl #3            // ADD <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | ADDXrs           | add	x12, x13, x0, lsl #44          // ADD <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | ADDXrs           | add	x5, x20, x28, lsr #16          // ADD <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ADDv1i64         | add	d0, d23, d21                   // ADD <V><d>, <V><n>, <V><m>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ADDv4i32         | add	v19.4s, v24.4s, v15.4s         // ADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADD_ZPmZ_D       | add	z29.d, p5/m, z29.d, z29.d      // ADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADD_ZZZ_H        | add	z10.h, z22.h, z13.h            // ADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ADDHNv4i32_v4i16 | addhn	v26.4h, v5.4s, v9.4s           // ADDHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ADDHNv8i16_v16i8 | addhn2	v1.16b, v19.8h, v6.8h  // ADDHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ADDPv2i64p       | addp	d1, v14.2d                     // ADDP <V><d>, <Vn>.<T>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ADDPv2i32        | addp	v7.2s, v1.2s, v2.2s            // ADDP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ADDPL_XXI        | addpl	x27, x6, #-6                   // ADDPL <Xd|SP>, <Xn|SP>, #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | adds	w17, wsp, w25                  // ADDS <Wd>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | adds	w6, wsp, w15, uxth             // ADDS <Wd>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | adds	w22, wsp, w30, uxtb #2         // ADDS <Wd>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | adds	w12, wsp, w29, lsl #4          // ADDS <Wd>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | adds	x14, x0, x10                   // ADDS <Xd>, <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrx          | adds	x13, x23, w8, uxtb             // ADDS <Xd>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXrx          | adds	x4, x26, w28, uxtb #1          // ADDS <Xd>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | adds	x10, x3, x29, lsl #2           // ADDS <Xd>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWri          | adds	w23, wsp, #502                 // ADDS <Wd>, <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSWri          | adds	w2, wsp, #2980, lsl #12        // ADDS <Wd>, <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXri          | adds	x12, x4, #1345                 // ADDS <Xd>, <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXri          | adds	x25, x18, #3037, lsl #12       // ADDS <Xd>, <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrs          | adds	w12, w13, w26                  // ADDS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrs          | adds	w0, w23, w20                   // ADDS <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSWrs          | adds	w13, w16, w12, lsl #28         // ADDS <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSWrs          | adds	w20, w19, w16, asr #0          // ADDS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | adds	x23, x12, x4                   // ADDS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | adds	x0, x13, x4, lsl #2            // ADDS <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXrs          | adds	x4, x7, x6, lsl #31            // ADDS <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXrs          | adds	x9, x8, x9, asr #41            // ADDS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | ADDVv8i8v        | addv	b0, v28.8b                     // ADDV B<d>, <Vn>.8B  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | ADDVv16i8v       | addv	b1, v26.16b                    // ADDV B<d>, <Vn>.16B  \\ ASIMD arith, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | ADDVv4i16v       | addv	h18, v13.4h                    // ADDV H<d>, <Vn>.4H  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | ADDVv8i16v       | addv	h29, v17.8h                    // ADDV H<d>, <Vn>.8H  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | ADDVv4i32v       | addv	s22, v18.4s                    // ADDV S<d>, <Vn>.4S  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ADDVL_XXI        | addvl	x1, x27, #-8                   // ADDVL <Xd|SP>, <Xn|SP>, #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADR              | adr	x3, test                       // ADR <Xd>, <label>  \\ Address generation  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADR_LSL_ZZZ_D_0  | adr	z26.d, [z1.d, z8.d]            // ADR <Zd>.<T>, [<Zn>.<T>, <Zm>.<T>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADR_LSL_ZZZ_S_2  | adr	z22.s, [z28.s, z8.s, lsl #2]   // ADR <Zd>.<T>, [<Zn>.<T>, <Zm>.<T>, <mod> #<amount>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADR_SXTW_ZZZ_D_0 | adr	z11.d, [z2.d, z29.d, sxtw]     // ADR <Zd>.D, [<Zn>.D, <Zm>.D, SXTW ]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADR_SXTW_ZZZ_D_2 | adr	z3.d, [z9.d, z9.d, sxtw #2]    // ADR <Zd>.D, [<Zn>.D, <Zm>.D, SXTW #<amount>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADR_UXTW_ZZZ_D_0 | adr	z6.d, [z7.d, z13.d, uxtw]      // ADR <Zd>.D, [<Zn>.D, <Zm>.D, UXTW ]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ADR_UXTW_ZZZ_D_1 | adr	z4.d, [z24.d, z22.d, uxtw #1]  // ADR <Zd>.D, [<Zn>.D, <Zm>.D, UXTW #<amount>]  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADRP             | adrp	x0, test                       // ADRP <Xd>, <label>  \\ Address generation  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ANDWri           | and	wsp, w16, #0xe00               // AND <Wd|WSP>, <Wn>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ANDXri           | and	x2, x22, #0x1e00               // AND <Xd|SP>, <Xn>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z1.b, z1.b, #0x70              // AND <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z7.h, z7.h, #0x60              // AND <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z7.s, z7.s, #0x2               // AND <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z7.d, z7.d, #0x4               // AND <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | AND_PPzPP        | and	p5.b, p1/z, p6.b, p4.b         // AND <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ANDWrs           | and	w11, w14, w24                  // AND <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ANDWrs           | and	w2, w21, w22, lsr #25          // AND <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ANDXrs           | and	x1, x20, x29                   // AND <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ANDXrs           | and	x8, x11, x22, asr #56          // AND <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ANDv8i8          | and	v29.8b, v26.8b, v26.8b         // AND <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZPmZ_D       | and	z17.d, p6/m, z17.d, z12.d      // AND <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZZZ          | and	z9.d, z5.d, z17.d              // AND <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSWri          | ands	w14, w8, #0x70                 // ANDS <Wd>, <Wn>, #<imms>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSXri          | ands	x4, x10, #0x60                 // ANDS <Xd>, <Xn>, #<immd>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSWrs          | ands	w29, w28, w12                  // ANDS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ANDSWrs          | ands	w7, w13, w23, asr #3           // ANDS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift by immed, flagset, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSXrs          | ands	x21, x9, x6                    // ANDS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ANDSXrs          | ands	x10, x27, x7, asr #20          // ANDS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, flagset  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | ANDS_PPzPP       | ands	p5.b, p1/z, p2.b, p7.b         // ANDS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | ANDV_VPZ_H       | andv	h7, p6, z31.h                  // ANDV <V><d>, <Pg>, <Zn>.<T>  \\ Reduction, logical   \\ 1 12  12  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMWri          | asr	w30, w14, #5                   // ASR <Wd>, <Wn>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | asr	x12, x21, #28                  // ASR <Xd>, <Xn>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZPmI_B       | asr	z7.b, p5/m, z7.b, #3           // ASR <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZPmI_H       | asr	z6.h, p6/m, z6.h, #5           // ASR <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZPmI_S       | asr	z28.s, p0/m, z28.s, #11        // ASR <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZPmI_D       | asr	z26.d, p5/m, z26.d, #24        // ASR <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZZI_B        | asr	z10.b, z14.b, #3               // ASR <Zd>.B, <Zn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZZI_H        | asr	z23.h, z18.h, #6               // ASR <Zd>.H, <Zn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZZI_S        | asr	z29.s, z11.s, #6               // ASR <Zd>.S, <Zn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZZI_D        | asr	z20.d, z26.d, #29              // ASR <Zd>.D, <Zn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ASRVWr           | asr	w3, w0, w20                    // ASR <Wd>, <Wn>, <Wm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ASRVXr           | asr	x7, x5, x21                    // ASR <Xd>, <Xn>, <Xm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_ZPmZ_S       | asr	z3.s, p0/m, z3.s, z10.s        // ASR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_WIDE_ZPmZ_S  | asr	z9.s, p2/m, z9.s, z8.d         // ASR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASR_WIDE_ZZZ_S   | asr	z26.s, z21.s, z21.d            // ASR <Zd>.<T>, <Zn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASRD_ZPmI_B      | asrd	z6.b, p4/m, z6.b, #2           // ASRD <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASRD_ZPmI_H      | asrd	z19.h, p3/m, z19.h, #6         // ASRD <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASRD_ZPmI_S      | asrd	z16.s, p3/m, z16.s, #2         // ASRD <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASRD_ZPmI_D      | asrd	z9.d, p6/m, z9.d, #12          // ASRD <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift right for divide  \\ 1 4  4  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | ASRR_ZPmZ_B      | asrr	z0.b, p0/m, z0.b, z19.b        // ASRR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ASRVWr           | asr	w24, w28, w13                  // ASRV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ASRVXr           | asr	x3, x21, x24                   // ASRV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | at	s12e1r, x28                    // AT <at_op>, <Xt>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | B                | b	test                           // B <label>  \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.eq	test                           // B.eq <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.eq	test                           // B.none <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.ne	test                           // B.ne <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.ne	test                           // B.any <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.hs	test                           // B.cs <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.hs	test                           // B.hs <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.hs	test                           // B.nlast <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.lo	test                           // B.cc <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.lo	test                           // B.lo <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.lo	test                           // B.last <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.mi	test                           // B.mi <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.mi	test                           // B.first <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.pl	test                           // B.pl <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.pl	test                           // B.nfrst <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.vs	test                           // B.vs <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.vc	test                           // B.vc <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.hi	test                           // B.hi <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.hi	test                           // B.pmore <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.ls	test                           // B.ls <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.ls	test                           // B.plast <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.ge	test                           // B.ge <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.ge	test                           // B.tcont <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.lt	test                           // B.lt <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.lt	test                           // B.tstop <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.gt	test                           // B.gt <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.le	test                           // B.le <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.al	test                           // B.al <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | Bcc              | b.nv	test                           // B.nv <label> \\ Branch, immed  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | BFCVT            | bfcvt	h6, s20                        // BFCVT <Hd>, <Sn>  \\ Scalar convert, F32 to BF16  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | BFCVT_ZPmZ       | bfcvt	z16.h, p6/m, z1.s              // BFCVT <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | BFCVTN           | bfcvtn	v12.4h, v15.4s         // BFCVTN <Vd>.<Ta>, <Vn>.4S  \\ ASIMD convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | BFCVTN2          | bfcvtn2	v15.8h, v13.4s         // BFCVTN2 <Vd>.<Ta>, <Vn>.4S  \\ ASIMD convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | BFCVTNT_ZPmZ     | bfcvtnt	z11.h, p7/m, z24.s     // BFCVTNT <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert, F32 to BF16  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | BF16DOTlanev4bf16 | bfdot	v0.2s, v24.4h, v14.2h[2]  // BFDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.2H[<index>]  \\ ASIMD dot product  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BFDOT_ZZI        | bfdot	z24.s, z26.h, z2.h[0]          // BFDOT <Zda>.S, <Zn>.H, <Zm>.H[<imm>]  \\ Dot product  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | BFDOTv8bf16      | bfdot	v31.4s, v21.8h, v14.8h         // BFDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BFDOT_ZZZ        | bfdot	z15.s, z3.h, z7.h              // BFDOT <Zda>.S, <Zn>.H, <Zm>.H  \\ Dot product  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | BFMWri           | bfi	w10, w26, #31, #1              // BFI <Wd>, <Wn>, #<lsbs>, #<widths>  \\ Bit field insert/clear, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | BFMXri           | bfi	x25, x7, #8, #1                // BFI <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ Bit field insert/clear, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | BFMWri           | bfi	w30, w26, #18, #13             // BFM <Wd>, <Wn>, #<immrs>, #<immss>  \\ Bitfield move, insert  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | BFMXri           | bfxil	x15, x20, #0, #36              // BFM <Xd>, <Xn>, #<immrd>, #<immsd>  \\ Bitfield move, insert  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BFMLALB_ZZZI     | bfmlalb	z13.s, z30.h, z0.h[0]  // BFMLALB <Zda>.S, <Zn>.H, <Zm>.H[<imm>]  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BFMLALB_ZZZ      | bfmlalb	z3.s, z14.h, z13.h     // BFMLALB <Zda>.S, <Zn>.H, <Zm>.H  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | BFMLALBIdx       | bfmlalb	v22.4s, v11.8h, v11.h[5]  // BFMLALB <Vd>.4S, <Vn>.8H, <Vm>.H[<index>]  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | BFMLALTIdx       | bfmlalt	v17.4s, v4.8h, v11.h[7]  // BFMLALT <Vd>.4S, <Vn>.8H, <Vm>.H[<index>]  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | BFMLALB          | bfmlalb	v13.4s, v5.8h, v17.8h  // BFMLALB <Vd>.4S, <Vn>.8H, <Vm>.8H  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | BFMLALT          | bfmlalt	v10.4s, v16.8h, v1.8h  // BFMLALT <Vd>.4S, <Vn>.8H, <Vm>.8H  \\ ASIMD multiply accumulate long  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BFMLALT_ZZZI     | bfmlalt	z23.s, z3.h, z2.h[2]   // BFMLALT <Zda>.S, <Zn>.H, <Zm>.H[<imm>]  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BFMLALT_ZZZ      | bfmlalt	z25.s, z21.h, z22.h    // BFMLALT <Zda>.S, <Zn>.H, <Zm>.H  \\ Multiply accumulate long  \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 5  | 3   | 4.00   | V1UnitV                                                          | BFMMLA           | bfmmla	v15.4s, v28.8h, v23.8h  // BFMMLA <Vd>.4S, <Vn>.8H, <Vm>.8H  \\ ASIMD matrix multiply accumulate  \\ 1 5 3 4.0 V1UnitV
+# CHECK-NEXT:   1    | 5  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | BFMMLA_ZZZ       | bfmmla	z26.s, z2.h, z12.h     // BFMMLA <Zda>.S, <Zn>.H, <Zm>.H  \\ Matrix multiply accumulate  \\ 1 5 3 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | BFMWri           | bfxil	w27, w23, #14, #14             // BFXIL <Wd>, <Wn>, #<lsbs>, #<widths>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | BFMXri           | bfxil	x0, x5, #11, #22               // BFXIL <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z28.b, z28.b, #0x8f            // BIC <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z18.h, z18.h, #0xff9f          // BIC <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z12.s, z12.s, #0xfffffffd      // BIC <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | AND_ZI           | and	z6.d, z6.d, #0xfffffffffffffffb  // BIC <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | BIC_PPzPP        | bic	p4.b, p4/z, p6.b, p0.b         // BIC <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | BICWrs           | bic	w0, w26, w22                   // BIC <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | BICWrs           | bic	w23, w10, w7, lsl #11          // BIC <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | BICXrs           | bic	x21, x20, x14                  // BIC <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | BICXrs           | bic	x21, x3, x17, lsr #35          // BIC <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BICv4i16         | bic	v6.4h, #217                    // BIC <Vd>.<Th>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BICv8i16         | bic	v23.8h, #101                   // BIC <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BICv2i32         | bic	v24.2s, #70                    // BIC <Vd>.<T>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BICv2i32         | bic	v31.2s, #192                   // BIC <Vd>.<T>, #<imm8>, LSL #<amount>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BICv16i8         | bic	v25.16b, v10.16b, v9.16b       // BIC <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BIC_ZPmZ_D       | bic	z15.d, p4/m, z15.d, z25.d      // BIC <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | BIC_ZZZ          | bic	z7.d, z8.d, z28.d              // BIC <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | BICSWrs          | bics	w24, w1, w25                   // BICS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | BICSWrs          | bics	w21, w0, w24, lsl #11          // BICS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift by immed, flagset, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | BICSXrs          | bics	x27, x25, x10                  // BICS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | BICSXrs          | bics	x22, x6, x27, lsl #62          // BICS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, flagset  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | BICS_PPzPP       | bics	p2.b, p4/z, p1.b, p7.b         // BICS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BIFv8i8          | bif	v0.8b, v25.8b, v4.8b           // BIF <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD bitwise insert  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BITv8i8          | bit	v5.8b, v12.8b, v22.8b          // BIT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD bitwise insert  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitB, V1UnitI, V1UnitS                                        | BL               | bl	test                           // BL <label>  \\ Branch and link, immed  \\ 2 1  1  2.0 V1UnitB,V1UnitS
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitB, V1UnitI, V1UnitS                                        | BLR              | blr	x11                            // BLR <Xn>  \\ Branch and link, register   \\ 2 1  1  2.0 V1UnitB,V1UnitS
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | BR               | br	x17                            // BR <Xn>  \\ Branch, register  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | BRK              | brk	#0x8415                        // BRK #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | BRKA_PPzP        | brka	p7.b, p7/z, p5.b               // BRKA <Pd>.B, <Pg>/<ZM>, <Pn>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | BRKAS_PPzP       | brkas	p6.b, p5/z, p0.b               // BRKAS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | BRKB_PPzP        | brkb	p5.b, p0/z, p1.b               // BRKB <Pd>.B, <Pg>/<ZM>, <Pn>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | BRKBS_PPzP       | brkbs	p6.b, p1/z, p4.b               // BRKBS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | BRKN_PPzP        | brkn	p7.b, p0/z, p6.b, p7.b         // BRKN <Pdm>.B, <Pg>/Z, <Pn>.B, <Pdm>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | BRKNS_PPzP       | brkns	p3.b, p1/z, p7.b, p3.b         // BRKNS <Pdm>.B, <Pg>/Z, <Pn>.B, <Pdm>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | BRKPA_PPzPP      | brkpa	p3.b, p5/z, p0.b, p1.b         // BRKPA <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | BRKPAS_PPzPP     | brkpas	p2.b, p5/z, p1.b, p3.b  // BRKPAS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | BRKPB_PPzPP      | brkpb	p1.b, p0/z, p7.b, p6.b         // BRKPB <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | BRKPBS_PPzPP     | brkpbs	p7.b, p1/z, p6.b, p1.b  // BRKPBS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Loop control, based on predicate and flag setting  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | BSLv16i8         | bsl	v27.16b, v13.16b, v21.16b      // BSL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD bitwise insert  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | CBNZW            | cbnz	w21, test                      // CBNZ <Wt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | CBNZX            | cbnz	x26, test                      // CBNZ <Xt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | CBZW             | cbz	w6, test                       // CBZ <Wt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | CBZX             | cbz	x4, test                       // CBZ <Xt>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMNWi           | ccmn	w8, #14, #3, hs                // CCMN <Wn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMNXi           | ccmn	x23, #17, #0, gt               // CCMN <Xn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMNWr           | ccmn	w17, w18, #12, hs              // CCMN <Wn>, <Wm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMNXr           | ccmn	x19, x29, #12, lo              // CCMN <Xn>, <Xm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMPWi           | ccmp	w24, #2, #5, hs                // CCMP <Wn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMPXi           | ccmp	x12, #8, #2, lo                // CCMP <Xn>, #<imm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMPWr           | ccmp	w2, w9, #3, lt                 // CCMP <Wn>, <Wm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CCMPXr           | ccmp	x11, x10, #13, ls              // CCMP <Xn>, <Xm>, #<nzcv>, <cond>  \\ Conditional compare, flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINCWr          | cinc	w23, w5, lt                    // CINC <Wd>, <Wn>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINCXr          | cinc	x2, x1, pl                     // CINC <Xd>, <Xn>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINVWr          | cinv	w9, w12, ge                    // CINV <Wd>, <Wn>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINVXr          | cinv	x9, x30, mi                    // CINV <Xd>, <Xn>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | CLASTA_VPZ_B     | clasta	b11, p4, b11, z21.b    // CLASTA <V><dn>, <Pg>, <V><dn>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   2    | 9  | 9   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13 | CLASTA_RPZ_B  | clasta	w8, p0, w8, z6.b       // CLASTA <R><dn>, <Pg>, <R><dn>, <Zm>.<T>  \\ Conditional extract operations, scalar form  \\ 2 9  9  1.0 V1UnitM0,V1UnitV1
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | CLASTA_ZPZ_S     | clasta	z25.s, p1, z25.s, z14.s  // CLASTA <Zdn>.<T>, <Pg>, <Zdn>.<T>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | CLASTB_VPZ_D     | clastb	d6, p7, d6, z31.d      // CLASTB <V><dn>, <Pg>, <V><dn>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   2    | 9  | 9   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13 | CLASTB_RPZ_B  | clastb	w28, p6, w28, z12.b    // CLASTB <R><dn>, <Pg>, <R><dn>, <Zm>.<T>  \\ Conditional extract operations, scalar form  \\ 2 9  9  1.0 V1UnitM0,V1UnitV1
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | CLASTB_ZPZ_H     | clastb	z27.h, p6, z27.h, z22.h  // CLASTB <Zdn>.<T>, <Pg>, <Zdn>.<T>, <Zm>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | CLREX            | clrex                               // CLREX   \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | CLREX            | clrex	#12                            // CLREX #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CLSv8i8          | cls	v5.8b, v22.8b                  // CLS <Vd>.<T>, <Vn>.<T>  \\ ASIMD count  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CLSWr            | cls	w25, w0                        // CLS <Wd>, <Wn>  \\ Count leading  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CLSXr            | cls	x22, x6                        // CLS <Xd>, <Xn>  \\ Count leading  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CLS_ZPmZ_D       | cls	z28.d, p3/m, z2.d              // CLS <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Count/reverse bits  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CLZv8i16         | clz	v24.8h, v30.8h                 // CLZ <Vd>.<T>, <Vn>.<T>  \\ ASIMD count  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CLZWr            | clz	w26, w27                       // CLZ <Wd>, <Wn>  \\ Count leading zeros  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CLZXr            | clz	x4, x0                         // CLZ <Xd>, <Xn>  \\ Count leading zeros  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CLZ_ZPmZ_S       | clz	z3.s, p3/m, z18.s              // CLZ <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Count/reverse bits  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMEQv1i64        | cmeq	d26, d5, d25                   // CMEQ <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMEQv8i16        | cmeq	v9.8h, v16.8h, v24.8h          // CMEQ <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMEQv1i64rz      | cmeq	d7, d26, #0                    // CMEQ <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMEQv4i16rz      | cmeq	v14.4h, v18.4h, #0             // CMEQ <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGEv1i64        | cmge	d26, d21, d28                  // CMGE <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGEv8i16        | cmge	v22.8h, v16.8h, v3.8h          // CMGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGEv1i64rz      | cmge	d30, d12, #0                   // CMGE <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGEv16i8rz      | cmge	v22.16b, v30.16b, #0           // CMGE <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGTv1i64        | cmgt	d23, d25, d12                  // CMGT <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGTv2i64        | cmgt	v3.2d, v29.2d, v11.2d          // CMGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGTv1i64rz      | cmgt	d28, d14, #0                   // CMGT <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMGTv2i32rz      | cmgt	v22.2s, v10.2s, #0             // CMGT <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMHIv1i64        | cmhi	d29, d16, d5                   // CMHI <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMHIv4i16        | cmhi	v28.4h, v25.4h, v21.4h         // CMHI <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMHSv1i64        | cmhs	d5, d3, d12                    // CMHS <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMHSv8i8         | cmhs	v6.8b, v31.8b, v12.8b          // CMHS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMLEv1i64rz      | cmle	d14, d21, #0                   // CMLE <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMLEv2i32rz      | cmle	v21.2s, v19.2s, #0             // CMLE <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMLTv1i64rz      | cmlt	d21, d24, #0                   // CMLT <V><d>, <V><n>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMLTv4i16rz      | cmlt	v26.4h, v12.4h, #0             // CMLT <Vd>.<T>, <Vn>.<T>, #0  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | cmn	wsp, w7                        // CMN <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | cmn	wsp, w8, sxtb                  // CMN <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | cmn	wsp, w3, uxtb #3               // CMN <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrx          | cmn	wsp, w7, lsl #3                // CMN <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | cmn	x2, x28                        // CMN <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrx          | cmn	x3, w0, uxtb                   // CMN <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXrx          | cmn	x0, w4, uxtb #3                // CMN <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | cmn	x14, x26, lsl #2               // CMN <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWri          | cmn	wsp, #613                      // CMN <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSWri          | cmn	wsp, #2991, lsl #12            // CMN <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXri          | cmn	x23, #3803                     // CMN <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXri          | cmn	x29, #3786, lsl #12            // CMN <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrs          | cmn	w12, w0                        // CMN <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSWrs          | cmn	w19, w27, lsl #1               // CMN <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSWrs          | cmn	w2, w11, lsl #29               // CMN <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSWrs          | cmn	w0, w0, asr #30                // CMN <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | cmn	x23, x28                       // CMN <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ADDSXrs          | cmn	x6, x1, lsl #2                 // CMN <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXrs          | cmn	x28, x30, lsl #26              // CMN <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ADDSXrs          | cmn	x25, x15, lsr #49              // CMN <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | cmp	wsp, w26                       // CMP <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | cmp	wsp, w13, sxth                 // CMP <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | cmp	wsp, w12, sxth #3              // CMP <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | cmp	wsp, w30, lsl #4               // CMP <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | cmp	x22, x18                       // CMP <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrx          | cmp	x16, w27, uxtb                 // CMP <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrx          | cmp	x16, w7, uxtb #4               // CMP <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | cmp	x21, x24, lsl #4               // CMP <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWri          | cmp	wsp, #2342                     // CMP <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWri          | cmp	wsp, #3664, lsl #12            // CMP <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXri          | cmp	x5, #1482                      // CMP <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXri          | cmp	x4, #3684, lsl #12             // CMP <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrs          | cmp	w14, w0, lsl #4                // CMP <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWrs          | cmp	w0, w23, lsl #29               // CMP <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWrs          | cmp	w2, w28, lsr #20               // CMP <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | cmp	x27, x10, lsl #1               // CMP <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrs          | cmp	x18, x12, lsl #14              // CMP <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrs          | cmp	x6, x7, lsr #0                 // CMP <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPEQ_PPzZI_H | cmpeq	p2.h, p0/z, z26.h, #-8         // CMPEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGE_PPzZI_B | cmpge	p1.b, p4/z, z28.b, #-6         // CMPGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGT_PPzZI_B | cmpgt	p1.b, p0/z, z13.b, #14         // CMPGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHI_PPzZI_D | cmphi	p1.d, p3/z, z23.d, #12         // CMPHI <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHS_PPzZI_D | cmphs	p7.d, p5/z, z23.d, #114        // CMPHS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPLE_PPzZI_B | cmple	p5.b, p2/z, z9.b, #9           // CMPLE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPLO_PPzZI_S | cmplo	p3.s, p5/z, z18.s, #87         // CMPLO <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPLS_PPzZI_D | cmpls	p6.d, p6/z, z31.d, #56         // CMPLS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPLT_PPzZI_H | cmplt	p0.h, p6/z, z29.h, #-13        // CMPLT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPNE_PPzZI_S | cmpne	p5.s, p4/z, z18.s, #15         // CMPNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #<imm>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPEQ_PPzZZ_S | cmpeq	p6.s, p5/z, z2.s, z9.s         // CMPEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGE_PPzZZ_S | cmpge	p7.s, p4/z, z15.s, z15.s       // CMPGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGT_PPzZZ_H | cmpgt	p2.h, p4/z, z26.h, z11.h       // CMPGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHI_PPzZZ_S | cmphi	p0.s, p4/z, z8.s, z4.s         // CMPHI <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHS_PPzZZ_D | cmphs	p1.d, p6/z, z26.d, z15.d       // CMPHS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPNE_PPzZZ_B | cmpne	p4.b, p3/z, z21.b, z16.b       // CMPNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPEQ_PPzZZ_D | cmpeq	p2.d, p3/z, z13.d, z18.d       // CMPEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGE_WIDE_PPzZZ_B | cmpge	p2.b, p3/z, z3.b, z16.d  // CMPGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGT_WIDE_PPzZZ_H | cmpgt	p2.h, p2/z, z28.h, z30.d  // CMPGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHI_WIDE_PPzZZ_H | cmphi	p0.h, p5/z, z30.h, z16.d  // CMPHI <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHS_WIDE_PPzZZ_H | cmphs	p7.h, p2/z, z1.h, z26.d  // CMPHS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPLE_WIDE_PPzZZ_B | cmple	p7.b, p7/z, z3.b, z13.d  // CMPLE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHI_PPzZZ_D | cmphi	p6.d, p2/z, z16.d, z16.d       // CMPLO <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPLS_WIDE_PPzZZ_H | cmpls	p3.h, p2/z, z12.h, z26.d  // CMPLS <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGT_PPzZZ_D | cmpgt	p0.d, p4/z, z26.d, z29.d       // CMPLT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPNE_WIDE_PPzZZ_S | cmpne	p0.s, p4/z, z30.s, z8.d  // CMPNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.D  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGE_PPzZZ_D | cmpge	p1.d, p3/z, z26.d, z2.d        // CMPLE <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHI_PPzZZ_B | cmphi	p7.b, p0/z, z25.b, z4.b        // CMPLO <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPHS_PPzZZ_D | cmphs	p4.d, p4/z, z14.d, z2.d        // CMPLS <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | CMPGT_PPzZZ_S | cmpgt	p2.s, p2/z, z21.s, z31.s       // CMPLT <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Compare and set flags  \\ 2 4  4  1.0 V1UnitV0,V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMTSTv1i64       | cmtst	d10, d6, d5                    // CMTST <V><d>, <V><n>, <V><m>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CMTSTv2i64       | cmtst	v13.2d, v13.2d, v13.2d         // CMTST <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSNEGWr          | cneg	w3, w17, hi                    // CNEG <Wd>, <Wn>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSNEGXr          | cneg	x26, x8, lo                    // CNEG <Xd>, <Xn>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CNOT_ZPmZ_S      | cnot	z7.s, p7/m, z8.s               // CNOT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | CNTv16i8         | cnt	v12.16b, v14.16b               // CNT <Vd>.<T>, <Vn>.<T>  \\ ASIMD count  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CNT_ZPmZ_H       | cnt	z26.h, p0/m, z27.h             // CNT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTB_XPiI        | cntb	x18                            // CNTB <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTB_XPiI        | cntb	x9, vl128                      // CNTB <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTB_XPiI        | cntb	x28, vl8, mul #13              // CNTB <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTD_XPiI        | cntd	x20                            // CNTD <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTD_XPiI        | cntd	x27, vl7                       // CNTD <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTD_XPiI        | cntd	x8, vl7, mul #2                // CNTD <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTH_XPiI        | cnth	x27                            // CNTH <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTH_XPiI        | cnth	x0, vl1                        // CNTH <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTH_XPiI        | cnth	x16, vl3, mul #6               // CNTH <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTW_XPiI        | cntw	x22                            // CNTW <Xd>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTW_XPiI        | cntw	x23, vl3                       // CNTW <Xd>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTW_XPiI        | cntw	x6, vl16, mul #11              // CNTW <Xd>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CNTP_XPP_S       | cntp	x22, p1, p2.s                  // CNTP <Xd>, <Pg>, <Pn>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | COMPACT_ZPZ_S    | compact	z17.s, p1, z18.s       // COMPACT <Zd>.<T>, <Pg>, <Zn>.<T>  \\ Conditional extract operations, SIMD&FP scalar and vector forms  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmV_B       | mov	z13.b, p0/m, b6                // CPY <Zd>.<T>, <Pg>/M, <V><n>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_B       | mov	z3.b, p6/m, #-118              // CPY <Zd>.B, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_S       | mov	z11.s, p5/m, #-62              // CPY <Zd>.<T>, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_H       | mov	z0.h, p0/m, #-11               // CPY <Zd>.<T>, <Pg>/M, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPzI_B       | mov	z5.b, p1/z, #-90               // CPY <Zd>.B, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPzI_H       | mov	z12.h, p1/z, #-118             // CPY <Zd>.<T>, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPzI_D       | mov	z25.d, p3/z, #-20736           // CPY <Zd>.<T>, <Pg>/Z, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV01                   | CPY_ZPmR_H       | mov	z24.h, p0/m, w19               // CPY <Zd>.<T>, <Pg>/M, <R><n>  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV01                   | CPY_ZPmR_S       | mov	z23.s, p2/m, wsp               // CPY <Zd>.<T>, <Pg>/M, <R2>SP  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32Brr         | crc32b	w27, w12, w15          // CRC32B <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32Hrr         | crc32h	w3, w15, w21           // CRC32H <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32Wrr         | crc32w	w9, w18, w24           // CRC32W <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32Xrr         | crc32x	w19, w6, x25           // CRC32X <Wd>, <Wn>, <Xm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32CBrr        | crc32cb	w25, w28, w30          // CRC32CB <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32CHrr        | crc32ch	w25, w26, w16          // CRC32CH <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32CWrr        | crc32cw	w27, w12, w23          // CRC32CW <Wd>, <Wn>, <Wm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CRC32CXrr        | crc32cx	w21, w28, x5           // CRC32CX <Wd>, <Wn>, <Xm>  \\ CRC checksum ops  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | csdb                                // CSDB  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSELWr           | csel	w25, w16, w30, ls              // CSEL <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSELXr           | csel	x28, x1, x2, pl                // CSEL <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINCWr          | cset	w6, ne                         // CSET <Wd>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINCXr          | cset	x11, lt                        // CSET <Xd>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINVWr          | csetm	w3, hi                         // CSETM <Wd>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINVXr          | csetm	x6, ne                         // CSETM <Xd>, <cond>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINCWr          | csinc	w9, w3, w14, lt                // CSINC <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINCXr          | csinc	x20, x11, x23, ge              // CSINC <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINVWr          | csinv	w1, w4, w3, hs                 // CSINV <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSINVXr          | csinv	x27, x21, x15, ne              // CSINV <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSNEGWr          | csneg	w5, w13, w4, hi                // CSNEG <Wd>, <Wn>, <Wm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | CSNEGXr          | cneg	x8, x29, ls                    // CSNEG <Xd>, <Xn>, <Xm>, <cond>  \\ Conditional select  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CTERMEQ_XX       | ctermeq	x4, x11                // CTERMEQ <R><n>, <R><m>  \\ Loop terminate  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | CTERMNE_XX       | ctermne	x0, x16                // CTERMNE <R><n>, <R><m>  \\ Loop terminate  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | dc	csw, x16                       // DC <dc_op>, <Xt>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DCPS1            | dcps1                               // DCPS1   \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DCPS1            | dcps1	#0x1127                        // DCPS1 #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DCPS2            | dcps2                               // DCPS2   \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DCPS2            | dcps2	#0x6884                        // DCPS2 #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DCPS3            | dcps3                               // DCPS3   \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DCPS3            | dcps3	#0xb8e2                        // DCPS3 #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECB_XPiI        | decb	x22                            // DECB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECB_XPiI        | decb	x5, vl256                      // DECB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECB_XPiI        | decb	x21, vl256, mul #7             // DECB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECD_XPiI        | decd	x11                            // DECD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECD_XPiI        | decd	x19                            // DECD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECD_XPiI        | decd	x24, vl2, mul #10              // DECD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECH_XPiI        | dech	x16                            // DECH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECH_XPiI        | dech	x20, mul4                      // DECH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECH_XPiI        | dech	x0, mul3, mul #15              // DECH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECW_XPiI        | decw	x27                            // DECW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECW_XPiI        | decw	x18, vl32                      // DECW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECW_XPiI        | decw	x29, vl6, mul #3               // DECW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECD_ZPiI        | decd	z19.d                          // DECD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECD_ZPiI        | decd	z22.d, mul3                    // DECD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECD_ZPiI        | decd	z1.d, vl128, mul #11           // DECD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECH_ZPiI        | dech	z23.h                          // DECH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECH_ZPiI        | dech	z29.h, vl5                     // DECH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECH_ZPiI        | dech	z28.h, vl64, mul #16           // DECH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECW_ZPiI        | decw	z8.s                           // DECW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECW_ZPiI        | decw	z4.s, vl64                     // DECW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DECW_ZPiI        | decw	z27.s, vl4, mul #10            // DECW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DECP_XP_B        | decp	x6, p6.b                       // DECP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 7  | 7   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV01[2]    | DECP_ZP_H        | decp	z22.h, p1.h                    // DECP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DMB              | dmb	sy                             // DMB <option>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DMB              | dmb	nshst                          // DMB #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | DRPS             | drps                                // DRPS  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi8            | mov	b15, v25.b[12]                 // DUP B<d>, <Vn>.B[<indexb>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi16           | mov	h2, v31.h[5]                   // DUP H<d>, <Vn>.H[<indexh>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi32           | mov	s10, v2.s[1]                   // DUP S<d>, <Vn>.S[<indexs>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi64           | mov	d24, v7.d[1]                   // DUP D<d>, <Vn>.D[<indexd>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPv8i8lane      | dup	v25.8b, v21.b[4]               // DUP <Vd>.<Tb>, <Vn>.B[<indexb>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPv8i16lane     | dup	v28.8h, v29.h[1]               // DUP <Vd>.<Th>, <Vn>.H[<indexh>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPv4i32lane     | dup	v24.4s, v9.s[3]                // DUP <Vd>.<Ts>, <Vn>.S[<indexs>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPv2i64lane     | dup	v20.2d, v3.d[0]                // DUP <Vd>.<Td>, <Vn>.D[<indexd>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DUPv4i32gpr      | dup	v19.4s, w27                    // DUP <Vd>.<T>, <R><n>  \\ ASIMD duplicate, gen reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_B         | mov	z30.b, #16                     // DUP <Zd>.B, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_H         | mov	z15.h, #105                    // DUP <Zd>.<T>, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_D         | mov	z22.d, #-14                    // DUP <Zd>.<T>, #<imm>, <shift>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_B        | mov	z2.b, z26.b[27]                // DUP <Zd>.B, <Zn>.B[<immb>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_H        | mov	z23.h, z22.h[2]                // DUP <Zd>.H, <Zn>.H[<immh>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_S        | mov	z29.s, z30.s[15]               // DUP <Zd>.S, <Zn>.S[<imms>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_D        | mov	z4.d, d7                       // DUP <Zd>.D, <Zn>.D[<immd>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DUP_ZR_D         | mov	z25.d, x28                     // DUP <Zd>.<T>, <R><n>  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DUP_ZR_S         | mov	z18.s, wsp                     // DUP <Zd>.<T>, <R2>SP  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUPM_ZI          | dupm	z18.b, #0x70                   // DUPM <Zd>.B, #<constb>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUPM_ZI          | dupm	z12.h, #0x60                   // DUPM <Zd>.H, #<consth>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUPM_ZI          | dupm	z16.s, #0x2                    // DUPM <Zd>.S, #<consts>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUPM_ZI          | dupm	z16.d, #0x4                    // DUPM <Zd>.D, #<constd>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EONWrs           | eon	w29, w4, w19                   // EON <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EONWrs           | eon	w14, w24, w28, asr #14         // EON <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EONXrs           | eon	x19, x12, x2                   // EON <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EONXrs           | eon	x23, x23, x23, asr #41         // EON <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z7.b, z7.b, #0x8f              // EON <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z3.h, z3.h, #0xff9f            // EON <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z2.s, z2.s, #0xfffffffd        // EON <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z24.d, z24.d, #0xfffffffffffffffb  // EON <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EORWri           | eor	wsp, w4, #0xe00                // EOR <Wd|WSP>, <Wn>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EORXri           | eor	x27, x25, #0x1e00              // EOR <Xd|SP>, <Xn>, #<immd>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z19.b, z19.b, #0x70            // EOR <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z18.h, z18.h, #0x60            // EOR <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z10.s, z10.s, #0x2             // EOR <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZI           | eor	z29.d, z29.d, #0x4             // EOR <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | EOR_PPzPP        | eor	p6.b, p7/z, p3.b, p5.b         // EOR <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EORWrs           | eor	w8, w27, w2                    // EOR <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EORWrs           | eor	w8, w7, w29, asr #30           // EOR <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EORXrs           | eor	x22, x16, x6                   // EOR <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EORXrs           | eor	x0, x23, x30, lsl #11          // EOR <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | EORv16i8         | eor	v8.16b, v10.16b, v19.16b       // EOR <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZPmZ_H       | eor	z8.h, p3/m, z8.h, z14.h        // EOR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | EOR_ZZZ          | eor	z30.d, z26.d, z20.d            // EOR <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | EORS_PPzPP       | eors	p1.b, p0/z, p3.b, p1.b         // EORS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | EORV_VPZ_H       | eorv	h17, p1, z15.h                 // EORV <V><d>, <Pg>, <Zn>.<T>  \\ Reduction, logical   \\ 1 12  12  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | ERET             | eret                                // ERET  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | esb                                 // ESB  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | EXTv8i8          | ext	v12.8b, v22.8b, v31.8b, #6     // EXT <Vd>.8B, <Vn>.8B, <Vm>.8B, #<index8>  \\ ASIMD extract  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | EXTv16i8         | ext	v17.16b, v18.16b, v8.16b, #10  // EXT <Vd>.16B, <Vn>.16B, <Vm>.16B, #<index16>  \\ ASIMD extract  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EXTRWrri         | ror	w19, w20, #16                  // EXTR <Wd>, <Wn>, <Wn>, #<lsbs>  \\ Bitfield extract, one reg  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitI, V1UnitM                                                 | EXTRWrri         | extr	w27, w4, w5, #23               // EXTR <Wd>, <Wn>, <Wm>, #<lsbs>  \\ Bitfield extract, two regs  \\ 1 3  3  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EXTRXrri         | ror	x25, x22, #62                  // EXTR <Xd>, <Xn>, <Xn>, #<lsbd>  \\ Bitfield extract, one reg  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitI, V1UnitM                                                 | EXTRXrri         | extr	x0, x12, x13, #17              // EXTR <Xd>, <Xn>, <Xm>, #<lsbd>  \\ Bitfield extract, two regs  \\ 1 3  3  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABD16           | fabd	h27, h20, h17                  // FABD <Hd>, <Hn>, <Hm>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABD32           | fabd	s16, s29, s6                   // FABD <V><d>, <V><n>, <V><m>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABDv8f16        | fabd	v13.8h, v28.8h, v12.8h         // FABD <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABDv4f32        | fabd	v12.4s, v4.4s, v31.4s          // FABD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FABD_ZPmZ_H      | fabd	z11.h, p6/m, z11.h, z5.h       // FABD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point absolute value/difference  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABSHr           | fabs	h25, h7                        // FABS <Hd>, <Hn>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABSSr           | fabs	s17, s12                       // FABS <Sd>, <Sn>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABSDr           | fabs	d30, d8                        // FABS <Dd>, <Dn>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABSv4f32        | fabs	v16.4s, v31.4s                 // FABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FABSv2f32        | fabs	v17.2s, v28.2s                 // FABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP absolute value/difference  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FABS_ZPmZ_S      | fabs	z26.s, p7/m, z24.s             // FABS <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Floating point absolute value/difference  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FACGE_PPzZZ_H    | facge	p0.h, p5/z, z15.h, z18.h       // FACGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FACGT_PPzZZ_S    | facgt	p7.s, p7/z, z10.s, z4.s        // FACGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGE16          | facge	h24, h26, h29                  // FACGE <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGE64          | facge	d25, d24, d7                   // FACGE <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGEv4f16       | facge	v25.4h, v16.4h, v11.4h         // FACGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGEv2f32       | facge	v19.2s, v24.2s, v5.2s          // FACGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGT16          | facgt	h0, h4, h10                    // FACGT <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGT32          | facgt	s29, s3, s2                    // FACGT <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGTv8f16       | facgt	v22.8h, v14.8h, v31.8h         // FACGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FACGTv4f32       | facgt	v22.4s, v8.4s, v2.4s           // FACGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FACGE_PPzZZ_H    | facge	p7.h, p5/z, z27.h, z22.h       // FACLE <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FACGT_PPzZZ_H    | facgt	p5.h, p5/z, z16.h, z31.h       // FACLT <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FADD_ZPmI_H      | fadd	z4.h, p7/m, z4.h, #1.0         // FADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDHrr          | fadd	h23, h27, h22                  // FADD <Hd>, <Hn>, <Hm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDSrr          | fadd	s1, s23, s27                   // FADD <Sd>, <Sn>, <Sm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDDrr          | fadd	d16, d15, d21                  // FADD <Dd>, <Dn>, <Dm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDv2f64        | fadd	v7.2d, v30.2d, v20.2d          // FADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDv2f64        | fadd	v16.2d, v13.2d, v11.2d         // FADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FADD_ZPmZ_H      | fadd	z26.h, p4/m, z26.h, z1.h       // FADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FADD_ZZZ_S       | fadd	z23.s, z7.s, z16.s             // FADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 19 | 19  | 0.06   | V1UnitV[18], V1UnitV0[18], V1UnitV01[18], V1UnitV02[18]          | FADDA_VPZ_H      | fadda	h8, p3, h8, z28.h              // FADDA H<dn>, <Pg>, H<dn>, <Zm>.H  \\ Floating point associative add, F16  \\ 1 19  19  0.06 V1UnitV0[18]
+# CHECK-NEXT:   1    | 11 | 11  | 0.10   | V1UnitV[10], V1UnitV0[10], V1UnitV01[10], V1UnitV02[10]          | FADDA_VPZ_S      | fadda	s11, p6, s11, z1.s             // FADDA S<dn>, <Pg>, S<dn>, <Zm>.S  \\ Floating point associative add, F32  \\ 1 11  11  0.1 V1UnitV0[10]
+# CHECK-NEXT:   1    | 8  | 8   | 0.67   | V1UnitV[3], V1UnitV01[3]                                         | FADDA_VPZ_D      | fadda	d27, p4, d27, z27.d            // FADDA D<dn>, <Pg>, D<dn>, <Zm>.D  \\ Floating point associative add, F64  \\ 1 8  8  0.67 V1UnitV01[3]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDPv2i16p      | faddp	h10, v19.2h                    // FADDP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDPv2i64p      | faddp	d11, v28.2d                    // FADDP <V><d>, <Vn>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDPv2f64       | faddp	v16.2d, v11.2d, v5.2d          // FADDP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FADDPv4f32       | faddp	v16.4s, v11.4s, v18.4s         // FADDP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 13 | 13  | 0.33   | V1UnitV[6], V1UnitV01[6]                                         | FADDV_VPZ_H      | faddv	h21, p2, z3.h                  // FADDV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+# CHECK-NEXT:   1    | 11 | 11  | 0.40   | V1UnitV[5], V1UnitV01[5]                                         | FADDV_VPZ_S      | faddv	s16, p2, z25.s                 // FADDV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+# CHECK-NEXT:   1    | 9  | 9   | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | FADDV_VPZ_D      | faddv	d18, p4, z7.d                  // FADDV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FCADD_ZPmZ_H     | fcadd	z29.h, p2/m, z29.h, z15.h, #270  // FCADD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>, <const>  \\ Floating point complex add  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCCMPHrr         | fccmp	h31, h3, #11, hs               // FCCMP <Hn>, <Hm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCCMPSrr         | fccmp	s5, s6, #0, lo                 // FCCMP <Sn>, <Sm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCCMPDrr         | fccmp	d17, d15, #0, ne               // FCCMP <Dn>, <Dm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCCMPEHrr        | fccmpe	h6, h1, #12, ne        // FCCMPE <Hn>, <Hm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCCMPESrr        | fccmpe	s16, s13, #10, vs      // FCCMPE <Sn>, <Sm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCCMPEDrr        | fccmpe	d17, d14, #15, ls      // FCCMPE <Dn>, <Dm>, #<nzcv>, <cond>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMEQ_PPzZZ_D    | fcmeq	p7.d, p1/z, z23.d, z21.d       // FCMEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMGE_PPzZZ_H    | fcmge	p6.h, p1/z, z19.h, z10.h       // FCMGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMGT_PPzZZ_S    | fcmgt	p5.s, p2/z, z29.s, z5.s        // FCMGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMNE_PPzZZ_D    | fcmne	p5.d, p0/z, z22.d, z15.d       // FCMNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMUO_PPzZZ_D    | fcmuo	p0.d, p2/z, z15.d, z23.d       // FCMUO <Pd>.<T>, <Pg>/Z, <Zn>.<T>, <Zm>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMEQ_PPzZ0_D    | fcmeq	p4.d, p5/z, z19.d, #0.0        // FCMEQ <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMGE_PPzZ0_D    | fcmge	p0.d, p5/z, z10.d, #0.0        // FCMGE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMGT_PPzZ0_D    | fcmgt	p6.d, p1/z, z8.d, #0.0         // FCMGT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMLE_PPzZ0_D    | fcmle	p2.d, p4/z, z26.d, #0.0        // FCMLE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMLT_PPzZ0_D    | fcmlt	p5.d, p5/z, z23.d, #0.0        // FCMLT <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMNE_PPzZ0_H    | fcmne	p2.h, p3/z, z7.h, #0.0         // FCMNE <Pd>.<T>, <Pg>/Z, <Zn>.<T>, #0.0  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQ16          | fcmeq	h30, h6, h1                    // FCMEQ <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQ32          | fcmeq	s17, s0, s21                   // FCMEQ <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQv2f32       | fcmeq	v19.2s, v31.2s, v19.2s         // FCMEQ <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQv4f32       | fcmeq	v12.4s, v11.4s, v26.4s         // FCMEQ <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQv1i16rz     | fcmeq	h19, h23, #0.0                 // FCMEQ <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQv1i32rz     | fcmeq	s25, s18, #0.0                 // FCMEQ <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQv2i32rz     | fcmeq	v8.2s, v16.2s, #0.0            // FCMEQ <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMEQv2i64rz     | fcmeq	v18.2d, v17.2d, #0.0           // FCMEQ <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGE16          | fcmge	h1, h16, h12                   // FCMGE <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGE64          | fcmge	d29, d9, d3                    // FCMGE <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGEv8f16       | fcmge	v20.8h, v19.8h, v22.8h         // FCMGE <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGEv2f64       | fcmge	v17.2d, v11.2d, v13.2d         // FCMGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGEv1i16rz     | fcmge	h10, h23, #0.0                 // FCMGE <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGEv1i64rz     | fcmge	d5, d17, #0.0                  // FCMGE <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGEv4i16rz     | fcmge	v18.4h, v27.4h, #0.0           // FCMGE <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGEv2i32rz     | fcmge	v17.2s, v11.2s, #0.0           // FCMGE <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGT16          | fcmgt	h4, h5, h0                     // FCMGT <Hd>, <Hn>, <Hm>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGT32          | fcmgt	s13, s20, s3                   // FCMGT <V><d>, <V><n>, <V><m>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGTv8f16       | fcmgt	v24.8h, v24.8h, v28.8h         // FCMGT <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGTv4f32       | fcmgt	v19.4s, v20.4s, v13.4s         // FCMGT <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGTv1i16rz     | fcmgt	h0, h18, #0.0                  // FCMGT <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGTv1i64rz     | fcmgt	d30, d23, #0.0                 // FCMGT <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGTv8i16rz     | fcmgt	v0.8h, v11.8h, #0.0            // FCMGT <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMGTv2i64rz     | fcmgt	v19.2d, v31.2d, #0.0           // FCMGT <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCMLA_ZZZI_H     | fcmla	z20.h, z12.h, z4.h[1], #90     // FCMLA <Zda>.H, <Zn>.H, <Zmh>.H[<immh>], <const>  \\ Floating point complex multiply add   \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCMLA_ZZZI_S     | fcmla	z1.s, z27.s, z6.s[0], #90      // FCMLA <Zda>.S, <Zn>.S, <Zm>.S[<imm>], <const>  \\ Floating point complex multiply add   \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 5  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCMLA_ZPmZZ_S    | fcmla	z25.s, p3/m, z13.s, z23.s, #180  // FCMLA <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>, <const>  \\ Floating point complex multiply add   \\ 1 5 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMGE_PPzZZ_S    | fcmge	p5.s, p3/z, z12.s, z28.s       // FCMLE <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLEv1i16rz     | fcmle	h18, h28, #0.0                 // FCMLE <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLEv1i64rz     | fcmle	d18, d16, #0.0                 // FCMLE <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLEv8i16rz     | fcmle	v16.8h, v11.8h, #0.0           // FCMLE <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLEv4i32rz     | fcmle	v22.4s, v30.4s, #0.0           // FCMLE <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMGT_PPzZZ_S    | fcmgt	p1.s, p1/z, z24.s, z13.s       // FCMLT <Pd>.<T>, <Pg>/Z, <Zm>.<T>, <Zn>.<T>  \\ Floating point compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLTv1i16rz     | fcmlt	h23, h7, #0.0                  // FCMLT <Hd>, <Hn>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLTv1i64rz     | fcmlt	d22, d28, #0.0                 // FCMLT <V><d>, <V><n>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLTv4i16rz     | fcmlt	v8.4h, v2.4h, #0.0             // FCMLT <Vd>.<Th>, <Vn>.<Th>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FCMLTv2i64rz     | fcmlt	v7.2d, v16.2d, #0.0            // FCMLT <Vd>.<T>, <Vn>.<T>, #0.0  \\ ASIMD FP compare  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPHrr          | fcmp	h5, h21                        // FCMP <Hn>, <Hm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPHri          | fcmp	h5, #0.0                       // FCMP <Hn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPSrr          | fcmp	s7, s0                         // FCMP <Sn>, <Sm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPSri          | fcmp	s28, #0.0                      // FCMP <Sn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPDrr          | fcmp	d1, d27                        // FCMP <Dn>, <Dm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPDri          | fcmp	d16, #0.0                      // FCMP <Dn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPEHrr         | fcmpe	h22, h21                       // FCMPE <Hn>, <Hm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPEHri         | fcmpe	h13, #0.0                      // FCMPE <Hn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPESrr         | fcmpe	s11, s29                       // FCMPE <Sn>, <Sm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPESri         | fcmpe	s15, #0.0                      // FCMPE <Sn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPEDrr         | fcmpe	d27, d22                       // FCMPE <Dn>, <Dm>  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCMPEDri         | fcmpe	d9, #0.0                       // FCMPE <Dn>, #0.0  \\ FP compare  \\ 1 2  2  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCPY_ZPmI_H      | fmov	z2.h, p7/m, #0.50000000        // FCPY <Zd>.<T>, <Pg>/M, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCSELHrrr        | fcsel	h26, h2, h11, hs               // FCSEL <Hd>, <Hn>, <Hm>, <cond>  \\ FP select  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCSELSrrr        | fcsel	s5, s1, s4, vc                 // FCSEL <Sd>, <Sn>, <Sm>, <cond>  \\ FP select  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCSELDrrr        | fcsel	d14, d0, d19, eq               // FCSEL <Dd>, <Dn>, <Dm>, <cond>  \\ FP select  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTSHr          | fcvt	s13, h13                       // FCVT <Sd>, <Hn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTDHr          | fcvt	d10, h6                        // FCVT <Dd>, <Hn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTHSr          | fcvt	h1, s1                         // FCVT <Hd>, <Sn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTDSr          | fcvt	d9, s23                        // FCVT <Dd>, <Sn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTHDr          | fcvt	h17, d16                       // FCVT <Hd>, <Dn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTSDr          | fcvt	s31, d27                       // FCVT <Sd>, <Dn>  \\ FP convert, from vec to vec reg  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | FCVT_ZPmZ_HtoS   | fcvt	z0.s, p1/m, z4.h               // FCVT <Zd>.S, <Pg>/M, <Zn>.H  \\ Floating point convert, long or narrow (F16 to F32 or F32 to F16)  \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVT_ZPmZ_HtoD   | fcvt	z6.d, p0/m, z17.h              // FCVT <Zd>.D, <Pg>/M, <Zn>.H  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | FCVT_ZPmZ_StoH   | fcvt	z7.h, p7/m, z5.s               // FCVT <Zd>.H, <Pg>/M, <Zn>.S  \\ Floating point convert, long or narrow (F16 to F32 or F32 to F16)  \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVT_ZPmZ_StoD   | fcvt	z11.d, p2/m, z18.s             // FCVT <Zd>.D, <Pg>/M, <Zn>.S  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVT_ZPmZ_DtoH   | fcvt	z26.h, p0/m, z30.d             // FCVT <Zd>.H, <Pg>/M, <Zn>.D  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVT_ZPmZ_DtoS   | fcvt	z13.s, p2/m, z3.d              // FCVT <Zd>.S, <Pg>/M, <Zn>.D  \\ Floating point convert, long or narrow (F16 to F64, F32 to F64, F64 to F32 or F64 to F16)  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTASUWHr       | fcvtas	w23, h3                // FCVTAS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTASUXHr       | fcvtas	x14, h29               // FCVTAS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTASUWSr       | fcvtas	w0, s13                // FCVTAS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTASUXSr       | fcvtas	x23, s15               // FCVTAS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTASUWDr       | fcvtas	w1, d31                // FCVTAS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTASUXDr       | fcvtas	x2, d3                 // FCVTAS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTASv1f16      | fcvtas	h27, h24               // FCVTAS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTASv1i32      | fcvtas	s16, s0                // FCVTAS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTASv1i64      | fcvtas	d14, d7                // FCVTAS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTASv4f16      | fcvtas	v5.4h, v16.4h          // FCVTAS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTASv8f16      | fcvtas	v13.8h, v30.8h         // FCVTAS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTASv2f32      | fcvtas	v12.2s, v1.2s          // FCVTAS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTASv4f32      | fcvtas	v9.4s, v31.4s          // FCVTAS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTASv2f64      | fcvtas	v2.2d, v22.2d          // FCVTAS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTAUUWHr       | fcvtau	w13, h27               // FCVTAU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTAUUXHr       | fcvtau	x8, h12                // FCVTAU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTAUUWSr       | fcvtau	w20, s10               // FCVTAU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTAUUXSr       | fcvtau	x27, s22               // FCVTAU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTAUUWDr       | fcvtau	w6, d26                // FCVTAU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTAUUXDr       | fcvtau	x16, d13               // FCVTAU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTAUv1f16      | fcvtau	h6, h29                // FCVTAU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTAUv1i32      | fcvtau	s23, s7                // FCVTAU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTAUv1i64      | fcvtau	d1, d26                // FCVTAU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTAUv4f16      | fcvtau	v12.4h, v13.4h         // FCVTAU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTAUv8f16      | fcvtau	v21.8h, v0.8h          // FCVTAU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTAUv2f32      | fcvtau	v31.2s, v6.2s          // FCVTAU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTAUv4f32      | fcvtau	v29.4s, v26.4s         // FCVTAU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTAUv2f64      | fcvtau	v9.2d, v7.2d           // FCVTAU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTLv4i16       | fcvtl	v30.4s, v4.4h                  // FCVTL <Vd>.4S, <Vn>.4H  \\ ASIMD FP convert, long (F16 to F32)  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTLv2i32       | fcvtl	v28.2d, v13.2s                 // FCVTL <Vd>.2D, <Vn>.2S  \\ ASIMD FP convert, long (F32 to F64)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTLv8i16       | fcvtl2	v14.4s, v29.8h         // FCVTL2 <Vd>.4S, <Vn>.8H  \\ ASIMD FP convert, long (F16 to F32)  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTLv4i32       | fcvtl2	v0.2d, v9.4s           // FCVTL2 <Vd>.2D, <Vn>.4S  \\ ASIMD FP convert, long (F32 to F64)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMSUWHr       | fcvtms	w15, h1                // FCVTMS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMSUXHr       | fcvtms	x5, h2                 // FCVTMS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMSUWSr       | fcvtms	w1, s16                // FCVTMS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMSUXSr       | fcvtms	x27, s22               // FCVTMS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMSUWDr       | fcvtms	w18, d21               // FCVTMS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMSUXDr       | fcvtms	x6, d26                // FCVTMS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMSv1f16      | fcvtms	h19, h29               // FCVTMS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMSv1i32      | fcvtms	s30, s14               // FCVTMS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMSv1i64      | fcvtms	d8, d20                // FCVTMS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTMSv4f16      | fcvtms	v27.4h, v7.4h          // FCVTMS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTMSv8f16      | fcvtms	v26.8h, v11.8h         // FCVTMS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMSv2f32      | fcvtms	v13.2s, v2.2s          // FCVTMS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTMSv4f32      | fcvtms	v18.4s, v21.4s         // FCVTMS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMSv2f64      | fcvtms	v15.2d, v16.2d         // FCVTMS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMUUWHr       | fcvtmu	w20, h6                // FCVTMU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMUUXHr       | fcvtmu	x7, h18                // FCVTMU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMUUWSr       | fcvtmu	w24, s19               // FCVTMU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMUUXSr       | fcvtmu	x7, s15                // FCVTMU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMUUWDr       | fcvtmu	w16, d16               // FCVTMU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTMUUXDr       | fcvtmu	x1, d18                // FCVTMU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMUv1f16      | fcvtmu	h20, h13               // FCVTMU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMUv1i32      | fcvtmu	s28, s25               // FCVTMU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMUv1i64      | fcvtmu	d3, d27                // FCVTMU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTMUv4f16      | fcvtmu	v18.4h, v2.4h          // FCVTMU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTMUv8f16      | fcvtmu	v10.8h, v11.8h         // FCVTMU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMUv2f32      | fcvtmu	v27.2s, v14.2s         // FCVTMU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTMUv4f32      | fcvtmu	v31.4s, v4.4s          // FCVTMU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTMUv2f64      | fcvtmu	v6.2d, v26.2d          // FCVTMU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTNv4i16       | fcvtn	v4.4h, v22.4s                  // FCVTN <Vd>.4H, <Vn>.4S  \\ ASIMD FP convert, narrow (F32 to F16)  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNv2i32       | fcvtn	v14.2s, v2.2d                  // FCVTN <Vd>.2S, <Vn>.2D  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTNv8i16       | fcvtn2	v0.8h, v30.4s          // FCVTN2 <Vd>.8H, <Vn>.4S  \\ ASIMD FP convert, narrow (F32 to F16)  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNv4i32       | fcvtn2	v21.4s, v13.2d         // FCVTN2 <Vd>.4S, <Vn>.2D  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNSUWHr       | fcvtns	w19, h15               // FCVTNS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNSUXHr       | fcvtns	x20, h0                // FCVTNS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNSUWSr       | fcvtns	w10, s5                // FCVTNS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNSUXSr       | fcvtns	x14, s12               // FCVTNS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNSUWDr       | fcvtns	w30, d2                // FCVTNS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNSUXDr       | fcvtns	x0, d12                // FCVTNS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNSv1f16      | fcvtns	h16, h25               // FCVTNS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNSv1i32      | fcvtns	s23, s19               // FCVTNS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNSv1i64      | fcvtns	d30, d1                // FCVTNS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTNSv4f16      | fcvtns	v28.4h, v19.4h         // FCVTNS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTNSv8f16      | fcvtns	v19.8h, v19.8h         // FCVTNS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNSv2f32      | fcvtns	v20.2s, v4.2s          // FCVTNS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTNSv4f32      | fcvtns	v28.4s, v29.4s         // FCVTNS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNSv2f64      | fcvtns	v21.2d, v31.2d         // FCVTNS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNUUWHr       | fcvtnu	w12, h3                // FCVTNU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNUUXHr       | fcvtnu	x23, h27               // FCVTNU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNUUWSr       | fcvtnu	w4, s23                // FCVTNU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNUUXSr       | fcvtnu	x5, s28                // FCVTNU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNUUWDr       | fcvtnu	w4, d11                // FCVTNU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTNUUXDr       | fcvtnu	x12, d8                // FCVTNU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNUv1f16      | fcvtnu	h24, h22               // FCVTNU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNUv1i32      | fcvtnu	s29, s22               // FCVTNU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNUv1i64      | fcvtnu	d18, d15               // FCVTNU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTNUv4f16      | fcvtnu	v5.4h, v12.4h          // FCVTNU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTNUv8f16      | fcvtnu	v26.8h, v20.8h         // FCVTNU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNUv2f32      | fcvtnu	v15.2s, v1.2s          // FCVTNU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTNUv4f32      | fcvtnu	v7.4s, v16.4s          // FCVTNU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTNUv2f64      | fcvtnu	v13.2d, v8.2d          // FCVTNU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPSUWHr       | fcvtps	w27, h14               // FCVTPS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPSUXHr       | fcvtps	x26, h20               // FCVTPS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPSUWSr       | fcvtps	w5, s27                // FCVTPS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPSUXSr       | fcvtps	x29, s6                // FCVTPS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPSUWDr       | fcvtps	w23, d25               // FCVTPS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPSUXDr       | fcvtps	x10, d16               // FCVTPS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPSv1f16      | fcvtps	h31, h22               // FCVTPS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPSv1i32      | fcvtps	s3, s3                 // FCVTPS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPSv1i64      | fcvtps	d10, d26               // FCVTPS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTPSv4f16      | fcvtps	v13.4h, v26.4h         // FCVTPS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTPSv8f16      | fcvtps	v26.8h, v10.8h         // FCVTPS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPSv2f32      | fcvtps	v18.2s, v8.2s          // FCVTPS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTPSv4f32      | fcvtps	v12.4s, v18.4s         // FCVTPS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPSv2f64      | fcvtps	v3.2d, v2.2d           // FCVTPS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPUUWHr       | fcvtpu	w25, h22               // FCVTPU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPUUXHr       | fcvtpu	x4, h24                // FCVTPU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPUUWSr       | fcvtpu	w13, s0                // FCVTPU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPUUXSr       | fcvtpu	x0, s17                // FCVTPU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPUUWDr       | fcvtpu	w16, d25               // FCVTPU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTPUUXDr       | fcvtpu	x15, d12               // FCVTPU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPUv1f16      | fcvtpu	h1, h29                // FCVTPU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPUv1i32      | fcvtpu	s21, s30               // FCVTPU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPUv1i64      | fcvtpu	d16, d26               // FCVTPU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTPUv4f16      | fcvtpu	v2.4h, v25.4h          // FCVTPU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTPUv8f16      | fcvtpu	v24.8h, v26.8h         // FCVTPU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPUv2f32      | fcvtpu	v6.2s, v23.2s          // FCVTPU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTPUv4f32      | fcvtpu	v10.4s, v6.4s          // FCVTPU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTPUv2f64      | fcvtpu	v7.2d, v23.2d          // FCVTPU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTXNv1i64      | fcvtxn	s29, d4                // FCVTXN <Vb><d>, <Va><n>  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTXNv2f32      | fcvtxn	v25.2s, v15.2d         // FCVTXN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTXNv4f32      | fcvtxn2	v21.4s, v6.2d          // FCVTXN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD FP convert, narrow (F64 to F32)  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSSWHri      | fcvtzs	w28, h26, #26          // FCVTZS <Wd>, <Hn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSSXHri      | fcvtzs	x22, h17, #58          // FCVTZS <Xd>, <Hn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSSWSri      | fcvtzs	w17, s23, #22          // FCVTZS <Wd>, <Sn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSSXSri      | fcvtzs	x15, s30, #2           // FCVTZS <Xd>, <Sn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSSWDri      | fcvtzs	w13, d17, #17          // FCVTZS <Wd>, <Dn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSSXDri      | fcvtzs	x14, d9, #24           // FCVTZS <Xd>, <Dn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSUWHr       | fcvtzs	w15, h10               // FCVTZS <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSUXHr       | fcvtzs	x4, h21                // FCVTZS <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSUWSr       | fcvtzs	w1, s4                 // FCVTZS <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSUXSr       | fcvtzs	x27, s27               // FCVTZS <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSUWDr       | fcvtzs	w24, d30               // FCVTZS <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZSUXDr       | fcvtzs	x18, d21               // FCVTZS <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSh          | fcvtzs	h29, h23, #16          // FCVTZS H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSs          | fcvtzs	s23, s15, #2           // FCVTZS S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSd          | fcvtzs	d20, d26, #57          // FCVTZS D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZSv4i16_shift | fcvtzs	v20.4h, v24.4h, #11    // FCVTZS <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTZSv8i16_shift | fcvtzs	v18.8h, v10.8h, #7     // FCVTZS <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv2i32_shift | fcvtzs	v16.2s, v2.2s, #11     // FCVTZS <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZSv4i32_shift | fcvtzs	v22.4s, v18.4s, #5     // FCVTZS <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv2i64_shift | fcvtzs	v14.2d, v30.2d, #54    // FCVTZS <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv1f16      | fcvtzs	h16, h27               // FCVTZS <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv1i32      | fcvtzs	s4, s5                 // FCVTZS S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv1i64      | fcvtzs	d4, d23                // FCVTZS D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZSv4f16      | fcvtzs	v8.4h, v16.4h          // FCVTZS <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTZSv8f16      | fcvtzs	v2.8h, v16.8h          // FCVTZS <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv2f32      | fcvtzs	v27.2s, v28.2s         // FCVTZS <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZSv4f32      | fcvtzs	v29.4s, v18.4s         // FCVTZS <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZSv2f64      | fcvtzs	v13.2d, v31.2d         // FCVTZS <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | FCVTZS_ZPmZ_HtoH | fcvtzs	z1.h, p2/m, z6.h       // FCVTZS <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | FCVTZS_ZPmZ_HtoS | fcvtzs	z19.s, p4/m, z16.h     // FCVTZS <Zd>.S, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | FCVTZS_ZPmZ_HtoD | fcvtzs	z14.d, p0/m, z6.h      // FCVTZS <Zd>.D, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | FCVTZS_ZPmZ_StoS | fcvtzs	z25.s, p5/m, z23.s     // FCVTZS <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | FCVTZS_ZPmZ_StoD | fcvtzs	z3.d, p1/m, z31.s      // FCVTZS <Zd>.D, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZS_ZPmZ_DtoS | fcvtzs	z28.s, p5/m, z23.d     // FCVTZS <Zd>.S, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZS_ZPmZ_DtoD | fcvtzs	z22.d, p6/m, z29.d     // FCVTZS <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUSWHri      | fcvtzu	w12, h19, #20          // FCVTZU <Wd>, <Hn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUSXHri      | fcvtzu	x17, h23, #12          // FCVTZU <Xd>, <Hn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUSWSri      | fcvtzu	w16, s3, #12           // FCVTZU <Wd>, <Sn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUSXSri      | fcvtzu	x27, s15, #8           // FCVTZU <Xd>, <Sn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUSWDri      | fcvtzu	w21, d10, #23          // FCVTZU <Wd>, <Dn>, #<sfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUSXDri      | fcvtzu	x26, d30, #27          // FCVTZU <Xd>, <Dn>, #<dfbits>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUUWHr       | fcvtzu	w26, h30               // FCVTZU <Wd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUUXHr       | fcvtzu	x9, h11                // FCVTZU <Xd>, <Hn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUUWSr       | fcvtzu	w20, s16               // FCVTZU <Wd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUUXSr       | fcvtzu	x7, s21                // FCVTZU <Xd>, <Sn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUUWDr       | fcvtzu	w25, d30               // FCVTZU <Wd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZUUXDr       | fcvtzu	x13, d8                // FCVTZU <Xd>, <Dn>  \\ FP convert, from vec to gen reg  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUh          | fcvtzu	h19, h8, #12           // FCVTZU H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUs          | fcvtzu	s25, s27, #10          // FCVTZU S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUd          | fcvtzu	d30, d16, #42          // FCVTZU D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZUv4i16_shift | fcvtzu	v19.4h, v26.4h, #9     // FCVTZU <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTZUv8i16_shift | fcvtzu	v27.8h, v6.8h, #11     // FCVTZU <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv2i32_shift | fcvtzu	v30.2s, v4.2s, #19     // FCVTZU <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZUv4i32_shift | fcvtzu	v31.4s, v6.4s, #22     // FCVTZU <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv2i64_shift | fcvtzu	v10.2d, v12.2d, #53    // FCVTZU <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv1f16      | fcvtzu	h25, h30               // FCVTZU <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv1i32      | fcvtzu	s2, s19                // FCVTZU S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv1i64      | fcvtzu	d4, d7                 // FCVTZU D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZUv4f16      | fcvtzu	v3.4h, v2.4h           // FCVTZU <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FCVTZUv8f16      | fcvtzu	v30.8h, v25.8h         // FCVTZU <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv2f32      | fcvtzu	v25.2s, v25.2s         // FCVTZU <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FCVTZUv4f32      | fcvtzu	v21.4s, v2.4s          // FCVTZU <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FCVTZUv2f64      | fcvtzu	v23.2d, v15.2d         // FCVTZU <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | FCVTZU_ZPmZ_HtoH | fcvtzu	z15.h, p0/m, z8.h      // FCVTZU <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | FCVTZU_ZPmZ_HtoS | fcvtzu	z8.s, p5/m, z18.h      // FCVTZU <Zd>.S, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | FCVTZU_ZPmZ_HtoD | fcvtzu	z11.d, p4/m, z24.h     // FCVTZU <Zd>.D, <Pg>/M, <Zn>.H  \\ Floating point convert to integer, F16  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | FCVTZU_ZPmZ_StoS | fcvtzu	z13.s, p7/m, z8.s      // FCVTZU <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | FCVTZU_ZPmZ_StoD | fcvtzu	z20.d, p2/m, z13.s     // FCVTZU <Zd>.D, <Pg>/M, <Zn>.S  \\ Floating point convert to integer, F32  \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZU_ZPmZ_DtoS | fcvtzu	z31.s, p3/m, z20.d     // FCVTZU <Zd>.S, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FCVTZU_ZPmZ_DtoD | fcvtzu	z4.d, p1/m, z25.d      // FCVTZU <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point convert to integer, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 7  | 7   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FDIVHrr          | fdiv	h1, h26, h23                   // FDIV <Hd>, <Hn>, <Hm>  \\ FP divide, H-form  \\ 1 7  7  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.67   | V1UnitV[3], V1UnitV02[3]                                         | FDIVSrr          | fdiv	s31, s18, s12                  // FDIV <Sd>, <Sn>, <Sm>  \\ FP divide, S-form  \\ 1 10 10 0.67 V1UnitV02[3]
+# CHECK-NEXT:   1    | 15 | 15  | 0.29   | V1UnitV[7], V1UnitV02[7]                                         | FDIVDrr          | fdiv	d6, d3, d0                     // FDIV <Dd>, <Dn>, <Dm>  \\ FP divide, D-form  \\ 1 15 15 0.29 V1UnitV02[7]
+# CHECK-NEXT:   1    | 7  | 7   | 0.29   | V1UnitV[7], V1UnitV02[7]                                         | FDIVv4f16        | fdiv	v21.4h, v15.4h, v22.4h         // FDIV <Vd>.4H, <Vn>.4H, <Vm>.4H  \\ ASIMD FP divide, D-form, F16  \\ 1 7  7  0.29 V1UnitV02[7]
+# CHECK-NEXT:   1    | 13 | 13  | 0.15   | V1UnitV[13], V1UnitV02[13]                                       | FDIVv8f16        | fdiv	v31.8h, v12.8h, v15.8h         // FDIV <Vd>.8H, <Vn>.8H, <Vm>.8H  \\ ASIMD FP divide, Q-form, F16  \\ 1 13 13 0.15 V1UnitV02[13]
+# CHECK-NEXT:   1    | 10 | 10  | 0.40   | V1UnitV[5], V1UnitV02[5]                                         | FDIVv2f32        | fdiv	v15.2s, v23.2s, v2.2s          // FDIV <Vd>.2S, <Vn>.2S, <Vm>.2S  \\ ASIMD FP divide, D-form, F32  \\ 1 10 10 0.4 V1UnitV02[5]
+# CHECK-NEXT:   1    | 10 | 10  | 0.22   | V1UnitV[9], V1UnitV02[9]                                         | FDIVv4f32        | fdiv	v7.4s, v27.4s, v22.4s          // FDIV <Vd>.4S, <Vn>.4S, <Vm>.4S  \\ ASIMD FP divide, Q-form, F32  \\ 1 10 10 0.22 V1UnitV02[9]
+# CHECK-NEXT:   1    | 15 | 15  | 0.14   | V1UnitV[14], V1UnitV02[14]                                       | FDIVv2f64        | fdiv	v31.2d, v25.2d, v8.2d          // FDIV <Vd>.2D, <Vn>.2D, <Vm>.2D  \\ ASIMD FP divide, Q-form, F64  \\ 1 15 15 0.14 V1UnitV02[14]
+# CHECK-NEXT:   1    | 13 | 13  | 0.08   | V1UnitV[12], V1UnitV0[12], V1UnitV01[12], V1UnitV02[12]          | FDIV_ZPmZ_H      | fdiv	z21.h, p7/m, z21.h, z15.h      // FDIV <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Floating point divide, F16  \\ 1 13 13 0.08 V1UnitV0[12]
+# CHECK-NEXT:   1    | 10 | 10  | 0.11   | V1UnitV[9], V1UnitV0[9], V1UnitV01[9], V1UnitV02[9]              | FDIV_ZPmZ_S      | fdiv	z17.s, p4/m, z17.s, z20.s      // FDIV <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Floating point divide, F32  \\ 1 10 10 0.11 V1UnitV0[9]
+# CHECK-NEXT:   1    | 15 | 15  | 0.07   | V1UnitV[14], V1UnitV0[14], V1UnitV01[14], V1UnitV02[14]          | FDIV_ZPmZ_D      | fdiv	z13.d, p3/m, z13.d, z28.d      // FDIV <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Floating point divide, F64  \\ 1 15 15 0.07 V1UnitV0[14]
+# CHECK-NEXT:   1    | 13 | 13  | 0.08   | V1UnitV[12], V1UnitV0[12], V1UnitV01[12], V1UnitV02[12]          | FDIVR_ZPmZ_H     | fdivr	z29.h, p4/m, z29.h, z1.h       // FDIVR <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Floating point divide, F16  \\ 1 13 13 0.08 V1UnitV0[12]
+# CHECK-NEXT:   1    | 10 | 10  | 0.11   | V1UnitV[9], V1UnitV0[9], V1UnitV01[9], V1UnitV02[9]              | FDIVR_ZPmZ_S     | fdivr	z13.s, p0/m, z13.s, z29.s      // FDIVR <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Floating point divide, F32  \\ 1 10 10 0.11 V1UnitV0[9]
+# CHECK-NEXT:   1    | 15 | 15  | 0.07   | V1UnitV[14], V1UnitV0[14], V1UnitV01[14], V1UnitV02[14]          | FDIVR_ZPmZ_D     | fdivr	z14.d, p3/m, z14.d, z31.d      // FDIVR <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Floating point divide, F64  \\ 1 15 15 0.07 V1UnitV0[14]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FDUP_ZI_S        | fmov	z19.s, #0.50000000             // FDUP <Zd>.<T>, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FEXPA_ZZ_H       | fexpa	z6.h, z3.h                     // FEXPA <Zd>.<T>, <Zn>.<T>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMAD_ZPmZZ_S     | fmad	z9.s, p5/m, z9.s, z7.s         // FMAD <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMADDHrrr        | fmadd	h27, h0, h6, h28               // FMADD <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMADDSrrr        | fmadd	s13, s24, s15, s5              // FMADD <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMADDDrrr        | fmadd	d19, d4, d2, d17               // FMADD <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMAX_ZPmI_D      | fmax	z25.d, p2/m, z25.d, #0.0       // FMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXHrr          | fmax	h8, h7, h11                    // FMAX <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXSrr          | fmax	s9, s21, s2                    // FMAX <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXDrr          | fmax	d4, d26, d26                   // FMAX <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXv4f32        | fmax	v0.4s, v13.4s, v21.4s          // FMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXv4f32        | fmax	v12.4s, v27.4s, v11.4s         // FMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMAX_ZPmZ_S      | fmax	z16.s, p5/m, z16.s, z12.s      // FMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMAXNM_ZPmI_D    | fmaxnm	z25.d, p5/m, z25.d, #1.0  // FMAXNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMHrr        | fmaxnm	h29, h13, h14          // FMAXNM <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMSrr        | fmaxnm	s25, s20, s0           // FMAXNM <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMDrr        | fmaxnm	d29, d25, d16          // FMAXNM <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMv4f32      | fmaxnm	v6.4s, v3.4s, v3.4s    // FMAXNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMv2f64      | fmaxnm	v9.2d, v15.2d, v11.2d  // FMAXNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMAXNM_ZPmZ_S    | fmaxnm	z6.s, p5/m, z6.s, z17.s  // FMAXNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMPv2i16p    | fmaxnmp	h25, v19.2h            // FMAXNMP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMPv2i64p    | fmaxnmp	d17, v29.2d            // FMAXNMP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMPv4f32     | fmaxnmp	v31.4s, v4.4s, v2.4s   // FMAXNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXNMPv4f32     | fmaxnmp	v23.4s, v15.4s, v1.4s  // FMAXNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMAXNMVv4i16v    | fmaxnmv	h0, v13.4h             // FMAXNMV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.33   | V1UnitV[3]                                                       | FMAXNMVv8i16v    | fmaxnmv	h12, v11.8h            // FMAXNMV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMAXNMVv4i32v    | fmaxnmv	s28, v31.4s            // FMAXNMV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 13 | 13  | 0.33   | V1UnitV[6], V1UnitV01[6]                                         | FMAXNMV_VPZ_H    | fmaxnmv	h9, p3, z2.h           // FMAXNMV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+# CHECK-NEXT:   1    | 11 | 11  | 0.40   | V1UnitV[5], V1UnitV01[5]                                         | FMAXNMV_VPZ_S    | fmaxnmv	s26, p6, z0.s          // FMAXNMV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+# CHECK-NEXT:   1    | 9  | 9   | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | FMAXNMV_VPZ_D    | fmaxnmv	d7, p1, z29.d          // FMAXNMV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXPv2i16p      | fmaxp	h15, v25.2h                    // FMAXP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXPv2i32p      | fmaxp	s6, v2.2s                      // FMAXP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXPv2f32       | fmaxp	v21.2s, v17.2s, v13.2s         // FMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMAXPv4f32       | fmaxp	v10.4s, v5.4s, v25.4s          // FMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMAXVv4i16v      | fmaxv	h23, v4.4h                     // FMAXV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.33   | V1UnitV[3]                                                       | FMAXVv8i16v      | fmaxv	h25, v15.8h                    // FMAXV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMAXVv4i32v      | fmaxv	s23, v2.4s                     // FMAXV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 13 | 13  | 0.33   | V1UnitV[6], V1UnitV01[6]                                         | FMAXV_VPZ_H      | fmaxv	h12, p0, z22.h                 // FMAXV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+# CHECK-NEXT:   1    | 11 | 11  | 0.40   | V1UnitV[5], V1UnitV01[5]                                         | FMAXV_VPZ_S      | fmaxv	s24, p5, z12.s                 // FMAXV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+# CHECK-NEXT:   1    | 9  | 9   | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | FMAXV_VPZ_D      | fmaxv	d1, p6, z25.d                  // FMAXV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMIN_ZPmI_D      | fmin	z24.d, p4/m, z24.d, #0.0       // FMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINHrr          | fmin	h4, h13, h17                   // FMIN <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINSrr          | fmin	s1, s14, s22                   // FMIN <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINDrr          | fmin	d18, d19, d22                  // FMIN <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINv4f32        | fmin	v6.4s, v25.4s, v27.4s          // FMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINv2f32        | fmin	v12.2s, v30.2s, v25.2s         // FMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMIN_ZPmZ_H      | fmin	z11.h, p3/m, z11.h, z16.h      // FMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMINNM_ZPmI_H    | fminnm	z19.h, p4/m, z19.h, #0.0  // FMINNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMHrr        | fminnm	h29, h23, h17          // FMINNM <Hd>, <Hn>, <Hm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMSrr        | fminnm	s24, s14, s30          // FMINNM <Sd>, <Sn>, <Sm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMDrr        | fminnm	d0, d26, d8            // FMINNM <Dd>, <Dn>, <Dm>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMv2f32      | fminnm	v16.2s, v23.2s, v27.2s  // FMINNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMv4f32      | fminnm	v23.4s, v19.4s, v22.4s  // FMINNM <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMINNM_ZPmZ_S    | fminnm	z24.s, p3/m, z24.s, z13.s  // FMINNM <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point min/max  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMPv2i16p    | fminnmp	h20, v14.2h            // FMINNMP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMPv2i64p    | fminnmp	d15, v8.2d             // FMINNMP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMPv2f64     | fminnmp	v27.2d, v27.2d, v16.2d  // FMINNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINNMPv4f32     | fminnmp	v2.4s, v14.4s, v14.4s  // FMINNMP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMINNMVv4i16v    | fminnmv	h19, v25.4h            // FMINNMV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.33   | V1UnitV[3]                                                       | FMINNMVv8i16v    | fminnmv	h23, v17.8h            // FMINNMV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMINNMVv4i32v    | fminnmv	s29, v17.4s            // FMINNMV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 13 | 13  | 0.33   | V1UnitV[6], V1UnitV01[6]                                         | FMINNMV_VPZ_H    | fminnmv	h24, p3, z1.h          // FMINNMV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+# CHECK-NEXT:   1    | 11 | 11  | 0.40   | V1UnitV[5], V1UnitV01[5]                                         | FMINNMV_VPZ_S    | fminnmv	s30, p3, z9.s          // FMINNMV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+# CHECK-NEXT:   1    | 9  | 9   | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | FMINNMV_VPZ_D    | fminnmv	d18, p5, z8.d          // FMINNMV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINPv2i16p      | fminp	h7, v10.2h                     // FMINP <Vh><d>, <Vn>.<Th>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINPv2i32p      | fminp	s17, v7.2s                     // FMINP <V><d>, <Vn>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINPv4f32       | fminp	v25.4s, v2.4s, v15.4s          // FMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMINPv2f32       | fminp	v14.2s, v28.2s, v15.2s         // FMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP max/min, pairwise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMINVv4i16v      | fminv	h3, v30.4h                     // FMINV H<d>, <Vn>.4H  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.33   | V1UnitV[3]                                                       | FMINVv8i16v      | fminv	h29, v12.8h                    // FMINV H<d>, <Vn>.8H  \\ ASIMD FP max/min, reduce, Q-form F16  \\ 1 6     6     1.33 V1UnitV[3]
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV[2]                                                       | FMINVv4i32v      | fminv	s16, v19.4s                    // FMINV S<d>, <Vn>.4S  \\ ASIMD FP max/min, reduce, F32 and D-form F16  \\ 1 4  4  2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 13 | 13  | 0.33   | V1UnitV[6], V1UnitV01[6]                                         | FMINV_VPZ_H      | fminv	h15, p2, z25.h                 // FMINV H<d>, <Pg>, <Zn>.H  \\ Floating point reduction, F16  \\ 1 13  13  0.33 V1UnitV01[6]
+# CHECK-NEXT:   1    | 11 | 11  | 0.40   | V1UnitV[5], V1UnitV01[5]                                         | FMINV_VPZ_S      | fminv	s4, p0, z6.s                   // FMINV S<d>, <Pg>, <Zn>.S  \\ Floating point reduction, F32  \\ 1 11  11  0.4 V1UnitV01[5]
+# CHECK-NEXT:   1    | 9  | 9   | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | FMINV_VPZ_D      | fminv	d20, p1, z5.d                  // FMINV D<d>, <Pg>, <Zn>.D  \\ Floating point reduction, F64  \\ 1 9  9  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv1i16_indexed | fmla	h23, h24, v15.h[4]             // FMLA <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv1i32_indexed | fmla	s9, s20, v28.s[2]              // FMLA S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv1i64_indexed | fmla	d12, d20, v7.d[1]              // FMLA D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv8i16_indexed | fmla	v29.8h, v15.8h, v10.h[4]       // FMLA <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv2i32_indexed | fmla	v2.2s, v16.2s, v28.s[0]        // FMLA <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv4i32_indexed | fmla	v14.4s, v14.4s, v5.s[3]        // FMLA <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv2i64_indexed | fmla	v10.2d, v14.2d, v21.d[1]       // FMLA <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLA_ZZZI_H      | fmla	z2.h, z4.h, z7.h[0]            // FMLA <Zda>.H, <Zn>.H, <Zmhs>.H[<immh>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLA_ZZZI_S      | fmla	z22.s, z15.s, z1.s[3]          // FMLA <Zda>.S, <Zn>.S, <Zmhs>.S[<imms>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLA_ZZZI_D      | fmla	z1.d, z30.d, z11.d[1]          // FMLA <Zda>.D, <Zn>.D, <Zmd>.D[<immd>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv4f32        | fmla	v1.4s, v24.4s, v12.4s          // FMLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLAv2f64        | fmla	v30.2d, v16.2d, v6.2d          // FMLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLA_ZPmZZ_S     | fmla	z6.s, p1/m, z24.s, z24.s       // FMLA <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv1i16_indexed | fmls	h8, h14, v7.h[4]               // FMLS <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv1i32_indexed | fmls	s20, s17, v5.s[2]              // FMLS S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv1i64_indexed | fmls	d11, d24, v29.d[0]             // FMLS D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv8i16_indexed | fmls	v30.8h, v18.8h, v4.h[6]        // FMLS <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv2i32_indexed | fmls	v10.2s, v27.2s, v0.s[0]        // FMLS <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv4i32_indexed | fmls	v27.4s, v7.4s, v24.s[0]        // FMLS <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv2i64_indexed | fmls	v10.2d, v22.2d, v29.d[0]       // FMLS <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLS_ZZZI_H      | fmls	z3.h, z31.h, z0.h[6]           // FMLS <Zda>.H, <Zn>.H, <Zmhs>.H[<immh>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLS_ZZZI_S      | fmls	z30.s, z8.s, z0.s[2]           // FMLS <Zda>.S, <Zn>.S, <Zmhs>.S[<imms>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLS_ZZZI_D      | fmls	z10.d, z20.d, z0.d[1]          // FMLS <Zda>.D, <Zn>.D, <Zmd>.D[<immd>]  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv2f32        | fmls	v6.2s, v3.2s, v12.2s           // FMLS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMLSv8f16        | fmls	v6.8h, v15.8h, v23.8h          // FMLS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLS_ZPmZZ_S     | fmls	z26.s, p5/m, z28.s, z26.s      // FMLS <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | FMOVHWr          | fmov	w15, h31                       // FMOV <Wd>, <Hn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | FMOVHXr          | fmov	x21, h14                       // FMOV <Xd>, <Hn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | FMOVWHr          | fmov	h6, w5                         // FMOV <Hd>, <Wn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | FMOVWSr          | fmov	s22, w0                        // FMOV <Sd>, <Wn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | FMOVSWr          | fmov	w23, s30                       // FMOV <Wd>, <Sn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | FMOVXHr          | fmov	h16, x27                       // FMOV <Hd>, <Xn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | FMOVXDr          | fmov	d22, x12                       // FMOV <Dd>, <Xn>  \\ FP transfer, from gen to low half of vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | FMOVXDHighr      | fmov	v7.d[1], x8                    // FMOV <Vd>.D[1], <Xn>  \\ FP transfer, from gen to high half of vec reg  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | FMOVDXr          | fmov	x26, d29                       // FMOV <Xd>, <Dn>  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | FMOVDXHighr      | fmov	x4, v26.d[1]                   // FMOV <Xd>, <Vn>.D[1]  \\ FP transfer, from vec to gen reg  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FCPY_ZPmI_S      | fmov	z2.s, p0/m, #0.50000000        // FMOV <Zd>.<T>, <Pg>/M, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FDUP_ZI_S        | fmov	z14.s, #0.50000000             // FMOV <Zd>.<T>, #<const>  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVHr           | fmov	h18, h28                       // FMOV <Hd>, <Hn>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVSr           | fmov	s13, s23                       // FMOV <Sd>, <Sn>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVDr           | fmov	d27, d17                       // FMOV <Dd>, <Dn>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVHi           | fmov	h29, #0.50000000               // FMOV <Hd>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVSi           | fmov	s22, #0.50000000               // FMOV <Sd>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVDi           | fmov	d18, #0.50000000               // FMOV <Dd>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVv2f32_ns     | fmov	v12.2s, #0.50000000            // FMOV <Vd>.<T>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVv2f32_ns     | fmov	v10.2s, #0.50000000            // FMOV <Vd>.<T>, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FMOVv2f64_ns     | fmov	v0.2d, #0.50000000             // FMOV <Vd>.2D, #<imm>  \\ ASIMD move, FP immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_D       | mov	z2.d, p2/m, #0                 // FMOV <Zd>.<T>, <Pg>/M, #0.0  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_S         | mov	z5.s, #0                       // FMOV <Zd>.<T>, #0.0  \\ Floating point copy  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMSB_ZPmZZ_S     | fmsb	z25.s, p5/m, z25.s, z29.s      // FMSB <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMSUBHrrr        | fmsub	h25, h28, h12, h24             // FMSUB <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMSUBSrrr        | fmsub	s31, s0, s23, s24              // FMSUB <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FMSUBDrrr        | fmsub	d12, d10, d20, d16             // FMSUB <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv1i16_indexed | fmul	h18, h4, v7.h[3]               // FMUL <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv1i32_indexed | fmul	s17, s23, v30.s[2]             // FMUL S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv1i64_indexed | fmul	d27, d8, v10.d[1]              // FMUL D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv4i16_indexed | fmul	v10.4h, v2.4h, v7.h[5]         // FMUL <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv2i32_indexed | fmul	v5.2s, v12.2s, v9.s[0]         // FMUL <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv4i32_indexed | fmul	v15.4s, v30.4s, v2.s[3]        // FMUL <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv2i64_indexed | fmul	v11.2d, v31.2d, v24.d[1]       // FMUL <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMUL_ZPmI_H      | fmul	z17.h, p5/m, z17.h, #2.0       // FMUL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMUL_ZZZI_H      | fmul	z27.h, z30.h, z0.h[0]          // FMUL <Zd>.H, <Zn>.H, <Zmhs>.H[<immh>]  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMUL_ZZZI_S      | fmul	z6.s, z16.s, z1.s[0]           // FMUL <Zd>.S, <Zn>.S, <Zmhs>.S[<imms>]  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMUL_ZZZI_D      | fmul	z4.d, z30.d, z2.d[0]           // FMUL <Zd>.D, <Zn>.D, <Zmd>.D[<immd>]  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULHrr          | fmul	h28, h14, h3                   // FMUL <Hd>, <Hn>, <Hm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULSrr          | fmul	s28, s16, s24                  // FMUL <Sd>, <Sn>, <Sm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULDrr          | fmul	d19, d19, d0                   // FMUL <Dd>, <Dn>, <Dm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv2f64        | fmul	v0.2d, v14.2d, v20.2d          // FMUL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULv2f64        | fmul	v9.2d, v29.2d, v7.2d           // FMUL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMUL_ZPmZ_D      | fmul	z22.d, p1/m, z22.d, z3.d       // FMUL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMUL_ZZZ_S       | fmul	z19.s, z14.s, z26.s            // FMUL <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv1i16_indexed | fmulx	h18, h17, v7.h[1]      // FMULX <Hd>, <Hn>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv1i32_indexed | fmulx	s23, s3, v3.s[2]       // FMULX S<d>, S<n>, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv1i64_indexed | fmulx	d3, d13, v30.d[0]      // FMULX D<d>, D<n>, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv4i16_indexed | fmulx	v28.4h, v25.4h, v15.h[1]  // FMULX <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv2i32_indexed | fmulx	v3.2s, v22.2s, v23.s[3]  // FMULX <Vd>.2S, <Vn>.2S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv4i32_indexed | fmulx	v5.4s, v28.4s, v15.s[3]  // FMULX <Vd>.4S, <Vn>.4S, <Vm>.S[<indexs>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv2i64_indexed | fmulx	v22.2d, v18.2d, v25.d[1]  // FMULX <Vd>.2D, <Vn>.2D, <Vm>.D[<indexd>]  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULX16          | fmulx	h20, h25, h0                   // FMULX <Hd>, <Hn>, <Hm>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULX64          | fmulx	d18, d19, d22                  // FMULX <V><d>, <V><n>, <V><m>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv2f64       | fmulx	v22.2d, v18.2d, v4.2d          // FMULX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FMULXv2f32       | fmulx	v16.2s, v4.2s, v27.2s          // FMULX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FMULX_ZPmZ_H     | fmulx	z7.h, p5/m, z7.h, z21.h        // FMULX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FNEGHr           | fneg	h2, h9                         // FNEG <Hd>, <Hn>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FNEGSr           | fneg	s11, s19                       // FNEG <Sd>, <Sn>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FNEGDr           | fneg	d5, d16                        // FNEG <Dd>, <Dn>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FNEGv2f64        | fneg	v26.2d, v2.2d                  // FNEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FNEGv2f32        | fneg	v14.2s, v24.2s                 // FNEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD FP negate  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FNEG_ZPmZ_S      | fneg	z16.s, p0/m, z25.s             // FNEG <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FNMAD_ZPmZZ_H    | fnmad	z6.h, p2/m, z14.h, z21.h       // FNMAD <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FNMADDHrrr       | fnmadd	h3, h18, h31, h24      // FNMADD <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FNMADDSrrr       | fnmadd	s8, s18, s2, s14       // FNMADD <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FNMADDDrrr       | fnmadd	d19, d29, d28, d30     // FNMADD <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FNMLA_ZPmZZ_D    | fnmla	z15.d, p0/m, z8.d, z29.d       // FNMLA <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FNMLS_ZPmZZ_D    | fnmls	z13.d, p0/m, z8.d, z12.d       // FNMLS <Zda>.<T>, <Pg>/M, <Zn>.<T>, <Zm>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FNMSB_ZPmZZ_D    | fnmsb	z30.d, p7/m, z8.d, z9.d        // FNMSB <Zdn>.<T>, <Pg>/M, <Zm>.<T>, <Za>.<T>  \\ Floating point multiply accumulate  \\ 1 4 2 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FNMSUBHrrr       | fnmsub	h3, h29, h24, h17      // FNMSUB <Hd>, <Hn>, <Hm>, <Ha>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FNMSUBSrrr       | fnmsub	s29, s26, s17, s4      // FNMSUB <Sd>, <Sn>, <Sm>, <Sa>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 2   | 4.00   | V1UnitV                                                          | FNMSUBDrrr       | fnmsub	d7, d13, d13, d4       // FNMSUB <Dd>, <Dn>, <Dm>, <Da>  \\ FP multiply accumulate  \\ 1 4 2 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FNMULHrr         | fnmul	h3, h15, h7                    // FNMUL <Hd>, <Hn>, <Hm>  \\ FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FNMULSrr         | fnmul	s16, s11, s2                   // FNMUL <Sd>, <Sn>, <Sm>  \\ FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 4.00   | V1UnitV                                                          | FNMULDrr         | fnmul	d12, d22, d14                  // FNMUL <Dd>, <Dn>, <Dm>  \\ FP multiply  \\ 1 3  3  4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRECPEv1f16      | frecpe	h20, h8                // FRECPE <Hd>, <Hn>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRECPEv1i32      | frecpe	s27, s7                // FRECPE S<d>, S<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRECPEv1i64      | frecpe	d2, d1                 // FRECPE D<d>, D<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRECPEv4f16      | frecpe	v28.4h, v27.4h         // FRECPE <Vd>.4H, <Vn>.4H  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRECPEv8f16      | frecpe	v9.8h, v6.8h           // FRECPE <Vd>.8H, <Vn>.8H  \\ ASIMD reciprocal and square root estimate, Q-form F16  \\ 1  6   6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRECPEv2f32      | frecpe	v25.2s, v28.2s         // FRECPE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRECPEv4f32      | frecpe	v21.4s, v18.4s         // FRECPE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRECPEv2f64      | frecpe	v10.2d, v26.2d         // FRECPE <Vd>.2D, <Vn>.2D  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRECPE_ZZ_H      | frecpe	z14.h, z0.h            // FRECPE <Zd>.H, <Zn>.H  \\ Floating point reciprocal estimate, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRECPE_ZZ_S      | frecpe	z5.s, z16.s            // FRECPE <Zd>.S, <Zn>.S  \\ Floating point reciprocal estimate, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRECPE_ZZ_D      | frecpe	z27.d, z11.d           // FRECPE <Zd>.D, <Zn>.D  \\ Floating point reciprocal estimate, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRECPS16         | frecps	h29, h19, h8           // FRECPS <Hd>, <Hn>, <Hm>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRECPS64         | frecps	d25, d17, d12          // FRECPS <V><d>, <V><n>, <V><m>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRECPSv8f16      | frecps	v12.8h, v25.8h, v4.8h  // FRECPS <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRECPSv2f64      | frecps	v7.2d, v29.2d, v18.2d  // FRECPS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV01                                               | FRECPS_ZZZ_S     | frecps	z11.s, z31.s, z1.s     // FRECPS <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point reciprocal step  \\ 1 4  4  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRECPXv1f16      | frecpx	h18, h11               // FRECPX <Hd>, <Hn>  \\ ASIMD reciprocal exponent  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRECPXv1i32      | frecpx	s13, s30               // FRECPX <V><d>, <V><n>  \\ ASIMD reciprocal exponent  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRECPX_ZPmZ_S    | frecpx	z15.s, p4/m, z12.s     // FRECPX <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Floating point  reciprocal exponent  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTN_ZPmZ_H    | frintn	z30.h, p3/m, z31.h     // FRINTN <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTN_ZPmZ_S    | frintn	z17.s, p4/m, z23.s     // FRINTN <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTN_ZPmZ_D    | frintn	z28.d, p1/m, z25.d     // FRINTN <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTA_ZPmZ_H    | frinta	z10.h, p6/m, z17.h     // FRINTA <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTA_ZPmZ_S    | frinta	z7.s, p4/m, z27.s      // FRINTA <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTA_ZPmZ_D    | frinta	z17.d, p4/m, z17.d     // FRINTA <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTM_ZPmZ_H    | frintm	z26.h, p7/m, z0.h      // FRINTM <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTM_ZPmZ_S    | frintm	z6.s, p0/m, z28.s      // FRINTM <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTM_ZPmZ_D    | frintm	z29.d, p4/m, z3.d      // FRINTM <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTP_ZPmZ_H    | frintp	z20.h, p4/m, z12.h     // FRINTP <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTP_ZPmZ_S    | frintp	z3.s, p7/m, z18.s      // FRINTP <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTP_ZPmZ_D    | frintp	z28.d, p7/m, z4.d      // FRINTP <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTZ_ZPmZ_H    | frintz	z27.h, p2/m, z12.h     // FRINTZ <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTZ_ZPmZ_S    | frintz	z12.s, p6/m, z3.s      // FRINTZ <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTZ_ZPmZ_D    | frintz	z12.d, p2/m, z31.d     // FRINTZ <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTI_ZPmZ_H    | frinti	z16.h, p4/m, z9.h      // FRINTI <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTI_ZPmZ_S    | frinti	z18.s, p6/m, z27.s     // FRINTI <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTI_ZPmZ_D    | frinti	z26.d, p2/m, z12.d     // FRINTI <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTX_ZPmZ_H    | frintx	z17.h, p0/m, z9.h      // FRINTX <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point round to integral, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTX_ZPmZ_S    | frintx	z27.s, p7/m, z16.s     // FRINTX <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point round to integral, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRINTX_ZPmZ_D    | frintx	z21.d, p4/m, z23.d     // FRINTX <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point round to integral, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTAHr         | frinta	h22, h10               // FRINTA <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTASr         | frinta	s15, s7                // FRINTA <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTADr         | frinta	d30, d10               // FRINTA <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTAv4f16      | frinta	v24.4h, v10.4h         // FRINTA <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTAv8f16      | frinta	v5.8h, v3.8h           // FRINTA <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTAv2f32      | frinta	v23.2s, v22.2s         // FRINTA <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTAv4f32      | frinta	v28.4s, v28.4s         // FRINTA <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTAv2f64      | frinta	v3.2d, v13.2d          // FRINTA <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTIHr         | frinti	h31, h14               // FRINTI <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTISr         | frinti	s23, s9                // FRINTI <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTIDr         | frinti	d8, d12                // FRINTI <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTIv4f16      | frinti	v6.4h, v10.4h          // FRINTI <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTIv8f16      | frinti	v22.8h, v7.8h          // FRINTI <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTIv2f32      | frinti	v9.2s, v25.2s          // FRINTI <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTIv4f32      | frinti	v23.4s, v7.4s          // FRINTI <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTIv2f64      | frinti	v28.2d, v5.2d          // FRINTI <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTMHr         | frintm	h0, h21                // FRINTM <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTMSr         | frintm	s22, s10               // FRINTM <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTMDr         | frintm	d5, d30                // FRINTM <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTMv4f16      | frintm	v3.4h, v8.4h           // FRINTM <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTMv8f16      | frintm	v19.8h, v26.8h         // FRINTM <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTMv2f32      | frintm	v15.2s, v8.2s          // FRINTM <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTMv4f32      | frintm	v20.4s, v26.4s         // FRINTM <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTMv2f64      | frintm	v20.2d, v11.2d         // FRINTM <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTNHr         | frintn	h12, h3                // FRINTN <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTNSr         | frintn	s27, s14               // FRINTN <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTNDr         | frintn	d30, d17               // FRINTN <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTNv4f16      | frintn	v27.4h, v4.4h          // FRINTN <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTNv8f16      | frintn	v17.8h, v19.8h         // FRINTN <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTNv2f32      | frintn	v23.2s, v23.2s         // FRINTN <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTNv4f32      | frintn	v2.4s, v4.4s           // FRINTN <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTNv2f64      | frintn	v24.2d, v12.2d         // FRINTN <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTPHr         | frintp	h17, h31               // FRINTP <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTPSr         | frintp	s14, s10               // FRINTP <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTPDr         | frintp	d25, d13               // FRINTP <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTPv4f16      | frintp	v22.4h, v25.4h         // FRINTP <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTPv8f16      | frintp	v18.8h, v11.8h         // FRINTP <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTPv2f32      | frintp	v31.2s, v5.2s          // FRINTP <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTPv4f32      | frintp	v0.4s, v24.4s          // FRINTP <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTPv2f64      | frintp	v1.2d, v3.2d           // FRINTP <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTXHr         | frintx	h4, h5                 // FRINTX <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTXSr         | frintx	s10, s28               // FRINTX <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTXDr         | frintx	d17, d19               // FRINTX <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTXv4f16      | frintx	v24.4h, v25.4h         // FRINTX <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTXv8f16      | frintx	v1.8h, v27.8h          // FRINTX <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTXv2f32      | frintx	v2.2s, v14.2s          // FRINTX <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTXv4f32      | frintx	v27.4s, v31.4s         // FRINTX <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTXv2f64      | frintx	v24.2d, v20.2d         // FRINTX <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTZHr         | frintz	h10, h29               // FRINTZ <Hd>, <Hn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTZSr         | frintz	s11, s23               // FRINTZ <Sd>, <Sn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTZDr         | frintz	d6, d11                // FRINTZ <Dd>, <Dn>  \\ FP round to integral  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTZv4f16      | frintz	v13.4h, v5.4h          // FRINTZ <Vd>.4H, <Vn>.4H  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRINTZv8f16      | frintz	v20.8h, v21.8h         // FRINTZ <Vd>.8H, <Vn>.8H  \\ ASIMD FP round, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTZv2f32      | frintz	v15.2s, v19.2s         // FRINTZ <Vd>.2S, <Vn>.2S  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRINTZv4f32      | frintz	v11.4s, v18.4s         // FRINTZ <Vd>.4S, <Vn>.4S  \\ ASIMD FP round, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRINTZv2f64      | frintz	v12.2d, v22.2d         // FRINTZ <Vd>.2D, <Vn>.2D  \\ ASIMD FP round, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRSQRTEv1f16     | frsqrte	h23, h26               // FRSQRTE <Hd>, <Hn>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRSQRTEv1i32     | frsqrte	s23, s5                // FRSQRTE S<d>, S<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRSQRTEv1i64     | frsqrte	d3, d11                // FRSQRTE D<d>, D<n>  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRSQRTEv4f16     | frsqrte	v16.4h, v15.4h         // FRSQRTE <Vd>.4H, <Vn>.4H  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | FRSQRTEv8f16     | frsqrte	v14.8h, v0.8h          // FRSQRTE <Vd>.8H, <Vn>.8H  \\ ASIMD reciprocal and square root estimate, Q-form F16  \\ 1  6   6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | FRSQRTEv2f32     | frsqrte	v6.2s, v8.2s           // FRSQRTE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form F32 and scalar forms  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRSQRTEv4f32     | frsqrte	v30.4s, v21.4s         // FRSQRTE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FRSQRTEv2f64     | frsqrte	v15.2d, v14.2d         // FRSQRTE <Vd>.2D, <Vn>.2D  \\ ASIMD reciprocal and square root estimate, D-form F16 and Q-form F32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRSQRTE_ZZ_H     | frsqrte	z6.h, z30.h            // FRSQRTE <Zd>.H, <Zn>.H  \\ Floating point reciprocal estimate, F16  \\ 1 6  6  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRSQRTE_ZZ_S     | frsqrte	z27.s, z15.s           // FRSQRTE <Zd>.S, <Zn>.S  \\ Floating point reciprocal estimate, F32  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | FRSQRTE_ZZ_D     | frsqrte	z6.d, z17.d            // FRSQRTE <Zd>.D, <Zn>.D  \\ Floating point reciprocal estimate, F64  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRSQRTS16        | frsqrts	h28, h26, h1           // FRSQRTS <Hd>, <Hn>, <Hm>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRSQRTS32        | frsqrts	s28, s1, s11           // FRSQRTS <V><d>, <V><n>, <V><m>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRSQRTSv4f16     | frsqrts	v8.4h, v9.4h, v30.4h   // FRSQRTS <Vd>.<Th>, <Vn>.<Th>, <Vm>.<Th>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 4.00   | V1UnitV                                                          | FRSQRTSv4f32     | frsqrts	v20.4s, v26.4s, v27.4s  // FRSQRTS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD reciprocal step  \\ 1  4   4  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV01                                               | FRSQRTS_ZZZ_H    | frsqrts	z10.h, z25.h, z22.h    // FRSQRTS <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point reciprocal step  \\ 1 4  4  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FSCALE_ZPmZ_H    | fscale	z2.h, p0/m, z2.h, z21.h  // FSCALE <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point multiply  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 7  | 7   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FSQRTHr          | fsqrt	h13, h24                       // FSQRT <Hd>, <Hn>  \\ FP square root, H-form  \\ 1 7  7  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 9  | 9   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | FSQRTSr          | fsqrt	s20, s15                       // FSQRT <Sd>, <Sn>  \\ FP square root, S-form  \\ 1 9 9 1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 16 | 16  | 0.25   | V1UnitV[8], V1UnitV02[8]                                         | FSQRTDr          | fsqrt	d25, d21                       // FSQRT <Dd>, <Dn>  \\ FP square root, D-form  \\ 1 16 16 0.25 V1UnitV02[8]
+# CHECK-NEXT:   1    | 7  | 7   | 0.29   | V1UnitV[7], V1UnitV02[7]                                         | FSQRTv4f16       | fsqrt	v24.4h, v14.4h                 // FSQRT <Vd>.4H, <Vn>.4H  \\ ASIMD FP square root, D-form, F16  \\ 1 7  7  0.29 V1UnitV02[7]
+# CHECK-NEXT:   1    | 13 | 13  | 0.15   | V1UnitV[13], V1UnitV02[13]                                       | FSQRTv8f16       | fsqrt	v12.8h, v3.8h                  // FSQRT <Vd>.8H, <Vn>.8H  \\ ASIMD FP square root, Q-form, F16  \\ 1 13 13 0.15 V1UnitV02[13]
+# CHECK-NEXT:   1    | 10 | 10  | 0.40   | V1UnitV[5], V1UnitV02[5]                                         | FSQRTv2f32       | fsqrt	v30.2s, v20.2s                 // FSQRT <Vd>.2S, <Vn>.2S  \\ ASIMD FP square root, D-form, F32  \\ 1 10 10 0.4 V1UnitV02[5]
+# CHECK-NEXT:   1    | 10 | 10  | 0.22   | V1UnitV[9], V1UnitV02[9]                                         | FSQRTv4f32       | fsqrt	v2.4s, v24.4s                  // FSQRT <Vd>.4S, <Vn>.4S  \\ ASIMD FP square root, Q-form, F32  \\ 1 10 10 0.22 V1UnitV02[9]
+# CHECK-NEXT:   1    | 16 | 16  | 0.13   | V1UnitV[15], V1UnitV02[15]                                       | FSQRTv2f64       | fsqrt	v28.2d, v25.2d                 // FSQRT <Vd>.2D, <Vn>.2D  \\ ASIMD FP square root, Q-form, F64  \\ 1 16 16 0.13 V1UnitV02[15]
+# CHECK-NEXT:   1    | 13 | 13  | 0.08   | V1UnitV[12], V1UnitV0[12], V1UnitV01[12], V1UnitV02[12]          | FSQRT_ZPmZ_H     | fsqrt	z13.h, p3/m, z11.h             // FSQRT <Zd>.H, <Pg>/M, <Zn>.H  \\ Floating point square root, F16  \\ 1 13 13 0.08 V1UnitV0[12]
+# CHECK-NEXT:   1    | 10 | 10  | 0.11   | V1UnitV[9], V1UnitV0[9], V1UnitV01[9], V1UnitV02[9]              | FSQRT_ZPmZ_S     | fsqrt	z2.s, p7/m, z0.s               // FSQRT <Zd>.S, <Pg>/M, <Zn>.S  \\ Floating point square root, F32  \\ 1 10 10 0.11 V1UnitV0[9]
+# CHECK-NEXT:   1    | 16 | 16  | 0.07   | V1UnitV[14], V1UnitV0[14], V1UnitV01[14], V1UnitV02[14]          | FSQRT_ZPmZ_D     | fsqrt	z17.d, p6/m, z17.d             // FSQRT <Zd>.D, <Pg>/M, <Zn>.D  \\ Floating point square root F64  \\ 1 16 16 0.07 V1UnitV0[14]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FSUB_ZPmI_D      | fsub	z12.d, p6/m, z12.d, #1.0       // FSUB <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FSUBHrr          | fsub	h20, h11, h18                  // FSUB <Hd>, <Hn>, <Hm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FSUBSrr          | fsub	s15, s4, s24                   // FSUB <Sd>, <Sn>, <Sm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FSUBDrr          | fsub	d25, d26, d4                   // FSUB <Dd>, <Dn>, <Dm>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FSUBv8f16        | fsub	v13.8h, v15.8h, v17.8h         // FSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | FSUBv2f32        | fsub	v1.2s, v31.2s, v27.2s          // FSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD FP arith, normal  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FSUB_ZPmZ_S      | fsub	z24.s, p4/m, z24.s, z10.s      // FSUB <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FSUB_ZZZ_H       | fsub	z19.h, z8.h, z29.h             // FSUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FSUBR_ZPmI_H     | fsubr	z22.h, p7/m, z22.h, #0.5       // FSUBR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FSUBR_ZPmZ_S     | fsubr	z13.s, p2/m, z13.s, z4.s       // FSUBR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Floating point arithmetic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FTMAD_ZZI_D      | ftmad	z19.d, z19.d, z6.d, #3         // FTMAD <Zdn>.<T>, <Zdn>.<T>, <Zm>.<T>, #<imm>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FTSMUL_ZZZ_S     | ftsmul	z21.s, z0.s, z10.s     // FTSMUL <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | FTSSEL_ZZZ_D     | ftssel	z5.d, z0.d, z15.d      // FTSSEL <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Floating point trigonometric   \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | hint	#9                             // HINT #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HLT              | hlt	#0x7a67                        // HLT #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HVC              | hvc	#0xecb9                        // HVC #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | ic	ialluis                        // IC <ic_op> \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | ic	ivau, x6                       // IC <ic_op2>, <Xt>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCB_XPiI        | incb	x18                            // INCB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCB_XPiI        | incb	x17, vl3                       // INCB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCB_XPiI        | incb	x17, mul3, mul #7              // INCB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCD_XPiI        | incd	x19                            // INCD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCD_XPiI        | incd	x17, vl3                       // INCD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCD_XPiI        | incd	x11, vl64, mul #7              // INCD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCH_XPiI        | inch	x24                            // INCH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCH_XPiI        | inch	x23                            // INCH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCH_XPiI        | inch	x22, vl1, mul #8               // INCH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCW_XPiI        | incw	x29                            // INCW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCW_XPiI        | incw	x2, vl64                       // INCW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCW_XPiI        | incw	x2, vl8                        // INCW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCD_ZPiI        | incd	z24.d                          // INCD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCD_ZPiI        | incd	z23.d, vl8                     // INCD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCD_ZPiI        | incd	z20.d, vl2, mul #11            // INCD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCH_ZPiI        | inch	z29.h                          // INCH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCH_ZPiI        | inch	z28.h, vl16                    // INCH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCH_ZPiI        | inch	z29.h, vl16, mul #13           // INCH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCW_ZPiI        | incw	z17.s                          // INCW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCW_ZPiI        | incw	z31.s, mul3                    // INCW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | INCW_ZPiI        | incw	z12.s, vl4, mul #5             // INCW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | INCP_XP_H        | incp	x7, p0.h                       // INCP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 7  | 7   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV01[2]    | INCP_ZP_D        | incp	z2.d, p6.d                     // INCP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_IR_B    | index	z8.b, #15, w14                 // INDEX <Zd>.B, #<imm>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_IR_H    | index	z14.h, #11, w10                // INDEX <Zd>.H, #<imm>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_IR_S    | index	z17.s, #14, w21                // INDEX <Zd>.S, #<imm>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 8  | 8   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2] | INDEX_IR_D | index	z5.d, #11, x15  // INDEX <Zd>.D, #<imm>, X<m>  \\ Horizontal operations, D form, scalar, imm/ scalar/ imm, scalar  \\ 2 8  8  0.5 V1UnitM0[2],V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | INDEX_II_B       | index	z16.b, #-2, #0                 // INDEX <Zd>.B, #<imm1>, #<imm2>  \\ Horizontal operations, B, H, S form, imm, imm  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | INDEX_II_H       | index	z13.h, #13, #2                 // INDEX <Zd>.H, #<imm1>, #<imm2>  \\ Horizontal operations, B, H, S form, imm, imm  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | INDEX_II_S       | index	z20.s, #6, #1                  // INDEX <Zd>.S, #<imm1>, #<imm2>  \\ Horizontal operations, B, H, S form, imm, imm  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 5   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | INDEX_II_D       | index	z13.d, #-15, #0                // INDEX <Zd>.D, #<imm1>, #<imm2>  \\ Horizontal operations, D form, imm, imm  \\ 1 5  5  0.5 V1UnitV0[2]
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_RI_B    | index	z28.b, w27, #1                 // INDEX <Zd>.B, W<n>, #<imm>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_RI_H    | index	z13.h, w28, #-5                // INDEX <Zd>.H, W<n>, #<imm>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_RI_S    | index	z22.s, w7, #8                  // INDEX <Zd>.S, W<n>, #<imm>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 8  | 8   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2] | INDEX_RI_D | index	z0.d, x25, #-8  // INDEX <Zd>.D, X<n>, #<imm>  \\ Horizontal operations, D form, scalar, imm/ scalar/ imm, scalar  \\ 2 8  8  0.5 V1UnitM0[2],V1UnitV0[2]
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_RR_B    | index	z6.b, w24, w8                  // INDEX <Zd>.B, W<n>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_RR_H    | index	z20.h, w4, w7                  // INDEX <Zd>.H, W<n>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 7  | 7   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02 | INDEX_RR_S    | index	z10.s, w2, w19                 // INDEX <Zd>.S, W<n>, W<m>  \\ Horizontal operations, B, H, S form, scalar, imm/ scalar/ imm, scalar  \\ 2 7  7  1.0 V1UnitM0,V1UnitV0
+# CHECK-NEXT:   2    | 8  | 8   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2] | INDEX_RR_D | index	z2.d, x23, x7  // INDEX <Zd>.D, X<n>, X<m>  \\ Horizontal operations, D form, scalar, imm/ scalar/ imm, scalar  \\ 2 8  8  0.5 V1UnitM0[2],V1UnitV0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi8lane       | mov	v15.b[7], v6.b[15]             // INS <Vd>.B[<index1b>], <Vn>.B[<index2b>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi16lane      | mov	v17.h[1], v3.h[2]              // INS <Vd>.H[<index1h>], <Vn>.H[<index2h>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi32lane      | mov	v4.s[1], v7.s[0]               // INS <Vd>.S[<index1s>], <Vn>.S[<index2s>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi64lane      | mov	v22.d[1], v25.d[1]             // INS <Vd>.D[<index1d>], <Vn>.D[<index2d>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi8gpr        | mov	v14.b[3], w12                  // INS <Vd>.B[<indexb>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi16gpr       | mov	v25.h[2], w14                  // INS <Vd>.H[<indexh>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi32gpr       | mov	v14.s[1], w29                  // INS <Vd>.S[<indexs>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi64gpr       | mov	v19.d[1], x27                  // INS <Vd>.D[<indexd>], X<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | INSR_ZV_D        | insr	z4.d, d0                       // INSR <Zdn>.<T>, <V><m>  \\ Extract/insert operation, SIMD and FP scalar form  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13 | INSR_ZR_D     | insr	z4.d, x14                      // INSR <Zdn>.<T>, <R><m>  \\ Extract/insert operation, scalar  \\ 2 6  6  1.0 V1UnitV1,V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | ISB              | isb                                 // ISB  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | ISB              | isb                                 // ISB <option>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | ISB              | isb	#1                             // ISB #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LASTA_VPZ_B      | lasta	b3, p1, z3.b                   // LASTA <V><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, SIMD and FP scalar form  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13 | LASTA_RPZ_B   | lasta	w16, p0, z10.b                 // LASTA <R><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, scalar  \\ 2 6  6  1.0 V1UnitV1,V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LASTB_VPZ_D      | lastb	d3, p1, z17.d                  // LASTB <V><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, SIMD and FP scalar form  \\ 1 3  3  1.0 V1UnitV1
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13 | LASTB_RPZ_D   | lastb	x4, p3, z31.d                  // LASTB <R><d>, <Pg>, <Zn>.<T>  \\ Extract/insert operation, scalar  \\ 2 6  6  1.0 V1UnitV1,V1UnitM0
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev8b        | ld1	{ v23.8b }, [x11]              // LD1 { <Vt>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev8b_POST   | ld1	{ v25.8b }, [x30], #8          // LD1 { <Vt>.8B }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev8b_POST   | ld1	{ v14.8b }, [x1], x26          // LD1 { <Vt>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev16b       | ld1	{ v12.16b }, [x19]             // LD1 { <Vt>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev16b_POST  | ld1	{ v24.16b }, [x28], #16        // LD1 { <Vt>.16B }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev16b_POST  | ld1	{ v21.16b }, [x25], x28        // LD1 { <Vt>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev4h        | ld1	{ v8.4h }, [x30]               // LD1 { <Vt>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev4h_POST   | ld1	{ v4.4h }, [x10], #8           // LD1 { <Vt>.4H }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev4h_POST   | ld1	{ v17.4h }, [x12], x16         // LD1 { <Vt>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev8h        | ld1	{ v24.8h }, [x27]              // LD1 { <Vt>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev8h_POST   | ld1	{ v21.8h }, [x24], #16         // LD1 { <Vt>.8H }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev8h_POST   | ld1	{ v9.8h }, [x9], x27           // LD1 { <Vt>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev2s        | ld1	{ v4.2s }, [x2]                // LD1 { <Vt>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev2s_POST   | ld1	{ v19.2s }, [x27], #8          // LD1 { <Vt>.2S }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev2s_POST   | ld1	{ v25.2s }, [x13], x19         // LD1 { <Vt>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev4s        | ld1	{ v3.4s }, [x4]                // LD1 { <Vt>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev4s_POST   | ld1	{ v24.4s }, [x20], #16         // LD1 { <Vt>.4S }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev4s_POST   | ld1	{ v29.4s }, [x25], x23         // LD1 { <Vt>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev1d        | ld1	{ v24.1d }, [x9]               // LD1 { <Vt>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev1d_POST   | ld1	{ v23.1d }, [x3], #8           // LD1 { <Vt>.1D }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev1d_POST   | ld1	{ v19.1d }, [x10], x19         // LD1 { <Vt>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, D-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LD1Onev2d        | ld1	{ v3.2d }, [x28]               // LD1 { <Vt>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev2d_POST   | ld1	{ v8.2d }, [x16], #16          // LD1 { <Vt>.2D }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LD1Onev2d_POST   | ld1	{ v5.2d }, [x1], x29           // LD1 { <Vt>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 1 reg, Q-form  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov8b        | ld1	{ v24.8b, v25.8b }, [x6]       // LD1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov8b_POST   | ld1	{ v17.8b, v18.8b }, [x18], #16  // LD1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov8b_POST   | ld1	{ v18.8b, v19.8b }, [x6], x11  // LD1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov16b       | ld1	{ v0.16b, v1.16b }, [x14]      // LD1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov16b_POST  | ld1	{ v20.16b, v21.16b }, [x2], #32  // LD1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov16b_POST  | ld1	{ v5.16b, v6.16b }, [x17], x25  // LD1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov4h        | ld1	{ v25.4h, v26.4h }, [x3]       // LD1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov4h_POST   | ld1	{ v10.4h, v11.4h }, [x14], #16  // LD1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov4h_POST   | ld1	{ v0.4h, v1.4h }, [x24], x15   // LD1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov8h        | ld1	{ v1.8h, v2.8h }, [x27]        // LD1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov8h_POST   | ld1	{ v22.8h, v23.8h }, [x13], #32  // LD1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov8h_POST   | ld1	{ v9.8h, v10.8h }, [x4], x13   // LD1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov2s        | ld1	{ v6.2s, v7.2s }, [x29]        // LD1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov2s_POST   | ld1	{ v23.2s, v24.2s }, [x10], #16  // LD1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov2s_POST   | ld1	{ v26.2s, v27.2s }, [x21], x29  // LD1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov4s        | ld1	{ v11.4s, v12.4s }, [x30]      // LD1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov4s_POST   | ld1	{ v23.4s, v24.4s }, [x14], #32  // LD1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov4s_POST   | ld1	{ v12.4s, v13.4s }, [x27], x22  // LD1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov1d        | ld1	{ v27.1d, v28.1d }, [x7]       // LD1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov1d_POST   | ld1	{ v13.1d, v14.1d }, [x29], #16  // LD1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], #16  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov1d_POST   | ld1	{ v1.1d, v2.1d }, [x7], x20    // LD1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Twov2d        | ld1	{ v13.2d, v14.2d }, [x13]      // LD1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov2d_POST   | ld1	{ v13.2d, v14.2d }, [x10], #32  // LD1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Twov2d_POST   | ld1	{ v20.2d, v21.2d }, [x29], x28  // LD1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 2 reg, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev8b      | ld1	{ v7.8b, v8.8b, v9.8b }, [x12]  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev8b_POST | ld1	{ v13.8b, v14.8b, v15.8b }, [x10], #24  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev8b_POST | ld1	{ v28.8b, v29.8b, v30.8b }, [x2], x21  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev16b     | ld1	{ v19.16b, v20.16b, v21.16b }, [x10]  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev16b_POST | ld1	{ v8.16b, v9.16b, v10.16b }, [x29], #48  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev16b_POST | ld1	{ v14.16b, v15.16b, v16.16b }, [x5], x17  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev4h      | ld1	{ v10.4h, v11.4h, v12.4h }, [x28]  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev4h_POST | ld1	{ v22.4h, v23.4h, v24.4h }, [x6], #24  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev4h_POST | ld1	{ v11.4h, v12.4h, v13.4h }, [x13], x23  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev8h      | ld1	{ v21.8h, v22.8h, v23.8h }, [x22]  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev8h_POST | ld1	{ v26.8h, v27.8h, v28.8h }, [x2], #48  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev8h_POST | ld1	{ v6.8h, v7.8h, v8.8h }, [x22], x6  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev2s      | ld1	{ v16.2s, v17.2s, v18.2s }, [x27]  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev2s_POST | ld1	{ v3.2s, v4.2s, v5.2s }, [x30], #24  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev2s_POST | ld1	{ v14.2s, v15.2s, v16.2s }, [x11], x28  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev4s      | ld1	{ v0.4s, v1.4s, v2.4s }, [x24]  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev4s_POST | ld1	{ v17.4s, v18.4s, v19.4s }, [x28], #48  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev4s_POST | ld1	{ v5.4s, v6.4s, v7.4s }, [x20], x13  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev1d      | ld1	{ v14.1d, v15.1d, v16.1d }, [x3]  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev1d_POST | ld1	{ v21.1d, v22.1d, v23.1d }, [x24], #24  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], #24  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev1d_POST | ld1	{ v25.1d, v26.1d, v27.1d }, [x18], x14  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, D-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.00   | V1UnitL[3]                                                       | LD1Threev2d      | ld1	{ v12.2d, v13.2d, v14.2d }, [x15]  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 1 6  6  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev2d_POST | ld1	{ v13.2d, v14.2d, v15.2d }, [x4], #48  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[3]                                              | LD1Threev2d_POST | ld1	{ v15.2d, v16.2d, v17.2d }, [x10], x6  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 3 reg, Q-form  \\ 2 6  6  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Fourv8b       | ld1	{ v4.8b, v5.8b, v6.8b, v7.8b }, [x13]  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv8b_POST  | ld1	{ v8.8b, v9.8b, v10.8b, v11.8b }, [x30], #32  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv8b_POST  | ld1	{ v4.8b, v5.8b, v6.8b, v7.8b }, [x20], x3  // LD1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 7  | 7   | 0.75   | V1UnitL[4]                                                       | LD1Fourv16b      | ld1	{ v13.16b, v14.16b, v15.16b, v16.16b }, [x9]  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv16b_POST | ld1	{ v3.16b, v4.16b, v5.16b, v6.16b }, [x17], #64  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv16b_POST | ld1	{ v10.16b, v11.16b, v12.16b, v13.16b }, [x19], x29  // LD1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Fourv4h       | ld1	{ v20.4h, v21.4h, v22.4h, v23.4h }, [x15]  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv4h_POST  | ld1	{ v4.4h, v5.4h, v6.4h, v7.4h }, [x12], #32  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv4h_POST  | ld1	{ v24.4h, v25.4h, v26.4h, v27.4h }, [x25], x0  // LD1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 7  | 7   | 0.75   | V1UnitL[4]                                                       | LD1Fourv8h       | ld1	{ v0.8h, v1.8h, v2.8h, v3.8h }, [x21]  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv8h_POST  | ld1	{ v12.8h, v13.8h, v14.8h, v15.8h }, [x21], #64  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv8h_POST  | ld1	{ v14.8h, v15.8h, v16.8h, v17.8h }, [x12], x23  // LD1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Fourv2s       | ld1	{ v21.2s, v22.2s, v23.2s, v24.2s }, [x21]  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv2s_POST  | ld1	{ v27.2s, v28.2s, v29.2s, v30.2s }, [x11], #32  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv2s_POST  | ld1	{ v24.2s, v25.2s, v26.2s, v27.2s }, [x1], x22  // LD1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 7  | 7   | 0.75   | V1UnitL[4]                                                       | LD1Fourv4s       | ld1	{ v15.4s, v16.4s, v17.4s, v18.4s }, [x28]  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv4s_POST  | ld1	{ v14.4s, v15.4s, v16.4s, v17.4s }, [x8], #64  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv4s_POST  | ld1	{ v11.4s, v12.4s, v13.4s, v14.4s }, [x2], x28  // LD1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LD1Fourv1d       | ld1	{ v22.1d, v23.1d, v24.1d, v25.1d }, [x4]  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv1d_POST  | ld1	{ v3.1d, v4.1d, v5.1d, v6.1d }, [x23], #32  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], #32  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LD1Fourv1d_POST  | ld1	{ v22.1d, v23.1d, v24.1d, v25.1d }, [x9], x22  // LD1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, D-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 7  | 7   | 0.75   | V1UnitL[4]                                                       | LD1Fourv2d       | ld1	{ v18.2d, v19.2d, v20.2d, v21.2d }, [x6]  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 1 7  7  0.75 V1UnitL[4]
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv2d_POST  | ld1	{ v3.2d, v4.2d, v5.2d, v6.2d }, [x3], #64  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   2    | 7  | 7   | 0.75   | V1UnitI, V1UnitL[4]                                              | LD1Fourv2d_POST  | ld1	{ v6.2d, v7.2d, v8.2d, v9.2d }, [x17], x18  // LD1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, multiple, 4 reg, Q-form  \\ 2 7  7  0.75 V1UnitL[4],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1i8            | ld1	{ v18.b }[3], [x23]            // LD1 { <Vt>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1i16           | ld1	{ v18.h }[3], [x1]             // LD1 { <Vt>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1i32           | ld1	{ v8.s }[0], [x24]             // LD1 { <Vt>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1i64           | ld1	{ v11.d }[0], [x13]            // LD1 { <Vt>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 1 element, one lane, D  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i8_POST       | ld1	{ v23.b }[1], [x13], #1        // LD1 { <Vt>.B }[<indexb>], [<Xn|SP>], #1  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i8_POST       | ld1	{ v10.b }[9], [x25], x14       // LD1 { <Vt>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i16_POST      | ld1	{ v6.h }[2], [x26], #2         // LD1 { <Vt>.H }[<indexh>], [<Xn|SP>], #2  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i16_POST      | ld1	{ v30.h }[6], [x27], x3        // LD1 { <Vt>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i32_POST      | ld1	{ v5.s }[1], [x10], #4         // LD1 { <Vt>.S }[<indexs>], [<Xn|SP>], #4  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i32_POST      | ld1	{ v13.s }[3], [x6], x24        // LD1 { <Vt>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i64_POST      | ld1	{ v26.d }[1], [x28], #8        // LD1 { <Vt>.D }[<indexd>], [<Xn|SP>], #8  \\ ASIMD load, 1 element, one lane, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1i64_POST      | ld1	{ v1.d }[1], [x20], x30        // LD1 { <Vt>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, one lane, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_IMM         | ld1b	{ z20.b }, p1/z, [x25]         // LD1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_IMM         | ld1b	{ z10.b }, p1/z, [x16, #-1, mul vl]  // LD1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_H_IMM       | ld1b	{ z31.h }, p1/z, [x4]          // LD1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_H_IMM       | ld1b	{ z5.h }, p5/z, [x8, #6, mul vl]  // LD1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_S_IMM       | ld1b	{ z1.s }, p3/z, [x12]          // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_S_IMM       | ld1b	{ z24.s }, p2/z, [x28, #1, mul vl]  // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_D_IMM       | ld1b	{ z25.d }, p5/z, [x2]          // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_D_IMM       | ld1b	{ z0.d }, p6/z, [x22, #5, mul vl]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B             | ld1b	{ z7.b }, p0/z, [x24, x11]     // LD1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_H           | ld1b	{ z26.h }, p5/z, [x5, x21]     // LD1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_S           | ld1b	{ z22.s }, p3/z, [x16, x12]    // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1B_D           | ld1b	{ z7.d }, p5/z, [x18, x12]     // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1B_D_UXTW     | ld1b	{ z2.d }, p0/z, [x15, z18.d, uxtw]  // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1B_S_SXTW     | ld1b	{ z20.s }, p6/z, [x2, z0.s, sxtw]  // LD1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1B_D          | ld1b	{ z15.d }, p4/z, [x23, z9.d]   // LD1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1B_S_IMM      | ld1b	{ z8.s }, p4/z, [z25.s, #22]   // LD1B { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1B_D_IMM      | ld1b	{ z13.d }, p2/z, [z3.d, #30]   // LD1B { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1D_SXTW_SCALED | ld1d	{ z21.d }, p1/z, [x24, z31.d, sxtw #3]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1D_SXTW       | ld1d	{ z7.d }, p0/z, [x13, z15.d, sxtw]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1D_SCALED     | ld1d	{ z14.d }, p1/z, [x26, z27.d, lsl #3]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1D            | ld1d	{ z30.d }, p7/z, [x14, z16.d]  // LD1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1D_IMM        | ld1d	{ z22.d }, p1/z, [z15.d]       // LD1D { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1D_IMM        | ld1d	{ z8.d }, p4/z, [z12.d, #200]  // LD1D { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_IMM         | ld1h	{ z3.h }, p2/z, [x21]          // LD1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_IMM         | ld1h	{ z15.h }, p0/z, [x25, #-3, mul vl]  // LD1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_S_IMM       | ld1h	{ z9.s }, p1/z, [x17]          // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_S_IMM       | ld1h	{ z1.s }, p3/z, [x14, #5, mul vl]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_D_IMM       | ld1h	{ z10.d }, p3/z, [x9]          // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_D_IMM       | ld1h	{ z2.d }, p7/z, [x1, #4, mul vl]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H             | ld1h	{ z26.h }, p5/z, [x10, x19, lsl #1]  // LD1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_S           | ld1h	{ z29.s }, p7/z, [x23, x11, lsl #1]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1H_D           | ld1h	{ z2.d }, p5/z, [x30, x9, lsl #1]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1H_S_SXTW_SCALED | ld1h	{ z14.s }, p7/z, [x14, z28.s, sxtw #1]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1H_D_SXTW_SCALED | ld1h	{ z28.d }, p7/z, [x8, z9.d, sxtw #1]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1H_D_UXTW     | ld1h	{ z16.d }, p5/z, [x7, z9.d, uxtw]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1H_S_UXTW     | ld1h	{ z27.s }, p4/z, [x4, z7.s, uxtw]  // LD1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1H_D_SCALED   | ld1h	{ z6.d }, p7/z, [x30, z26.d, lsl #1]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1H_D          | ld1h	{ z11.d }, p2/z, [x20, z25.d]  // LD1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1H_S_IMM      | ld1h	{ z6.s }, p7/z, [z31.s]        // LD1H { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1H_S_IMM      | ld1h	{ z1.s }, p3/z, [z12.s, #8]    // LD1H { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1H_D_IMM      | ld1h	{ z7.d }, p7/z, [z9.d]         // LD1H { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1H_D_IMM      | ld1h	{ z13.d }, p3/z, [z5.d, #8]    // LD1H { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv8b          | ld1r	{ v8.8b }, [x23]               // LD1R { <Vt>.8B }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv8b_POST     | ld1r	{ v4.8b }, [x25], #1           // LD1R { <Vt>.8B }, [<Xn|SP>], #1  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv8b_POST     | ld1r	{ v14.8b }, [x24], x14         // LD1R { <Vt>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv16b         | ld1r	{ v8.16b }, [x24]              // LD1R { <Vt>.16B }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv16b_POST    | ld1r	{ v21.16b }, [x30], #1         // LD1R { <Vt>.16B }, [<Xn|SP>], #1  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv16b_POST    | ld1r	{ v1.16b }, [x3], x9           // LD1R { <Vt>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv4h          | ld1r	{ v28.4h }, [x9]               // LD1R { <Vt>.4H }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv4h_POST     | ld1r	{ v10.4h }, [x27], #2          // LD1R { <Vt>.4H }, [<Xn|SP>], #2  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv4h_POST     | ld1r	{ v12.4h }, [x8], x20          // LD1R { <Vt>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv8h          | ld1r	{ v3.8h }, [x16]               // LD1R { <Vt>.8H }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv8h_POST     | ld1r	{ v27.8h }, [x18], #2          // LD1R { <Vt>.8H }, [<Xn|SP>], #2  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv8h_POST     | ld1r	{ v20.8h }, [x20], x4          // LD1R { <Vt>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv2s          | ld1r	{ v10.2s }, [x20]              // LD1R { <Vt>.2S }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv2s_POST     | ld1r	{ v28.2s }, [x8], #4           // LD1R { <Vt>.2S }, [<Xn|SP>], #4  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv2s_POST     | ld1r	{ v4.2s }, [x0], x12           // LD1R { <Vt>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv4s          | ld1r	{ v11.4s }, [x3]               // LD1R { <Vt>.4S }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv4s_POST     | ld1r	{ v18.4s }, [x3], #4           // LD1R { <Vt>.4S }, [<Xn|SP>], #4  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv4s_POST     | ld1r	{ v2.4s }, [x4], x1            // LD1R { <Vt>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv1d          | ld1r	{ v3.1d }, [x15]               // LD1R { <Vt>.1D }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, D-form, D  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv1d_POST     | ld1r	{ v16.1d }, [x2], #8           // LD1R { <Vt>.1D }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, all lanes, D-form, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv1d_POST     | ld1r	{ v24.1d }, [x21], x3          // LD1R { <Vt>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, D-form, D  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD1Rv2d          | ld1r	{ v18.2d }, [x0]               // LD1R { <Vt>.2D }, [<Xn|SP>]  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv2d_POST     | ld1r	{ v8.2d }, [x18], #8           // LD1R { <Vt>.2D }, [<Xn|SP>], #8  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD1Rv2d_POST     | ld1r	{ v8.2d }, [x16], x28          // LD1R { <Vt>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 1 element, all lanes, Q-form  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_IMM        | ld1rb	{ z13.b }, p0/z, [x9]          // LD1RB { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_IMM        | ld1rb	{ z30.b }, p6/z, [x21, #28]    // LD1RB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_H_IMM      | ld1rb	{ z10.h }, p1/z, [x9]          // LD1RB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_H_IMM      | ld1rb	{ z25.h }, p3/z, [x26, #6]     // LD1RB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_S_IMM      | ld1rb	{ z24.s }, p2/z, [x19]         // LD1RB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_S_IMM      | ld1rb	{ z16.s }, p1/z, [x8, #54]     // LD1RB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_D_IMM      | ld1rb	{ z17.d }, p7/z, [x4]          // LD1RB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RB_D_IMM      | ld1rb	{ z4.d }, p7/z, [x20, #18]     // LD1RB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RD_IMM        | ld1rd	{ z12.d }, p7/z, [x20]         // LD1RD { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RD_IMM        | ld1rd	{ z19.d }, p5/z, [x13, #384]   // LD1RD { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RH_IMM        | ld1rh	{ z13.h }, p7/z, [x0]          // LD1RH { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RH_IMM        | ld1rh	{ z23.h }, p0/z, [x18, #56]    // LD1RH { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RH_S_IMM      | ld1rh	{ z24.s }, p6/z, [x27]         // LD1RH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RH_S_IMM      | ld1rh	{ z6.s }, p7/z, [x1, #84]      // LD1RH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RH_D_IMM      | ld1rh	{ z3.d }, p4/z, [x25]          // LD1RH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RH_D_IMM      | ld1rh	{ z25.d }, p5/z, [x5, #108]    // LD1RH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_B_IMM      | ld1rqb	{ z31.b }, p1/z, [x6]  // LD1RQB { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_B_IMM      | ld1rqb	{ z21.b }, p7/z, [x29, #112]  // LD1RQB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_B          | ld1rqb	{ z7.b }, p6/z, [x26, x26]  // LD1RQB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load broadcast, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_D_IMM      | ld1rqd	{ z10.d }, p0/z, [x28]  // LD1RQD { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_D_IMM      | ld1rqd	{ z29.d }, p5/z, [x6, #-16]  // LD1RQD { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_D          | ld1rqd	{ z5.d }, p6/z, [x7, x8, lsl #3]  // LD1RQD { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous load broadcast, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_H_IMM      | ld1rqh	{ z29.h }, p3/z, [x3]  // LD1RQH { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_H_IMM      | ld1rqh	{ z29.h }, p4/z, [x30, #112]  // LD1RQH { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1RQ_H          | ld1rqh	{ z9.h }, p0/z, [x23, x11, lsl #1]  // LD1RQH { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load broadcast, scalar + scalar + S \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_W_IMM      | ld1rqw	{ z11.s }, p0/z, [x26]  // LD1RQW { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_W_IMM      | ld1rqw	{ z7.s }, p3/z, [x16, #-80]  // LD1RQW { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RQ_W          | ld1rqw	{ z2.s }, p0/z, [x21, x23, lsl #2]  // LD1RQW { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous load broadcast, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSB_H_IMM     | ld1rsb	{ z6.h }, p6/z, [x23]  // LD1RSB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSB_H_IMM     | ld1rsb	{ z28.h }, p3/z, [x21, #43]  // LD1RSB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSB_S_IMM     | ld1rsb	{ z13.s }, p5/z, [x14]  // LD1RSB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSB_S_IMM     | ld1rsb	{ z26.s }, p3/z, [x15, #4]  // LD1RSB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSB_D_IMM     | ld1rsb	{ z23.d }, p2/z, [x21]  // LD1RSB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSB_D_IMM     | ld1rsb	{ z29.d }, p6/z, [x14, #25]  // LD1RSB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSH_S_IMM     | ld1rsh	{ z25.s }, p2/z, [x4]  // LD1RSH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSH_S_IMM     | ld1rsh	{ z30.s }, p5/z, [x6, #124]  // LD1RSH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSH_D_IMM     | ld1rsh	{ z24.d }, p4/z, [x6]  // LD1RSH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSH_D_IMM     | ld1rsh	{ z14.d }, p3/z, [x20, #98]  // LD1RSH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSW_IMM       | ld1rsw	{ z2.d }, p0/z, [x23]  // LD1RSW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RSW_IMM       | ld1rsw	{ z18.d }, p7/z, [x11]  // LD1RSW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RW_IMM        | ld1rw	{ z12.s }, p7/z, [x9]          // LD1RW { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RW_IMM        | ld1rw	{ z25.s }, p7/z, [x17, #60]    // LD1RW { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RW_D_IMM      | ld1rw	{ z22.d }, p5/z, [x1]          // LD1RW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1RW_D_IMM      | ld1rw	{ z2.d }, p3/z, [x3, #36]      // LD1RW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>]  \\ Contiguous load broadcast, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_H_IMM      | ld1sb	{ z28.h }, p6/z, [x9]          // LD1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_H_IMM      | ld1sb	{ z22.h }, p2/z, [x19, #7, mul vl]  // LD1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_S_IMM      | ld1sb	{ z22.s }, p3/z, [x23]         // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_S_IMM      | ld1sb	{ z2.s }, p6/z, [x22, #-2, mul vl]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_D_IMM      | ld1sb	{ z31.d }, p6/z, [x10]         // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_D_IMM      | ld1sb	{ z23.d }, p5/z, [x2, #-4, mul vl]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_H          | ld1sb	{ z3.h }, p5/z, [x10, x23]     // LD1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_S          | ld1sb	{ z16.s }, p7/z, [x27, x16]    // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SB_D          | ld1sb	{ z13.d }, p7/z, [x28, x18]    // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SB_D_UXTW    | ld1sb	{ z30.d }, p6/z, [x22, z27.d, uxtw]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SB_S_UXTW    | ld1sb	{ z23.s }, p5/z, [x17, z10.s, uxtw]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SB_D         | ld1sb	{ z23.d }, p2/z, [x28, z10.d]  // LD1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SB_S_IMM     | ld1sb	{ z14.s }, p4/z, [z18.s, #24]  // LD1SB { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SB_D_IMM     | ld1sb	{ z5.d }, p0/z, [z25.d, #31]   // LD1SB { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SH_S_IMM      | ld1sh	{ z8.s }, p3/z, [x21]          // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SH_S_IMM      | ld1sh	{ z29.s }, p4/z, [x11, #-4, mul vl]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SH_D_IMM      | ld1sh	{ z13.d }, p6/z, [x18]         // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SH_D_IMM      | ld1sh	{ z19.d }, p2/z, [x29, #-3, mul vl]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1SH_S          | ld1sh	{ z28.s }, p0/z, [x6, x28, lsl #1]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LD1SH_D          | ld1sh	{ z26.d }, p0/z, [x7, x12, lsl #1]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SH_S_UXTW_SCALED | ld1sh	{ z22.s }, p3/z, [x7, z1.s, uxtw #1]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SH_D_SXTW_SCALED | ld1sh	{ z3.d }, p6/z, [x11, z14.d, sxtw #1]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SH_D_SXTW    | ld1sh	{ z27.d }, p3/z, [x19, z23.d, sxtw]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SH_S_SXTW    | ld1sh	{ z12.s }, p5/z, [x27, z13.s, sxtw]  // LD1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SH_D_SCALED  | ld1sh	{ z9.d }, p0/z, [x22, z8.d, lsl #1]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SH_D         | ld1sh	{ z22.d }, p0/z, [x27, z12.d]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SH_S_IMM     | ld1sh	{ z1.s }, p2/z, [z9.s, #44]    // LD1SH { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SH_D_IMM     | ld1sh	{ z11.d }, p5/z, [z30.d, #34]  // LD1SH { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SW_D_IMM      | ld1sw	{ z7.d }, p1/z, [x19]          // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SW_D_IMM      | ld1sw	{ z28.d }, p1/z, [x26, #4, mul vl]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LD1SW_D          | ld1sw	{ z26.d }, p4/z, [x20, x17, lsl #2]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous load, scalar + scalar  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SW_D_SXTW_SCALED | ld1sw	{ z22.d }, p1/z, [x14, z23.d, sxtw #2]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SW_D_SXTW    | ld1sw	{ z4.d }, p3/z, [x20, z15.d, sxtw]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1SW_D_SCALED  | ld1sw	{ z1.d }, p4/z, [x20, z23.d, lsl #2]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SW_D         | ld1sw	{ z2.d }, p7/z, [x4, z0.d]     // LD1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SW_D_IMM     | ld1sw	{ z12.d }, p7/z, [z21.d]       // LD1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1SW_D_IMM     | ld1sw	{ z27.d }, p3/z, [z10.d, #24]  // LD1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1W_SXTW_SCALED | ld1w	{ z9.s }, p0/z, [x18, z9.s, sxtw #2]  // LD1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1W_D_UXTW_SCALED | ld1w	{ z14.d }, p5/z, [x26, z2.d, uxtw #2]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1W_D_UXTW     | ld1w	{ z31.d }, p6/z, [x17, z2.d, uxtw]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1W_SXTW       | ld1w	{ z14.s }, p2/z, [x18, z28.s, sxtw]  // LD1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1W_D_SCALED   | ld1w	{ z13.d }, p3/z, [x5, z11.d, lsl #2]  // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1W_D          | ld1w	{ z24.d }, p3/z, [x2, z17.d]   // LD1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1W_IMM        | ld1w	{ z4.s }, p0/z, [z1.s]         // LD1W { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLD1W_IMM        | ld1w	{ z17.s }, p6/z, [z26.s, #60]  // LD1W { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1W_D_IMM      | ld1w	{ z31.d }, p7/z, [z22.d]       // LD1W { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLD1W_D_IMM      | ld1w	{ z2.d }, p3/z, [z6.d, #116]   // LD1W { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD2Twov8b        | ld2	{ v13.8b, v14.8b }, [x4]       // LD2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD2Twov8b_POST   | ld2	{ v20.8b, v21.8b }, [x11], #16  // LD2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD2Twov8b_POST   | ld2	{ v13.8b, v14.8b }, [x4], x7   // LD2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Twov16b       | ld2	{ v26.16b, v27.16b }, [x16]    // LD2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov16b_POST  | ld2	{ v15.16b, v16.16b }, [x3], #32  // LD2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov16b_POST  | ld2	{ v24.16b, v25.16b }, [x7], x30  // LD2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD2Twov4h        | ld2	{ v0.4h, v1.4h }, [x21]        // LD2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD2Twov4h_POST   | ld2	{ v5.4h, v6.4h }, [x30], #16   // LD2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD2Twov4h_POST   | ld2	{ v5.4h, v6.4h }, [x22], x1    // LD2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Twov8h        | ld2	{ v8.8h, v9.8h }, [x28]        // LD2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov8h_POST   | ld2	{ v14.8h, v15.8h }, [x19], #32  // LD2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov8h_POST   | ld2	{ v28.8h, v29.8h }, [x26], x7  // LD2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 3.00   | V1UnitL, V1UnitV                                                 | LD2Twov2s        | ld2	{ v2.2s, v3.2s }, [x16]        // LD2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 2 8  8  3.0 V1UnitL,V1UnitV
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD2Twov2s_POST   | ld2	{ v23.2s, v24.2s }, [x5], #16  // LD2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 3.00   | V1UnitI, V1UnitL, V1UnitV                                        | LD2Twov2s_POST   | ld2	{ v22.2s, v23.2s }, [x11], x12  // LD2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, D-form, B/H/S  \\ 3 8  8  3.0 V1UnitL,V1UnitV,V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Twov4s        | ld2	{ v22.4s, v23.4s }, [x4]       // LD2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov4s_POST   | ld2	{ v27.4s, v28.4s }, [x18], #32  // LD2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov4s_POST   | ld2	{ v22.4s, v23.4s }, [x26], x29  // LD2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Twov2d        | ld2	{ v22.2d, v23.2d }, [x17]      // LD2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD load, 2 element, multiple, Q-form, D  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov2d_POST   | ld2	{ v12.2d, v13.2d }, [x19], #32  // LD2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD load, 2 element, multiple, Q-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Twov2d_POST   | ld2	{ v6.2d, v7.2d }, [x11], x24   // LD2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, multiple, Q-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2i8            | ld2	{ v29.b, v30.b }[3], [x1]      // LD2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, B/H  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2i16           | ld2	{ v23.h, v24.h }[7], [x14]     // LD2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, B/H  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2i32           | ld2	{ v26.s, v27.s }[1], [x17]     // LD2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2i64           | ld2	{ v1.d, v2.d }[0], [x10]       // LD2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 2 element, one lane, D  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i8_POST       | ld2	{ v20.b, v21.b }[9], [x24], #2  // LD2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], #2  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i8_POST       | ld2	{ v29.b, v30.b }[6], [x18], x19  // LD2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i16_POST      | ld2	{ v2.h, v3.h }[3], [x12], #4   // LD2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], #4  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i16_POST      | ld2	{ v11.h, v12.h }[3], [x18], x17  // LD2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, B/H  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i32_POST      | ld2	{ v15.s, v16.s }[1], [x7], #8  // LD2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], #8  \\ ASIMD load, 2 element, one lane, S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i32_POST      | ld2	{ v29.s, v30.s }[1], [x12], x0  // LD2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i64_POST      | ld2	{ v1.d, v2.d }[1], [x3], #16   // LD2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], #16  \\ ASIMD load, 2 element, one lane, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2i64_POST      | ld2	{ v10.d, v11.d }[1], [x18], x27  // LD2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, one lane, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2B_IMM         | ld2b	{ z9.b, z10.b }, p2/z, [x22]   // LD2B { <Zt1>.B, <Zt2>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2B_IMM         | ld2b	{ z28.b, z29.b }, p3/z, [x22, #4, mul vl]  // LD2B { <Zt1>.B, <Zt2>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 9  | 9   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2B             | ld2b	{ z26.b, z27.b }, p1/z, [x3, x12]  // LD2B { <Zt1>.B, <Zt2>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 2 9  9  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2D_IMM         | ld2d	{ z12.d, z13.d }, p5/z, [x24]  // LD2D { <Zt1>.D, <Zt2>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2D_IMM         | ld2d	{ z22.d, z23.d }, p2/z, [x21, #-2, mul vl]  // LD2D { <Zt1>.D, <Zt2>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 9  | 9   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2D             | ld2d	{ z22.d, z23.d }, p6/z, [x14, x4, lsl #3]  // LD2D { <Zt1>.D, <Zt2>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 2 9  9  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2H_IMM         | ld2h	{ z5.h, z6.h }, p5/z, [x20]    // LD2H { <Zt1>.H, <Zt2>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2H_IMM         | ld2h	{ z27.h, z28.h }, p7/z, [x11, #14, mul vl]  // LD2H { <Zt1>.H, <Zt2>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   3    | 10 | 10  | 1.00   | V1UnitI[2], V1UnitL[2], V1UnitL01[2], V1UnitS[2], V1UnitV[2], V1UnitV01[2] | LD2H   | ld2h	{ z18.h, z19.h }, p3/z, [x9, x17, lsl #1]  // LD2H { <Zt1>.H, <Zt2>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 3 10  10  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitS[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv8b          | ld2r	{ v10.8b, v11.8b }, [x20]      // LD2R { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv8b_POST     | ld2r	{ v18.8b, v19.8b }, [x11], #2  // LD2R { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #2  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv8b_POST     | ld2r	{ v28.8b, v29.8b }, [x30], x14  // LD2R { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv16b         | ld2r	{ v10.16b, v11.16b }, [x23]    // LD2R { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv16b_POST    | ld2r	{ v24.16b, v25.16b }, [x1], #2  // LD2R { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #2  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv16b_POST    | ld2r	{ v20.16b, v21.16b }, [x11], x7  // LD2R { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv4h          | ld2r	{ v25.4h, v26.4h }, [x11]      // LD2R { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv4h_POST     | ld2r	{ v28.4h, v29.4h }, [x18], #4  // LD2R { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #4  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv4h_POST     | ld2r	{ v21.4h, v22.4h }, [x2], x17  // LD2R { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv8h          | ld2r	{ v23.8h, v24.8h }, [x10]      // LD2R { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv8h_POST     | ld2r	{ v19.8h, v20.8h }, [x29], #4  // LD2R { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #4  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv8h_POST     | ld2r	{ v13.8h, v14.8h }, [x13], x5  // LD2R { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv2s          | ld2r	{ v25.2s, v26.2s }, [x19]      // LD2R { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv2s_POST     | ld2r	{ v5.2s, v6.2s }, [x28], #8    // LD2R { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #8  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv2s_POST     | ld2r	{ v4.2s, v5.2s }, [x14], x19   // LD2R { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv4s          | ld2r	{ v8.4s, v9.4s }, [x17]        // LD2R { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv4s_POST     | ld2r	{ v22.4s, v23.4s }, [x5], #8   // LD2R { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #8  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv4s_POST     | ld2r	{ v29.4s, v30.4s }, [x4], x18  // LD2R { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv1d          | ld2r	{ v9.1d, v10.1d }, [x25]       // LD2R { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, D-form, D  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv1d_POST     | ld2r	{ v15.1d, v16.1d }, [x26], #16  // LD2R { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, all lanes, D-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv1d_POST     | ld2r	{ v10.1d, v11.1d }, [x28], x26  // LD2R { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, D-form, D  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.50   | V1UnitL[2], V1UnitV[2]                                           | LD2Rv2d          | ld2r	{ v26.2d, v27.2d }, [x8]       // LD2R { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 2 8  8  1.5 V1UnitL[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv2d_POST     | ld2r	{ v14.2d, v15.2d }, [x3], #16  // LD2R { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #16  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.50   | V1UnitI, V1UnitL[2], V1UnitV[2]                                  | LD2Rv2d_POST     | ld2r	{ v24.2d, v25.2d }, [x6], x14  // LD2R { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 2 element, all lanes, Q-form  \\ 3 8  8  1.5 V1UnitL[2],V1UnitV[2],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2W_IMM         | ld2w	{ z21.s, z22.s }, p4/z, [x12]  // LD2W { <Zt1>.S, <Zt2>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2W_IMM         | ld2w	{ z29.s, z30.s }, p2/z, [x19, #6, mul vl]  // LD2W { <Zt1>.S, <Zt2>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load two structures to two vectors, scalar + imm  \\ 2 8  8  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 9  | 9   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | LD2W             | ld2w	{ z18.s, z19.s }, p6/z, [x22, x22, lsl #2]  // LD2W { <Zt1>.S, <Zt2>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous Load two structures to two vectors, scalar + scalar  \\ 2 9  9  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev8b      | ld3	{ v8.8b, v9.8b, v10.8b }, [x0]  // LD3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev8b_POST | ld3	{ v6.8b, v7.8b, v8.8b }, [x26], #24  // LD3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev8b_POST | ld3	{ v20.8b, v21.8b, v22.8b }, [x25], x24  // LD3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev16b     | ld3	{ v15.16b, v16.16b, v17.16b }, [x5]  // LD3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev16b_POST | ld3	{ v19.16b, v20.16b, v21.16b }, [x3], #48  // LD3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev16b_POST | ld3	{ v26.16b, v27.16b, v28.16b }, [x8], x29  // LD3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev4h      | ld3	{ v15.4h, v16.4h, v17.4h }, [x8]  // LD3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev4h_POST | ld3	{ v4.4h, v5.4h, v6.4h }, [x5], #24  // LD3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev4h_POST | ld3	{ v24.4h, v25.4h, v26.4h }, [x25], x0  // LD3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev8h      | ld3	{ v7.8h, v8.8h, v9.8h }, [x21]  // LD3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev8h_POST | ld3	{ v4.8h, v5.8h, v6.8h }, [x26], #48  // LD3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev8h_POST | ld3	{ v12.8h, v13.8h, v14.8h }, [x0], x25  // LD3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev2s      | ld3	{ v16.2s, v17.2s, v18.2s }, [x0]  // LD3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev2s_POST | ld3	{ v9.2s, v10.2s, v11.2s }, [x1], #24  // LD3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev2s_POST | ld3	{ v27.2s, v28.2s, v29.2s }, [x23], x4  // LD3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev4s      | ld3	{ v12.4s, v13.4s, v14.4s }, [x25]  // LD3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev4s_POST | ld3	{ v12.4s, v13.4s, v14.4s }, [x27], #48  // LD3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev4s_POST | ld3	{ v2.4s, v3.4s, v4.4s }, [x22], x21  // LD3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Threev2d      | ld3	{ v10.2d, v11.2d, v12.2d }, [x18]  // LD3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD load, 3 element, multiple, Q-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev2d_POST | ld3	{ v25.2d, v26.2d, v27.2d }, [x4], #48  // LD3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD load, 3 element, multiple, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Threev2d_POST | ld3	{ v6.2d, v7.2d, v8.2d }, [x10], x24  // LD3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, multiple, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3i8            | ld3	{ v17.b, v18.b, v19.b }[2], [x27]  // LD3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3i16           | ld3	{ v18.h, v19.h, v20.h }[5], [x16]  // LD3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3i32           | ld3	{ v1.s, v2.s, v3.s }[3], [x14]  // LD3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3i64           | ld3	{ v5.d, v6.d, v7.d }[1], [x14]  // LD3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 3 element, one lane, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i8_POST       | ld3	{ v16.b, v17.b, v18.b }[3], [x15], #3  // LD3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], #3  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i8_POST       | ld3	{ v14.b, v15.b, v16.b }[4], [x23], x6  // LD3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i16_POST      | ld3	{ v11.h, v12.h, v13.h }[1], [x28], #6  // LD3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], #6  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i16_POST      | ld3	{ v4.h, v5.h, v6.h }[2], [x5], x15  // LD3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i32_POST      | ld3	{ v26.s, v27.s, v28.s }[0], [x14], #12  // LD3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], #12  \\ ASIMD load, 3 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i32_POST      | ld3	{ v1.s, v2.s, v3.s }[0], [x26], x20  // LD3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i64_POST      | ld3	{ v14.d, v15.d, v16.d }[1], [x30], #24  // LD3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], #24  \\ ASIMD load, 3 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3i64_POST      | ld3	{ v23.d, v24.d, v25.d }[0], [x24], x14  // LD3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3B_IMM         | ld3b	{ z29.b - z31.b }, p3/z, [x17]  // LD3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3B_IMM         | ld3b	{ z23.b - z25.b }, p7/z, [x12, #18, mul vl]  // LD3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   3    | 13 | 13  | 0.33   | V1UnitI[6], V1UnitL[6], V1UnitL01[6], V1UnitS[6], V1UnitV[6], V1UnitV01[6] | LD3B   | ld3b	{ z23.b - z25.b }, p3/z, [x12, x12]  // LD3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3D_IMM         | ld3d	{ z20.d - z22.d }, p2/z, [x6]  // LD3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3D_IMM         | ld3d	{ z1.d - z3.d }, p2/z, [x9, #-15, mul vl]  // LD3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   3    | 13 | 13  | 0.33   | V1UnitI[6], V1UnitL[6], V1UnitL01[6], V1UnitS[6], V1UnitV[6], V1UnitV01[6] | LD3D   | ld3d	{ z13.d - z15.d }, p6/z, [x27, x30, lsl #3]  // LD3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3H_IMM         | ld3h	{ z26.h - z28.h }, p1/z, [x29]  // LD3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3H_IMM         | ld3h	{ z14.h - z16.h }, p3/z, [x18, #9, mul vl]  // LD3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   3    | 13 | 13  | 0.33   | V1UnitI[6], V1UnitL[6], V1UnitL01[6], V1UnitS[6], V1UnitV[6], V1UnitV01[6] | LD3H   | ld3h	{ z5.h - z7.h }, p3/z, [x6, x21, lsl #1]  // LD3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv8b          | ld3r	{ v24.8b, v25.8b, v26.8b }, [x10]  // LD3R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv8b_POST     | ld3r	{ v14.8b, v15.8b, v16.8b }, [x11], #3  // LD3R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #3  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv8b_POST     | ld3r	{ v22.8b, v23.8b, v24.8b }, [x0], x11  // LD3R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv16b         | ld3r	{ v17.16b, v18.16b, v19.16b }, [x3]  // LD3R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv16b_POST    | ld3r	{ v7.16b, v8.16b, v9.16b }, [x29], #3  // LD3R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #3  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv16b_POST    | ld3r	{ v3.16b, v4.16b, v5.16b }, [x20], x5  // LD3R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv4h          | ld3r	{ v3.4h, v4.4h, v5.4h }, [x1]  // LD3R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv4h_POST     | ld3r	{ v8.4h, v9.4h, v10.4h }, [x3], #6  // LD3R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #6  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv4h_POST     | ld3r	{ v4.4h, v5.4h, v6.4h }, [x0], x28  // LD3R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv8h          | ld3r	{ v6.8h, v7.8h, v8.8h }, [x28]  // LD3R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv8h_POST     | ld3r	{ v4.8h, v5.8h, v6.8h }, [x11], #6  // LD3R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #6  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv8h_POST     | ld3r	{ v3.8h, v4.8h, v5.8h }, [x17], x0  // LD3R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv2s          | ld3r	{ v18.2s, v19.2s, v20.2s }, [x24]  // LD3R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv2s_POST     | ld3r	{ v8.2s, v9.2s, v10.2s }, [x22], #12  // LD3R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #12  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv2s_POST     | ld3r	{ v12.2s, v13.2s, v14.2s }, [x0], x14  // LD3R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv4s          | ld3r	{ v28.4s, v29.4s, v30.4s }, [x2]  // LD3R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv4s_POST     | ld3r	{ v21.4s, v22.4s, v23.4s }, [x22], #12  // LD3R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #12  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv4s_POST     | ld3r	{ v28.4s, v29.4s, v30.4s }, [x13], x25  // LD3R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv1d          | ld3r	{ v1.1d, v2.1d, v3.1d }, [x28]  // LD3R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, D-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv1d_POST     | ld3r	{ v0.1d, v1.1d, v2.1d }, [x7], #24  // LD3R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv1d_POST     | ld3r	{ v22.1d, v23.1d, v24.1d }, [x9], x15  // LD3R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD3Rv2d          | ld3r	{ v8.2d, v9.2d, v10.2d }, [x3]  // LD3R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD load, 3 element, all lanes, Q-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv2d_POST     | ld3r	{ v3.2d, v4.2d, v5.2d }, [x25], #24  // LD3R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #24  \\ ASIMD load, 3 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD3Rv2d_POST     | ld3r	{ v8.2d, v9.2d, v10.2d }, [x18], x13  // LD3R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 3 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3W_IMM         | ld3w	{ z23.s - z25.s }, p1/z, [x8]  // LD3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | LD3W_IMM         | ld3w	{ z6.s - z8.s }, p4/z, [x0, #18, mul vl]  // LD3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load three structures to three vectors, scalar + imm  \\ 2 11  11  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   3    | 13 | 13  | 0.33   | V1UnitI[6], V1UnitL[6], V1UnitL01[6], V1UnitS[6], V1UnitV[6], V1UnitV01[6] | LD3W   | ld3w	{ z27.s - z29.s }, p3/z, [x3, x6, lsl #2]  // LD3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous Load three structures to three vectors, scalar + scalar  \\ 3 13  13  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitS[6]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Fourv8b       | ld4	{ v6.8b, v7.8b, v8.8b, v9.8b }, [x27]  // LD4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Fourv8b_POST  | ld4	{ v20.8b, v21.8b, v22.8b, v23.8b }, [x10], #32  // LD4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Fourv8b_POST  | ld4	{ v18.8b, v19.8b, v20.8b, v21.8b }, [x24], x11  // LD4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | LD4Fourv16b      | ld4	{ v11.16b, v12.16b, v13.16b, v14.16b }, [x5]  // LD4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv16b_POST | ld4	{ v10.16b, v11.16b, v12.16b, v13.16b }, [x12], #64  // LD4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv16b_POST | ld4	{ v12.16b, v13.16b, v14.16b, v15.16b }, [x4], x17  // LD4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Fourv4h       | ld4	{ v21.4h, v22.4h, v23.4h, v24.4h }, [x14]  // LD4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Fourv4h_POST  | ld4	{ v10.4h, v11.4h, v12.4h, v13.4h }, [x19], #32  // LD4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Fourv4h_POST  | ld4	{ v5.4h, v6.4h, v7.4h, v8.4h }, [x15], x17  // LD4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | LD4Fourv8h       | ld4	{ v9.8h, v10.8h, v11.8h, v12.8h }, [x1]  // LD4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv8h_POST  | ld4	{ v2.8h, v3.8h, v4.8h, v5.8h }, [x0], #64  // LD4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv8h_POST  | ld4	{ v4.8h, v5.8h, v6.8h, v7.8h }, [x17], x17  // LD4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Fourv2s       | ld4	{ v23.2s, v24.2s, v25.2s, v26.2s }, [x24]  // LD4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Fourv2s_POST  | ld4	{ v25.2s, v26.2s, v27.2s, v28.2s }, [x3], #32  // LD4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Fourv2s_POST  | ld4	{ v22.2s, v23.2s, v24.2s, v25.2s }, [x14], x15  // LD4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | LD4Fourv4s       | ld4	{ v17.4s, v18.4s, v19.4s, v20.4s }, [x4]  // LD4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv4s_POST  | ld4	{ v25.4s, v26.4s, v27.4s, v28.4s }, [x19], #64  // LD4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv4s_POST  | ld4	{ v4.4s, v5.4s, v6.4s, v7.4s }, [x28], x3  // LD4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, B/H/S  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | LD4Fourv2d       | ld4	{ v2.2d, v3.2d, v4.2d, v5.2d }, [x24]  // LD4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD load, 4 element, multiple, Q-form, D  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv2d_POST  | ld4	{ v18.2d, v19.2d, v20.2d, v21.2d }, [x0], #64  // LD4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD load, 4 element, multiple, Q-form, D  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   3    | 9  | 9   | 0.50   | V1UnitI, V1UnitL[6], V1UnitV[6]                                  | LD4Fourv2d_POST  | ld4	{ v27.2d, v28.2d, v29.2d, v30.2d }, [x27], x4  // LD4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, multiple, Q-form, D  \\ 3 9  9  0.5 V1UnitL[6],V1UnitV[6],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4i8            | ld4	{ v4.b, v5.b, v6.b, v7.b }[12], [x27]  // LD4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4i16           | ld4	{ v5.h, v6.h, v7.h, v8.h }[0], [x4]  // LD4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, B/H  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4i32           | ld4	{ v0.s, v1.s, v2.s, v3.s }[0], [x26]  // LD4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4i64           | ld4	{ v2.d, v3.d, v4.d, v5.d }[0], [x29]  // LD4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD load, 4 element, one lane, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i8_POST       | ld4	{ v26.b, v27.b, v28.b, v29.b }[4], [x13], #4  // LD4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], #4  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i8_POST       | ld4	{ v10.b, v11.b, v12.b, v13.b }[11], [x24], x21  // LD4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i16_POST      | ld4	{ v8.h, v9.h, v10.h, v11.h }[0], [x17], #8  // LD4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], #8  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i16_POST      | ld4	{ v21.h, v22.h, v23.h, v24.h }[2], [x21], x24  // LD4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, B/H  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i32_POST      | ld4	{ v1.s, v2.s, v3.s, v4.s }[1], [x28], #16  // LD4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], #16  \\ ASIMD load, 4 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i32_POST      | ld4	{ v20.s, v21.s, v22.s, v23.s }[1], [x27], x16  // LD4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i64_POST      | ld4	{ v18.d, v19.d, v20.d, v21.d }[1], [x26], #32  // LD4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], #32  \\ ASIMD load, 4 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4i64_POST      | ld4	{ v8.d, v9.d, v10.d, v11.d }[0], [x23], x0  // LD4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, one lane, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4B_IMM         | ld4b	{ z16.b - z19.b }, p3/z, [x23]  // LD4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4B_IMM         | ld4b	{ z7.b - z10.b }, p5/z, [x3, #12, mul vl]  // LD4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   3    | 13 | 13  | 0.25   | V1UnitI[8], V1UnitL[8], V1UnitL01[8], V1UnitS[8], V1UnitV[8], V1UnitV01[8] | LD4B   | ld4b	{ z7.b - z10.b }, p4/z, [x20, x12]  // LD4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4D_IMM         | ld4d	{ z26.d - z29.d }, p7/z, [x10]  // LD4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4D_IMM         | ld4d	{ z27.d - z30.d }, p0/z, [x6, #24, mul vl]  // LD4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   3    | 13 | 13  | 0.25   | V1UnitI[8], V1UnitL[8], V1UnitL01[8], V1UnitS[8], V1UnitV[8], V1UnitV01[8] | LD4D   | ld4d	{ z7.d - z10.d }, p4/z, [x25, x8, lsl #3]  // LD4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4H_IMM         | ld4h	{ z4.h - z7.h }, p4/z, [x19]   // LD4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4H_IMM         | ld4h	{ z4.h - z7.h }, p1/z, [x16, #-8, mul vl]  // LD4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   3    | 13 | 13  | 0.25   | V1UnitI[8], V1UnitL[8], V1UnitL01[8], V1UnitS[8], V1UnitV[8], V1UnitV01[8] | LD4H   | ld4h	{ z10.h - z13.h }, p2/z, [x8, x28, lsl #1]  // LD4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv8b          | ld4r	{ v20.8b, v21.8b, v22.8b, v23.8b }, [x23]  // LD4R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv8b_POST     | ld4r	{ v24.8b, v25.8b, v26.8b, v27.8b }, [x15], #4  // LD4R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #4  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv8b_POST     | ld4r	{ v4.8b, v5.8b, v6.8b, v7.8b }, [x26], x6  // LD4R { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv16b         | ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x25]  // LD4R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv16b_POST    | ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x14], #4  // LD4R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #4  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv16b_POST    | ld4r	{ v0.16b, v1.16b, v2.16b, v3.16b }, [x29], x11  // LD4R { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv4h          | ld4r	{ v16.4h, v17.4h, v18.4h, v19.4h }, [x6]  // LD4R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv4h_POST     | ld4r	{ v14.4h, v15.4h, v16.4h, v17.4h }, [x0], #8  // LD4R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #8  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv4h_POST     | ld4r	{ v21.4h, v22.4h, v23.4h, v24.4h }, [x25], x22  // LD4R { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv8h          | ld4r	{ v4.8h, v5.8h, v6.8h, v7.8h }, [x23]  // LD4R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv8h_POST     | ld4r	{ v25.8h, v26.8h, v27.8h, v28.8h }, [x7], #8  // LD4R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #8  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv8h_POST     | ld4r	{ v13.8h, v14.8h, v15.8h, v16.8h }, [x19], x27  // LD4R { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv2s          | ld4r	{ v0.2s, v1.2s, v2.2s, v3.2s }, [x30]  // LD4R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv2s_POST     | ld4r	{ v23.2s, v24.2s, v25.2s, v26.2s }, [x29], #16  // LD4R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #16  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv2s_POST     | ld4r	{ v19.2s, v20.2s, v21.2s, v22.2s }, [x9], x0  // LD4R { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv4s          | ld4r	{ v7.4s, v8.4s, v9.4s, v10.4s }, [x23]  // LD4R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv4s_POST     | ld4r	{ v9.4s, v10.4s, v11.4s, v12.4s }, [x3], #16  // LD4R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #16  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv4s_POST     | ld4r	{ v3.4s, v4.4s, v5.4s, v6.4s }, [x10], x22  // LD4R { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, B/H/S  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv1d          | ld4r	{ v7.1d, v8.1d, v9.1d, v10.1d }, [x26]  // LD4R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, D-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv1d_POST     | ld4r	{ v11.1d, v12.1d, v13.1d, v14.1d }, [x5], #32  // LD4R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv1d_POST     | ld4r	{ v12.1d, v13.1d, v14.1d, v15.1d }, [x30], x17  // LD4R { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, D-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 8  | 8   | 1.00   | V1UnitL[3], V1UnitV[3]                                           | LD4Rv2d          | ld4r	{ v7.2d, v8.2d, v9.2d, v10.2d }, [x8]  // LD4R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD load, 4 element, all lanes, Q-form, D  \\ 2 8  8  1.0 V1UnitL[3],V1UnitV[3]
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv2d_POST     | ld4r	{ v12.2d, v13.2d, v14.2d, v15.2d }, [x2], #32  // LD4R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #32  \\ ASIMD load, 4 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   3    | 8  | 8   | 1.00   | V1UnitI, V1UnitL[3], V1UnitV[3]                                  | LD4Rv2d_POST     | ld4r	{ v17.2d, v18.2d, v19.2d, v20.2d }, [x21], x13  // LD4R { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD load, 4 element, all lanes, Q-form, D  \\ 3 8  8  1.0 V1UnitL[3],V1UnitV[3],V1UnitI
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4W_IMM         | ld4w	{ z18.s - z21.s }, p6/z, [x4]  // LD4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   2    | 12 | 12  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | LD4W_IMM         | ld4w	{ z21.s - z24.s }, p5/z, [x16, #-8, mul vl]  // LD4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous Load four structures to four vectors, scalar + imm  \\ 2 12  12  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   3    | 13 | 13  | 0.25   | V1UnitI[8], V1UnitL[8], V1UnitL01[8], V1UnitS[8], V1UnitV[8], V1UnitV01[8] | LD4W   | ld4w	{ z25.s - z28.s }, p2/z, [x23, x8, lsl #2]  // LD4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous Load four structures to four vectors, scalar + scalar  \\ 3 13  13  0.25 V1UnitL01[8],V1UnitV01[8],V1UnitS[8]
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURi          | ldapur	w7, [x24]              // LDAPUR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURi          | ldapur	w25, [x29, #68]        // LDAPUR <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURXi         | ldapur	x20, [x13]             // LDAPUR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURXi         | ldapur	x29, [x4, #-199]       // LDAPUR <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURBi         | ldapurb	w13, [x17]             // LDAPURB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURBi         | ldapurb	w20, [x19, #124]       // LDAPURB <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURHi         | ldapurh	w3, [x22]              // LDAPURH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURHi         | ldapurh	w1, [x6, #113]         // LDAPURH <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSBWi       | ldapursb	w7, [x8]               // LDAPURSB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSBWi       | ldapursb	w29, [x22, #-76]       // LDAPURSB <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSBXi       | ldapursb	x29, [x7]              // LDAPURSB <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSBXi       | ldapursb	x6, [x0, #-254]        // LDAPURSB <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSHWi       | ldapursh	w17, [x19]             // LDAPURSH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSHWi       | ldapursh	w26, [x18, #-114]      // LDAPURSH <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSHXi       | ldapursh	x3, [x3]               // LDAPURSH <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSHXi       | ldapursh	x13, [x25, #30]        // LDAPURSH <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSWi        | ldapursw	x3, [x18]              // LDAPURSW <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | LDAPURSWi        | ldapursw	x21, [x25]             // LDAPURSW <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARW            | ldar	w9, [x20]                      // LDAR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARW            | ldar	w15, [x0]                      // LDAR <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARX            | ldar	x5, [x25]                      // LDAR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARX            | ldar	x11, [x2]                      // LDAR <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARB            | ldarb	w16, [x21]                     // LDARB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARB            | ldarb	w14, [x30]                     // LDARB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARH            | ldarh	w26, [x25]                     // LDARH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDARH            | ldarh	w21, [x2]                      // LDARH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDAXPW           | ldaxp	w13, w22, [x28]                // LDAXP <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDAXPW           | ldaxp	w11, w19, [x20]                // LDAXP <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDAXPX           | ldaxp	x25, x8, [x16]                 // LDAXP <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDAXPX           | ldaxp	x28, x17, [x25]                // LDAXP <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRW           | ldaxr	w4, [x5]                       // LDAXR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRW           | ldaxr	w10, [x7]                      // LDAXR <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRX           | ldaxr	x22, [x21]                     // LDAXR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRX           | ldaxr	x7, [x1]                       // LDAXR <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRB           | ldaxrb	w12, [x30]             // LDAXRB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRB           | ldaxrb	w27, [x2]              // LDAXRB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRH           | ldaxrh	w30, [x16]             // LDAXRH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDAXRH           | ldaxrh	w14, [x3]              // LDAXRH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B           | ldff1b	{ z10.b }, p3/z, [x10]  // LDFF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B           | ldff1b	{ z2.b }, p5/z, [x28, x2]  // LDFF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B_H         | ldff1b	{ z2.h }, p0/z, [x14]  // LDFF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B_H         | ldff1b	{ z30.h }, p3/z, [x25, x18]  // LDFF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B_S         | ldff1b	{ z17.s }, p5/z, [x24]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B_S         | ldff1b	{ z17.s }, p7/z, [x11, x15]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B_D         | ldff1b	{ z9.d }, p2/z, [x3]   // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1B_D         | ldff1b	{ z5.d }, p2/z, [x6, x8]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1B_D_SXTW   | ldff1b	{ z7.d }, p3/z, [x27, z19.d, sxtw]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1B_S_SXTW   | ldff1b	{ z13.s }, p3/z, [x24, z25.s, sxtw]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1B_D        | ldff1b	{ z27.d }, p0/z, [x13, z16.d]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1B_S_IMM    | ldff1b	{ z7.s }, p7/z, [z16.s]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1B_S_IMM    | ldff1b	{ z11.s }, p5/z, [z8.s, #25]  // LDFF1B { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1B_D_IMM    | ldff1b	{ z2.d }, p7/z, [z19.d]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1B_D_IMM    | ldff1b	{ z3.d }, p5/z, [z0.d, #11]  // LDFF1B { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1D           | ldff1d	{ z21.d }, p2/z, [x20]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1D           | ldff1d	{ z9.d }, p3/z, [x28, x30, lsl #3]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1D_SXTW_SCALED | ldff1d	{ z21.d }, p4/z, [x11, z12.d, sxtw #3]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1D_UXTW     | ldff1d	{ z6.d }, p4/z, [x15, z1.d, uxtw]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1D_SCALED   | ldff1d	{ z12.d }, p7/z, [x11, z28.d, lsl #3]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #3]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1D          | ldff1d	{ z26.d }, p4/z, [x30, z5.d]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1D_IMM      | ldff1d	{ z10.d }, p5/z, [z10.d]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1D_IMM      | ldff1d	{ z21.d }, p6/z, [z3.d, #48]  // LDFF1D { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1H           | ldff1h	{ z14.h }, p3/z, [x22]  // LDFF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1H           | ldff1h	{ z15.h }, p2/z, [x24, x8, lsl #1]  // LDFF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1H_S         | ldff1h	{ z23.s }, p0/z, [x12]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1H_S         | ldff1h	{ z18.s }, p0/z, [x7, x25, lsl #1]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1H_D         | ldff1h	{ z16.d }, p0/z, [x11]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1H_D         | ldff1h	{ z25.d }, p3/z, [x24, x19, lsl #1]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1H_S_SXTW_SCALED | ldff1h	{ z9.s }, p2/z, [x3, z24.s, sxtw #1]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1H_D_UXTW_SCALED | ldff1h	{ z7.d }, p0/z, [x8, z17.d, uxtw #1]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1H_D_SXTW   | ldff1h	{ z9.d }, p5/z, [x4, z10.d, sxtw]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1H_S_UXTW   | ldff1h	{ z4.s }, p4/z, [x6, z27.s, uxtw]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1H_D_SCALED | ldff1h	{ z25.d }, p1/z, [x29, z6.d, lsl #1]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1H_D        | ldff1h	{ z10.d }, p7/z, [x1, z26.d]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1H_S_IMM    | ldff1h	{ z4.s }, p1/z, [z27.s]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1H_S_IMM    | ldff1h	{ z5.s }, p3/z, [z8.s, #62]  // LDFF1H { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1H_D_IMM    | ldff1h	{ z16.d }, p5/z, [z10.d]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1H_D_IMM    | ldff1h	{ z15.d }, p2/z, [z19.d, #34]  // LDFF1H { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SB_H        | ldff1sb	{ z0.h }, p2/z, [x2]   // LDFF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SB_H        | ldff1sb	{ z29.h }, p1/z, [x16, x21]  // LDFF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SB_S        | ldff1sb	{ z20.s }, p7/z, [x8]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SB_S        | ldff1sb	{ z8.s }, p2/z, [x4, x14]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SB_D        | ldff1sb	{ z11.d }, p4/z, [x6]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SB_D        | ldff1sb	{ z17.d }, p4/z, [x16, x10]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SB_D_SXTW  | ldff1sb	{ z13.d }, p2/z, [x28, z8.d, sxtw]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SB_S_SXTW  | ldff1sb	{ z3.s }, p2/z, [x26, z24.s, sxtw]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SB_D       | ldff1sb	{ z10.d }, p7/z, [x20, z6.d]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SB_S_IMM   | ldff1sb	{ z18.s }, p3/z, [z9.s]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SB_S_IMM   | ldff1sb	{ z25.s }, p2/z, [z29.s, #25]  // LDFF1SB { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SB_D_IMM   | ldff1sb	{ z8.d }, p0/z, [z24.d]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SB_D_IMM   | ldff1sb	{ z7.d }, p0/z, [z4.d, #9]  // LDFF1SB { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SH_S        | ldff1sh	{ z2.s }, p2/z, [x6]   // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SH_S        | ldff1sh	{ z9.s }, p3/z, [x30, x16, lsl #1]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SH_D        | ldff1sh	{ z7.d }, p4/z, [x30]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SH_D        | ldff1sh	{ z1.d }, p0/z, [x29, x0, lsl #1]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous first faulting load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SH_S_SXTW_SCALED | ldff1sh	{ z25.s }, p4/z, [x5, z9.s, sxtw #1]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SH_D_SXTW_SCALED | ldff1sh	{ z17.d }, p3/z, [x0, z25.d, sxtw #1]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SH_D_SXTW  | ldff1sh	{ z12.d }, p7/z, [x5, z15.d, sxtw]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SH_S_UXTW  | ldff1sh	{ z8.s }, p5/z, [x3, z21.s, uxtw]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SH_D_SCALED | ldff1sh	{ z14.d }, p6/z, [x17, z27.d, lsl #1]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SH_D       | ldff1sh	{ z23.d }, p4/z, [x22, z0.d]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SH_S_IMM   | ldff1sh	{ z6.s }, p4/z, [z6.s]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SH_S_IMM   | ldff1sh	{ z3.s }, p7/z, [z26.s, #16]  // LDFF1SH { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SH_D_IMM   | ldff1sh	{ z25.d }, p3/z, [z17.d]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SH_D_IMM   | ldff1sh	{ z2.d }, p3/z, [z31.d, #26]  // LDFF1SH { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SW_D        | ldff1sw	{ z16.d }, p2/z, [x8]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1SW_D        | ldff1sw	{ z27.d }, p1/z, [x6, x11, lsl #2]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SW_D_UXTW_SCALED | ldff1sw	{ z27.d }, p3/z, [x5, z20.d, uxtw #2]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SW_D_SXTW  | ldff1sw	{ z15.d }, p1/z, [x13, z26.d, sxtw]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1SW_D_SCALED | ldff1sw	{ z24.d }, p2/z, [x7, z23.d, lsl #2]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SW_D       | ldff1sw	{ z8.d }, p3/z, [x5, z22.d]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SW_D_IMM   | ldff1sw	{ z16.d }, p6/z, [z12.d]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1SW_D_IMM   | ldff1sw	{ z3.d }, p1/z, [z13.d, #60]  // LDFF1SW { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1W           | ldff1w	{ z2.s }, p5/z, [x13]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1W           | ldff1w	{ z9.s }, p3/z, [x16, x19, lsl #2]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1W_D         | ldff1w	{ z31.d }, p6/z, [x3]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDFF1W_D         | ldff1w	{ z30.d }, p4/z, [x25, x12, lsl #2]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous first faulting load, scalar + scalar   \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1W_UXTW_SCALED | ldff1w	{ z27.s }, p6/z, [x10, z17.s, uxtw #2]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1W_D_SXTW_SCALED | ldff1w	{ z8.d }, p4/z, [x28, z31.d, sxtw #2]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1W_D_UXTW   | ldff1w	{ z1.d }, p0/z, [x23, z14.d, uxtw]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1W_UXTW     | ldff1w	{ z17.s }, p5/z, [x8, z6.s, uxtw]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Zm>.S, <mod>]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1W_D_SCALED | ldff1w	{ z19.d }, p3/z, [x7, z18.d, lsl #2]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Gather load, 32-bit scaled offset  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1W_D        | ldff1w	{ z23.d }, p2/z, [x16, z4.d]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Zm>.D]  \\ Gather load, 32-bit unpacked unscaled offset  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1W_IMM      | ldff1w	{ z24.s }, p6/z, [z24.s]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Zn>.S]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 11 | 11  | 0.25   | V1UnitL[12], V1UnitV[12]                                         | GLDFF1W_IMM      | ldff1w	{ z20.s }, p0/z, [z6.s, #36]  // LDFF1W { <Zt>.S }, <Pg>/Z, [<Zn>.S, #<imm>]  \\ Gather load, vector + imm, 32-bit element size  \\ 2 11  11  0.25 V1UnitL[12],V1UnitV[12]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1W_D_IMM    | ldff1w	{ z21.d }, p5/z, [z12.d]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Zn>.D]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   2    | 9  | 9   | 0.50   | V1UnitL[6], V1UnitV[6]                                           | GLDFF1W_D_IMM    | ldff1w	{ z29.d }, p2/z, [z11.d, #40]  // LDFF1W { <Zt>.D }, <Pg>/Z, [<Zn>.D, #<imm>]  \\ Gather load, vector + imm, 64-bit element size  \\ 2 9  9  0.5 V1UnitL[6],V1UnitV[6]
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_IMM       | ldnf1b	{ z17.b }, p5/z, [x20]  // LDNF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_IMM       | ldnf1b	{ z8.b }, p5/z, [x26, #1, mul vl]  // LDNF1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_H_IMM     | ldnf1b	{ z4.h }, p3/z, [x25]  // LDNF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_H_IMM     | ldnf1b	{ z31.h }, p3/z, [x7]  // LDNF1B { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_S_IMM     | ldnf1b	{ z2.s }, p7/z, [x25]  // LDNF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_S_IMM     | ldnf1b	{ z17.s }, p5/z, [x29, #2, mul vl]  // LDNF1B { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_D_IMM     | ldnf1b	{ z6.d }, p5/z, [x26]  // LDNF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1B_D_IMM     | ldnf1b	{ z18.d }, p4/z, [x20, #5, mul vl]  // LDNF1B { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1D_IMM       | ldnf1d	{ z5.d }, p6/z, [x6]   // LDNF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1D_IMM       | ldnf1d	{ z19.d }, p0/z, [x15, #-1, mul vl]  // LDNF1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1H_IMM       | ldnf1h	{ z7.h }, p5/z, [x22]  // LDNF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1H_IMM       | ldnf1h	{ z27.h }, p1/z, [x2, #6, mul vl]  // LDNF1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1H_S_IMM     | ldnf1h	{ z18.s }, p2/z, [x13]  // LDNF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1H_S_IMM     | ldnf1h	{ z8.s }, p2/z, [x29, #-8, mul vl]  // LDNF1H { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1H_D_IMM     | ldnf1h	{ z26.d }, p5/z, [x5]  // LDNF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1H_D_IMM     | ldnf1h	{ z20.d }, p0/z, [x29, #-6, mul vl]  // LDNF1H { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SB_H_IMM    | ldnf1sb	{ z17.h }, p0/z, [x23]  // LDNF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SB_H_IMM    | ldnf1sb	{ z14.h }, p0/z, [x18, #-5, mul vl]  // LDNF1SB { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SB_S_IMM    | ldnf1sb	{ z23.s }, p0/z, [x3]  // LDNF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SB_S_IMM    | ldnf1sb	{ z13.s }, p7/z, [x15, #-8, mul vl]  // LDNF1SB { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SB_D_IMM    | ldnf1sb	{ z14.d }, p4/z, [x7]  // LDNF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SB_D_IMM    | ldnf1sb	{ z13.d }, p7/z, [x25, #6, mul vl]  // LDNF1SB { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SH_S_IMM    | ldnf1sh	{ z28.s }, p4/z, [x9]  // LDNF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SH_S_IMM    | ldnf1sh	{ z3.s }, p1/z, [x14, #-2, mul vl]  // LDNF1SH { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SH_D_IMM    | ldnf1sh	{ z1.d }, p2/z, [x0]   // LDNF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SH_D_IMM    | ldnf1sh	{ z14.d }, p3/z, [x8, #3, mul vl]  // LDNF1SH { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SW_D_IMM    | ldnf1sw	{ z8.d }, p4/z, [x9]   // LDNF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1SW_D_IMM    | ldnf1sw	{ z28.d }, p4/z, [x13, #-7, mul vl]  // LDNF1SW { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1W_IMM       | ldnf1w	{ z15.s }, p5/z, [x27]  // LDNF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1W_IMM       | ldnf1w	{ z28.s }, p0/z, [x28, #-1, mul vl]  // LDNF1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1W_D_IMM     | ldnf1w	{ z28.d }, p5/z, [x13]  // LDNF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNF1W_D_IMM     | ldnf1w	{ z4.d }, p0/z, [x12, #2, mul vl]  // LDNF1W { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous non faulting load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDNPSi           | ldnp	s1, s13, [x4]                  // LDNP <St1>, <St2>, [<Xn|SP>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDNPSi           | ldnp	s30, s5, [x11, #-184]          // LDNP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDNPDi           | ldnp	d3, d12, [x21]                 // LDNP <Dt1>, <Dt2>, [<Xn|SP>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDNPDi           | ldnp	d12, d5, [x7, #-424]           // LDNP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LDNPQi           | ldnp	q0, q14, [x24]                 // LDNP <Qt1>, <Qt2>, [<Xn|SP>]  \\ Load vector pair, immed offset, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LDNPQi           | ldnp	q4, q1, [x27, #80]             // LDNP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Load vector pair, immed offset, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDNPWi           | ldnp	w4, w20, [x25]                 // LDNP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDNPWi           | ldnp	w30, w4, [x21, #-196]          // LDNP <Wt1>, <Wt2>, [<Xn|SP>, #<imm32>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitL[3]                                                       | LDNPXi           | ldnp	x7, x30, [x18]                 // LDNP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitL[3]                                                       | LDNPXi           | ldnp	x5, x19, [x1, #-240]           // LDNP <Xt1>, <Xt2>, [<Xn|SP>, #<imm64>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1B_ZRI       | ldnt1b	{ z9.b }, p2/z, [x21]  // LDNT1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1B_ZRI       | ldnt1b	{ z30.b }, p5/z, [x30, #-3, mul vl]  // LDNT1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDNT1B_ZRR       | ldnt1b	{ z10.b }, p5/z, [x12, x17]  // LDNT1B { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]  \\ Non temporal load, scalar + scalar  \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1D_ZRI       | ldnt1d	{ z27.d }, p2/z, [x12]  // LDNT1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1D_ZRI       | ldnt1d	{ z5.d }, p7/z, [x22, #6, mul vl]  // LDNT1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDNT1D_ZRR       | ldnt1d	{ z28.d }, p2/z, [x14, x0, lsl #3]  // LDNT1D { <Zt>.D }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #3]  \\ Non temporal load, scalar + scalar  \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1H_ZRI       | ldnt1h	{ z11.h }, p0/z, [x21]  // LDNT1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1H_ZRI       | ldnt1h	{ z19.h }, p1/z, [x24, #-5, mul vl]  // LDNT1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 7  | 7   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDNT1H_ZRR       | ldnt1h	{ z27.h }, p0/z, [x22, x24, lsl #1]  // LDNT1H { <Zt>.H }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #1]  \\ Non temporal load, scalar + scalar  \\ 2 7  7  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1W_ZRI       | ldnt1w	{ z27.s }, p4/z, [x19]  // LDNT1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDNT1W_ZRI       | ldnt1w	{ z15.s }, p0/z, [x22, #3, mul vl]  // LDNT1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal load, scalar + imm  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS                             | LDNT1W_ZRR       | ldnt1w	{ z25.s }, p4/z, [x12, x21, lsl #2]  // LDNT1W { <Zt>.S }, <Pg>/Z, [<Xn|SP>, <Xm>, LSL #2]  \\ Non temporal load, scalar + scalar  \\ 2 6  6  2.0 V1UnitL01,V1UnitS
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDPSpost         | ldp	s19, s15, [x24], #-64          // LDP <St1>, <St2>, [<Xn|SP>], #<imm32>  \\ Load vector pair, immed post-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDPDpost         | ldp	d9, d1, [x20], #296            // LDP <Dt1>, <Dt2>, [<Xn|SP>], #<imm64>  \\ Load vector pair, immed post-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LDPQpost         | ldp	q18, q24, [x11], #144          // LDP <Qt1>, <Qt2>, [<Xn|SP>], #<imm128>  \\ Load vector pair, immed post-index, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDPSpre          | ldp	s10, s30, [x0, #-4]!           // LDP <St1>, <St2>, [<Xn|SP>, #<imm32>]!  \\ Load vector pair, immed pre-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDPDpre          | ldp	d26, d11, [x16, #-304]!        // LDP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]!  \\ Load vector pair, immed pre-index, S/D-form  \\ 2 6  6  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 1.50   | V1UnitI, V1UnitL[2]                                              | LDPQpre          | ldp	q18, q12, [x25, #960]!         // LDP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]!  \\ Load vector pair, immed pre-index, Q-form  \\ 2 6  6  1.5 V1UnitL[2],V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDPSi            | ldp	s12, s31, [x20, #-192]         // LDP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDPDi            | ldp	d26, d6, [x22, #-144]          // LDP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Load vector pair, immed offset, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 1.50   | V1UnitL[2]                                                       | LDPQi            | ldp	q5, q19, [x9, #-448]           // LDP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Load vector pair, immed offset, Q-form  \\ 1 6  6  1.5 V1UnitL[2]
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDPWpost         | ldp	w10, w18, [x16], #-96          // LDP <Wt1>, <Wt2>, [<Xn|SP>], #<imm32>  \\ Load pair, immed post-index or immed pre-index, normal, W-form  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[3]                                              | LDPXpost         | ldp	x13, x16, [x11], #288          // LDP <Xt1>, <Xt2>, [<Xn|SP>], #<imm64>  \\ Load pair, immed post-index or immed pre-index, normal, X-form  \\ 2 4  4  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDPWpre          | ldp	w7, w16, [x13, #-116]!         // LDP <Wt1>, <Wt2>, [<Xn|SP>, #<imm32>]!  \\ Load pair, immed post-index or immed pre-index, normal, W-form  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[3]                                              | LDPXpre          | ldp	x26, x3, [x14, #16]!           // LDP <Xt1>, <Xt2>, [<Xn|SP>, #<imm64>]!  \\ Load pair, immed post-index or immed pre-index, normal, X-form  \\ 2 4  4  1.0 V1UnitL[3],V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDPWi            | ldp	w25, w23, [x22]                // LDP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDPWi            | ldp	w3, w21, [x17, #40]            // LDP <Wt1>, <Wt2>, [<Xn|SP>, #<imm32>]  \\ Load pair, signed immed offset, normal, W-form  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitL[3]                                                       | LDPXi            | ldp	x6, x25, [x17]                 // LDP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitL[3]                                                       | LDPXi            | ldp	x9, x21, [x3, #104]            // LDP <Xt1>, <Xt2>, [<Xn|SP>, #<imm64>]  \\ Load pair, signed immed offset, normal, X-form  \\ 1 4  4  1.0 V1UnitL[3]
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitL[3]                                              | LDPSWpost        | ldpsw	x23, x26, [x30], #-160         // LDPSW <Xt1>, <Xt2>, [<Xn|SP>], #<imm>  \\ Load pair, immed post-index or immed pre-index, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitL[3]                                              | LDPSWpre         | ldpsw	x19, x28, [x21, #-248]!        // LDPSW <Xt1>, <Xt2>, [<Xn|SP>, #<imm>]!  \\ Load pair, immed post-index or immed pre-index, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitL[3]                                              | LDPSWi           | ldpsw	x13, x20, [x15]                // LDPSW <Xt1>, <Xt2>, [<Xn|SP>]  \\ Load pair, signed immed offset, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitL[3]                                              | LDPSWi           | ldpsw	x9, x27, [x8, #80]             // LDPSW <Xt1>, <Xt2>, [<Xn|SP>, #<imm>]  \\ Load pair, signed immed offset, signed words  \\ 2 5  5  1.0 V1UnitI,V1UnitL[3]
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRWpost         | ldr	w13, [x2], #-22                // LDR <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRXpost         | ldr	x6, [x9], #248                 // LDR <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRWpre          | ldr	w20, [x10, #13]!               // LDR <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRXpre          | ldr	x23, [x20, #-24]!              // LDR <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWui           | ldr	w19, [x15, #11620]             // LDR <Wt>, [<Xn|SP>, #<pimm32>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXui           | ldr	x2, [x13, #18528]              // LDR <Xt>, [<Xn|SP>, #<pimm64>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRBpost         | ldr	b0, [x15], #-18                // LDR <Bt>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHpost         | ldr	h25, [x4], #-156               // LDR <Ht>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSpost         | ldr	s28, [x6], #162                // LDR <St>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRDpost         | ldr	d23, [x8], #-176               // LDR <Dt>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRQpost         | ldr	q5, [x18], #70                 // LDR <Qt>, [<Xn|SP>], #<simm>  \\ Load vector reg, immed post-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRBpre          | ldr	b9, [x0, #-104]!               // LDR <Bt>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHpre          | ldr	h24, [x10, #34]!               // LDR <Ht>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSpre          | ldr	s29, [x5, #168]!               // LDR <St>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRDpre          | ldr	d22, [x9, #-1]!                // LDR <Dt>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 3.00   | V1UnitI, V1UnitL                                                 | LDRQpre          | ldr	q27, [x20, #-204]!             // LDR <Qt>, [<Xn|SP>, #<simm>]!  \\ Load vector reg, immed pre-index  \\ 2 6  6  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRBui           | ldr	b23, [x0, #349]                // LDR <Bt>, [<Xn|SP>, #<pimmb>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRHui           | ldr	h1, [x15, #3540]               // LDR <Ht>, [<Xn|SP>, #<pimmh>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSui           | ldr	s14, [x7, #16208]              // LDR <St>, [<Xn|SP>, #<pimms>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDui           | ldr	d4, [x17, #7368]               // LDR <Dt>, [<Xn|SP>, #<pimmd>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRQui           | ldr	q14, [x6, #4624]               // LDR <Qt>, [<Xn|SP>, #<pimmq>]  \\ Load vector reg, unsigned immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWl            | ldr	w15, test                      // LDR <Wt>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXl            | ldr	x26, test                      // LDR <Xt>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSl            | ldr	s17, test                      // LDR <St>, <label>  \\ Load vector reg, literal, S/D/Q forms  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDl            | ldr	d10, test                      // LDR <Dt>, <label>  \\ Load vector reg, literal, S/D/Q forms  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRQl            | ldr	q22, test                      // LDR <Qt>, <label>  \\ Load vector reg, literal, S/D/Q forms  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitM                                        | LDR_PXI          | ldr	p0, [x28]                      // LDR <Pt>, [<Xn|SP>]  \\ Load predicate  \\ 2 6  6  2.0 V1UnitL,V1UnitM
+# CHECK-NEXT:   2    | 6  | 6   | 2.00   | V1UnitI, V1UnitL, V1UnitM                                        | LDR_PXI          | ldr	p1, [x6, #-53, mul vl]         // LDR <Pt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Load predicate  \\ 2 6  6  2.0 V1UnitL,V1UnitM
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroX          | ldr	w30, [x10, x0]                 // LDR <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroX          | ldr	x13, [x4, x21]                 // LDR <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroW          | ldr	w25, [x18, w26, uxtw]          // LDR <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroW          | ldr	x20, [x29, w26, uxtw]          // LDR <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroW          | ldr	w26, [x12, w0, uxtw #2]        // LDR <Wt>, [<Xn|SP>, <Wm>, UXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroW          | ldr	x13, [x2, w10, uxtw #3]        // LDR <Xt>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroW          | ldr	w13, [x18, w19, sxtw]          // LDR <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroW          | ldr	x5, [x26, w12, sxtw]           // LDR <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroW          | ldr	w16, [x9, w24, sxtw #2]        // LDR <Wt>, [<Xn|SP>, <Wm>, SXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroW          | ldr	x21, [x29, w4, sxtw #3]        // LDR <Xt>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroX          | ldr	w19, [x15, x1, sxtx]           // LDR <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroX          | ldr	x25, [x4, x20, sxtx]           // LDR <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroX          | ldr	w3, [x1, x17, sxtx #2]         // LDR <Wt>, [<Xn|SP>, <Xm>, SXTX #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroX          | ldr	x2, [x13, x26, sxtx #3]        // LDR <Xt>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRWroX          | ldr	w1, [x18, x17, lsl #2]         // LDR <Wt>, [<Xn|SP>, <Xm>, LSL #2]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRXroX          | ldr	x22, [x17, x3, lsl #3]         // LDR <Xt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRBroX          | ldr	b8, [x30, x10]                 // LDR <Bt>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRBroW          | ldr	b25, [x21, w8, uxtw]           // LDR <Bt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRBroW          | ldr	b7, [x9, w29, sxtw]            // LDR <Bt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRBroX          | ldr	b31, [x17, x6, sxtx]           // LDR <Bt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRHroX          | ldr	h11, [x13, x9]                 // LDR <Ht>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRHroW          | ldr	h6, [x4, w4, uxtw]             // LDR <Ht>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRHroW          | ldr	h28, [x3, w28, sxtw]           // LDR <Ht>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRHroX          | ldr	h3, [x15, x19, sxtx]           // LDR <Ht>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHroW          | ldr	h24, [x27, w5, uxtw #1]        // LDR <Ht>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHroW          | ldr	h22, [x28, w11, sxtw #1]       // LDR <Ht>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHroX          | ldr	h3, [x18, x26, sxtx #1]        // LDR <Ht>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHroX          | ldr	h8, [x23, x19, lsl #1]         // LDR <Ht>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load vector reg, register offset, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroX          | ldr	s21, [x1, x29]                 // LDR <St>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroW          | ldr	s12, [x30, w5, uxtw]           // LDR <St>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroW          | ldr	s15, [x2, w20, sxtw]           // LDR <St>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroX          | ldr	s11, [x25, x20, sxtx]          // LDR <St>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroW          | ldr	s9, [x24, w27, uxtw #2]        // LDR <St>, [<Xn|SP>, <Wm>, UXTW #2]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroW          | ldr	s7, [x2, w5, sxtw #2]          // LDR <St>, [<Xn|SP>, <Wm>, SXTW #2]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroX          | ldr	s13, [x19, x28, sxtx #2]       // LDR <St>, [<Xn|SP>, <Xm>, SXTX #2]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRSroX          | ldr	s21, [x10, x4, lsl #2]         // LDR <St>, [<Xn|SP>, <Xm>, LSL #2]  \\ Load vector reg, register offset, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroX          | ldr	d10, [x23, x10]                // LDR <Dt>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroW          | ldr	d24, [x26, w7, uxtw]           // LDR <Dt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroW          | ldr	d28, [x12, w2, sxtw]           // LDR <Dt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroX          | ldr	d0, [x7, x29, sxtx]            // LDR <Dt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroW          | ldr	d24, [x9, w27, uxtw #3]        // LDR <Dt>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroW          | ldr	d5, [x17, w2, sxtw #3]         // LDR <Dt>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroX          | ldr	d2, [x5, x16, sxtx #3]         // LDR <Dt>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load vector reg, register offset, extend, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRDroX          | ldr	d2, [x29, x18, lsl #3]         // LDR <Dt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load vector reg, register offset, scale, S/D-form  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRQroX          | ldr	q9, [x13, x16]                 // LDR <Qt>, [<Xn|SP>, <Xm>]  \\ Load vector reg, register offset, basic  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRQroW          | ldr	q16, [x16, w1, uxtw]           // LDR <Qt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRQroW          | ldr	q1, [x17, w5, sxtw]            // LDR <Qt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDRQroX          | ldr	q1, [x8, x9, sxtx]             // LDR <Qt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load vector reg, register offset, extend  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRQroW          | ldr	q23, [x26, w23, uxtw #4]       // LDR <Qt>, [<Xn|SP>, <Wm>, UXTW #4]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRQroW          | ldr	q3, [x18, w23, sxtw #4]        // LDR <Qt>, [<Xn|SP>, <Wm>, SXTW #4]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRQroX          | ldr	q2, [x28, x30, sxtx #4]        // LDR <Qt>, [<Xn|SP>, <Xm>, SXTX #4]  \\ Load vector reg, register offset, extend, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 7  | 7   | 3.00   | V1UnitI, V1UnitL                                                 | LDRQroX          | ldr	q21, [x23, x27, lsl #4]        // LDR <Qt>, [<Xn|SP>, <Xm>, LSL #4]  \\ Load vector reg, register offset, scale, H/Q-form  \\ 2 7  7  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDR_ZXI          | ldr	z26, [x4]                      // LDR <Zt>, [<Xn|SP>]  \\ Load vector  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 6  | 6   | 2.00   | V1UnitL, V1UnitL01                                               | LDR_ZXI          | ldr	z18, [x27, #16, mul vl]        // LDR <Zt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Load vector  \\ 1 6  6  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRBBpost        | ldrb	w4, [x17], #0                  // LDRB <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRBBpre         | ldrb	w27, [x23, #114]!              // LDRB <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRBBui          | ldrb	w26, [x19]                     // LDRB <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRBBui          | ldrb	w29, [x18, #3179]              // LDRB <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRBBroX         | ldrb	w16, [x25, x9]                 // LDRB <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRBBroW         | ldrb	w9, [x15, w19, uxtw]           // LDRB <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRBBroW         | ldrb	w25, [x7, w0, sxtw]            // LDRB <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRBBroX         | ldrb	w0, [x18, x21, sxtx]           // LDRB <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHHpost        | ldrh	w9, [x1], #-2                  // LDRH <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHHpre         | ldrh	w12, [x29, #-41]!              // LDRH <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRHHui          | ldrh	w28, [x3]                      // LDRH <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRHHui          | ldrh	w27, [x19, #3156]              // LDRH <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRHHroX         | ldrh	w20, [x25, x15]                // LDRH <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRHHroW         | ldrh	w22, [x0, w24, uxtw]           // LDRH <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRHHroW         | ldrh	w6, [x17, w18, sxtw]           // LDRH <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRHHroX         | ldrh	w21, [x13, x30, sxtx]          // LDRH <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHHroW         | ldrh	w14, [x21, w21, uxtw #1]       // LDRH <Wt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHHroW         | ldrh	w0, [x29, w13, sxtw #1]        // LDRH <Wt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHHroX         | ldrh	w11, [x20, x0, sxtx #1]        // LDRH <Wt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRHHroX         | ldrh	w12, [x17, x27, lsl #1]        // LDRH <Wt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load register, register offset, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSBWpost       | ldrsb	w12, [x13], #-250              // LDRSB <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSBXpost       | ldrsb	x10, [x2], #-229               // LDRSB <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSBWpre        | ldrsb	w5, [x2, #-169]!               // LDRSB <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSBXpre        | ldrsb	x28, [x12, #-46]!              // LDRSB <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBWui         | ldrsb	w5, [x26]                      // LDRSB <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBWui         | ldrsb	w24, [x0, #3862]               // LDRSB <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBXui         | ldrsb	x6, [x0]                       // LDRSB <Xt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBXui         | ldrsb	x20, [x0, #653]                // LDRSB <Xt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBWroX        | ldrsb	w30, [x22, x21]                // LDRSB <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBWroW        | ldrsb	w24, [x2, w14, uxtw]           // LDRSB <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBWroW        | ldrsb	w7, [x1, w8, sxtw]             // LDRSB <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBWroX        | ldrsb	w4, [x8, x25, sxtx]            // LDRSB <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBXroX        | ldrsb	x12, [x28, x27]                // LDRSB <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBXroW        | ldrsb	x10, [x5, w9, uxtw]            // LDRSB <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBXroW        | ldrsb	x19, [x23, w24, sxtw]          // LDRSB <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSBXroX        | ldrsb	x20, [x10, x13, sxtx]          // LDRSB <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHWpost       | ldrsh	w5, [x0], #-115                // LDRSH <Wt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHXpost       | ldrsh	x30, [x18], #-50               // LDRSH <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHWpre        | ldrsh	w27, [x15, #-45]!              // LDRSH <Wt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHXpre        | ldrsh	x14, [x24, #27]!               // LDRSH <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHWui         | ldrsh	w18, [x13]                     // LDRSH <Wt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHWui         | ldrsh	w11, [x27, #4094]              // LDRSH <Wt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHXui         | ldrsh	x19, [x26]                     // LDRSH <Xt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHXui         | ldrsh	x19, [x9, #6652]               // LDRSH <Xt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHWroX        | ldrsh	w18, [x30, x24]                // LDRSH <Wt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHWroW        | ldrsh	w13, [x25, w7, uxtw]           // LDRSH <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHWroW        | ldrsh	w3, [x16, w28, sxtw]           // LDRSH <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHWroX        | ldrsh	w0, [x13, x14, sxtx]           // LDRSH <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHWroW        | ldrsh	w0, [x5, w21, uxtw #1]         // LDRSH <Wt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHWroW        | ldrsh	w26, [x6, w29, sxtw #1]        // LDRSH <Wt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHWroX        | ldrsh	w22, [x26, x15, sxtx #1]       // LDRSH <Wt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHWroX        | ldrsh	w26, [x20, x21, lsl #1]        // LDRSH <Wt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load register, register offset, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHXroX        | ldrsh	x4, [x9, x24]                  // LDRSH <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHXroW        | ldrsh	x25, [x8, w13, uxtw]           // LDRSH <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHXroW        | ldrsh	x25, [x20, w10, sxtw]          // LDRSH <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSHXroX        | ldrsh	x6, [x13, x10, sxtx]           // LDRSH <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHXroW        | ldrsh	x15, [x0, w28, uxtw #1]        // LDRSH <Xt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHXroW        | ldrsh	x19, [x9, w15, sxtw #1]        // LDRSH <Xt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHXroX        | ldrsh	x1, [x17, x26, sxtx #1]        // LDRSH <Xt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Load register, register offset, extend, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 5  | 5   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSHXroX        | ldrsh	x7, [x29, x17, lsl #1]         // LDRSH <Xt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Load register, register offset, scale by 2  \\ 2 5  5  3.0 V1UnitI,V1UnitL
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSWpost        | ldrsw	x4, [x21], #-93                // LDRSW <Xt>, [<Xn|SP>], #<simm>  \\ Load register, immed post-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 3.00   | V1UnitI, V1UnitL                                                 | LDRSWpre         | ldrsw	x6, [x28, #96]!                // LDRSW <Xt>, [<Xn|SP>, #<simm>]!  \\ Load register, immed pre-index  \\ 2 4  4  3.0 V1UnitL,V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWui          | ldrsw	x1, [x23]                      // LDRSW <Xt>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWui          | ldrsw	x6, [x19, #4552]               // LDRSW <Xt>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWl           | ldrsw	x20, test                      // LDRSW <Xt>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroX         | ldrsw	x21, [x25, x7]                 // LDRSW <Xt>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroW         | ldrsw	x12, [x28, w12, uxtw]          // LDRSW <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroW         | ldrsw	x22, [x26, w21, sxtw]          // LDRSW <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroX         | ldrsw	x0, [x21, x19, sxtx]           // LDRSW <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroW         | ldrsw	x23, [x17, w19, uxtw #2]       // LDRSW <Xt>, [<Xn|SP>, <Wm>, UXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroW         | ldrsw	x23, [x30, w11, sxtw #2]       // LDRSW <Xt>, [<Xn|SP>, <Wm>, SXTW #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroX         | ldrsw	x29, [x12, x5, sxtx #2]        // LDRSW <Xt>, [<Xn|SP>, <Xm>, SXTX #2]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDRSWroX         | ldrsw	x3, [x1, x17, lsl #2]          // LDRSW <Xt>, [<Xn|SP>, <Xm>, LSL #2]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRWi           | ldtr	w12, [x9]                      // LDTR <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRWi           | ldtr	w9, [x3, #-55]                 // LDTR <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRXi           | ldtr	x9, [x9]                       // LDTR <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRXi           | ldtr	x25, [x1, #103]                // LDTR <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRBi           | ldtrb	w27, [x7]                      // LDTRB <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRBi           | ldtrb	w8, [x1, #-90]                 // LDTRB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRHi           | ldtrh	w13, [x21]                     // LDTRH <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRHi           | ldtrh	w10, [x15, #-67]               // LDTRH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSBWi         | ldtrsb	w15, [x19]             // LDTRSB <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSBWi         | ldtrsb	w28, [x19, #-202]      // LDTRSB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSBXi         | ldtrsb	x17, [x6]              // LDTRSB <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSBXi         | ldtrsb	x0, [x11, #180]        // LDTRSB <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSHWi         | ldtrsh	w19, [x26]             // LDTRSH <Wt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSHWi         | ldtrsh	w16, [x28, #-233]      // LDTRSH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSHXi         | ldtrsh	x26, [x22]             // LDTRSH <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSHXi         | ldtrsh	x27, [x19, #-76]       // LDTRSH <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSWi          | ldtrsw	x23, [x28]             // LDTRSW <Xt>, [<Xn|SP>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDTRSWi          | ldtrsw	x26, [x21, #45]        // LDTRSW <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, immed unprivileged  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURBi           | ldur	b24, [x3]                      // LDUR <Bt>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURBi           | ldur	b9, [x25, #240]                // LDUR <Bt>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURHi           | ldur	h29, [x21]                     // LDUR <Ht>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURHi           | ldur	h5, [x23, #-5]                 // LDUR <Ht>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURSi           | ldur	s12, [x14]                     // LDUR <St>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURSi           | ldur	s22, [x10, #108]               // LDUR <St>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURDi           | ldur	d16, [x14]                     // LDUR <Dt>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURDi           | ldur	d22, [x24, #-198]              // LDUR <Dt>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURQi           | ldur	q25, [x9]                      // LDUR <Qt>, [<Xn|SP>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 6  | 6   | 3.00   | V1UnitL                                                          | LDURQi           | ldur	q5, [x24, #233]                // LDUR <Qt>, [<Xn|SP>, #<simm>]  \\ Load vector reg, unscaled immed  \\ 1 6  6  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURWi           | ldur	w19, [x30]                     // LDUR <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURWi           | ldur	w24, [x12, #202]               // LDUR <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURXi           | ldur	x0, [x3]                       // LDUR <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURXi           | ldur	x14, [x14, #17]                // LDUR <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURBBi          | ldurb	w9, [x24]                      // LDURB <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURBBi          | ldurb	w12, [x5, #92]                 // LDURB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURHHi          | ldurh	w27, [x14]                     // LDURH <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURHHi          | ldurh	w13, [x30, #-173]              // LDURH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSBWi         | ldursb	w5, [x8]               // LDURSB <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSBWi         | ldursb	w21, [x10, #172]       // LDURSB <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSBXi         | ldursb	x19, [x15]             // LDURSB <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSBXi         | ldursb	x16, [x11, #-173]      // LDURSB <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSHWi         | ldursh	w21, [x12]             // LDURSH <Wt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSHWi         | ldursh	w16, [x18, #203]       // LDURSH <Wt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSHXi         | ldursh	x4, [x28]              // LDURSH <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSHXi         | ldursh	x5, [x3, #-133]        // LDURSH <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSWi          | ldursw	x21, [x7]              // LDURSW <Xt>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDURSWi          | ldursw	x11, [x16, #169]       // LDURSW <Xt>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDXPW            | ldxp	w23, w14, [x17]                // LDXP <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDXPW            | ldxp	w2, w8, [x21]                  // LDXP <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDXPX            | ldxp	x5, x6, [x30]                  // LDXP <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 4  | 4   | 1.50   | V1UnitL[2]                                                       | LDXPX            | ldxp	x10, x26, [x6]                 // LDXP <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRW            | ldxr	w4, [x9]                       // LDXR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRW            | ldxr	w7, [x3]                       // LDXR <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRX            | ldxr	x6, [x27]                      // LDXR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRX            | ldxr	x3, [x4]                       // LDXR <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRB            | ldxrb	w17, [x21]                     // LDXRB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRB            | ldxrb	w14, [x3]                      // LDXRB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRH            | ldxrh	w14, [x1]                      // LDXRH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | LDXRH            | ldxrh	w24, [x11]                     // LDXRH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | lsl	w25, w0, #22                   // LSL <Wd>, <Wn>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMXri          | lsl	x27, x7, #56                   // LSL <Xd>, <Xn>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZPmI_B       | lsl	z1.b, p1/m, z1.b, #3           // LSL <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZPmI_H       | lsl	z7.h, p3/m, z7.h, #5           // LSL <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZPmI_S       | lsl	z10.s, p3/m, z10.s, #7         // LSL <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZPmI_D       | lsl	z21.d, p7/m, z21.d, #28        // LSL <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZZI_B        | lsl	z13.b, z4.b, #2                // LSL <Zd>.B, <Zn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZZI_H        | lsl	z11.h, z16.h, #1               // LSL <Zd>.H, <Zn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZZI_S        | lsl	z16.s, z11.s, #6               // LSL <Zd>.S, <Zn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZZI_D        | lsl	z18.d, z4.d, #26               // LSL <Zd>.D, <Zn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSLVWr           | lsl	w4, w9, w12                    // LSL <Wd>, <Wn>, <Wm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSLVXr           | lsl	x7, x29, x22                   // LSL <Xd>, <Xn>, <Xm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_ZPmZ_D       | lsl	z3.d, p2/m, z3.d, z15.d        // LSL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_WIDE_ZPmZ_S  | lsl	z3.s, p6/m, z3.s, z8.d         // LSL <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSL_WIDE_ZZZ_S   | lsl	z19.s, z25.s, z25.d            // LSL <Zd>.<T>, <Zn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSLR_ZPmZ_H      | lslr	z3.h, p5/m, z3.h, z23.h        // LSLR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSLVWr           | lsl	w6, w8, w2                     // LSLV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSLVXr           | lsl	x7, x26, x21                   // LSLV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | lsr	w0, w0, #30                    // LSR <Wd>, <Wn>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMXri          | lsr	x23, x24, #23                  // LSR <Xd>, <Xn>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZPmI_B       | lsr	z21.b, p5/m, z21.b, #3         // LSR <Zdn>.B, <Pg>/M, <Zdn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZPmI_H       | lsr	z1.h, p4/m, z1.h, #5           // LSR <Zdn>.H, <Pg>/M, <Zdn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZPmI_S       | lsr	z24.s, p7/m, z24.s, #9         // LSR <Zdn>.S, <Pg>/M, <Zdn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZPmI_D       | lsr	z13.d, p3/m, z13.d, #4         // LSR <Zdn>.D, <Pg>/M, <Zdn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZZI_B        | lsr	z3.b, z11.b, #3                // LSR <Zd>.B, <Zn>.B, #<constb>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZZI_H        | lsr	z5.h, z12.h, #2                // LSR <Zd>.H, <Zn>.H, #<consth>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZZI_S        | lsr	z21.s, z16.s, #15              // LSR <Zd>.S, <Zn>.S, #<consts>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZZI_D        | lsr	z21.d, z15.d, #8               // LSR <Zd>.D, <Zn>.D, #<constd>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSRVWr           | lsr	w17, w20, w15                  // LSR <Wd>, <Wn>, <Wm>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSRVXr           | lsr	x24, x4, x20                   // LSR <Xd>, <Xn>, <Xm>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_ZPmZ_D       | lsr	z30.d, p3/m, z30.d, z28.d      // LSR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_WIDE_ZPmZ_H  | lsr	z18.h, p3/m, z18.h, z29.d      // LSR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSR_WIDE_ZZZ_H   | lsr	z7.h, z30.h, z11.d             // LSR <Zd>.<T>, <Zn>.<T>, <Zm>.D  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | LSRR_ZPmZ_B      | lsrr	z14.b, p1/m, z14.b, z16.b      // LSRR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, shift  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSRVWr           | lsr	w0, w28, w19                   // LSRV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | LSRVXr           | lsr	x16, x22, x19                  // LSRV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MAD_ZPmZZ_B      | mad	z17.b, p7/m, z4.b, z5.b        // MAD <Zdn>.B, <Pg>/M, <Zm>.B, <Za>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MAD_ZPmZZ_H      | mad	z29.h, p4/m, z31.h, z18.h      // MAD <Zdn>.H, <Pg>/M, <Zm>.H, <Za>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MAD_ZPmZZ_S      | mad	z7.s, p4/m, z5.s, z29.s        // MAD <Zdn>.S, <Pg>/M, <Zm>.S, <Za>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 2   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | MAD_ZPmZZ_D      | mad	z28.d, p7/m, z18.d, z2.d       // MAD <Zdn>.D, <Pg>/M, <Zm>.D, <Za>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | MADDWrrr         | madd	w15, w9, w9, w29               // MADD <Wd>, <Wn>, <Wm>, <Wa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | MADDXrrr         | madd	x29, x22, x21, x21             // MADD <Xd>, <Xn>, <Xm>, <Xa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | MLAv8i16_indexed | mla	v15.8h, v22.8h, v4.h[3]        // MLA <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | MLAv2i32_indexed | mla	v28.2s, v10.2s, v2.s[0]        // MLA <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | MLAv4i32         | mla	v31.4s, v18.4s, v27.4s         // MLA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLA_ZPmZZ_B      | mla	z1.b, p0/m, z3.b, z3.b         // MLA <Zda>.B, <Pg>/M, <Zn>.B, <Zm>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLA_ZPmZZ_H      | mla	z21.h, p2/m, z31.h, z30.h      // MLA <Zda>.H, <Pg>/M, <Zn>.H, <Zm>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLA_ZPmZZ_S      | mla	z24.s, p3/m, z11.s, z9.s       // MLA <Zda>.S, <Pg>/M, <Zn>.S, <Zm>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 2   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | MLA_ZPmZZ_D      | mla	z2.d, p0/m, z12.d, z5.d        // MLA <Zda>.D, <Pg>/M, <Zn>.D, <Zm>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | MLSv8i16_indexed | mls	v25.8h, v29.8h, v0.h[4]        // MLS <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | MLSv2i32_indexed | mls	v22.2s, v29.2s, v0.s[3]        // MLS <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | MLSv4i32         | mls	v26.4s, v5.4s, v28.4s          // MLS <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLS_ZPmZZ_B      | mls	z11.b, p1/m, z28.b, z6.b       // MLS <Zda>.B, <Pg>/M, <Zn>.B, <Zm>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLS_ZPmZZ_H      | mls	z31.h, p0/m, z25.h, z24.h      // MLS <Zda>.H, <Pg>/M, <Zn>.H, <Zm>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLS_ZPmZZ_S      | mls	z1.s, p5/m, z7.s, z13.s        // MLS <Zda>.S, <Pg>/M, <Zn>.S, <Zm>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 2   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | MLS_ZPmZZ_D      | mls	z2.d, p1/m, z17.d, z10.d       // MLS <Zda>.D, <Pg>/M, <Zn>.D, <Zm>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | MSUBWrrr         | mneg	w14, w30, w30                  // MNEG <Wd>, <Wn>, <Wm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | MSUBXrrr         | mneg	x21, x3, x9                    // MNEG <Xd>, <Xn>, <Xm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmV_S       | mov	z9.s, p2/m, s10                // MOV <Zd>.<T>, <Pg>/M, <V><n>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_B        | mov	z17.b, z29.b[38]               // MOV <Zd>.B, <Zn>.B[<immb>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_H        | mov	z26.h, z7.h[16]                // MOV <Zd>.H, <Zn>.H[<immh>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_S        | mov	z14.s, z21.s[13]               // MOV <Zd>.S, <Zn>.S[<imms>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_D        | mov	z22.d, z14.d[2]                // MOV <Zd>.D, <Zn>.D[<immd>]  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZZI_S        | mov	z21.s, s25                     // MOV <Zd>.<T>, <V><n>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRWri           | orr	wsp, wzr, #0xe00               // MOV <Wd|WSP>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZXi           | mov	x3, #7680                      // MOV <Xd|SP>, #<immd>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi8lane       | mov	v30.b[12], v17.b[14]           // MOV <Vd>.B[<index1b>], <Vn>.B[<index2b>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi16lane      | mov	v10.h[3], v17.h[5]             // MOV <Vd>.H[<index1h>], <Vn>.H[<index2h>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi32lane      | mov	v19.s[2], v2.s[1]              // MOV <Vd>.S[<index1s>], <Vn>.S[<index2s>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | INSvi64lane      | mov	v21.d[1], v16.d[0]             // MOV <Vd>.D[<index1d>], <Vn>.D[<index2d>]  \\ ASIMD insert, element to element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi8gpr        | mov	v5.b[12], w23                  // MOV <Vd>.B[<indexb>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi16gpr       | mov	v27.h[6], w6                   // MOV <Vd>.H[<indexh>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi32gpr       | mov	v21.s[0], w21                  // MOV <Vd>.S[<indexs>], W<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV                              | INSvi64gpr       | mov	v13.d[0], x10                  // MOV <Vd>.D[<indexd>], X<n>  \\ ASIMD transfer, gen reg to element  \\ 2 5  5  1.0 V1UnitM0,V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_B       | mov	z30.b, p7/m, #77               // MOV <Zd>.B, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_D       | mov	z30.d, p7/m, #-89              // MOV <Zd>.<T>, <Pg>/M, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPmI_H       | mov	z10.h, p5/m, #72               // MOV <Zd>.<T>, <Pg>/M, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPzI_B       | mov	z19.b, p6/z, #0                // MOV <Zd>.B, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPzI_D       | mov	z6.d, p1/z, #-109              // MOV <Zd>.<T>, <Pg>/Z, #<imm>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | CPY_ZPzI_D       | mov	z12.d, p7/z, #10240            // MOV <Zd>.<T>, <Pg>/Z, #<imm>, <shift>  \\ Copy, scalar SIMD&FP or imm  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_B         | mov	z30.b, #-31                    // MOV <Zd>.B, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_H         | mov	z2.h, #-56                     // MOV <Zd>.<T>, #<imm>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_H         | mov	z20.h, #20992                  // MOV <Zd>.<T>, #<imm>, <shift>  \\ Duplicate, immediate and indexed form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZWi           | mov	w24, #3584                     // MOV <Wd>, #<imms>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZXi           | mov	x15, #3584                     // MOV <Xd>, #<immd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SEL_PPPP         | mov	p0.b, p0/m, p6.b               // MOV <Pd>.B, <Pg>/M, <Pn>.B  \\ Predicate select  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | AND_PPzPP        | mov	p3.b, p7/z, p2.b               // MOV <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRWrs           | mov	w21, w11                       // MOV <Wd>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRXrs           | mov	x14, x0                        // MOV <Xd>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi8            | mov	b15, v21.b[8]                  // MOV B<d>, <Vn>.B[<indexb>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi16           | mov	h13, v17.h[3]                  // MOV H<d>, <Vn>.H[<indexh>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi32           | mov	s7, v11.s[0]                   // MOV S<d>, <Vn>.S[<indexs>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | DUPi64           | mov	d27, v24.d[1]                  // MOV D<d>, <Vn>.D[<indexd>]  \\ ASIMD duplicate, element  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV01                   | CPY_ZPmR_D       | mov	z12.d, p5/m, x24               // MOV <Zd>.<T>, <Pg>/M, <R><n>  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+# CHECK-NEXT:   2    | 5  | 5   | 1.00   | V1UnitI, V1UnitM, V1UnitM0, V1UnitV, V1UnitV01                   | CPY_ZPmR_D       | mov	z31.d, p6/m, sp                // MOV <Zd>.<T>, <Pg>/M, <R2>SP  \\ Copy, scalar  \\ 2 5  5  1.0 V1UnitM0,V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DUP_ZR_B         | mov	z19.b, w27                     // MOV <Zd>.<T>, <R><n>  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | DUP_ZR_H         | mov	z17.h, wsp                     // MOV <Zd>.<T>, <R2>SP  \\ Duplicate, scalar form  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi32         | mov	w13, v12.s[2]                  // MOV <Wd>, <Vn>.S[<indexs>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi64_idx0    | mov	x30, v18.d[0]                  // MOV <Xd>, <Vn>.D[<indexd>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ADDWri           | mov	wsp, wsp                       // MOV <Wd|WSP>, <Wn|WSP>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRXrs           | mov	x1, x11                        // MOV <Xd|SP>, <Xn|SP>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORRv16i8         | mov	v12.16b, v6.16b                // MOV <Vd>.<T>, <Vn>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SEL_ZPZZ_D       | mov	z1.d, p3/m, z6.d               // MOV <Zd>.<T>, <Pv>/M, <Zn>.<T>  \\ Select, vector form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZZZ          | mov	z24.d, z25.d                   // MOV <Zd>.D, <Zn>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZWi           | mov	w30, #3584                     // MOV <Wd>, #<imms>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZXi           | mov	x4, #3584                      // MOV <Xd>, #<immd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_B         | mov	z14.b, #112                    // MOV <Zd>.B, #<constb>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_H         | mov	z8.h, #96                      // MOV <Zd>.H, #<consth>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_S         | mov	z2.s, #2                       // MOV <Zd>.S, #<consts>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | DUP_ZI_D         | mov	z6.d, #4                       // MOV <Zd>.D, #<constd>  \\ Broadcast logical bitmask immediate to vector   \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ORR_PPzPP        | mov	p2.b, p5.b                     // MOV <Pd>.B, <Pn>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv16b_ns      | movi	v7.16b, #177                   // MOVI <Vd>.<Tb>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv8i16        | movi	v14.8h, #174                   // MOVI <Vd>.<Th>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv4i16        | movi	v13.4h, #74, lsl #8            // MOVI <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv2i32        | movi	v19.2s, #226                   // MOVI <Vd>.<Ts>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv2i32        | movi	v0.2s, #137, lsl #24           // MOVI <Vd>.<Ts>, #<imm8>, LSL #<amounts>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv4s_msl      | movi	v1.4s, #122, msl #8            // MOVI <Vd>.<Ts>, #<imm8>, MSL #<amountones>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVID            | movi	d16, #0000000000000000         // MOVI <Dd>, #<imm>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MOVIv2d_ns       | movi	v13.2d, #0xff00ff00ff00ff00    // MOVI <Vd>.2D, #<imm>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVKWi           | movk	w8, #57951                     // MOVK <Wd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVKWi           | movk	w6, #34540                     // MOVK <Wd>, #<imm>, LSL #<shifts>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVKXi           | movk	x1, #56641                     // MOVK <Xd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVKXi           | movk	x23, #3111, lsl #48            // MOVK <Xd>, #<imm>, LSL #<shiftd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVNWi           | mov	w16, #-52527                   // MOVN <Wd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVNWi           | mov	w27, #-47743                   // MOVN <Wd>, #<imm>, LSL #<shifts>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVNXi           | mov	x10, #-63432                   // MOVN <Xd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVNXi           | mov	x0, #2116973299840843775       // MOVN <Xd>, #<imm>, LSL #<shiftd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | MOVPRFX_ZPmZ_B   | movprfx	z22.b, p0/m, z4.b      // MOVPRFX <Zd>.<T>, <Pg>/<ZM>, <Zn>.<T>  \\ Move prefix  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MLA_ZPmZZ_B      | mla	z22.b, p0/m, z19.b, z25.b      // Ignore
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | MOVPRFX_ZZ       | movprfx	z3, z26                // MOVPRFX <Zd>, <Zn>  \\ Move prefix  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | FMLA_ZPmZZ_D     | fmla	z3.d, p0/m, z8.d, z19.d        // Ignore
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | ANDS_PPzPP       | movs	p0.b, p7/z, p3.b               // MOVS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | ORRS_PPzPP       | movs	p4.b, p0.b                     // MOVS <Pd>.B, <Pn>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZWi           | mov	w3, #9629                      // MOVZ <Wd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZWi           | mov	w23, #710082560                // MOVZ <Wd>, #<imm>, LSL #<shifts>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZXi           | mov	x0, #22630                     // MOVZ <Xd>, #<imm>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | MOVZXi           | mov	x11, #5760103923406864384      // MOVZ <Xd>, #<imm>, LSL #<shiftd>  \\ Move immed  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | MRS              | mrs	x4, ACTLR_EL1                  // MRS <Xt>, <systemreg>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | MRS              | mrs	x14, S2_4_C0_C5_4              // MRS <Xt>, S<op0>_<op1>_<Cn>_<Cm>_<op2>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MSB_ZPmZZ_B      | msb	z18.b, p1/m, z27.b, z0.b       // MSB <Zdn>.B, <Pg>/M, <Zm>.B, <Za>.B  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MSB_ZPmZZ_H      | msb	z27.h, p5/m, z23.h, z1.h       // MSB <Zdn>.H, <Pg>/M, <Zm>.H, <Za>.H  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 2   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MSB_ZPmZZ_S      | msb	z26.s, p2/m, z0.s, z2.s        // MSB <Zdn>.S, <Pg>/M, <Zm>.S, <Za>.S  \\ Multiply accumulate, B, H, S element size  \\ 1 4 2 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 2   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | MSB_ZPmZZ_D      | msb	z1.d, p6/m, z12.d, z12.d       // MSB <Zdn>.D, <Pg>/M, <Zm>.D, <Za>.D  \\ Multiply accumulate, D element size  \\ 1 5 2 0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | MSRpstateImm4    | msr	DAIFSet, #0                    // MSR <pstatefield1>, #<imm1>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | MSRpstateImm4    | msr	SPSel, #0                      // MSR <pstatefield2>, #<imm2>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | MSR              | msr	ACTLR_EL3, x18                 // MSR <systemreg>, <Xt>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | MSR              | msr	S3_6_C8_C12_1, x23             // MSR S<op0>_<op1>_<Cn>_<Cm>_<op2>, <Xt>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | MSUBWrrr         | msub	w6, w26, w13, w13              // MSUB <Wd>, <Wn>, <Wm>, <Wa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | MSUBXrrr         | msub	x14, x28, x9, x3               // MSUB <Xd>, <Xn>, <Xm>, <Xa>  \\ Multiply accumulate, X-form  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | MULv4i16_indexed | mul	v26.4h, v20.4h, v14.h[5]       // MUL <Vd>.4H, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | MULv8i16_indexed | mul	v5.8h, v21.8h, v3.h[7]         // MUL <Vd>.8H, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | MULv2i32_indexed | mul	v29.2s, v10.2s, v3.s[1]        // MUL <Vd>.2S, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | MULv4i32_indexed | mul	v30.4s, v11.4s, v4.s[0]        // MUL <Vd>.4S, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MUL_ZI_B         | mul	z16.b, z16.b, #-118            // MUL <Zdn>.B, <Zdn>.B, #<imm>  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MUL_ZI_H         | mul	z9.h, z9.h, #-56               // MUL <Zdn>.H, <Zdn>.H, #<imm>  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MUL_ZI_S         | mul	z23.s, z23.s, #74              // MUL <Zdn>.S, <Zdn>.S, #<imm>  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 5   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | MUL_ZI_D         | mul	z15.d, z15.d, #20              // MUL <Zdn>.D, <Zdn>.D, #<imm>  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | MULv8i16         | mul	v3.8h, v9.8h, v8.8h            // MUL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MUL_ZPmZ_B       | mul	z17.b, p6/m, z17.b, z9.b       // MUL <Zdn>.B, <Pg>/M, <Zdn>.B, <Zm>.B  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MUL_ZPmZ_H       | mul	z18.h, p7/m, z18.h, z15.h      // MUL <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | MUL_ZPmZ_S       | mul	z29.s, p6/m, z29.s, z8.s       // MUL <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 5   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | MUL_ZPmZ_D       | mul	z25.d, p1/m, z25.d, z25.d      // MUL <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | MADDWrrr         | mul	w8, w13, w20                   // MUL <Wd>, <Wn>, <Wm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | MADDXrrr         | mul	x12, x8, x25                   // MUL <Xd>, <Xn>, <Xm>  \\ Multiply  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNWrs           | mvn	w0, w18                        // MVN <Wd>, <Wm>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNWrs           | mvn	w25, w27, asr #6               // MVN <Wd>, <Wm>, <shift> #<wamount>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNXrs           | mvn	x1, x21                        // MVN <Xd>, <Xm>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNXrs           | mvn	x9, x23, asr #39               // MVN <Xd>, <Xm>, <shift> #<amount>  \\ Move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | NOTv16i8         | mvn	v16.16b, v24.16b               // MVN <Vd>.<T>, <Vn>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MVNIv4i16        | mvni	v9.4h, #237                    // MVNI <Vd>.<Th>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MVNIv8i16        | mvni	v8.8h, #171, lsl #8            // MVNI <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MVNIv2i32        | mvni	v7.2s, #81                     // MVNI <Vd>.<Ts>, #<imm8>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MVNIv4i32        | mvni	v22.4s, #15, lsl #8            // MVNI <Vd>.<Ts>, #<imm8>, LSL #<amounts>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | MVNIv4s_msl      | mvni	v12.4s, #141, msl #8           // MVNI <Vd>.<Ts>, #<imm8>, MSL #<amountones>  \\ ASIMD move, integer immed  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | NAND_PPzPP       | nand	p5.b, p4/z, p5.b, p5.b         // NAND <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | NANDS_PPzPP      | nands	p6.b, p3/z, p4.b, p5.b         // NANDS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWrs           | neg	w25, w20, lsl #4               // NEG <Wd>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBWrs           | neg	w0, w29, lsl #9                // NEG <Wd>, <Wm>, LSL #<wamounth>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBWrs           | neg	w7, w28, asr #24               // NEG <Wd>, <Wm>, <shift> #<wamount>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXrs           | neg	x29, x11, lsl #3               // NEG <Xd>, <Xm>, LSL #<amountl>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBXrs           | neg	x24, x10, lsl #54              // NEG <Xd>, <Xm>, LSL #<amounth>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBXrs           | neg	x0, x16, lsr #2                // NEG <Xd>, <Xm>, <shift> #<amount>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | NEGv1i64         | neg	d18, d20                       // NEG <V><d>, <V><n>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | NEGv2i64         | neg	v16.2d, v14.2d                 // NEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | NEG_ZPmZ_B       | neg	z16.b, p2/m, z15.b             // NEG <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrs          | negs	w30, w22, lsl #2               // NEGS <Wd>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWrs          | negs	w8, w8, lsl #15                // NEGS <Wd>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWrs          | negs	w12, w21, asr #15              // NEGS <Wd>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | negs	x24, x23, lsl #1               // NEGS <Xd>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrs          | negs	x20, x13, lsl #20              // NEGS <Xd>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrs          | negs	x1, x22, lsr #30               // NEGS <Xd>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBCWr            | ngc	w11, w9                        // NGC <Wd>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBCXr            | ngc	x30, x4                        // NGC <Xd>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SBCSWr           | ngcs	w13, w22                       // NGCS <Wd>, <Wm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SBCSXr           | ngcs	x15, x1                        // NGCS <Xd>, <Xm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | nop                                 // NOP  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | NOR_PPzPP        | nor	p4.b, p4/z, p0.b, p4.b         // NOR <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | NORS_PPzPP       | nors	p1.b, p0/z, p7.b, p6.b         // NORS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | EOR_PPzPP        | not	p7.b, p2/z, p6.b               // NOT <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | NOT_ZPmZ_S       | not	z29.s, p4/m, z9.s              // NOT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | NOTv8i8          | mvn	v15.8b, v29.8b                 // NOT <Vd>.<T>, <Vn>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | EORS_PPzPP       | nots	p7.b, p3/z, p1.b               // NOTS <Pd>.B, <Pg>/Z, <Pn>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z5.b, z5.b, #0x8f              // ORN <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z14.h, z14.h, #0xff9f          // ORN <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z14.s, z14.s, #0xfffffffd      // ORN <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z27.d, z27.d, #0xfffffffffffffffb  // ORN <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ORN_PPzPP        | orn	p1.b, p2/z, p3.b, p5.b         // ORN <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNWrs           | orn	w2, w27, w7                    // ORN <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNWrs           | orn	w6, w28, w14, lsl #19          // ORN <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNXrs           | orn	x22, x12, x3                   // ORN <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORNXrs           | orn	x19, x17, x0, lsl #58          // ORN <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORNv8i8          | orn	v29.8b, v19.8b, v16.8b         // ORN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | ORNS_PPzPP       | orns	p3.b, p3/z, p0.b, p3.b         // ORNS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRWri           | orr	wsp, w27, #0xe00               // ORR <Wd|WSP>, <Wn>, #<imms>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRXri           | orr	x27, x6, #0x1e00               // ORR <Xd|SP>, <Xn>, #<immd>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z4.b, z4.b, #0x70              // ORR <Zdn>.B, <Zdn>.B, #<constb>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z26.h, z26.h, #0x60            // ORR <Zdn>.H, <Zdn>.H, #<consth>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z3.s, z3.s, #0x2               // ORR <Zdn>.S, <Zdn>.S, #<consts>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZI           | orr	z30.d, z30.d, #0x4             // ORR <Zdn>.D, <Zdn>.D, #<constd>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ORR_PPzPP        | orr	p6.b, p4/z, p4.b, p3.b         // ORR <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRWrs           | orr	w14, w1, w23                   // ORR <Wd>, <Wn>, <Wm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRWrs           | orr	w25, w22, w0, asr #20          // ORR <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRXrs           | orr	x11, x6, x13                   // ORR <Xd>, <Xn>, <Xm>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | ORRXrs           | orr	x26, x26, x7, lsl #62          // ORR <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORRv4i16         | orr	v9.4h, #18                     // ORR <Vd>.<Th>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORRv8i16         | orr	v20.8h, #175                   // ORR <Vd>.<Th>, #<imm8>, LSL #<amounth>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORRv4i32         | orr	v4.4s, #0                      // ORR <Vd>.<T>, #<imm8>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORRv4i32         | orr	v17.4s, #119, lsl #24          // ORR <Vd>.<T>, #<imm8>, LSL #<amount>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ORRv16i8         | orr	v12.16b, v9.16b, v1.16b        // ORR <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD logical  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZPmZ_H       | orr	z28.h, p3/m, z28.h, z7.h       // ORR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | ORR_ZZZ          | orr	z8.d, z14.d, z19.d             // ORR <Zd>.D, <Zn>.D, <Zm>.D  \\ Logical  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | ORRS_PPzPP       | orrs	p7.b, p7/z, p6.b, p5.b         // ORRS <Pd>.B, <Pg>/Z, <Pn>.B, <Pm>.B  \\ Predicate logical, flag setting  \\ 1 2  2  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[4], V1UnitV01[4]                                         | ORV_VPZ_D        | orv	d19, p6, z31.d                 // ORV <V><d>, <Pg>, <Zn>.<T>  \\ Reduction, logical   \\ 1 12  12  0.5 V1UnitV01[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PFALSE           | pfalse	p6.b                   // PFALSE <Pd>.B  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PFIRST_B         | pfirst	p0.b, p5, p0.b         // PFIRST <Pdn>.B, <Pg>, <Pdn>.B  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | PMULv8i8         | pmul	v30.8b, v0.8b, v27.8b          // PMUL <Vd>.8B, <Vn>.8B, <Vm>.8B  \\ ASIMD multiply/multiply long (8x8) polynomial, D-form  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV01                                               | PMULv16i8        | pmul	v7.16b, v20.16b, v18.16b       // PMUL <Vd>.16B, <Vn>.16B, <Vm>.16B  \\ ASIMD multiply/multiply long (8x8) polynomial, Q-form  \\ 1 3  3  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PNEXT_S          | pnext	p5.s, p5, p5.s                 // PNEXT <Pdn>.<T>, <Pv>, <Pdn>.<T>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_PRI         | prfb	#14, p5, [x21]                 // PRFB #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_PRI         | prfb	#14, p3, [x28, #-24, mul vl]   // PRFB #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_PRI         | prfb	pstl1strm, p7, [x5]            // PRFB <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_PRI         | prfb	pldl2keep, p1, [x12, #11, mul vl]  // PRFB <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_PRR         | prfb	pldl1keep, p7, [x4, x9]        // PRFB <prfop>, <Pg>, [<Xn|SP>, <Xm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_S_UXTW_SCALED | prfb	pldl3strm, p4, [x3, z15.s, uxtw]  // PRFB <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_D_UXTW_SCALED | prfb	pldl1strm, p7, [x28, z4.d, uxtw]  // PRFB <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_D_SCALED    | prfb	pstl3keep, p2, [x18, z19.d]    // PRFB <prfop>, <Pg>, [<Xn|SP>, <Zm>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_S_PZI       | prfb	pstl3keep, p1, [z28.s]         // PRFB #<imm4>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_S_PZI       | prfb	pstl1keep, p0, [z22.s, #21]    // PRFB #<imm4>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_S_PZI       | prfb	pstl1strm, p2, [z25.s]         // PRFB <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_S_PZI       | prfb	pstl2strm, p1, [z31.s, #18]    // PRFB <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_D_PZI       | prfb	pstl2strm, p5, [z25.d]         // PRFB #<imm4>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_D_PZI       | prfb	pldl2keep, p2, [z4.d, #10]     // PRFB #<imm4>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_D_PZI       | prfb	pstl2keep, p5, [z5.d]          // PRFB <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFB_D_PZI       | prfb	pldl1keep, p1, [z31.d, #17]    // PRFB <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_PRI         | prfd	pstl3strm, p3, [x21]           // PRFD #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_PRI         | prfd	pldl3keep, p5, [x3, #-7, mul vl]  // PRFD #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_PRI         | prfd	pstl3keep, p0, [x29]           // PRFD <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_PRI         | prfd	pldl1strm, p3, [x15, #-16, mul vl]  // PRFD <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_PRR         | prfd	pstl2keep, p3, [x24, x24, lsl #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_S_SXTW_SCALED | prfd	pstl1strm, p3, [x27, z27.s, sxtw #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #3]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_D_UXTW_SCALED | prfd	pstl1keep, p0, [x21, z2.d, uxtw #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_D_SCALED    | prfd	pldl1strm, p7, [x22, z22.d, lsl #3]  // PRFD <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, LSL #3]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_S_PZI       | prfd	pldl2strm, p1, [z2.s]          // PRFD #<imm4>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_S_PZI       | prfd	pstl1keep, p7, [z10.s, #72]    // PRFD #<imm4>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_S_PZI       | prfd	pstl1keep, p3, [z19.s]         // PRFD <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_S_PZI       | prfd	pstl2strm, p4, [z26.s, #248]   // PRFD <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_D_PZI       | prfd	#15, p1, [z17.d]               // PRFD #<imm4>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_D_PZI       | prfd	pldl2strm, p0, [z6.d, #24]     // PRFD #<imm4>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_D_PZI       | prfd	pstl1keep, p3, [z31.d]         // PRFD <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFD_D_PZI       | prfd	pstl1strm, p7, [z10.d, #40]    // PRFD <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_PRI         | prfh	pldl2strm, p3, [x17]           // PRFH #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_PRI         | prfh	#6, p3, [x6, #19, mul vl]      // PRFH #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_PRI         | prfh	pldl3keep, p6, [x2]            // PRFH <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_PRI         | prfh	pldl2keep, p6, [x18, #-4, mul vl]  // PRFH <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_PRR         | prfh	pstl2keep, p1, [x28, x9, lsl #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_S_UXTW_SCALED | prfh	pldl1strm, p6, [x0, z10.s, uxtw #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_D_UXTW_SCALED | prfh	pldl3keep, p7, [x24, z21.d, uxtw #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_D_SCALED    | prfh	pstl1strm, p5, [x10, z6.d, lsl #1]  // PRFH <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, LSL #1]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_S_PZI       | prfh	pldl3strm, p6, [z0.s]          // PRFH <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_S_PZI       | prfh	pstl3strm, p0, [z30.s, #12]    // PRFH <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_D_PZI       | prfh	pstl2keep, p2, [z21.d]         // PRFH <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFH_D_PZI       | prfh	pstl2keep, p1, [z8.d, #14]     // PRFH <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMui           | prfm	pldl1strm, [x5]                // PRFM <prfop>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMui           | prfm	pstl3keep, [x19, #10160]       // PRFM <prfop>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMui           | prfm	#25, [x28]                     // PRFM #<imm5>, [<Xn|SP>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMui           | prfm	#7, [x15, #6776]               // PRFM #<imm5>, [<Xn|SP>, #<pimm>]  \\ Load register, unsigned immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMl            | prfm	pldl3strm, test                // PRFM <prfop>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMl            | prfm	pldl1keep, test                // PRFM #<imm5>, <label>  \\ Load register, literal  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | prfm	pldl1keep, [x25, x16]          // PRFM <prfop>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | rprfm #16, x18, [x1]                // PRFM #<imm5>, [<Xn|SP>, <Xm>]  \\ Load register, register offset, basic  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	pldl1keep, [x14, w8, uxtw]     // PRFM <prfop>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	plil3keep, [x8, w5, uxtw]      // PRFM #<imm5>, [<Xn|SP>, <Wm>, UXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	pldl2keep, [x16, w16, sxtw]    // PRFM <prfop>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	plil2strm, [x25, w11, sxtw]    // PRFM #<imm5>, [<Xn|SP>, <Wm>, SXTW]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | prfm	pstl2strm, [x3, x24, sxtx]     // PRFM <prfop>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | rprfm #49, x2, [x5]                 // PRFM #<imm5>, [<Xn|SP>, <Xm>, SXTX]  \\ Load register, register offset, extend  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	pldl2keep, [x10, w29, uxtw #3]  // PRFM <prfop>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	pstl1strm, [x9, w27, uxtw #3]  // PRFM #<imm5>, [<Xn|SP>, <Wm>, UXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	pldl1keep, [x24, w0, sxtw #3]  // PRFM <prfop>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroW          | prfm	pldl3keep, [x30, w25, sxtw #3]  // PRFM #<imm5>, [<Xn|SP>, <Wm>, SXTW #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | prfm	pstl1strm, [x18, x20, sxtx #3]  // PRFM <prfop>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | prfm	pstl2strm, [x29, x25, sxtx #3]  // PRFM #<imm5>, [<Xn|SP>, <Xm>, SXTX #3]  \\ Load register, register offset, extend, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | prfm	pstl3keep, [x2, x5, lsl #3]    // PRFM <prfop>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFMroX          | prfm	plil1keep, [x22, x3, lsl #3]   // PRFM #<imm5>, [<Xn|SP>, <Xm>, LSL #3]  \\ Load register, register offset, scale by 4/8  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFUMi           | prfum	pstl1keep, [x7]                // PRFUM <prfop>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFUMi           | prfum	pldl2keep, [x7, #-37]          // PRFUM <prfop>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFUMi           | prfum	pstl3keep, [x21]               // PRFUM #<imm5>, [<Xn|SP>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 3.00   | V1UnitL                                                          | PRFUMi           | prfum	#23, [x6, #-131]               // PRFUM #<imm5>, [<Xn|SP>, #<simm>]  \\ Load register, unscaled immed  \\ 1 4  4  3.0 V1UnitL
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_PRI         | prfw	pldl2strm, p2, [x4]            // PRFW #<imm4>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_PRI         | prfw	#6, p4, [x7, #6, mul vl]       // PRFW #<imm4>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_PRI         | prfw	pldl3keep, p3, [x2]            // PRFW <prfop>, <Pg>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_PRI         | prfw	pstl1keep, p7, [x2, #-31, mul vl]  // PRFW <prfop>, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_PRR         | prfw	pstl1keep, p4, [x18, x21, lsl #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_S_UXTW_SCALED | prfw	pldl2strm, p0, [x15, z6.s, uxtw #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_D_SXTW_SCALED | prfw	pstl2keep, p0, [x27, z18.d, sxtw #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_D_SCALED    | prfw	pstl2keep, p3, [x19, z8.d, lsl #2]  // PRFW <prfop>, <Pg>, [<Xn|SP>, <Zm>.D, LSL #2]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_S_PZI       | prfw	#7, p7, [z27.s]                // PRFW #<imm4>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_S_PZI       | prfw	pstl1strm, p5, [z16.s, #72]    // PRFW #<imm4>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_S_PZI       | prfw	pldl3keep, p4, [z2.s]          // PRFW <prfop>, <Pg>, [<Zn>.S]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_S_PZI       | prfw	pstl3keep, p2, [z0.s, #40]     // PRFW <prfop>, <Pg>, [<Zn>.S, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_D_PZI       | prfw	#7, p1, [z20.d]                // PRFW #<imm4>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_D_PZI       | prfw	#7, p2, [z10.d, #108]          // PRFW #<imm4>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_D_PZI       | prfw	pstl1keep, p6, [z12.d]         // PRFW <prfop>, <Pg>, [<Zn>.D]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01                                               | PRFW_D_PZI       | prfw	pstl2strm, p0, [z18.d, #60]    // PRFW <prfop>, <Pg>, [<Zn>.D, #<imm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | psb	csync                          // PSB CSYNC  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DSB              | pssbb                               // PSSBB  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PTEST_PP         | ptest	p0, p5.b                       // PTEST <Pg>, <Pn>.B  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PTRUE_B          | ptrue	p2.b                           // PTRUE <Pd>.<T>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PTRUE_D          | ptrue	p3.d, pow2                     // PTRUE <Pd>.<T>, <pattern>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PTRUE_H          | ptrue	p0.h                           // PTRUE <Pd>.<T>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PTRUE_S          | ptrue	p4.s, #21                      // PTRUE <Pd>.<T>, #<uimm5>  \\ Predicate set/initialize/find next  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | PTRUES_H         | ptrues	p3.h                   // PTRUES <Pd>.<T>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | PTRUES_D         | ptrues	p3.d, vl32             // PTRUES <Pd>.<T>, <pattern>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | PTRUES_B         | ptrues	p0.b                   // PTRUES <Pd>.<T>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | PTRUES_D         | ptrues	p2.d, vl128            // PTRUES <Pd>.<T>, #<uimm5>  \\ Predicate set/initialize, set flags  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PUNPKHI_PP       | punpkhi	p4.h, p4.b             // PUNPKHI <Pd>.H, <Pn>.B  \\ Predicate unpack and widen  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | PUNPKLO_PP       | punpklo	p1.h, p4.b             // PUNPKLO <Pd>.H, <Pn>.B  \\ Predicate unpack and widen  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | RADDHNv2i64_v2i32 | raddhn	v17.2s, v22.2d, v5.2d  // RADDHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | RADDHNv2i64_v4i32 | raddhn2	v21.4s, v11.2d, v1.2d  // RADDHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | RBITv16i8        | rbit	v16.16b, v21.16b               // RBIT <Vd>.<T>, <Vn>.<T>  \\ ASIMD bit reverse  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | RBITWr           | rbit	w27, w10                       // RBIT <Wd>, <Wn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | RBITXr           | rbit	x30, x0                        // RBIT <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | RBIT_ZPmZ_S      | rbit	z23.s, p3/m, z10.s             // RBIT <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Count/reverse bits  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | RDFFR_PPz        | rdffr	p2.b, p1/z                     // RDFFR <Pd>.B, <Pg>/Z  \\ Read first fault register, predicated  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | RDFFR_P          | rdffr	p5.b                           // RDFFR <Pd>.B  \\ Read first fault register, unpredicated  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 4  | 4   | 0.33   | V1UnitI[6], V1UnitM[6]                                           | RDFFRS_PPz       | rdffrs	p7.b, p2/z             // RDFFRS <Pd>.B, <Pg>/Z  \\ Read first fault register and set flags  \\ 1 4  4  0.33 V1UnitM[6]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | RDVLI_XI         | rdvl	x20, #-20                      // RDVL <Xd>, #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | RET              | ret                                 // RET  \\ Branch, register  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | RET              | ret	x14                            // RET {<Xn>}  \\ Branch, register  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | REV_PP_H         | rev	p1.h, p2.h                     // REV <Pd>.<T>, <Pn>.<T>  \\ Predicate reverse  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | REV_ZZ_D         | rev	z11.d, z24.d                   // REV <Zd>.<T>, <Zn>.<T>  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | REVWr            | rev	w19, w20                       // REV <Wd>, <Wn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | REVXr            | rev	x30, x15                       // REV <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | REV16v16i8       | rev16	v5.16b, v26.16b                // REV16 <Vd>.<T>, <Vn>.<T>  \\ ASIMD reverse  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | REV16Wr          | rev16	w1, w25                        // REV16 <Wd>, <Wn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | REV16Xr          | rev16	x27, x11                       // REV16 <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | REV32v8i16       | rev32	v22.8h, v4.8h                  // REV32 <Vd>.<T>, <Vn>.<T>  \\ ASIMD reverse  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | REV32Xr          | rev32	x30, x6                        // REV32 <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | REVXr            | rev	x5, x2                         // REV64 <Xd>, <Xn>  \\ Reverse bits/bytes  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | REV64v2i32       | rev64	v0.2s, v19.2s                  // REV64 <Vd>.<T>, <Vn>.<T>  \\ ASIMD reverse  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | REVB_ZPmZ_D      | revb	z3.d, p2/m, z21.d              // REVB <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | REVH_ZPmZ_D      | revh	z1.d, p5/m, z19.d              // REVH <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | REVW_ZPmZ_D      | revw	z16.d, p1/m, z3.d              // REVW <Zd>.D, <Pg>/M, <Zn>.D  \\ Reverse, vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EXTRWrri         | ror	w20, w13, #21                  // ROR <Wd>, <Ws>, #<shifts>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | EXTRXrri         | ror	x5, x8, #7                     // ROR <Xd>, <Xs>, #<shiftd>  \\ Move, shift by immed, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | RORVWr           | ror	w29, w26, w0                   // ROR <Wd>, <Wn>, <Wm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | RORVXr           | ror	x4, x13, x3                    // ROR <Xd>, <Xn>, <Xm>  \\ Move, shift by register, no flagset, unconditional  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | RORVWr           | ror	w26, w0, w28                   // RORV <Wd>, <Wn>, <Wm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | RORVXr           | ror	x21, x29, x17                  // RORV <Xd>, <Xn>, <Xm>  \\ Variable shift  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | RSHRNv8i8_shift  | rshrn	v24.8b, v0.8h, #4              // RSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | RSHRNv4i16_shift | rshrn	v8.4h, v24.4s, #16             // RSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | RSHRNv2i32_shift | rshrn	v12.2s, v12.2d, #28            // RSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | RSHRNv16i8_shift | rshrn2	v1.16b, v16.8h, #6     // RSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | RSHRNv8i16_shift | rshrn2	v1.8h, v28.4s, #3      // RSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | RSHRNv4i32_shift | rshrn2	v20.4s, v19.2d, #14    // RSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | RSUBHNv8i16_v8i8 | rsubhn	v3.8b, v9.8h, v16.8h   // RSUBHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | RSUBHNv2i64_v4i32 | rsubhn2	v31.4s, v12.2d, v15.2d  // RSUBHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SABAv16i8        | saba	v8.16b, v27.16b, v13.16b       // SABA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff accum  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SABALv2i32_v2i64 | sabal	v2.2d, v5.2s, v31.2s           // SABAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SABALv4i32_v2i64 | sabal2	v21.2d, v15.4s, v13.4s  // SABAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SABDv2i32        | sabd	v12.2s, v11.2s, v27.2s         // SABD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SABD_ZPmZ_S      | sabd	z14.s, p1/m, z14.s, z23.s      // SABD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SABDLv2i32_v2i64 | sabdl	v28.2d, v4.2s, v19.2s          // SABDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SABDLv16i8_v8i16 | sabdl2	v10.8h, v30.16b, v4.16b  // SABDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SADALPv8i8_v4i16 | sadalp	v3.4h, v5.8b           // SADALP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD pairwise add and accumulate long  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SADDLv8i8_v8i16  | saddl	v7.8h, v3.8b, v23.8b           // SADDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SADDLv8i16_v4i32 | saddl2	v21.4s, v5.8h, v10.8h  // SADDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SADDLPv16i8_v8i16 | saddlp	v13.8h, v29.16b        // SADDLP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SADDLVv8i8v      | saddlv	h18, v28.8b            // SADDLV H<d>, <Vn>.8B  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | SADDLVv16i8v     | saddlv	h30, v4.16b            // SADDLV H<d>, <Vn>.16B  \\ ASIMD arith, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SADDLVv4i16v     | saddlv	s24, v29.4h            // SADDLV S<d>, <Vn>.4H  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SADDLVv8i16v     | saddlv	s22, v23.8h            // SADDLV S<d>, <Vn>.8H  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SADDLVv4i32v     | saddlv	d2, v27.4s             // SADDLV D<d>, <Vn>.4S  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 14 | 14  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SADDV_VPZ_B      | saddv	d19, p6, z1.b                  // SADDV <Dd>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SADDV_VPZ_H      | saddv	d7, p2, z14.h                  // SADDV <Dd>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SADDV_VPZ_S      | saddv	d4, p7, z27.s                  // SADDV <Dd>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SADDWv4i16_v4i32 | saddw	v8.4s, v0.4s, v1.4h            // SADDW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SADDWv16i8_v8i16 | saddw2	v24.8h, v10.8h, v30.16b  // SADDW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBCWr            | sbc	w0, w16, w1                    // SBC <Wd>, <Wn>, <Wm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBCXr            | sbc	x19, x3, x9                    // SBC <Xd>, <Xn>, <Xm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SBCSWr           | sbcs	w26, w28, w0                   // SBCS <Wd>, <Wn>, <Wm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SBCSXr           | sbcs	x8, x26, x29                   // SBCS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMWri          | sbfiz	w14, w5, #21, #8               // SBFIZ <Wd>, <Wn>, #<lsbs>, #<widths>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | sbfiz	x14, x1, #56, #2               // SBFIZ <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMWri          | sbfiz	w24, w11, #5, #20              // SBFM <Wd>, <Wn>, #<immrs>, #<immss>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | sbfx	x14, x1, #36, #20              // SBFM <Xd>, <Xn>, #<immrd>, #<immsd>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMWri          | asr	w16, w16, #31                  // SBFX <Wd>, <Wn>, #<lsbs>, #<widths>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | sbfx	x14, x28, #53, #8              // SBFX <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFSWHri       | scvtf	h18, w17, #30                  // SCVTF <Hd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFSWSri       | scvtf	s14, w9, #19                   // SCVTF <Sd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFSWDri       | scvtf	d16, w3, #13                   // SCVTF <Dd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFSXHri       | scvtf	h28, x25, #23                  // SCVTF <Hd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFSXSri       | scvtf	s27, x19, #5                   // SCVTF <Sd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFSXDri       | scvtf	d15, x22, #32                  // SCVTF <Dd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFUWHri       | scvtf	h22, w7                        // SCVTF <Hd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFUWSri       | scvtf	s22, w10                       // SCVTF <Sd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFUWDri       | scvtf	d23, w6                        // SCVTF <Dd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFUXHri       | scvtf	h21, x12                       // SCVTF <Hd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFUXSri       | scvtf	s25, x28                       // SCVTF <Sd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SCVTFUXDri       | scvtf	d12, x0                        // SCVTF <Dd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFh           | scvtf	h4, h8, #9                     // SCVTF H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFs           | scvtf	s29, s12, #1                   // SCVTF S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFd           | scvtf	d1, d12, #26                   // SCVTF D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | SCVTFv4i16_shift | scvtf	v25.4h, v13.4h, #8             // SCVTF <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | SCVTFv8i16_shift | scvtf	v4.8h, v8.8h, #10              // SCVTF <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv2i32_shift | scvtf	v5.2s, v2.2s, #26              // SCVTF <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | SCVTFv4i32_shift | scvtf	v2.4s, v24.4s, #10             // SCVTF <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv2i64_shift | scvtf	v11.2d, v2.2d, #42             // SCVTF <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv1i16       | scvtf	h5, h14                        // SCVTF <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv1i32       | scvtf	s5, s16                        // SCVTF S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv1i64       | scvtf	d12, d11                       // SCVTF D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | SCVTFv4f16       | scvtf	v22.4h, v10.4h                 // SCVTF <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | SCVTFv8f16       | scvtf	v16.8h, v13.8h                 // SCVTF <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv2f32       | scvtf	v9.2s, v31.2s                  // SCVTF <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | SCVTFv4f32       | scvtf	v2.4s, v7.4s                   // SCVTF <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SCVTFv2f64       | scvtf	v18.2d, v11.2d                 // SCVTF <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | SCVTF_ZPmZ_HtoH  | scvtf	z3.h, p3/m, z29.h              // SCVTF <Zd>.H, <Pg>/M, <Zn>.H  \\ Convert to floating point, 16b to half  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | SCVTF_ZPmZ_StoH  | scvtf	z1.h, p5/m, z27.s              // SCVTF <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | SCVTF_ZPmZ_StoS  | scvtf	z30.s, p4/m, z29.s             // SCVTF <Zd>.S, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | SCVTF_ZPmZ_StoD  | scvtf	z18.d, p3/m, z16.s             // SCVTF <Zd>.D, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SCVTF_ZPmZ_DtoH  | scvtf	z18.h, p1/m, z14.d             // SCVTF <Zd>.H, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SCVTF_ZPmZ_DtoS  | scvtf	z10.s, p1/m, z11.d             // SCVTF <Zd>.S, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SCVTF_ZPmZ_DtoD  | scvtf	z3.d, p2/m, z27.d              // SCVTF <Zd>.D, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 12 | 12  | 0.08   | V1UnitI[12], V1UnitM[12], V1UnitM0[12]                           | SDIVWr           | sdiv	w6, w28, w24                   // SDIV <Wd>, <Wn>, <Wm>  \\ Divide, W-form  \\ 1 12 12 0.08 V1UnitM0[12]
+# CHECK-NEXT:   1    | 20 | 20  | 0.05   | V1UnitI[20], V1UnitM[20], V1UnitM0[20]                           | SDIVXr           | sdiv	x19, x2, x14                   // SDIV <Xd>, <Xn>, <Xm>  \\ Divide, X-form  \\ 1 20 20 0.05 V1UnitM0[20]
+# CHECK-NEXT:   1    | 12 | 12  | 0.09   | V1UnitV[11], V1UnitV0[11], V1UnitV01[11], V1UnitV02[11]          | SDIV_ZPmZ_S      | sdiv	z24.s, p1/m, z24.s, z14.s      // SDIV <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+# CHECK-NEXT:   1    | 20 | 20  | 0.05   | V1UnitV[20], V1UnitV0[20], V1UnitV01[20], V1UnitV02[20]          | SDIV_ZPmZ_D      | sdiv	z7.d, p6/m, z7.d, z20.d        // SDIV <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+# CHECK-NEXT:   1    | 12 | 12  | 0.09   | V1UnitV[11], V1UnitV0[11], V1UnitV01[11], V1UnitV02[11]          | SDIVR_ZPmZ_S     | sdivr	z10.s, p2/m, z10.s, z7.s       // SDIVR <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+# CHECK-NEXT:   1    | 20 | 20  | 0.05   | V1UnitV[20], V1UnitV0[20], V1UnitV01[20], V1UnitV02[20]          | SDIVR_ZPmZ_D     | sdivr	z0.d, p3/m, z0.d, z9.d         // SDIVR <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV, V1UnitV01                                               | SDOT_ZZZI_S      | sdot	z6.s, z29.b, z0.b[2]           // SDOT <Zda>.S, <Zn>.B, <Zmb>.B[<imms>]  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 1   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SDOT_ZZZI_D      | sdot	z0.d, z18.h, z10.h[1]          // SDOT <Zda>.D, <Zn>.H, <Zmh>.H[<immd>]  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV, V1UnitV01                                               | SDOT_ZZZ_S       | sdot	z28.s, z30.b, z14.b            // SDOT <Zda>.S, <Zn>.B, <Zm>.B  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 1   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SDOT_ZZZ_D       | sdot	z19.d, z5.h, z8.h              // SDOT <Zda>.D, <Zn>.H, <Zm>.H  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | SDOTlanev16i8    | sdot	v2.4s, v27.16b, v5.4b[0]       // SDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<indexs>]  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | SDOTv8i8         | sdot	v3.2s, v20.8b, v10.8b          // SDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SEL_PPPP         | sel	p1.b, p7, p5.b, p4.b           // SEL <Pd>.B, <Pg>, <Pn>.B, <Pm>.B  \\ Predicate select  \\ 1 1  1  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SEL_ZPZZ_H       | sel	z0.h, p7, z13.h, z13.h         // SEL <Zd>.<T>, <Pv>, <Zn>.<T>, <Zm>.<T>  \\ Select, vector form  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SETFFR           | setffr                              // SETFFR  \\ Set first fault register  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | sev                                 // SEV  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | sevl                                // SEVL  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SHADDv16i8       | shadd	v25.16b, v1.16b, v10.16b       // SHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLd             | shl	d17, d3, #16                   // SHL <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLv8i8_shift    | shl	v23.8b, v18.8b, #6             // SHL <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLv8i16_shift   | shl	v0.8h, v23.8h, #10             // SHL <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLv4i32_shift   | shl	v0.4s, v18.4s, #30             // SHL <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLv2i64_shift   | shl	v20.2d, v28.2d, #40            // SHL <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLLv8i8         | shll	v3.8h, v13.8b, #8              // SHLL <Vd>.8H, <Vn>.8B, #8  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLLv4i16        | shll	v26.4s, v18.4h, #16            // SHLL <Vd>.4S, <Vn>.4H, #16  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLLv2i32        | shll	v4.2d, v25.2s, #32             // SHLL <Vd>.2D, <Vn>.2S, #32  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLLv16i8        | shll2	v12.8h, v28.16b, #8            // SHLL2 <Vd>.8H, <Vn>.16B, #8  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLLv8i16        | shll2	v11.4s, v22.8h, #16            // SHLL2 <Vd>.4S, <Vn>.8H, #16  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHLLv4i32        | shll2	v2.2d, v29.4s, #32             // SHLL2 <Vd>.2D, <Vn>.4S, #32  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHRNv8i8_shift   | shrn	v27.8b, v23.8h, #3             // SHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHRNv4i16_shift  | shrn	v17.4h, v1.4s, #13             // SHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHRNv2i32_shift  | shrn	v13.2s, v0.2d, #12             // SHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHRNv16i8_shift  | shrn2	v4.16b, v29.8h, #8             // SHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHRNv8i16_shift  | shrn2	v9.8h, v18.4s, #10             // SHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SHRNv4i32_shift  | shrn2	v5.4s, v12.2d, #16             // SHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SHSUBv8i16       | shsub	v15.8h, v5.8h, v27.8h          // SHSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SLId             | sli	d7, d19, #53                   // SLI <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SLIv16i8_shift   | sli	v16.16b, v26.16b, #7           // SLI <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SLIv4i16_shift   | sli	v14.4h, v10.4h, #15            // SLI <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SLIv2i32_shift   | sli	v29.2s, v14.2s, #13            // SLI <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SLIv2i64_shift   | sli	v25.2d, v21.2d, #41            // SLI <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SMADDLrrr        | smaddl	x17, w27, w30, x3      // SMADDL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SMAX_ZI_S        | smax	z3.s, z3.s, #-39               // SMAX <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SMAX_ZPmZ_B      | smax	z0.b, p5/m, z0.b, z20.b        // SMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SMAXv16i8        | smax	v30.16b, v3.16b, v30.16b       // SMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SMAXPv8i16       | smaxp	v21.8h, v16.8h, v7.8h          // SMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SMAXVv8i8v       | smaxv	b4, v30.8b                     // SMAXV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | SMAXVv16i8v      | smaxv	b15, v16.16b                   // SMAXV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SMAXVv4i16v      | smaxv	h28, v14.4h                    // SMAXV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SMAXVv8i16v      | smaxv	h6, v19.8h                     // SMAXV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SMAXVv4i32v      | smaxv	s3, v14.4s                     // SMAXV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 14 | 14  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMAXV_VPZ_B      | smaxv	b19, p4, z14.b                 // SMAXV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMAXV_VPZ_H      | smaxv	h0, p6, z20.h                  // SMAXV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMAXV_VPZ_S      | smaxv	s11, p2, z28.s                 // SMAXV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 8  | 8   | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMAXV_VPZ_D      | smaxv	d24, p5, z24.d                 // SMAXV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SMC              | smc	#0x7e57                        // SMC #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SMIN_ZI_S        | smin	z21.s, z21.s, #59              // SMIN <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SMIN_ZPmZ_S      | smin	z22.s, p0/m, z22.s, z30.s      // SMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SMINv4i32        | smin	v29.4s, v24.4s, v24.4s         // SMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SMINPv8i16       | sminp	v7.8h, v27.8h, v7.8h           // SMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SMINVv8i8v       | sminv	b6, v11.8b                     // SMINV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | SMINVv16i8v      | sminv	b24, v8.16b                    // SMINV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SMINVv4i16v      | sminv	h24, v23.4h                    // SMINV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SMINVv8i16v      | sminv	h2, v9.8h                      // SMINV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SMINVv4i32v      | sminv	s16, v15.4s                    // SMINV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 14 | 14  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMINV_VPZ_B      | sminv	b4, p2, z10.b                  // SMINV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMINV_VPZ_H      | sminv	h15, p7, z10.h                 // SMINV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMINV_VPZ_S      | sminv	s29, p0, z27.s                 // SMINV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 8  | 8   | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | SMINV_VPZ_D      | sminv	d17, p2, z18.d                 // SMINV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLALv4i16_indexed | smlal	v16.4s, v9.4h, v11.h[4]  // SMLAL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLALv2i32_indexed | smlal	v0.2d, v25.2s, v1.s[1]  // SMLAL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLALv8i16_indexed | smlal2	v1.4s, v9.8h, v0.h[6]  // SMLAL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLALv4i32_indexed | smlal2	v30.2d, v22.4s, v7.s[2]  // SMLAL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLALv8i8_v8i16  | smlal	v25.8h, v24.8b, v28.8b         // SMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLALv8i16_v4i32 | smlal2	v30.4s, v31.8h, v13.8h  // SMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLSLv4i16_indexed | smlsl	v14.4s, v23.4h, v12.h[7]  // SMLSL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLSLv2i32_indexed | smlsl	v25.2d, v27.2s, v1.s[1]  // SMLSL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLSLv8i16_indexed | smlsl2	v12.4s, v11.8h, v12.h[0]  // SMLSL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLSLv4i32_indexed | smlsl2	v11.2d, v28.4s, v7.s[2]  // SMLSL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLSLv4i16_v4i32 | smlsl	v11.4s, v14.4h, v15.4h         // SMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | SMLSLv8i16_v4i32 | smlsl2	v21.4s, v27.8h, v16.8h  // SMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | SMMLA            | smmla	v0.4s, v17.16b, v31.16b        // SMMLA <Vd>.4S, <Vn>.16B, <Vm>.16B  \\ ASIMD matrix multiply-accumulate  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SMSUBLrrr        | smnegl	x3, w23, w18           // SMNEGL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi8to32_idx0 | smov	w15, v22.b[0]                  // SMOV <Wd>, <Vn>.B[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi8to32      | smov	w6, v28.b[9]                   // SMOV <Wd>, <Vn>.B[<indexb>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi16to32_idx0 | smov	w26, v27.h[0]                  // SMOV <Wd>, <Vn>.H[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi16to32     | smov	w18, v29.h[6]                  // SMOV <Wd>, <Vn>.H[<indexh>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi8to64_idx0 | smov	x21, v0.b[0]                   // SMOV <Xd>, <Vn>.B[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi8to64      | smov	x16, v29.b[8]                  // SMOV <Xd>, <Vn>.B[<indexb>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi16to64_idx0 | smov	x9, v27.h[0]                   // SMOV <Xd>, <Vn>.H[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi16to64     | smov	x4, v21.h[2]                   // SMOV <Xd>, <Vn>.H[<indexh>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi32to64_idx0 | smov	x15, v3.s[0]                   // SMOV <Xd>, <Vn>.S[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | SMOVvi32to64     | smov	x5, v29.s[1]                   // SMOV <Xd>, <Vn>.S[<indexs>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SMSUBLrrr        | smsubl	x8, w24, w13, x6       // SMSUBL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SMULH_ZPmZ_B     | smulh	z11.b, p5/m, z11.b, z17.b      // SMULH <Zdn>.B, <Pg>/M, <Zdn>.B, <Zm>.B  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SMULH_ZPmZ_H     | smulh	z8.h, p0/m, z8.h, z4.h         // SMULH <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | SMULH_ZPmZ_S     | smulh	z27.s, p7/m, z27.s, z30.s      // SMULH <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 5   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | SMULH_ZPmZ_D     | smulh	z4.d, p7/m, z4.d, z28.d        // SMULH <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitI, V1UnitM                                                 | SMULHrr          | smulh	x8, x29, x17                   // SMULH <Xd>, <Xn>, <Xm>  \\ Multiply high  \\ 1 3  3  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SMADDLrrr        | smull	x19, w0, w6                    // SMULL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SMULLv4i16_indexed | smull	v3.4s, v26.4h, v1.h[5]  // SMULL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SMULLv2i32_indexed | smull	v31.2d, v23.2s, v6.s[2]  // SMULL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SMULLv8i16_indexed | smull2	v13.4s, v18.8h, v0.h[3]  // SMULL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SMULLv4i32_indexed | smull2	v11.2d, v1.4s, v7.s[0]  // SMULL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SMULLv2i32_v2i64 | smull	v28.2d, v26.2s, v20.2s         // SMULL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SMULLv4i32_v2i64 | smull2	v7.2d, v14.4s, v15.4s  // SMULL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQABSv1i64       | sqabs	d15, d26                       // SQABS <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQABSv8i16       | sqabs	v25.8h, v24.8h                 // SQABS <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQADD_ZI_B       | sqadd	z1.b, z1.b, #164               // SQADD <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQADD_ZI_H       | sqadd	z18.h, z18.h, #166             // SQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQADD_ZI_D       | sqadd	z3.d, z3.d, #158               // SQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQADD_ZZZ_D      | sqadd	z19.d, z27.d, z28.d            // SQADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQADDv1i16       | sqadd	h12, h18, h10                  // SQADD <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQADDv2i32       | sqadd	v15.2s, v13.2s, v28.2s         // SQADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECB_XPiWdI    | sqdecb	x26, w26               // SQDECB <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECB_XPiWdI    | sqdecb	x16, w16, vl64         // SQDECB <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECB_XPiWdI    | sqdecb	x4, w4, vl1, mul #16   // SQDECB <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECB_XPiI      | sqdecb	x4                     // SQDECB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECB_XPiI      | sqdecb	x28, vl6               // SQDECB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECB_XPiI      | sqdecb	x20, vl7, mul #4       // SQDECB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECD_XPiWdI    | sqdecd	x1, w1                 // SQDECD <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECD_XPiWdI    | sqdecd	x11, w11, mul3         // SQDECD <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECD_XPiWdI    | sqdecd	x14, w14, vl2, mul #16  // SQDECD <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECD_XPiI      | sqdecd	x18                    // SQDECD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECD_XPiI      | sqdecd	x11, vl5               // SQDECD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECD_XPiI      | sqdecd	x21, all, mul #13      // SQDECD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECD_ZPiI      | sqdecd	z27.d                  // SQDECD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECD_ZPiI      | sqdecd	z2.d, vl128            // SQDECD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECD_ZPiI      | sqdecd	z23.d, vl1, mul #16    // SQDECD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECH_XPiWdI    | sqdech	x7, w7                 // SQDECH <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECH_XPiWdI    | sqdech	x10, w10, vl128        // SQDECH <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECH_XPiWdI    | sqdech	x16, w16, vl6, mul #11  // SQDECH <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECH_XPiI      | sqdech	x6                     // SQDECH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECH_XPiI      | sqdech	x17, vl128             // SQDECH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECH_XPiI      | sqdech	x27, vl128, mul #4     // SQDECH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECH_ZPiI      | sqdech	z16.h                  // SQDECH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECH_ZPiI      | sqdech	z21.h, vl6             // SQDECH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECH_ZPiI      | sqdech	z7.h, mul3, mul #7     // SQDECH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECP_XPWd_B    | sqdecp	x1, p4.b, w1           // SQDECP <Xdn>, <Pm>.<T>, <Wdn>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECP_XP_D      | sqdecp	x26, p6.d              // SQDECP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 7  | 7   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV01[2]    | SQDECP_ZP_D      | sqdecp	z10.d, p3.d            // SQDECP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECW_XPiWdI    | sqdecw	x13, w13               // SQDECW <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECW_XPiWdI    | sqdecw	x2, w2, pow2           // SQDECW <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECW_XPiWdI    | sqdecw	x26, w26, vl8, mul #10  // SQDECW <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECW_XPiI      | sqdecw	x10                    // SQDECW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECW_XPiI      | sqdecw	x17, vl128             // SQDECW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQDECW_XPiI      | sqdecw	x13, mul4, mul #3      // SQDECW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECW_ZPiI      | sqdecw	z7.s                   // SQDECW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECW_ZPiI      | sqdecw	z10.s, pow2            // SQDECW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQDECW_ZPiI      | sqdecw	z28.s, vl2, mul #15    // SQDECW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv1i32_indexed | sqdmlal	s23, h16, v4.h[7]      // SQDMLAL S<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv1i64_indexed | sqdmlal	d12, s18, v3.s[0]      // SQDMLAL D<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv4i16_indexed | sqdmlal	v20.4s, v30.4h, v12.h[3]  // SQDMLAL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv2i32_indexed | sqdmlal	v11.2d, v24.2s, v0.s[3]  // SQDMLAL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv8i16_indexed | sqdmlal2	v2.4s, v17.8h, v5.h[6]  // SQDMLAL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv4i32_indexed | sqdmlal2	v23.2d, v30.4s, v6.s[0]  // SQDMLAL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALi32       | sqdmlal	d16, s12, s15          // SQDMLAL <Va><d>, <Vb><n>, <Vb><m>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv4i16_v4i32 | sqdmlal	v8.4s, v24.4h, v31.4h  // SQDMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLALv8i16_v4i32 | sqdmlal2	v29.4s, v11.8h, v13.8h  // SQDMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv1i32_indexed | sqdmlsl	s26, h21, v11.h[1]     // SQDMLSL S<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv1i64_indexed | sqdmlsl	d6, s16, v3.s[1]       // SQDMLSL D<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv4i16_indexed | sqdmlsl	v4.4s, v22.4h, v13.h[2]  // SQDMLSL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv2i32_indexed | sqdmlsl	v26.2d, v7.2s, v3.s[0]  // SQDMLSL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv8i16_indexed | sqdmlsl2	v2.4s, v28.8h, v4.h[6]  // SQDMLSL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv4i32_indexed | sqdmlsl2	v4.2d, v3.4s, v3.s[2]  // SQDMLSL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLi32       | sqdmlsl	d13, s21, s8           // SQDMLSL <Va><d>, <Vb><n>, <Vb><m>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv4i16_v4i32 | sqdmlsl	v11.4s, v19.4h, v5.4h  // SQDMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMLSLv8i16_v4i32 | sqdmlsl2	v27.4s, v8.8h, v22.8h  // SQDMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate saturating long  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULHv1i16_indexed | sqdmulh	h14, h17, v6.h[6]      // SQDMULH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULHv1i32_indexed | sqdmulh	s19, s6, v6.s[3]       // SQDMULH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULHv4i16_indexed | sqdmulh	v8.4h, v16.4h, v5.h[4]  // SQDMULH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULHv2i32_indexed | sqdmulh	v16.2s, v24.2s, v7.s[2]  // SQDMULH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULHv1i16     | sqdmulh	h26, h21, h17          // SQDMULH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULHv2i32     | sqdmulh	v20.2s, v11.2s, v29.2s  // SQDMULH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv1i32_indexed | sqdmull	s25, h5, v1.h[3]       // SQDMULL S<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv1i64_indexed | sqdmull	d29, s23, v0.s[2]      // SQDMULL D<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv4i16_indexed | sqdmull	v8.4s, v19.4h, v1.h[2]  // SQDMULL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv2i32_indexed | sqdmull	v20.2d, v10.2s, v6.s[2]  // SQDMULL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv8i16_indexed | sqdmull2	v10.4s, v25.8h, v0.h[7]  // SQDMULL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv4i32_indexed | sqdmull2	v4.2d, v29.4s, v2.s[3]  // SQDMULL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLi32       | sqdmull	d19, s2, s0            // SQDMULL <Va><d>, <Vb><n>, <Vb><m>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv2i32_v2i64 | sqdmull	v14.2d, v23.2s, v13.2s  // SQDMULL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | SQDMULLv8i16_v4i32 | sqdmull2	v12.4s, v11.8h, v1.8h  // SQDMULL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCB_XPiWdI    | sqincb	x12, w12               // SQINCB <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCB_XPiWdI    | sqincb	x1, w1, vl8            // SQINCB <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCB_XPiWdI    | sqincb	x16, w16, vl2, mul #16  // SQINCB <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCB_XPiI      | sqincb	x5                     // SQINCB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCB_XPiI      | sqincb	x4, vl6                // SQINCB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCB_XPiI      | sqincb	x30, all, mul #7       // SQINCB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCD_XPiWdI    | sqincd	x28, w28               // SQINCD <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCD_XPiWdI    | sqincd	x16, w16, vl8          // SQINCD <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCD_XPiWdI    | sqincd	x22, w22, vl6, mul #16  // SQINCD <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCD_XPiI      | sqincd	x10                    // SQINCD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCD_XPiI      | sqincd	x17, vl5               // SQINCD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCD_XPiI      | sqincd	x13, vl64              // SQINCD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCD_ZPiI      | sqincd	z24.d                  // SQINCD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCD_ZPiI      | sqincd	z10.d, vl128           // SQINCD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCD_ZPiI      | sqincd	z29.d, vl128, mul #12  // SQINCD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCH_XPiWdI    | sqinch	x28, w28               // SQINCH <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCH_XPiWdI    | sqinch	x30, w30, vl1          // SQINCH <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCH_XPiWdI    | sqinch	x16, w16, vl4, mul #2  // SQINCH <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCH_XPiI      | sqinch	x23                    // SQINCH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCH_XPiI      | sqinch	x10, vl64              // SQINCH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCH_XPiI      | sqinch	x16, pow2, mul #2      // SQINCH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCH_ZPiI      | sqinch	z3.h                   // SQINCH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCH_ZPiI      | sqinch	z23.h, vl4             // SQINCH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCH_ZPiI      | sqinch	z6.h, vl128, mul #3    // SQINCH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCP_XPWd_H    | sqincp	x13, p2.h, w13         // SQINCP <Xdn>, <Pm>.<T>, <Wdn>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCP_XP_H      | sqincp	x0, p7.h               // SQINCP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 7  | 7   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV01[2]    | SQINCP_ZP_H      | sqincp	z9.h, p1.h             // SQINCP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCW_XPiWdI    | sqincw	x24, w24               // SQINCW <Xdn>, <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCW_XPiWdI    | sqincw	x16, w16, mul4         // SQINCW <Xdn>, <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCW_XPiWdI    | sqincw	x27, w27, vl32, mul #15  // SQINCW <Xdn>, <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCW_XPiI      | sqincw	x29                    // SQINCW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCW_XPiI      | sqincw	x25, vl7               // SQINCW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | SQINCW_XPiI      | sqincw	x21, vl8, mul #3       // SQINCW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCW_ZPiI      | sqincw	z30.s                  // SQINCW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCW_ZPiI      | sqincw	z8.s, mul3             // SQINCW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQINCW_ZPiI      | sqincw	z0.s, vl5, mul #9      // SQINCW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQNEGv1i64       | sqneg	d24, d22                       // SQNEG <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQNEGv16i8       | sqneg	v30.16b, v15.16b               // SQNEG <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLAHv1i16_indexed | sqrdmlah	h14, h4, v6.h[7]       // SQRDMLAH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLAHv1i32_indexed | sqrdmlah	s24, s17, v6.s[2]      // SQRDMLAH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLAHv4i16_indexed | sqrdmlah	v17.4h, v18.4h, v4.h[7]  // SQRDMLAH <Vd>.4H, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLAHv2i32_indexed | sqrdmlah	v10.2s, v17.2s, v3.s[3]  // SQRDMLAH <Vd>.2S, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLAHv1i32    | sqrdmlah	s3, s3, s5             // SQRDMLAH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLAHv8i16    | sqrdmlah	v16.8h, v30.8h, v28.8h  // SQRDMLAH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv1i16_indexed | sqrdmlsh	h13, h26, v4.h[2]      // SQRDMLSH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv1i32_indexed | sqrdmlsh	s26, s29, v7.s[0]      // SQRDMLSH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv8i16_indexed | sqrdmlsh	v1.8h, v21.8h, v8.h[1]  // SQRDMLSH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv4i16_indexed | sqrdmlsh	v8.4h, v11.4h, v1.h[3]  // SQRDMLSH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv2i32_indexed | sqrdmlsh	v20.2s, v29.2s, v4.s[3]  // SQRDMLSH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv4i32_indexed | sqrdmlsh	v21.4s, v9.4s, v1.s[0]  // SQRDMLSH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv1i32    | sqrdmlsh	s30, s20, s13          // SQRDMLSH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMLSHv4i16    | sqrdmlsh	v20.4h, v2.4h, v23.4h  // SQRDMLSH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply accumulate high  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMULHv1i16_indexed | sqrdmulh	h3, h25, v2.h[1]       // SQRDMULH H<d>, H<n>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMULHv1i32_indexed | sqrdmulh	s9, s24, v4.s[3]       // SQRDMULH S<d>, S<n>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMULHv8i16_indexed | sqrdmulh	v0.8h, v15.8h, v0.h[5]  // SQRDMULH <Vd>.<Th>, <Vn>.<Th>, <Vmh>.H[<indexh>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMULHv2i32_indexed | sqrdmulh	v6.2s, v29.2s, v4.s[2]  // SQRDMULH <Vd>.<Ts>, <Vn>.<Ts>, <Vms>.S[<indexs>]  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMULHv1i16    | sqrdmulh	h5, h2, h20            // SQRDMULH <V><d>, <V><n>, <V><m>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV02                                               | SQRDMULHv2i32    | sqrdmulh	v31.2s, v17.2s, v4.2s  // SQRDMULH <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD multiply  \\ 1 4  4  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHLv1i64      | sqrshl	d6, d1, d30            // SQRSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHLv8i8       | sqrshl	v15.8b, v26.8b, v21.8b  // SQRSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNb         | sqrshrn	b6, h24, #3            // SQRSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNh         | sqrshrn	h11, s22, #8           // SQRSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNs         | sqrshrn	s4, d9, #13            // SQRSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNv8i8_shift | sqrshrn	v31.8b, v31.8h, #2     // SQRSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNv4i16_shift | sqrshrn	v27.4h, v11.4s, #8     // SQRSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNv2i32_shift | sqrshrn	v4.2s, v30.2d, #10     // SQRSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNv16i8_shift | sqrshrn2	v11.16b, v30.8h, #7    // SQRSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNv8i16_shift | sqrshrn2	v14.8h, v3.4s, #12     // SQRSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRNv4i32_shift | sqrshrn2	v13.4s, v28.2d, #24    // SQRSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNb        | sqrshrun	b5, h0, #3             // SQRSHRUN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNh        | sqrshrun	h25, s11, #7           // SQRSHRUN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNs        | sqrshrun	s15, d18, #2           // SQRSHRUN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNv8i8_shift | sqrshrun	v0.8b, v3.8h, #7       // SQRSHRUN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNv4i16_shift | sqrshrun	v5.4h, v8.4s, #7       // SQRSHRUN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNv2i32_shift | sqrshrun	v7.2s, v8.2d, #13      // SQRSHRUN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNv16i8_shift | sqrshrun2	v14.16b, v14.8h, #3    // SQRSHRUN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNv8i16_shift | sqrshrun2	v9.8h, v16.4s, #10     // SQRSHRUN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQRSHRUNv4i32_shift | sqrshrun2	v12.4s, v23.2d, #30    // SQRSHRUN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLb           | sqshl	b15, b3, #4                    // SQSHL B<d>, B<n>, #<shiftb>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLh           | sqshl	h21, h0, #5                    // SQSHL H<d>, H<n>, #<shifth>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLs           | sqshl	s26, s9, #24                   // SQSHL S<d>, S<n>, #<shifts>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLd           | sqshl	d8, d23, #17                   // SQSHL D<d>, D<n>, #<shiftd>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLv16i8_shift | sqshl	v25.16b, v26.16b, #5           // SQSHL <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLv4i16_shift | sqshl	v29.4h, v1.4h, #7              // SQSHL <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLv2i32_shift | sqshl	v0.2s, v5.2s, #1               // SQSHL <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLv2i64_shift | sqshl	v11.2d, v2.2d, #23             // SQSHL <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLv1i32       | sqshl	s17, s4, s23                   // SQSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLv16i8       | sqshl	v23.16b, v23.16b, v23.16b      // SQSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUb          | sqshlu	b3, b27, #5            // SQSHLU B<d>, B<n>, #<shiftb>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUh          | sqshlu	h23, h4, #6            // SQSHLU H<d>, H<n>, #<shifth>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUs          | sqshlu	s29, s29, #30          // SQSHLU S<d>, S<n>, #<shifts>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUd          | sqshlu	d14, d5, #22           // SQSHLU D<d>, D<n>, #<shiftd>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUv8i8_shift | sqshlu	v11.8b, v17.8b, #6     // SQSHLU <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUv8i16_shift | sqshlu	v18.8h, v8.8h, #14     // SQSHLU <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUv4i32_shift | sqshlu	v25.4s, v7.4s, #13     // SQSHLU <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHLUv2i64_shift | sqshlu	v19.2d, v14.2d, #39    // SQSHLU <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNb          | sqshrn	b17, h30, #7           // SQSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNh          | sqshrn	h30, s15, #5           // SQSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNs          | sqshrn	s16, d0, #20           // SQSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNv8i8_shift | sqshrn	v3.8b, v25.8h, #1      // SQSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNv4i16_shift | sqshrn	v23.4h, v14.4s, #6     // SQSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNv2i32_shift | sqshrn	v6.2s, v29.2d, #10     // SQSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNv16i8_shift | sqshrn2	v31.16b, v31.8h, #8    // SQSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNv8i16_shift | sqshrn2	v13.8h, v6.4s, #13     // SQSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRNv4i32_shift | sqshrn2	v30.4s, v0.2d, #1      // SQSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNb         | sqshrun	b3, h16, #3            // SQSHRUN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNh         | sqshrun	h11, s10, #7           // SQSHRUN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNs         | sqshrun	s18, d1, #13           // SQSHRUN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNv8i8_shift | sqshrun	v21.8b, v27.8h, #5     // SQSHRUN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNv4i16_shift | sqshrun	v18.4h, v19.4s, #2     // SQSHRUN <Vd>.4H, <Vn>.4S, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNv2i32_shift | sqshrun	v2.2s, v14.2d, #3      // SQSHRUN <Vd>.2S, <Vn>.2D, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNv16i8_shift | sqshrun2	v10.16b, v28.8h, #5    // SQSHRUN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNv8i16_shift | sqshrun2	v4.8h, v28.4s, #12     // SQSHRUN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQSHRUNv4i32_shift | sqshrun2	v7.4s, v18.2d, #16     // SQSHRUN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQSUB_ZI_B       | sqsub	z13.b, z13.b, #114             // SQSUB <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQSUB_ZI_H       | sqsub	z28.h, z28.h, #139             // SQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQSUB_ZI_S       | sqsub	z11.s, z11.s, #14              // SQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SQSUB_ZZZ_S      | sqsub	z28.s, z9.s, z12.s             // SQSUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQSUBv1i8        | sqsub	b3, b13, b12                   // SQSUB <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SQSUBv8i16       | sqsub	v20.8h, v18.8h, v12.8h         // SQSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQXTNv1i8        | sqxtn	b11, h22                       // SQXTN <Vb><d>, <Va><n>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQXTNv2i32       | sqxtn	v3.2s, v17.2d                  // SQXTN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQXTNv8i16       | sqxtn2	v17.8h, v27.4s         // SQXTN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQXTUNv1i8       | sqxtun	b30, h18               // SQXTUN <Vb><d>, <Va><n>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQXTUNv8i8       | sqxtun	v26.8b, v21.8h         // SQXTUN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SQXTUNv16i8      | sqxtun2	v22.16b, v6.8h         // SQXTUN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SRHADDv8i8       | srhadd	v29.8b, v3.8b, v8.8b   // SRHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SRId             | sri	d30, d17, #61                  // SRI <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SRIv16i8_shift   | sri	v23.16b, v30.16b, #2           // SRI <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SRIv4i16_shift   | sri	v1.4h, v0.4h, #4               // SRI <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SRIv2i32_shift   | sri	v28.2s, v6.2s, #16             // SRI <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SRIv2i64_shift   | sri	v8.2d, v19.2d, #40             // SRI <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed and insert, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHLv1i64       | srshl	d30, d8, d8                    // SRSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHLv8i8        | srshl	v20.8b, v23.8b, v27.8b         // SRSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHRd           | srshr	d20, d18, #27                  // SRSHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHRv8i8_shift  | srshr	v20.8b, v0.8b, #7              // SRSHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHRv8i16_shift | srshr	v27.8h, v19.8h, #9             // SRSHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHRv2i32_shift | srshr	v8.2s, v20.2s, #31             // SRSHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | SRSHRv2i64_shift | srshr	v31.2d, v17.2d, #33            // SRSHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SRSRAd           | srsra	d13, d10, #25                  // SRSRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SRSRAv16i8_shift | srsra	v31.16b, v15.16b, #5           // SRSRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SRSRAv4i16_shift | srsra	v14.4h, v27.4h, #7             // SRSRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SRSRAv2i32_shift | srsra	v17.2s, v8.2s, #8              // SRSRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SRSRAv2i64_shift | srsra	v22.2d, v4.2d, #12             // SRSRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | DSB              | ssbb                                // SSBB  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLv1i64        | sshl	d29, d30, d9                   // SSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLv2i64        | sshl	v13.2d, v7.2d, v27.2d          // SSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv8i8_shift  | sshll	v9.8h, v2.8b, #0               // SSHLL <Vd>.8H, <Vn>.8B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv4i16_shift | sshll	v12.4s, v3.4h, #4              // SSHLL <Vd>.4S, <Vn>.4H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv2i32_shift | sshll	v17.2d, v6.2s, #22             // SSHLL <Vd>.2D, <Vn>.2S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv16i8_shift | sshll2	v28.8h, v12.16b, #7    // SSHLL2 <Vd>.8H, <Vn>.16B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv8i16_shift | sshll2	v29.4s, v22.8h, #7     // SSHLL2 <Vd>.4S, <Vn>.8H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv4i32_shift | sshll2	v17.2d, v13.4s, #22    // SSHLL2 <Vd>.2D, <Vn>.4S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHRd            | sshr	d3, d18, #10                   // SSHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHRv8i8_shift   | sshr	v20.8b, v28.8b, #2             // SSHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHRv4i16_shift  | sshr	v20.4h, v23.4h, #10            // SSHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHRv2i32_shift  | sshr	v13.2s, v23.2s, #2             // SSHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHRv2i64_shift  | sshr	v3.2d, v8.2d, #61              // SSHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SSRAd            | ssra	d28, d30, #51                  // SSRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SSRAv8i8_shift   | ssra	v9.8b, v18.8b, #2              // SSRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SSRAv4i16_shift  | ssra	v21.4h, v24.4h, #3             // SSRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SSRAv2i32_shift  | ssra	v28.2s, v17.2s, #6             // SSRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | SSRAv2i64_shift  | ssra	v0.2d, v23.2d, #35             // SSRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SSUBLv4i16_v4i32 | ssubl	v13.4s, v9.4h, v5.4h           // SSUBL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SSUBLv8i16_v4i32 | ssubl2	v18.4s, v29.8h, v17.8h  // SSUBL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SSUBWv2i32_v2i64 | ssubw	v5.2d, v13.2d, v4.2s           // SSUBW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SSUBWv8i16_v4i32 | ssubw2	v4.4s, v26.4s, v31.8h  // SSUBW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev8b        | st1	{ v18.8b }, [x15]              // ST1 { <Vt>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev16b       | st1	{ v31.16b }, [x29]             // ST1 { <Vt>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev4h        | st1	{ v19.4h }, [x7]               // ST1 { <Vt>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev8h        | st1	{ v27.8h }, [x17]              // ST1 { <Vt>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev2s        | st1	{ v25.2s }, [x6]               // ST1 { <Vt>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev4s        | st1	{ v22.4s }, [x19]              // ST1 { <Vt>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev1d        | st1	{ v20.1d }, [x10]              // ST1 { <Vt>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Onev2d        | st1	{ v8.2d }, [x15]               // ST1 { <Vt>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev8b_POST   | st1	{ v16.8b }, [x14], #8          // ST1 { <Vt>.8B }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev16b_POST  | st1	{ v10.16b }, [x8], #16         // ST1 { <Vt>.16B }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev4h_POST   | st1	{ v29.4h }, [x17], #8          // ST1 { <Vt>.4H }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev8h_POST   | st1	{ v14.8h }, [x28], #16         // ST1 { <Vt>.8H }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev2s_POST   | st1	{ v18.2s }, [x20], #8          // ST1 { <Vt>.2S }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev4s_POST   | st1	{ v28.4s }, [x1], #16          // ST1 { <Vt>.4S }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev1d_POST   | st1	{ v17.1d }, [x27], #8          // ST1 { <Vt>.1D }, [<Xn|SP>], #8  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev2d_POST   | st1	{ v30.2d }, [x4], #16          // ST1 { <Vt>.2D }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev8b_POST   | st1	{ v13.8b }, [x8], x7           // ST1 { <Vt>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev16b_POST  | st1	{ v4.16b }, [x7], x26          // ST1 { <Vt>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev4h_POST   | st1	{ v17.4h }, [x10], x4          // ST1 { <Vt>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev8h_POST   | st1	{ v18.8h }, [x15], x1          // ST1 { <Vt>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev2s_POST   | st1	{ v6.2s }, [x17], x24          // ST1 { <Vt>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev4s_POST   | st1	{ v26.4s }, [x20], x29         // ST1 { <Vt>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev1d_POST   | st1	{ v13.1d }, [x3], x20          // ST1 { <Vt>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Onev2d_POST   | st1	{ v15.2d }, [x21], x11         // ST1 { <Vt>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 1 reg, Q-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Twov8b        | st1	{ v8.8b, v9.8b }, [x18]        // ST1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Twov16b       | st1	{ v1.16b, v2.16b }, [x4]       // ST1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Twov4h        | st1	{ v22.4h, v23.4h }, [x22]      // ST1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Twov8h        | st1	{ v18.8h, v19.8h }, [x2]       // ST1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Twov2s        | st1	{ v13.2s, v14.2s }, [x9]       // ST1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Twov4s        | st1	{ v15.4s, v16.4s }, [x12]      // ST1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1Twov1d        | st1	{ v21.1d, v22.1d }, [x29]      // ST1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Twov2d        | st1	{ v26.2d, v27.2d }, [x28]      // ST1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov8b_POST   | st1	{ v23.8b, v24.8b }, [x4], #16  // ST1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov16b_POST  | st1	{ v15.16b, v16.16b }, [x16], #32  // ST1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov4h_POST   | st1	{ v7.4h, v8.4h }, [x7], #16    // ST1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov8h_POST   | st1	{ v8.8h, v9.8h }, [x1], #32    // ST1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov2s_POST   | st1	{ v23.2s, v24.2s }, [x7], #16  // ST1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov4s_POST   | st1	{ v8.4s, v9.4s }, [x15], #32   // ST1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov1d_POST   | st1	{ v14.1d, v15.1d }, [x11], #16  // ST1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], #16  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov2d_POST   | st1	{ v12.2d, v13.2d }, [x2], #32  // ST1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov8b_POST   | st1	{ v3.8b, v4.8b }, [x28], x14   // ST1 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov16b_POST  | st1	{ v19.16b, v20.16b }, [x13], x7  // ST1 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov4h_POST   | st1	{ v28.4h, v29.4h }, [x14], x5  // ST1 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov8h_POST   | st1	{ v9.8h, v10.8h }, [x28], x9   // ST1 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov2s_POST   | st1	{ v10.2s, v11.2s }, [x10], x2  // ST1 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov4s_POST   | st1	{ v13.4s, v14.4s }, [x8], x15  // ST1 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1Twov1d_POST   | st1	{ v5.1d, v6.1d }, [x9], x14    // ST1 { <Vt>.1D, <Vt2>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, D-form  \\ 3 2  2  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Twov2d_POST   | st1	{ v14.2d, v15.2d }, [x24], x1  // ST1 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 2 reg, Q-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Threev8b      | st1	{ v15.8b, v16.8b, v17.8b }, [x0]  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST1Threev16b     | st1	{ v27.16b, v28.16b, v29.16b }, [x18]  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Threev4h      | st1	{ v13.4h, v14.4h, v15.4h }, [x7]  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST1Threev8h      | st1	{ v8.8h, v9.8h, v10.8h }, [x16]  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Threev2s      | st1	{ v12.2s, v13.2s, v14.2s }, [x3]  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST1Threev4s      | st1	{ v19.4s, v20.4s, v21.4s }, [x7]  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Threev1d      | st1	{ v5.1d, v6.1d, v7.1d }, [x3]  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST1Threev2d      | st1	{ v13.2d, v14.2d, v15.2d }, [x27]  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 2 2  2  0.67 V1UnitL01[3],V1UnitV01[3]
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev8b_POST | st1	{ v3.8b, v4.8b, v5.8b }, [x21], #24  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev16b_POST | st1	{ v25.16b, v26.16b, v27.16b }, [x4], #48  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev4h_POST | st1	{ v24.4h, v25.4h, v26.4h }, [x9], #24  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev8h_POST | st1	{ v0.8h, v1.8h, v2.8h }, [x7], #48  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev2s_POST | st1	{ v3.2s, v4.2s, v5.2s }, [x4], #24  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev4s_POST | st1	{ v25.4s, v26.4s, v27.4s }, [x14], #48  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev1d_POST | st1	{ v7.1d, v8.1d, v9.1d }, [x13], #24  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], #24  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev2d_POST | st1	{ v19.2d, v20.2d, v21.2d }, [x5], #48  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev8b_POST | st1	{ v5.8b, v6.8b, v7.8b }, [x17], x25  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev16b_POST | st1	{ v12.16b, v13.16b, v14.16b }, [x29], x23  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev4h_POST | st1	{ v18.4h, v19.4h, v20.4h }, [x0], x14  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev8h_POST | st1	{ v16.8h, v17.8h, v18.8h }, [x1], x18  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev2s_POST | st1	{ v1.2s, v2.2s, v3.2s }, [x15], x29  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev4s_POST | st1	{ v2.4s, v3.4s, v4.4s }, [x29], x6  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Threev1d_POST | st1	{ v8.1d, v9.1d, v10.1d }, [x13], x27  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST1Threev2d_POST | st1	{ v8.2d, v9.2d, v10.2d }, [x18], x19  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 3 reg, Q-form  \\ 3 2  2  0.67 V1UnitL01[3],V1UnitV01[3],V1UnitI
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Fourv8b       | st1	{ v21.8b, v22.8b, v23.8b, v24.8b }, [x14]  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]               | ST1Fourv16b      | st1	{ v18.16b, v19.16b, v20.16b, v21.16b }, [x29]  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Fourv4h       | st1	{ v23.4h, v24.4h, v25.4h, v26.4h }, [x24]  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]               | ST1Fourv8h       | st1	{ v7.8h, v8.8h, v9.8h, v10.8h }, [x19]  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Fourv2s       | st1	{ v6.2s, v7.2s, v8.2s, v9.2s }, [x13]  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]               | ST1Fourv4s       | st1	{ v26.4s, v27.4s, v28.4s, v29.4s }, [x12]  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+# CHECK-NEXT:   2    | 2  | 2   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST1Fourv1d       | st1	{ v0.1d, v1.1d, v2.1d, v3.1d }, [x10]  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 2 2  2  1.0 V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]               | ST1Fourv2d       | st1	{ v25.2d, v26.2d, v27.2d, v28.2d }, [x19]  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 2 2  2  0.5 V1UnitL01[4],V1UnitV01[4]
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv8b_POST  | st1	{ v27.8b, v28.8b, v29.8b, v30.8b }, [x17], #32  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv16b_POST | st1	{ v26.16b, v27.16b, v28.16b, v29.16b }, [x0], #64  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv4h_POST  | st1	{ v18.4h, v19.4h, v20.4h, v21.4h }, [x22], #32  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv8h_POST  | st1	{ v12.8h, v13.8h, v14.8h, v15.8h }, [x13], #64  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv2s_POST  | st1	{ v13.2s, v14.2s, v15.2s, v16.2s }, [x25], #32  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv4s_POST  | st1	{ v4.4s, v5.4s, v6.4s, v7.4s }, [x11], #64  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv1d_POST  | st1	{ v7.1d, v8.1d, v9.1d, v10.1d }, [x13], #32  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], #32  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv2d_POST  | st1	{ v12.2d, v13.2d, v14.2d, v15.2d }, [x25], #64  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv8b_POST  | st1	{ v21.8b, v22.8b, v23.8b, v24.8b }, [x25], x28  // ST1 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv16b_POST | st1	{ v26.16b, v27.16b, v28.16b, v29.16b }, [x24], x5  // ST1 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv4h_POST  | st1	{ v20.4h, v21.4h, v22.4h, v23.4h }, [x25], x19  // ST1 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv8h_POST  | st1	{ v20.8h, v21.8h, v22.8h, v23.8h }, [x18], x0  // ST1 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv2s_POST  | st1	{ v4.2s, v5.2s, v6.2s, v7.2s }, [x9], x5  // ST1 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv4s_POST  | st1	{ v7.4s, v8.4s, v9.4s, v10.4s }, [x12], x30  // ST1 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST1Fourv1d_POST  | st1	{ v23.1d, v24.1d, v25.1d, v26.1d }, [x23], x4  // ST1 { <Vt>.1D, <Vt2>.1D, <Vt3>.1D, <Vt4>.1D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, D-form  \\ 3 2  2  1.0 V1UnitL01[2],V1UnitV01[2],V1UnitI
+# CHECK-NEXT:   3    | 2  | 2   | 0.50   | V1UnitI, V1UnitL[4], V1UnitL01[4], V1UnitV[4], V1UnitV01[4]      | ST1Fourv2d_POST  | st1	{ v20.2d, v21.2d, v22.2d, v23.2d }, [x7], x14  // ST1 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, multiple, 4 reg, Q-form  \\ 3 2  2  0.5 V1UnitL01[4],V1UnitV01[4],V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1i8            | st1	{ v1.b }[5], [x1]              // ST1 { <Vt>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1i16           | st1	{ v0.h }[2], [x1]              // ST1 { <Vt>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1i32           | st1	{ v31.s }[1], [x16]            // ST1 { <Vt>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST1i64           | st1	{ v15.d }[1], [x8]             // ST1 { <Vt>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 1 element, one lane, D  \\ 2 4  4  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i8_POST       | st1	{ v15.b }[1], [x12], #1        // ST1 { <Vt>.B }[<indexb>], [<Xn|SP>], #1  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i8_POST       | st1	{ v16.b }[3], [x0], x2         // ST1 { <Vt>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i16_POST      | st1	{ v29.h }[2], [x27], #2        // ST1 { <Vt>.H }[<indexh>], [<Xn|SP>], #2  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i16_POST      | st1	{ v15.h }[4], [x30], x9        // ST1 { <Vt>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i32_POST      | st1	{ v3.s }[1], [x24], #4         // ST1 { <Vt>.S }[<indexs>], [<Xn|SP>], #4  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i32_POST      | st1	{ v26.s }[0], [x2], x30        // ST1 { <Vt>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i64_POST      | st1	{ v19.d }[1], [x9], #8         // ST1 { <Vt>.D }[<indexd>], [<Xn|SP>], #8  \\ ASIMD store, 1 element, one lane, D  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST1i64_POST      | st1	{ v29.d }[0], [x26], x22       // ST1 { <Vt>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 1 element, one lane, D  \\ 3 4  4  2.0 V1UnitL01,V1UnitV01,V1UnitI
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | ST1B_H_IMM       | st1b	{ z7.h }, p2, [x14]            // ST1B { <Zt>.<T> }, <Pg>, [<Xn|SP>]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | ST1B_S_IMM       | st1b	{ z16.s }, p4, [x20, #3, mul vl]  // ST1B { <Zt>.<T> }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | ST1B_S           | st1b	{ z17.s }, p3, [x20, x0]       // ST1B { <Zt>.<T> }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1B_D_UXTW     | st1b	{ z0.d }, p4, [x11, z13.d, uxtw]  // ST1B { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1B_S_SXTW     | st1b	{ z16.s }, p4, [x19, z25.s, sxtw]  // ST1B { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ Scatter store, 32-bit unscaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1B_D          | st1b	{ z10.d }, p3, [x12, z21.d]    // ST1B { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1B_S_IMM      | st1b	{ z17.s }, p7, [z28.s]         // ST1B { <Zt>.S }, <Pg>, [<Zn>.S]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1B_S_IMM      | st1b	{ z16.s }, p0, [z25.s, #7]     // ST1B { <Zt>.S }, <Pg>, [<Zn>.S, #<imm>]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1B_D_IMM      | st1b	{ z15.d }, p6, [z27.d]         // ST1B { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1B_D_IMM      | st1b	{ z2.d }, p0, [z21.d, #24]     // ST1B { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1D_SXTW_SCALED | st1d	{ z10.d }, p2, [x26, z5.d, sxtw #3]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #3]  \\ Scatter store, 32-bit unpacked scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1D_UXTW       | st1d	{ z18.d }, p2, [x7, z1.d, uxtw]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1D_SCALED     | st1d	{ z9.d }, p6, [x6, z12.d, lsl #3]  // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, LSL #3]  \\ Scatter store, 64-bit scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1D            | st1d	{ z3.d }, p3, [x1, z30.d]      // ST1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1D_IMM        | st1d	{ z18.d }, p0, [z7.d]          // ST1D { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1D_IMM        | st1d	{ z4.d }, p2, [z2.d, #136]     // ST1D { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | ST1H_S_IMM       | st1h	{ z28.s }, p3, [x18]           // ST1H { <Zt>.<T> }, <Pg>, [<Xn|SP>]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | ST1H_IMM         | st1h	{ z23.h }, p1, [x14, #-8, mul vl]  // ST1H { <Zt>.<T> }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store, scalar + imm  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS, V1UnitV                    | ST1H_S           | st1h	{ z25.s }, p3, [x17, x8, lsl #1]  // ST1H { <Zt>.<T> }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store, scalar + scalar   \\ 3 2  2  2.0 V1UnitL01,V1UnitS,V1UnitV
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1H_S_SXTW_SCALED | st1h	{ z12.s }, p3, [x24, z30.s, sxtw #1]  // ST1H { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #1]  \\ Scatter store, 32-bit scaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1H_D_UXTW_SCALED | st1h	{ z26.d }, p5, [x9, z17.d, uxtw #1]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #1]  \\ Scatter store, 32-bit unpacked scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1H_D_SXTW     | st1h	{ z23.d }, p1, [x5, z25.d, sxtw]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1H_S_SXTW     | st1h	{ z14.s }, p4, [x22, z17.s, sxtw]  // ST1H { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ Scatter store, 32-bit unscaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1H_D_SCALED   | st1h	{ z23.d }, p3, [x25, z11.d, lsl #1]  // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, LSL #1]  \\ Scatter store, 64-bit scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1H_D          | st1h	{ z0.d }, p4, [x21, z21.d]     // ST1H { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1H_S_IMM      | st1h	{ z29.s }, p5, [z9.s]          // ST1H { <Zt>.S }, <Pg>, [<Zn>.S]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1H_S_IMM      | st1h	{ z4.s }, p7, [z23.s, #40]     // ST1H { <Zt>.S }, <Pg>, [<Zn>.S, #<imm>]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1H_D_IMM      | st1h	{ z27.d }, p2, [z3.d]          // ST1H { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1H_D_IMM      | st1h	{ z11.d }, p6, [z7.d, #38]     // ST1H { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1W_SXTW_SCALED | st1w	{ z25.s }, p1, [x9, z28.s, sxtw #2]  // ST1W { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod> #2]  \\ Scatter store, 32-bit scaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1W_D_SXTW_SCALED | st1w	{ z13.d }, p3, [x16, z9.d, sxtw #2]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod> #2]  \\ Scatter store, 32-bit unpacked scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1W_D_SXTW     | st1w	{ z21.d }, p1, [x24, z23.d, sxtw]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, <mod>]  \\ Scatter store, 32-bit unpacked unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1W_UXTW       | st1w	{ z17.s }, p1, [x5, z22.s, uxtw]  // ST1W { <Zt>.S }, <Pg>, [<Xn|SP>, <Zm>.S, <mod>]  \\ Scatter store, 32-bit unscaled offset  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1W_D_SCALED   | st1w	{ z28.d }, p1, [x5, z8.d, lsl #2]  // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D, LSL #2]  \\ Scatter store, 64-bit scaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1W_D          | st1w	{ z26.d }, p3, [x3, z0.d]      // ST1W { <Zt>.D }, <Pg>, [<Xn|SP>, <Zm>.D]  \\ Scatter store, 64-bit unscaled offset  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1W_IMM        | st1w	{ z28.s }, p6, [z21.s]         // ST1W { <Zt>.S }, <Pg>, [<Zn>.S]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 10 | 10  | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8]                             | SST1W_IMM        | st1w	{ z26.s }, p3, [z24.s, #120]   // ST1W { <Zt>.S }, <Pg>, [<Zn>.S, #<imm>]  \\ Scatter store vector + imm 32-bit element size  \\ 2 10  10  0.25 V1UnitL01[8],V1UnitV[8]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1W_D_IMM      | st1w	{ z3.d }, p0, [z12.d]          // ST1W { <Zt>.D }, <Pg>, [<Zn>.D]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 6  | 6   | 0.50   | V1UnitL[4], V1UnitL01[4], V1UnitV[4]                             | SST1W_D_IMM      | st1w	{ z17.d }, p2, [z1.d, #80]     // ST1W { <Zt>.D }, <Pg>, [<Zn>.D, #<imm>]  \\ Scatter store vector + imm 64-bit element size  \\ 2 6  6  0.5 V1UnitL01[4],V1UnitV[4]
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2Twov8b        | st2	{ v14.8b, v15.8b }, [x2]       // ST2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST2Twov16b       | st2	{ v6.16b, v7.16b }, [x23]      // ST2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2Twov4h        | st2	{ v10.4h, v11.4h }, [x18]      // ST2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST2Twov8h        | st2	{ v10.8h, v11.8h }, [x18]      // ST2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2Twov2s        | st2	{ v25.2s, v26.2s }, [x29]      // ST2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST2Twov4s        | st2	{ v26.4s, v27.4s }, [x14]      // ST2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST2Twov2d        | st2	{ v10.2d, v11.2d }, [x1]       // ST2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>]  \\ ASIMD store, 2 element, multiple, Q-form, D  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2Twov8b_POST   | st2	{ v21.8b, v22.8b }, [x22], #16  // ST2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], #16  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov16b_POST  | st2	{ v26.16b, v27.16b }, [x2], #32  // ST2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2Twov4h_POST   | st2	{ v19.4h, v20.4h }, [x27], #16  // ST2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], #16  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov8h_POST   | st2	{ v28.8h, v29.8h }, [x22], #32  // ST2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2Twov2s_POST   | st2	{ v1.2s, v2.2s }, [x26], #16   // ST2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], #16  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov4s_POST   | st2	{ v19.4s, v20.4s }, [x7], #32  // ST2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov2d_POST   | st2	{ v22.2d, v23.2d }, [x18], #32  // ST2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], #32  \\ ASIMD store, 2 element, multiple, Q-form, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2Twov8b_POST   | st2	{ v29.8b, v30.8b }, [x9], x2   // ST2 { <Vt>.8B, <Vt2>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov16b_POST  | st2	{ v17.16b, v18.16b }, [x4], x0  // ST2 { <Vt>.16B, <Vt2>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2Twov4h_POST   | st2	{ v9.4h, v10.4h }, [x7], x25   // ST2 { <Vt>.4H, <Vt2>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov8h_POST   | st2	{ v8.8h, v9.8h }, [x11], x8    // ST2 { <Vt>.8H, <Vt2>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2Twov2s_POST   | st2	{ v17.2s, v18.2s }, [x2], x8   // ST2 { <Vt>.2S, <Vt2>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, D-form, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov4s_POST   | st2	{ v9.4s, v10.4s }, [x23], x12  // ST2 { <Vt>.4S, <Vt2>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST2Twov2d_POST   | st2	{ v29.2d, v30.2d }, [x25], x11  // ST2 { <Vt>.2D, <Vt2>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, multiple, Q-form, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2i8            | st2	{ v21.b, v22.b }[15], [x15]    // ST2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2i16           | st2	{ v28.h, v29.h }[2], [x6]      // ST2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2i32           | st2	{ v14.s, v15.s }[1], [x25]     // ST2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   2    | 4  | 4   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | ST2i64           | st2	{ v17.d, v18.d }[1], [x1]      // ST2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 2 element, one lane, D  \\ 2 4  4  2.0 V1UnitV01,V1UnitL01
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i8_POST       | st2	{ v9.b, v10.b }[15], [x12], #2  // ST2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], #2  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i8_POST       | st2	{ v19.b, v20.b }[9], [x27], x28  // ST2 { <Vt>.B, <Vt2>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i16_POST      | st2	{ v18.h, v19.h }[3], [x30], #4  // ST2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], #4  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i16_POST      | st2	{ v13.h, v14.h }[5], [x23], x24  // ST2 { <Vt>.H, <Vt2>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i32_POST      | st2	{ v23.s, v24.s }[1], [x22], #8  // ST2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], #8  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i32_POST      | st2	{ v16.s, v17.s }[3], [x12], x16  // ST2 { <Vt>.S, <Vt2>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, B/H/S  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i64_POST      | st2	{ v27.d, v28.d }[0], [x16], #16  // ST2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], #16  \\ ASIMD store, 2 element, one lane, D  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | ST2i64_POST      | st2	{ v6.d, v7.d }[1], [x14], x5   // ST2 { <Vt>.D, <Vt2>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 2 element, one lane, D  \\ 3 4  4  2.0 V1UnitV01,V1UnitL01,V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2B_IMM         | st2b	{ z19.b, z20.b }, p1, [x18]    // ST2B { <Zt1>.B, <Zt2>.B }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2B_IMM         | st2b	{ z26.b, z27.b }, p7, [x15, #-6, mul vl]  // ST2B { <Zt1>.B, <Zt2>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2B             | st2b	{ z19.b, z20.b }, p1, [x23, x27]  // ST2B { <Zt1>.B, <Zt2>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2D_IMM         | st2d	{ z29.d, z30.d }, p4, [x8]     // ST2D { <Zt1>.D, <Zt2>.D }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2D_IMM         | st2d	{ z16.d, z17.d }, p3, [x20, #14, mul vl]  // ST2D { <Zt1>.D, <Zt2>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2D             | st2d	{ z17.d, z18.d }, p7, [x2, x28, lsl #3]  // ST2D { <Zt1>.D, <Zt2>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2H_IMM         | st2h	{ z5.h, z6.h }, p7, [x23]      // ST2H { <Zt1>.H, <Zt2>.H }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2H_IMM         | st2h	{ z11.h, z12.h }, p6, [x4, #10, mul vl]  // ST2H { <Zt1>.H, <Zt2>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI[2], V1UnitL[2], V1UnitL01[2], V1UnitS[2], V1UnitV[2]     | ST2H             | st2h	{ z3.h, z4.h }, p3, [x22, x16, lsl #1]  // ST2H { <Zt1>.H, <Zt2>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 3 4  4  1.0 V1UnitL01[2],V1UnitS[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2W_IMM         | st2w	{ z14.s, z15.s }, p4, [x17]    // ST2W { <Zt1>.S, <Zt2>.S }, <Pg>, [<Xn|SP>]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2W_IMM         | st2w	{ z9.s, z10.s }, p5, [x19, #-8, mul vl]  // ST2W { <Zt1>.S, <Zt2>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store two structures from two vectors, scalar + imm  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2]                             | ST2W             | st2w	{ z5.s, z6.s }, p3, [x23, x13, lsl #2]  // ST2W { <Zt1>.S, <Zt2>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous store two structures from two vectors, scalar + scalar  \\ 2 4  4  1.0 V1UnitL01[2],V1UnitV[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3Threev8b      | st3	{ v10.8b, v11.8b, v12.8b }, [x18]  // ST3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 5  | 5   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST3Threev16b     | st3	{ v26.16b, v27.16b, v28.16b }, [x4]  // ST3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3Threev4h      | st3	{ v25.4h, v26.4h, v27.4h }, [x11]  // ST3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 5  | 5   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST3Threev8h      | st3	{ v0.8h, v1.8h, v2.8h }, [x0]  // ST3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3Threev2s      | st3	{ v19.2s, v20.2s, v21.2s }, [x30]  // ST3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 5  | 5   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST3Threev4s      | st3	{ v24.4s, v25.4s, v26.4s }, [x8]  // ST3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+# CHECK-NEXT:   2    | 5  | 5   | 0.67   | V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]               | ST3Threev2d      | st3	{ v24.2d, v25.2d, v26.2d }, [x25]  // ST3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>]  \\ ASIMD store, 3 element, multiple, Q-form, D  \\ 2 5  5  0.67 V1UnitV01[3],V1UnitL01[3]
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3Threev8b_POST | st3	{ v25.8b, v26.8b, v27.8b }, [x23], #24  // ST3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], #24  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev16b_POST | st3	{ v9.16b, v10.16b, v11.16b }, [x26], #48  // ST3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3Threev4h_POST | st3	{ v24.4h, v25.4h, v26.4h }, [x3], #24  // ST3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], #24  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev8h_POST | st3	{ v23.8h, v24.8h, v25.8h }, [x22], #48  // ST3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3Threev2s_POST | st3	{ v7.2s, v8.2s, v9.2s }, [x8], #24  // ST3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], #24  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev4s_POST | st3	{ v11.4s, v12.4s, v13.4s }, [x15], #48  // ST3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev2d_POST | st3	{ v1.2d, v2.2d, v3.2d }, [x4], #48  // ST3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], #48  \\ ASIMD store, 3 element, multiple, Q-form, D  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3Threev8b_POST | st3	{ v16.8b, v17.8b, v18.8b }, [x26], x2  // ST3 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev16b_POST | st3	{ v9.16b, v10.16b, v11.16b }, [x3], x18  // ST3 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3Threev4h_POST | st3	{ v2.4h, v3.4h, v4.4h }, [x4], x4  // ST3 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev8h_POST | st3	{ v27.8h, v28.8h, v29.8h }, [x27], x8  // ST3 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3Threev2s_POST | st3	{ v26.2s, v27.2s, v28.2s }, [x2], x25  // ST3 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, D-form, B/H/S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev4s_POST | st3	{ v5.4s, v6.4s, v7.4s }, [x18], x29  // ST3 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, B/H/S  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   3    | 5  | 5   | 0.67   | V1UnitI, V1UnitL[3], V1UnitL01[3], V1UnitV[3], V1UnitV01[3]      | ST3Threev2d_POST | st3	{ v26.2d, v27.2d, v28.2d }, [x14], x5  // ST3 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, multiple, Q-form, D  \\ 3 5  5  0.67 V1UnitV01[3],V1UnitL01[3],V1UnitI
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3i8            | st3	{ v8.b, v9.b, v10.b }[4], [x18]  // ST3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, B/H  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3i16           | st3	{ v11.h, v12.h, v13.h }[4], [x0]  // ST3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, B/H  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3i32           | st3	{ v9.s, v10.s, v11.s }[2], [x20]  // ST3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, S  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST3i64           | st3	{ v16.d, v17.d, v18.d }[0], [x13]  // ST3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 3 element, one lane, D  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i8_POST       | st3	{ v26.b, v27.b, v28.b }[1], [x12], #3  // ST3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], #3  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i8_POST       | st3	{ v27.b, v28.b, v29.b }[15], [x19], x23  // ST3 { <Vt>.B, <Vt2>.B, <Vt3>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i16_POST      | st3	{ v24.h, v25.h, v26.h }[2], [x14], #6  // ST3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], #6  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i16_POST      | st3	{ v1.h, v2.h, v3.h }[2], [x0], x23  // ST3 { <Vt>.H, <Vt2>.H, <Vt3>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, B/H  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i32_POST      | st3	{ v25.s, v26.s, v27.s }[2], [x10], #12  // ST3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], #12  \\ ASIMD store, 3 element, one lane, S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i32_POST      | st3	{ v8.s, v9.s, v10.s }[0], [x11], x20  // ST3 { <Vt>.S, <Vt2>.S, <Vt3>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, S  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i64_POST      | st3	{ v19.d, v20.d, v21.d }[1], [x5], #24  // ST3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], #24  \\ ASIMD store, 3 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST3i64_POST      | st3	{ v10.d, v11.d, v12.d }[0], [x12], x11  // ST3 { <Vt>.D, <Vt2>.D, <Vt3>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 3 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3B_IMM         | st3b	{ z0.b - z2.b }, p6, [x26]     // ST3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3B_IMM         | st3b	{ z22.b - z24.b }, p6, [x25, #3, mul vl]  // ST3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   3    | 7  | 7   | 0.22   | V1UnitI[9], V1UnitL[9], V1UnitL01[9], V1UnitS[9], V1UnitV[9]     | ST3B             | st3b	{ z14.b - z16.b }, p2, [x29, x27]  // ST3B { <Zt1>.B, <Zt2>.B, <Zt3>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3D_IMM         | st3d	{ z6.d - z8.d }, p2, [x12]     // ST3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3D_IMM         | st3d	{ z20.d - z22.d }, p5, [x15, #9, mul vl]  // ST3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   3    | 7  | 7   | 0.22   | V1UnitI[9], V1UnitL[9], V1UnitL01[9], V1UnitS[9], V1UnitV[9]     | ST3D             | st3d	{ z15.d - z17.d }, p7, [x0, x9, lsl #3]  // ST3D { <Zt1>.D, <Zt2>.D, <Zt3>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3H_IMM         | st3h	{ z17.h - z19.h }, p3, [x14]   // ST3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3H_IMM         | st3h	{ z21.h - z23.h }, p0, [x15, #6, mul vl]  // ST3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   3    | 7  | 7   | 0.22   | V1UnitI[9], V1UnitL[9], V1UnitL01[9], V1UnitS[9], V1UnitV[9]     | ST3H             | st3h	{ z2.h - z4.h }, p3, [x21, x9, lsl #1]  // ST3H { <Zt1>.H, <Zt2>.H, <Zt3>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3W_IMM         | st3w	{ z9.s - z11.s }, p3, [x29]    // ST3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>, [<Xn|SP>]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 7  | 7   | 0.22   | V1UnitL[9], V1UnitL01[9], V1UnitV[9]                             | ST3W_IMM         | st3w	{ z11.s - z13.s }, p4, [x13, #15, mul vl]  // ST3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store three structures from three vectors, scalar + imm  \\ 2 7  7  0.22 V1UnitL01[9],V1UnitV[9]
+# CHECK-NEXT:   3    | 7  | 7   | 0.22   | V1UnitI[9], V1UnitL[9], V1UnitL01[9], V1UnitS[9], V1UnitV[9]     | ST3W             | st3w	{ z19.s - z21.s }, p2, [x22, x28, lsl #2]  // ST3W { <Zt1>.S, <Zt2>.S, <Zt3>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous store three structures from three vectors, scalar + scalar  \\ 3 7  7  0.22 V1UnitL01[9],V1UnitS[9],V1UnitV[9]
+# CHECK-NEXT:   2    | 6  | 6   | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | ST4Fourv8b       | st4	{ v17.8b, v18.8b, v19.8b, v20.8b }, [x8]  // ST4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 2 6  6  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 7  | 7   | 0.17   | V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]           | ST4Fourv16b      | st4	{ v7.16b, v8.16b, v9.16b, v10.16b }, [x15]  // ST4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 2 7  7  0.17 V1UnitV01[12],V1UnitL01[12]
+# CHECK-NEXT:   2    | 6  | 6   | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | ST4Fourv4h       | st4	{ v5.4h, v6.4h, v7.4h, v8.4h }, [x13]  // ST4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 2 6  6  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 7  | 7   | 0.17   | V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]           | ST4Fourv8h       | st4	{ v11.8h, v12.8h, v13.8h, v14.8h }, [x1]  // ST4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 2 7  7  0.17 V1UnitV01[12],V1UnitL01[12]
+# CHECK-NEXT:   2    | 6  | 6   | 0.33   | V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]               | ST4Fourv2s       | st4	{ v15.2s, v16.2s, v17.2s, v18.2s }, [x18]  // ST4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 2 6  6  0.33 V1UnitV01[6],V1UnitL01[6]
+# CHECK-NEXT:   2    | 7  | 7   | 0.17   | V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]           | ST4Fourv4s       | st4	{ v21.4s, v22.4s, v23.4s, v24.4s }, [x6]  // ST4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 2 7  7  0.17 V1UnitV01[12],V1UnitL01[12]
+# CHECK-NEXT:   2    | 4  | 4   | 0.25   | V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]               | ST4Fourv2d       | st4	{ v25.2d, v26.2d, v27.2d, v28.2d }, [x16]  // ST4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>]  \\ ASIMD store, 4 element, multiple, Q-form, D  \\ 2 4  4  0.25 V1UnitV01[8],V1UnitL01[8]
+# CHECK-NEXT:   3    | 6  | 6   | 0.33   | V1UnitI, V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]      | ST4Fourv8b_POST  | st4	{ v16.8b, v17.8b, v18.8b, v19.8b }, [x24], #32  // ST4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], #32  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+# CHECK-NEXT:   3    | 7  | 7   | 0.17   | V1UnitI, V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]  | ST4Fourv16b_POST | st4	{ v2.16b, v3.16b, v4.16b, v5.16b }, [x13], #64  // ST4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 0.33   | V1UnitI, V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]      | ST4Fourv4h_POST  | st4	{ v17.4h, v18.4h, v19.4h, v20.4h }, [x3], #32  // ST4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], #32  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+# CHECK-NEXT:   3    | 7  | 7   | 0.17   | V1UnitI, V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]  | ST4Fourv8h_POST  | st4	{ v18.8h, v19.8h, v20.8h, v21.8h }, [x5], #64  // ST4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 0.33   | V1UnitI, V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]      | ST4Fourv2s_POST  | st4	{ v26.2s, v27.2s, v28.2s, v29.2s }, [x17], #32  // ST4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], #32  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+# CHECK-NEXT:   3    | 7  | 7   | 0.17   | V1UnitI, V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]  | ST4Fourv4s_POST  | st4	{ v21.4s, v22.4s, v23.4s, v24.4s }, [x7], #64  // ST4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 0.25   | V1UnitI, V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]      | ST4Fourv2d_POST  | st4	{ v27.2d, v28.2d, v29.2d, v30.2d }, [x25], #64  // ST4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], #64  \\ ASIMD store, 4 element, multiple, Q-form, D  \\ 3 4  4  0.25 V1UnitV01[8],V1UnitL01[8],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 0.33   | V1UnitI, V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]      | ST4Fourv8b_POST  | st4	{ v24.8b, v25.8b, v26.8b, v27.8b }, [x24], x8  // ST4 { <Vt>.8B, <Vt2>.8B, <Vt3>.8B, <Vt4>.8B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+# CHECK-NEXT:   3    | 7  | 7   | 0.17   | V1UnitI, V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]  | ST4Fourv16b_POST | st4	{ v2.16b, v3.16b, v4.16b, v5.16b }, [x21], x21  // ST4 { <Vt>.16B, <Vt2>.16B, <Vt3>.16B, <Vt4>.16B }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 0.33   | V1UnitI, V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]      | ST4Fourv4h_POST  | st4	{ v11.4h, v12.4h, v13.4h, v14.4h }, [x29], x3  // ST4 { <Vt>.4H, <Vt2>.4H, <Vt3>.4H, <Vt4>.4H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+# CHECK-NEXT:   3    | 7  | 7   | 0.17   | V1UnitI, V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]  | ST4Fourv8h_POST  | st4	{ v16.8h, v17.8h, v18.8h, v19.8h }, [x13], x3  // ST4 { <Vt>.8H, <Vt2>.8H, <Vt3>.8H, <Vt4>.8H }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 0.33   | V1UnitI, V1UnitL[6], V1UnitL01[6], V1UnitV[6], V1UnitV01[6]      | ST4Fourv2s_POST  | st4	{ v13.2s, v14.2s, v15.2s, v16.2s }, [x0], x0  // ST4 { <Vt>.2S, <Vt2>.2S, <Vt3>.2S, <Vt4>.2S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, D-form, B/H/S  \\ 3 6  6  0.33 V1UnitV01[6],V1UnitL01[6],V1UnitI
+# CHECK-NEXT:   3    | 7  | 7   | 0.17   | V1UnitI, V1UnitL[12], V1UnitL01[12], V1UnitV[12], V1UnitV01[12]  | ST4Fourv4s_POST  | st4	{ v26.4s, v27.4s, v28.4s, v29.4s }, [x1], x22  // ST4 { <Vt>.4S, <Vt2>.4S, <Vt3>.4S, <Vt4>.4S }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, B/H/S  \\ 3 7  7  0.17 V1UnitV01[12],V1UnitL01[12],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 0.25   | V1UnitI, V1UnitL[8], V1UnitL01[8], V1UnitV[8], V1UnitV01[8]      | ST4Fourv2d_POST  | st4	{ v18.2d, v19.2d, v20.2d, v21.2d }, [x10], x28  // ST4 { <Vt>.2D, <Vt2>.2D, <Vt3>.2D, <Vt4>.2D }, [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, multiple, Q-form, D  \\ 3 4  4  0.25 V1UnitV01[8],V1UnitL01[8],V1UnitI
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST4i8            | st4	{ v10.b, v11.b, v12.b, v13.b }[3], [x5]  // ST4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, B/H  \\ 2 6  6  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST4i16           | st4	{ v5.h, v6.h, v7.h, v8.h }[4], [x13]  // ST4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, B/H  \\ 2 6  6  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 6  | 6   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST4i32           | st4	{ v22.s, v23.s, v24.s, v25.s }[0], [x7]  // ST4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, S  \\ 2 6  6  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   2    | 4  | 4   | 1.00   | V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]               | ST4i64           | st4	{ v23.d, v24.d, v25.d, v26.d }[1], [x5]  // ST4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>]  \\ ASIMD store, 4 element, one lane, D  \\ 2 4  4  1.0 V1UnitV01[2],V1UnitL01[2]
+# CHECK-NEXT:   3    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i8_POST       | st4	{ v22.b, v23.b, v24.b, v25.b }[0], [x29], #4  // ST4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], #4  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i8_POST       | st4	{ v6.b, v7.b, v8.b, v9.b }[9], [x26], x21  // ST4 { <Vt>.B, <Vt2>.B, <Vt3>.B, <Vt4>.B }[<indexb>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i16_POST      | st4	{ v19.h, v20.h, v21.h, v22.h }[2], [x18], #8  // ST4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], #8  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i16_POST      | st4	{ v6.h, v7.h, v8.h, v9.h }[4], [x9], x9  // ST4 { <Vt>.H, <Vt2>.H, <Vt3>.H, <Vt4>.H }[<indexh>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, B/H  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i32_POST      | st4	{ v19.s, v20.s, v21.s, v22.s }[2], [x27], #16  // ST4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], #16  \\ ASIMD store, 4 element, one lane, S  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 6  | 6   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i32_POST      | st4	{ v22.s, v23.s, v24.s, v25.s }[0], [x29], x21  // ST4 { <Vt>.S, <Vt2>.S, <Vt3>.S, <Vt4>.S }[<indexs>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, S  \\ 3 6  6  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i64_POST      | st4	{ v10.d, v11.d, v12.d, v13.d }[0], [x16], #32  // ST4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], #32  \\ ASIMD store, 4 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   3    | 4  | 4   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | ST4i64_POST      | st4	{ v10.d, v11.d, v12.d, v13.d }[0], [x12], x11  // ST4 { <Vt>.D, <Vt2>.D, <Vt3>.D, <Vt4>.D }[<indexd>], [<Xn|SP>], <Xm>  \\ ASIMD store, 4 element, one lane, D  \\ 3 4  4  1.0 V1UnitV01[2],V1UnitL01[2],V1UnitI
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4B_IMM         | st4b	{ z22.b - z25.b }, p0, [x0]    // ST4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4B_IMM         | st4b	{ z1.b - z4.b }, p7, [x1, #20, mul vl]  // ST4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   3    | 11 | 11  | 0.11   | V1UnitI[18], V1UnitL[18], V1UnitL01[18], V1UnitS[18], V1UnitV[18] | ST4B            | st4b	{ z28.b - z31.b }, p4, [x27, x20]  // ST4B { <Zt1>.B, <Zt2>.B, <Zt3>.B, <Zt4>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4D_IMM         | st4d	{ z19.d - z22.d }, p1, [x11]   // ST4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4D_IMM         | st4d	{ z0.d - z3.d }, p6, [x7, #-24, mul vl]  // ST4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   3    | 11 | 11  | 0.11   | V1UnitI[18], V1UnitL[18], V1UnitL01[18], V1UnitS[18], V1UnitV[18] | ST4D            | st4d	{ z28.d - z31.d }, p5, [x19, x20, lsl #3]  // ST4D { <Zt1>.D, <Zt2>.D, <Zt3>.D, <Zt4>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4H_IMM         | st4h	{ z14.h - z17.h }, p1, [x24]   // ST4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4H_IMM         | st4h	{ z27.h - z30.h }, p3, [x26, #16, mul vl]  // ST4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   3    | 11 | 11  | 0.11   | V1UnitI[18], V1UnitL[18], V1UnitL01[18], V1UnitS[18], V1UnitV[18] | ST4H            | st4h	{ z2.h - z5.h }, p5, [x30, x17, lsl #1]  // ST4H { <Zt1>.H, <Zt2>.H, <Zt3>.H, <Zt4>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4W_IMM         | st4w	{ z3.s - z6.s }, p0, [x0]      // ST4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>, [<Xn|SP>]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 11 | 11  | 0.11   | V1UnitL[18], V1UnitL01[18], V1UnitV[18]                          | ST4W_IMM         | st4w	{ z5.s - z8.s }, p2, [x0, #-20, mul vl]  // ST4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Contiguous store four structures from four vectors, scalar + imm  \\ 2 11  11  0.11 V1UnitL01[18],V1UnitV[18]
+# CHECK-NEXT:   3    | 11 | 11  | 0.11   | V1UnitI[18], V1UnitL[18], V1UnitL01[18], V1UnitS[18], V1UnitV[18] | ST4W            | st4w	{ z21.s - z24.s }, p5, [x5, x18, lsl #2]  // ST4W { <Zt1>.S, <Zt2>.S, <Zt3>.S, <Zt4>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Contiguous store four structures from four vectors, scalar + scalar  \\ 3 11  11  0.11 V1UnitL01[18],V1UnitS[18],V1UnitV[18]
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLRB            | stlrb	w19, [x26]                     // STLRB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLRB            | stlrb	w9, [x19]                      // STLRB <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLRH            | stlrh	w4, [x7]                       // STLRH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLRH            | stlrh	w20, [x5]                      // STLRH <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURWi          | stlur	w3, [x27]                      // STLUR <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURWi          | stlur	w0, [x15, #-14]                // STLUR <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURXi          | stlur	x23, [x25]                     // STLUR <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURXi          | stlur	x18, [x6, #101]                // STLUR <Xt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURBi          | stlurb	w30, [x17]             // STLURB <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURBi          | stlurb	w25, [x21, #-8]        // STLURB <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURHi          | stlurh	w9, [x29]              // STLURH <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STLURHi          | stlurh	w6, [x27, #-224]       // STLURH <Wt>, [<Xn|SP>, #<simm>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXPW           | stlxp	w26, w11, w12, [x7]            // STLXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXPW           | stlxp	w24, w10, w16, [x8]            // STLXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXPX           | stlxp	w1, x25, x26, [x10]            // STLXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXPX           | stlxp	w10, x7, x20, [x22]            // STLXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRW           | stlxr	w23, w8, [x6]                  // STLXR <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRW           | stlxr	w29, w28, [x26]                // STLXR <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRX           | stlxr	w23, x8, [x7]                  // STLXR <Ws>, <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRX           | stlxr	w14, x18, [x23]                // STLXR <Ws>, <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRB           | stlxrb	w2, w7, [x10]          // STLXRB <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRB           | stlxrb	w0, w1, [x20]          // STLXRB <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRH           | stlxrh	w16, w17, [x21]        // STLXRH <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STLXRH           | stlxrh	w12, w26, [x23]        // STLXRH <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STNPSi           | stnp	s29, s16, [x11]                // STNP <St1>, <St2>, [<Xn|SP>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STNPSi           | stnp	s17, s19, [x27, #-40]          // STNP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STNPDi           | stnp	d4, d3, [x30]                  // STNP <Dt1>, <Dt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STNPDi           | stnp	d25, d31, [x28, #328]          // STNP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STNPQi           | stnp	q28, q22, [x3]                 // STNP <Qt1>, <Qt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STNPQi           | stnp	q17, q15, [x16, #656]          // STNP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STNPWi           | stnp	w29, w25, [x5]                 // STNP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STNPWi           | stnp	w16, w18, [x27, #-232]         // STNP <Wt1>, <Wt2>, [<Xn|SP>, #<imms>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STNPXi           | stnp	x20, x16, [x8]                 // STNP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STNPXi           | stnp	x6, x20, [x15, #-120]          // STNP <Xt1>, <Xt2>, [<Xn|SP>, #<immd>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1B_ZRI       | stnt1b	{ z18.b }, p7, [x21]   // STNT1B { <Zt>.B }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1B_ZRI       | stnt1b	{ z9.b }, p6, [x26, #-7, mul vl]  // STNT1B { <Zt>.B }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1B_ZRR       | stnt1b	{ z18.b }, p1, [x1, x20]  // STNT1B { <Zt>.B }, <Pg>, [<Xn|SP>, <Xm>]  \\ Non temporal store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1D_ZRI       | stnt1d	{ z16.d }, p3, [x3]    // STNT1D { <Zt>.D }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1D_ZRI       | stnt1d	{ z27.d }, p4, [x16, #-6, mul vl]  // STNT1D { <Zt>.D }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1D_ZRR       | stnt1d	{ z11.d }, p0, [x18, x22, lsl #3]  // STNT1D { <Zt>.D }, <Pg>, [<Xn|SP>, <Xm>, LSL #3]  \\ Non temporal store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1H_ZRI       | stnt1h	{ z27.h }, p5, [x16]   // STNT1H { <Zt>.H }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1H_ZRI       | stnt1h	{ z2.h }, p2, [x30, #-8, mul vl]  // STNT1H { <Zt>.H }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitS, V1UnitV                    | STNT1H_ZRR       | stnt1h	{ z0.h }, p1, [x7, x1, lsl #1]  // STNT1H { <Zt>.H }, <Pg>, [<Xn|SP>, <Xm>, LSL #1]  \\ Non temporal store, scalar + scalar  \\ 3 2  2  2.0 V1UnitL01,V1UnitS,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1W_ZRI       | stnt1w	{ z9.s }, p3, [x20]    // STNT1W { <Zt>.S }, <Pg>, [<Xn|SP>]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1W_ZRI       | stnt1w	{ z12.s }, p4, [x11, #-6, mul vl]  // STNT1W { <Zt>.S }, <Pg>, [<Xn|SP>, #<imm>, MUL VL]  \\ Non temporal store, scalar + imm   \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STNT1W_ZRR       | stnt1w	{ z28.s }, p6, [x6, x0, lsl #2]  // STNT1W { <Zt>.S }, <Pg>, [<Xn|SP>, <Xm>, LSL #2]  \\ Non temporal store, scalar + scalar  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STPSpost         | stp	s10, s19, [x13], #76           // STP <St1>, <St2>, [<Xn|SP>], #<imm32>  \\ Store vector pair, immed post-index, S-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STPDpost         | stp	d19, d20, [x30], #-144         // STP <Dt1>, <Dt2>, [<Xn|SP>], #<imm64>  \\ Store vector pair, immed post-index, D-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | STPQpost         | stp	q3, q17, [x14], #-976          // STP <Qt1>, <Qt2>, [<Xn|SP>], #<imm128>  \\ Store vector pair, immed post-index, Q-form  \\ 3 2  2  1.0 V1UnitI,V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STPSpre          | stp	s19, s24, [x27, #-224]!        // STP <St1>, <St2>, [<Xn|SP>, #<imm32>]!  \\ Store vector pair, immed pre-index, S-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STPDpre          | stp	d16, d21, [x28, #168]!         // STP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]!  \\ Store vector pair, immed pre-index, D-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 1.00   | V1UnitI, V1UnitL[2], V1UnitL01[2], V1UnitV[2], V1UnitV01[2]      | STPQpre          | stp	q10, q31, [x0, #608]!          // STP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]!  \\ Store vector pair, immed pre-index, Q-form  \\ 3 2  2  1.0 V1UnitI,V1UnitL01[2],V1UnitV01[2]
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STPSi            | stp	s27, s11, [x30]                // STP <St1>, <St2>, [<Xn|SP>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STPDi            | stp	d30, d19, [x25]                // STP <Dt1>, <Dt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STPQi            | stp	q25, q3, [x27]                 // STP <Qt1>, <Qt2>, [<Xn|SP>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STPSi            | stp	s29, s13, [x0, #-44]           // STP <St1>, <St2>, [<Xn|SP>, #<imm32>]  \\ Store vector pair, immed offset, S-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STPDi            | stp	d15, d12, [x20, #-72]          // STP <Dt1>, <Dt2>, [<Xn|SP>, #<imm64>]  \\ Store vector pair, immed offset, D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STPQi            | stp	q13, q16, [x3, #320]           // STP <Qt1>, <Qt2>, [<Xn|SP>, #<imm128>]  \\ Store vector pair, immed offset, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STPWpost         | stp	w18, w8, [x6], #196            // STP <Wt1>, <Wt2>, [<Xn|SP>], #<imms>  \\ Store pair, immed post-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STPXpost         | stp	x10, x17, [x7], #-328          // STP <Xt1>, <Xt2>, [<Xn|SP>], #<immd>  \\ Store pair, immed post-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STPWpre          | stp	w4, w3, [x0, #-36]!            // STP <Wt1>, <Wt2>, [<Xn|SP>, #<imms>]!  \\ Store pair, immed pre-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STPXpre          | stp	x14, x13, [x24, #-272]!        // STP <Xt1>, <Xt2>, [<Xn|SP>, #<immd>]!  \\ Store pair, immed pre-index  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STPWi            | stp	w27, w30, [x20]                // STP <Wt1>, <Wt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STPXi            | stp	x3, x6, [x16]                  // STP <Xt1>, <Xt2>, [<Xn|SP>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STPWi            | stp	w9, w14, [x10, #-24]           // STP <Wt1>, <Wt2>, [<Xn|SP>, #<imms>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STPXi            | stp	x27, x4, [x14, #-448]          // STP <Xt1>, <Xt2>, [<Xn|SP>, #<immd>]  \\ Store pair, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRWpost         | str	w14, [x2], #-72                // STR <Wt>, [<Xn|SP>], #<simm>  \\ Store, immed post-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXpost         | str	x28, [x14], #-130              // STR <Xt>, [<Xn|SP>], #<simm>  \\ Store register, immed post-index  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRWpre          | str	w9, [x29, #-227]!              // STR <Wt>, [<Xn|SP>, #<simm>]!  \\ Store, immed pre-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXpre          | str	x13, [x5, #233]!               // STR <Xt>, [<Xn|SP>, #<simm>]!  \\ Store register, immed pre-index   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWui           | str	w2, [x30]                      // STR <Wt>, [<Xn|SP>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWui           | str	w28, [x2, #1796]               // STR <Wt>, [<Xn|SP>, #<pimm32>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXui           | str	x22, [x29]                     // STR <Xt>, [<Xn|SP>]  \\ Store register, unsigned immed  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXui           | str	x2, [x10, #9472]               // STR <Xt>, [<Xn|SP>, #<pimm64>]  \\ Store register, unsigned immed  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBpost         | str	b21, [x28], #-62               // STR <Bt>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHpost         | str	h13, [x10], #-194              // STR <Ht>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSpost         | str	s14, [x8], #166                // STR <St>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDpost         | str	d24, [x10], #134               // STR <Dt>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQpost         | str	q20, [x30], #-108              // STR <Qt>, [<Xn|SP>], #<simm>  \\ Store vector reg, unsigned immed, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBpre          | str	b9, [x24, #242]!               // STR <Bt>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHpre          | str	h0, [x4, #-193]!               // STR <Ht>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSpre          | str	s19, [x23, #115]!              // STR <St>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDpre          | str	d20, [x2, #-30]!               // STR <Dt>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQpre          | str	q24, [x20, #62]!               // STR <Qt>, [<Xn|SP>, #<simm>]!  \\ Store vector reg, immed post-index, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBui           | str	b5, [x11]                      // STR <Bt>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBui           | str	b20, [x23, #2409]              // STR <Bt>, [<Xn|SP>, #<pimm8>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHui           | str	h23, [x15]                     // STR <Ht>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHui           | str	h24, [x6, #492]                // STR <Ht>, [<Xn|SP>, #<pimm16>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSui           | str	s25, [x19]                     // STR <St>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSui           | str	s2, [x14, #984]                // STR <St>, [<Xn|SP>, #<pimm32>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDui           | str	d15, [x2]                      // STR <Dt>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDui           | str	d27, [x7, #25704]              // STR <Dt>, [<Xn|SP>, #<pimm64>]  \\ Store vector reg, immed pre-index, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQui           | str	q13, [x16]                     // STR <Qt>, [<Xn|SP>]  \\ Store vector reg, immed pre-index, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQui           | str	q4, [x7, #96]                  // STR <Qt>, [<Xn|SP>, #<pimm128>]  \\ Store vector reg, immed pre-index, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitL, V1UnitL01                                               | STR_PXI          | str	p4, [x5]                       // STR <Pt>, [<Xn|SP>]  \\ Store from predicate reg  \\ 1 1  1  2.0 V1UnitL01
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitL, V1UnitL01                                               | STR_PXI          | str	p3, [x21, #-78, mul vl]        // STR <Pt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Store from predicate reg  \\ 1 1  1  2.0 V1UnitL01
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroX          | str	w14, [x9, x17]                 // STR <Wt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroX          | str	x5, [x0, x22]                  // STR <Xt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroW          | str	w24, [x21, w29, uxtw]          // STR <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroW          | str	x27, [x26, w24, uxtw]          // STR <Xt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroW          | str	w28, [x29, w29, sxtw]          // STR <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroW          | str	x25, [x1, w24, sxtw]           // STR <Xt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroX          | str	w2, [x24, x12, sxtx]           // STR <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroX          | str	x3, [x24, x27, sxtx]           // STR <Xt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroW          | str	w29, [x30, w30, uxtw #2]       // STR <Wt>, [<Xn|SP>, <Wm>, UXTW #2] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroW          | str	x5, [x13, w8, uxtw #3]         // STR <Xt>, [<Xn|SP>, <Wm>, UXTW #3] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroW          | str	w28, [x7, w24, sxtw #2]        // STR <Wt>, [<Xn|SP>, <Wm>, SXTW #2] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroW          | str	x23, [x2, w26, sxtw #3]        // STR <Xt>, [<Xn|SP>, <Wm>, SXTW #3] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroX          | str	w11, [x8, x30, sxtx #2]        // STR <Wt>, [<Xn|SP>, <Xm>, SXTX #2] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroX          | str	x20, [x4, x2, sxtx #3]         // STR <Xt>, [<Xn|SP>, <Xm>, SXTX #3] \\ Store register, register offset, extend, scale by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRWroX          | str	w8, [x11, x10, lsl #2]         // STR <Wt>, [<Xn|SP>, <Xm>, LSL #2]  \\ Store register, register offset, scaled by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRXroX          | str	x27, [x2, x11, lsl #3]         // STR <Xt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Store register, register offset, scaled by 4/8  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBroX          | str	b14, [x13, x25]                // STR <Bt>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBroW          | str	b30, [x16, w26, uxtw]          // STR <Bt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBroW          | str	b20, [x19, w3, sxtw]           // STR <Bt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRBroX          | str	b13, [x29, x19, sxtx]          // STR <Bt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHroX          | str	h16, [x5, x24]                 // STR <Ht>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHroW          | str	h15, [x15, w15, uxtw]          // STR <Ht>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHroW          | str	h3, [x6, w15, sxtw]            // STR <Ht>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRHroX          | str	h2, [x1, x28, sxtx]            // STR <Ht>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRHroW          | str	h30, [x29, w30, uxtw #1]       // STR <Ht>, [<Xn|SP>, <Wm>, UXTW #1] \\ Store vector reg, register offset, extend, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRHroW          | str	h10, [x21, w11, sxtw #1]       // STR <Ht>, [<Xn|SP>, <Wm>, SXTW #1] \\ Store vector reg, register offset, extend, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRHroX          | str	h0, [x15, x9, sxtx #1]         // STR <Ht>, [<Xn|SP>, <Xm>, SXTX #1] \\ Store vector reg, register offset, extend, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRHroX          | str	h13, [x0, x26, lsl #1]         // STR <Ht>, [<Xn|SP>, <Xm>, LSL #1]  \\ Store vector reg, register offset, scale, H-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroX          | str	s2, [x16, x17]                 // STR <St>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroW          | str	s20, [x24, w10, uxtw]          // STR <St>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroW          | str	s4, [x9, w14, sxtw]            // STR <St>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroX          | str	s3, [x23, x26, sxtx]           // STR <St>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroW          | str	s27, [x17, w9, uxtw #2]        // STR <St>, [<Xn|SP>, <Wm>, UXTW #2] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroW          | str	s0, [x11, w20, sxtw #2]        // STR <St>, [<Xn|SP>, <Wm>, SXTW #2] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroX          | str	s20, [x17, x14, sxtx #2]       // STR <St>, [<Xn|SP>, <Xm>, SXTX #2] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRSroX          | str	s0, [x15, x28, lsl #2]         // STR <St>, [<Xn|SP>, <Xm>, LSL #2]  \\ Store vector reg, register offset, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroX          | str	d5, [x26, x6]                  // STR <Dt>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroW          | str	d11, [x9, w5, uxtw]            // STR <Dt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroW          | str	d16, [x20, w8, sxtw]           // STR <Dt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroX          | str	d0, [x12, x9, sxtx]            // STR <Dt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroW          | str	d4, [x21, w25, uxtw #3]        // STR <Dt>, [<Xn|SP>, <Wm>, UXTW #3] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroW          | str	d28, [x20, w4, sxtw #3]        // STR <Dt>, [<Xn|SP>, <Wm>, SXTW #3] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroX          | str	d20, [x13, x23, sxtx #3]       // STR <Dt>, [<Xn|SP>, <Xm>, SXTX #3] \\ Store vector reg, register offset, extend, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRDroX          | str	d31, [x19, x28, lsl #3]        // STR <Dt>, [<Xn|SP>, <Xm>, LSL #3]  \\ Store vector reg, register offset, scale, S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQroX          | str	q13, [x24, x1]                 // STR <Qt>, [<Xn|SP>, <Xm>]  \\ Store vector reg, register offset, basic, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQroW          | str	q1, [x25, w9, uxtw]            // STR <Qt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store vector reg, register offset, extend, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQroW          | str	q25, [x20, w15, sxtw]          // STR <Qt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store vector reg, register offset, extend, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STRQroX          | str	q25, [x0, x15, sxtx]           // STR <Qt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store vector reg, register offset, extend, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRQroW          | str	q6, [x13, w0, uxtw #4]         // STR <Qt>, [<Xn|SP>, <Wm>, UXTW #4] \\ Store vector reg, register offset, extend, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRQroW          | str	q27, [x4, w15, sxtw #4]        // STR <Qt>, [<Xn|SP>, <Wm>, SXTW #4] \\ Store vector reg, register offset, extend, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRQroX          | str	q3, [x23, x0, sxtx #4]         // STR <Qt>, [<Xn|SP>, <Xm>, SXTX #4] \\ Store vector reg, register offset, extend, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitI, V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                  | STRQroX          | str	q27, [x1, x28, lsl #4]         // STR <Qt>, [<Xn|SP>, <Xm>, LSL #4]  \\ Store vector reg, register offset, scale, Q-form  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STR_ZXI          | str	z3, [x0]                       // STR <Zt>, [<Xn|SP>]  \\ Store from vector reg  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV                                      | STR_ZXI          | str	z8, [x6, #188, mul vl]         // STR <Zt>, [<Xn|SP>, #<imm>, MUL VL]  \\ Store from vector reg  \\ 2 2  2  2.0 V1UnitL01,V1UnitV
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRBBpost        | strb	w23, [x11], #34                // STRB <Wt>, [<Xn|SP>], #<simm>  \\ Store, immed post-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRBBpre         | strb	w5, [x19, #-175]!              // STRB <Wt>, [<Xn|SP>, #<simm>]!  \\ Store, immed pre-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRBBui          | strb	w18, [x30]                     // STRB <Wt>, [<Xn|SP>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRBBui          | strb	w12, [x9, #2315]               // STRB <Wt>, [<Xn|SP>, #<pimm>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRBBroW         | strb	w5, [x26, w7, uxtw]            // STRB <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRBBroW         | strb	w18, [x2, w28, sxtw]           // STRB <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRBBroX         | strb	w21, [x21, x7, sxtx]           // STRB <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRBBroX         | strb	w9, [x6, x21]                  // STRB <Wt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRHHpost        | strh	w21, [x8], #192                // STRH <Wt>, [<Xn|SP>], #<simm>  \\ Store, immed post-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   3    | 1  | 1   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRHHpre         | strh	w8, [x26, #-204]!              // STRH <Wt>, [<Xn|SP>, #<simm>]!  \\ Store, immed pre-indexed  \\ 3 1  1  2.0 V1UnitL01,V1UnitD,V1UnitI
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRHHui          | strh	w6, [x7]                       // STRH <Wt>, [<Xn|SP>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRHHui          | strh	w0, [x19, #7514]               // STRH <Wt>, [<Xn|SP>, #<pimm>]  \\ Store, immed offset  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRHHroX         | strh	w12, [x0, x11]                 // STRH <Wt>, [<Xn|SP>, <Xm>]  \\ Store register, register offset, basic  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRHHroW         | strh	w5, [x18, w8, uxtw]            // STRH <Wt>, [<Xn|SP>, <Wm>, UXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRHHroW         | strh	w28, [x29, w0, sxtw]           // STRH <Wt>, [<Xn|SP>, <Wm>, SXTW]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STRHHroX         | strh	w7, [x17, x0, sxtx]            // STRH <Wt>, [<Xn|SP>, <Xm>, SXTX]  \\ Store register, register offset, extend  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRHHroW         | strh	w7, [x2, w14, uxtw #1]         // STRH <Wt>, [<Xn|SP>, <Wm>, UXTW #1]  \\ Store register, register offset, extend, scale by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRHHroW         | strh	w7, [x16, w29, sxtw #1]        // STRH <Wt>, [<Xn|SP>, <Wm>, SXTW #1]  \\ Store register, register offset, extend, scale by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRHHroX         | strh	w5, [x1, x13, sxtx #1]         // STRH <Wt>, [<Xn|SP>, <Xm>, SXTX #1]  \\ Store register, register offset, extend, scale by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 2  | 2   | 2.00   | V1UnitD, V1UnitI, V1UnitL, V1UnitL01                             | STRHHroX         | strh	w14, [x28, x2, lsl #1]         // STRH <Wt>, [<Xn|SP>, <Xm>, LSL #1]  \\ Store register, register offset, scaled by 1  \\ 3 2  2  2.0 V1UnitI,V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRWi           | sttr	w17, [x20]                     // STTR <Wt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRWi           | sttr	w14, [x30, #-35]               // STTR <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRXi           | sttr	x10, [x16]                     // STTR <Xt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRXi           | sttr	x16, [x8, #-25]                // STTR <Xt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRBi           | sttrb	w13, [x2]                      // STTRB <Wt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRBi           | sttrb	w0, [x20, #-114]               // STTRB <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRHi           | sttrh	w26, [x11]                     // STTRH <Wt>, [<Xn|SP>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STTRHi           | sttrh	w11, [x30, #-78]               // STTRH <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, immed unprivileged  \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURBi           | stur	b29, [x8]                      // STUR <Bt>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURBi           | stur	b5, [x0, #80]                  // STUR <Bt>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURHi           | stur	h10, [x15]                     // STUR <Ht>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURHi           | stur	h10, [x12, #-227]              // STUR <Ht>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURSi           | stur	s10, [x4]                      // STUR <St>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURSi           | stur	s9, [x14, #21]                 // STUR <St>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURDi           | stur	d1, [x28]                      // STUR <Dt>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURDi           | stur	d6, [x6, #188]                 // STUR <Dt>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, B/H/S/D-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURQi           | stur	q6, [x16]                      // STUR <Qt>, [<Xn|SP>]  \\ Store vector reg, unscaled immed, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitL, V1UnitL01, V1UnitV, V1UnitV01                           | STURQi           | stur	q5, [x13, #-253]               // STUR <Qt>, [<Xn|SP>, #<simm>]  \\ Store vector reg, unscaled immed, Q-form  \\ 2 2  2  2.0 V1UnitL01,V1UnitV01
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURWi           | stur	w29, [x27]                     // STUR <Wt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURWi           | stur	w14, [x2, #-34]                // STUR <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURXi           | stur	x29, [x10]                     // STUR <Xt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURXi           | stur	x30, [x25, #127]               // STUR <Xt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURBBi          | sturb	w21, [x5]                      // STURB <Wt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURBBi          | sturb	w25, [x26, #-117]              // STURB <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURHHi          | sturh	w0, [x11]                      // STURH <Wt>, [<Xn|SP>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   2    | 1  | 1   | 2.00   | V1UnitD, V1UnitL, V1UnitL01                                      | STURHHi          | sturh	w7, [x10, #-209]               // STURH <Wt>, [<Xn|SP>, #<simm>]  \\ Store register, unscaled immed   \\ 2 1  1  2.0 V1UnitL01,V1UnitD
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXPW            | stxp	w29, w24, w6, [x9]             // STXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXPW            | stxp	w26, w19, w22, [x11]           // STXP <Ws>, <Wt1>, <Wt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXPX            | stxp	w30, x6, x3, [x1]              // STXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXPX            | stxp	w7, x2, x10, [x25]             // STXP <Ws>, <Xt1>, <Xt2>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRW            | stxr	w19, w21, [x9]                 // STXR <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRW            | stxr	w25, w1, [x24]                 // STXR <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRX            | stxr	w25, x30, [x28]                // STXR <Ws>, <Xt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRX            | stxr	w30, x20, [x23]                // STXR <Ws>, <Xt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRB            | stxrb	w0, w26, [x10]                 // STXRB <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRB            | stxrb	w10, w16, [x25]                // STXRB <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRH            | stxrh	w0, w20, [x8]                  // STXRH <Ws>, <Wt>, [<Xn|SP>]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   3    | 5  | 5   | 1.50   | V1UnitD, V1UnitL[2], V1UnitL01                                   | STXRH            | stxrh	w12, w14, [x1]                 // STXRH <Ws>, <Wt>, [<Xn|SP>, #0]  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWrx           | sub	w13, wsp, w10                  // SUB <Wd>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWrx           | sub	w22, wsp, w13, uxtb            // SUB <Wd>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWrx           | sub	w18, wsp, w23, sxtb #1         // SUB <Wd>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, no flagset  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWrx           | sub	w13, wsp, w8, lsl #4           // SUB <Wd>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXrs           | sub	x6, x8, x22                    // SUB <Xd>, <Xn|SP>, X<m>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXrx           | sub	x16, x2, w19, uxtb             // SUB <Xd>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBXrx           | sub	x16, x3, w27, uxtb #2          // SUB <Xd>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, extend and shift  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXrs           | sub	x4, x13, x16, lsl #3           // SUB <Xd>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWri           | sub	wsp, wsp, #50                  // SUB <Wd|WSP>, <Wn|WSP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWri           | sub	wsp, wsp, #84, lsl #12         // SUB <Wd|WSP>, <Wn|WSP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXri           | sub	x18, x22, #36                  // SUB <Xd|SP>, <Xn|SP>, #<imm>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXri           | sub	x17, x20, #184                 // SUB <Xd|SP>, <Xn|SP>, #<imm>, <shift>  \\ ALU, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUB_ZI_B         | sub	z18.b, z18.b, #117             // SUB <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUB_ZI_S         | sub	z22.s, z22.s, #4               // SUB <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUB_ZI_H         | sub	z15.h, z15.h, #50176           // SUB <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBWrs           | sub	w0, w21, w2, lsl #4            // SUB <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, no flagset   \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBWrs           | sub	w22, w7, w13, lsl #19          // SUB <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBWrs           | sub	w1, w18, w16, asr #4           // SUB <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SUBXrs           | sub	x27, x29, x16, lsl #1          // SUB <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, LSL shift, shift <= 4  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBXrs           | sub	x24, x10, x15, lsl #35         // SUB <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | SUBXrs           | sub	x24, x19, x13, lsr #20         // SUB <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, LSR/ASR/ROR shift or LSL shift > 4  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SUBv1i64         | sub	d18, d25, d0                   // SUB <V><d>, <V><n>, <V><m>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SUBv2i32         | sub	v15.2s, v14.2s, v11.2s         // SUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUB_ZPmZ_H       | sub	z18.h, p4/m, z18.h, z7.h       // SUB <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUB_ZZZ_B        | sub	z29.b, z19.b, z8.b             // SUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SUBHNv4i32_v4i16 | subhn	v7.4h, v10.4s, v13.4s          // SUBHN <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SUBHNv2i64_v4i32 | subhn2	v24.4s, v24.2d, v8.2d  // SUBHN2 <Vd>.<Tb>, <Vn>.<Ta>, <Vm>.<Ta>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUBR_ZI_B        | subr	z13.b, z13.b, #229             // SUBR <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUBR_ZI_S        | subr	z17.s, z17.s, #140             // SUBR <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUBR_ZI_D        | subr	z15.d, z15.d, #100             // SUBR <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUBR_ZPmZ_D      | subr	z21.d, p7/m, z21.d, z24.d      // SUBR <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | subs	w25, wsp, w13                  // SUBS <Wd>, <Wn|WSP>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | subs	w10, wsp, w9, uxth             // SUBS <Wd>, <Wn|WSP>, <Wm>, <wextend>   \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | subs	w20, wsp, w3, sxth #2          // SUBS <Wd>, <Wn|WSP>, <Wm>, <wextend> #<amount>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrx          | subs	w12, wsp, w27, lsl #4          // SUBS <Wd>, <Wn|WSP>, <Wm>, LSL #<amount>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | subs	x16, x20, x21                  // SUBS <Xd>, <Xn|SP>, X<m>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrx          | subs	x15, x2, w11, uxtb             // SUBS <Xd>, <Xn|SP>, <R><m>, <extend>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrx64        | subs	x13, x15, x14, sxtx #1         // SUBS <Xd>, <Xn|SP>, <R><m>, <extend> #<amount>  \\ ALU, flagset, extend and shift  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | subs	x30, x1, x26, lsl #3           // SUBS <Xd>, <Xn|SP>, X<m>, LSL #<amount>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWri          | subs	w25, wsp, #239                 // SUBS <Wd>, <Wn|WSP>, #<imm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWri          | subs	w13, wsp, #75, lsl #12         // SUBS <Wd>, <Wn|WSP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXri          | subs	x9, x3, #173                   // SUBS <Xd>, <Xn|SP>, #<imm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXri          | subs	x30, x25, #82, lsl #12         // SUBS <Xd>, <Xn|SP>, #<imm>, <shift>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrs          | subs	w16, w27, w25                  // SUBS <Wd>, <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSWrs          | subs	w0, w30, w27, lsl #4           // SUBS <Wd>, <Wn>, <Wm>, LSL #<wamountl>  \\ Arithmetic, LSL shift by immed, shift <= 4, unconditional, flagset   \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWrs          | subs	w17, w27, w3, lsl #20          // SUBS <Wd>, <Wn>, <Wm>, LSL #<wamounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSWrs          | subs	w27, w7, w27, asr #5           // SUBS <Wd>, <Wn>, <Wm>, <shift> #<wamount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift by immed or LSL shift by immed > 4, unconditional  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | subs	x21, x22, x17                  // SUBS <Xd>, <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | SUBSXrs          | subs	x18, x1, x5                    // SUBS <Xd>, <Xn>, <Xm>, LSL #<amountl>  \\ Arithmetic, flagset, LSL shift, shift <= 4  \\ 2 1   1   3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrs          | subs	x28, x26, x4, lsl #49          // SUBS <Xd>, <Xn>, <Xm>, LSL #<amounth>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | SUBSXrs          | subs	x26, x14, x30, lsr #35         // SUBS <Xd>, <Xn>, <Xm>, <shift> #<amount>  \\ Arithmetic, flagset, LSR/ASR/ROR shift or LSL shift > 4  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | SUDOTlanev8i8    | sudot	v4.2s, v20.8b, v18.4b[2]       // SUDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product using signed and unsigned integers  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV[2]                                                       | SUDOT_ZZZI       | sudot	z5.s, z30.b, z3.b[1]           // SUDOT <Zda>.S, <Zn>.B, <Zm>.B[<imm>]  \\ Dot product, 8 bit, using signed and unsigned integers  \\ 1 3 1 2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUNPKHI_ZZ_D     | sunpkhi	z22.d, z16.s           // SUNPKHI <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | SUNPKLO_ZZ_H     | sunpklo	z10.h, z0.b            // SUNPKLO <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SUQADDv1i8       | suqadd	b15, b21               // SUQADD <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | SUQADDv16i8      | suqadd	v26.16b, v27.16b       // SUQADD <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SVC              | svc	#0x89cb                        // SVC #<imm>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMWri          | sxtb	w7, w20                        // SXTB <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | sxtb	x18, w14                       // SXTB <Xd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | SXTB_ZPmZ_H      | sxtb	z16.h, p5/m, z15.h             // SXTB <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | SXTH_ZPmZ_S      | sxth	z4.s, p7/m, z11.s              // SXTH <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | SXTW_ZPmZ_D      | sxtw	z12.d, p1/m, z16.d             // SXTW <Zd>.D, <Pg>/M, <Zn>.D  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMWri          | sxth	w23, w2                        // SXTH <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | sxth	x22, w17                       // SXTH <Xd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv8i8_shift  | sshll	v4.8h, v21.8b, #0              // SXTL <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | SSHLLv4i32_shift | sshll2	v20.2d, v30.4s, #0     // SXTL2 <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | SBFMXri          | sxtw	x18, w22                       // SXTW <Xd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | sys	#6, c6, c0, #3                 // SYS #<op1>, <Cn>, <Cm>, #<op2> \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | sys	#7, c12, c5, #3, x8            // SYS #<op1>, <Cn>, <Cm>, #<op2>, <Xt>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSLxt           | sysl	x16, #5, c11, c8, #5           // SYSL <Xt>, #<op1>, <Cn>, <Cm>, #<op2>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | TBLv8i8Two       | tbl	v7.8b, { v2.16b, v3.16b }, v17.8b  // TBL <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 1 or 2 table regs  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV01[2]                                         | TBLv16i8Three    | tbl	v3.16b, { v10.16b, v11.16b, v12.16b }, v29.16b  // TBL <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 3 table regs  \\ 1 4  4  1.0 V1UnitV01[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.67   | V1UnitV[3], V1UnitV01[3]                                         | TBLv8i8Four      | tbl	v9.8b, { v22.16b, v23.16b, v24.16b, v25.16b }, v14.8b  // TBL <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B, <Vn+3>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 4 table regs  \\ 1 4  4  0.67 V1UnitV01[3]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | TBLv16i8One      | tbl	v29.16b, { v3.16b }, v17.16b   // TBL <Vd>.<Ta>, { <Vn>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup, 1 or 2 table regs  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | TBNZW            | tbnz	w3, #28, test                  // TBNZ W<t>, #<imms>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | TBNZX            | tbnz	x30, #48, test                 // TBNZ X<t>, #<immd>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV01[2]                                         | TBXv8i8Two       | tbx	v25.8b, { v13.16b, v14.16b }, v30.8b  // TBX <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 2 table reg  \\ 1 4  4  1.0 V1UnitV01[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.67   | V1UnitV[3], V1UnitV01[3]                                         | TBXv16i8Three    | tbx	v22.16b, { v3.16b, v4.16b, v5.16b }, v25.16b  // TBX <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 3 table reg  \\ 1 6  6  0.67 V1UnitV01[3]
+# CHECK-NEXT:   1    | 6  | 6   | 0.40   | V1UnitV[5], V1UnitV01[5]                                         | TBXv16i8Four     | tbx	v23.16b, { v0.16b, v1.16b, v2.16b, v3.16b }, v26.16b  // TBX <Vd>.<Ta>, { <Vn>.16B, <Vn+1>.16B, <Vn+2>.16B, <Vn+3>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 4 table reg  \\ 1 6  6  0.4 V1UnitV01[5]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | TBXv8i8One       | tbx	v16.8b, { v21.16b }, v18.8b    // TBX <Vd>.<Ta>, { <Vn>.16B }, <Vm>.<Ta>  \\ ASIMD table lookup extension, 1 table reg  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | TBZW             | tbz	w17, #16, test                 // TBZ W<t>, #<imms>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 2.00   | V1UnitB                                                          | TBZX             | tbz	x22, #41, test                 // TBZ X<t>, #<immd>, <label>  \\ Compare and branch  \\ 1 1  1  2.0 V1UnitB
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | tlbi	vmalle1                        // TLBI <tlbi_op> \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | SYSxt            | tlbi	ipas2e1is, x7                  // TLBI <tlbi_op2>, <Xt> \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | TRN1v2i32        | trn1	v30.2s, v21.2s, v25.2s         // TRN1 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD transpose  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | TRN1_PPP_S       | trn1	p1.s, p4.s, p0.s               // TRN1 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate transpose  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | TRN2_PPP_H       | trn2	p0.h, p5.h, p7.h               // TRN2 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate transpose  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | TRN2v2i64        | trn2	v27.2d, v29.2d, v10.2d         // TRN2 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD transpose  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSWri          | tst	w25, #0xe00                    // TST <Wn>, #<imms>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSXri          | tst	x3, #0x1e00                    // TST <Xn>, #<immd>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSWrs          | tst	w9, w14                        // TST <Wn>, <Wm>  \\ ALU, basic, unconditional, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ANDSWrs          | tst	w10, w3, asr #16               // TST <Wn>, <Wm>, <shift> #<wamount>  \\ Test/Compare, shift by immed  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   2    | 1  | 1   | 3.00   | V1UnitFlg, V1UnitI                                               | ANDSXrs          | tst	x11, x28                       // TST <Xn>, <Xm>  \\ ALU, basic, flagset  \\ 2 1  1  3.0 V1UnitI,V1UnitFlg
+# CHECK-NEXT:   2    | 2  | 2   | 2.00   | V1UnitFlg, V1UnitI, V1UnitM                                      | ANDSXrs          | tst	x9, x7, asr #33                // TST <Xn>, <Xm>, <shift> #<amount>  \\ Logical, shift, flagset  \\ 2 2  2  2.0 V1UnitM,V1UnitFlg
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | UABAv16i8        | uaba	v13.16b, v14.16b, v19.16b      // UABA <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff accum  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | UABALv2i32_v2i64 | uabal	v13.2d, v16.2s, v11.2s         // UABAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | UABALv8i16_v4i32 | uabal2	v17.4s, v0.8h, v1.8h   // UABAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff accum long  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UABDv4i32        | uabd	v23.4s, v4.4s, v30.4s          // UABD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD absolute diff  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UABD_ZPmZ_B      | uabd	z5.b, p5/m, z5.b, z10.b        // UABD <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UABDLv4i16_v4i32 | uabdl	v13.4s, v26.4h, v7.4h          // UABDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UABDLv4i32_v2i64 | uabdl2	v15.2d, v9.4s, v10.4s  // UABDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD absolute diff long  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | UADALPv2i32_v1i64 | uadalp	v31.1d, v14.2s         // UADALP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD pairwise add and accumulate long  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UADDLv8i8_v8i16  | uaddl	v29.8h, v8.8b, v31.8b          // UADDL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UADDLv8i16_v4i32 | uaddl2	v15.4s, v22.8h, v14.8h  // UADDL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UADDLPv2i32_v1i64 | uaddlp	v15.1d, v5.2s          // UADDLP <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD arith, pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UADDLVv8i8v      | uaddlv	h24, v24.8b            // UADDLV H<d>, <Vn>.8B  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | UADDLVv16i8v     | uaddlv	h19, v31.16b           // UADDLV H<d>, <Vn>.16B  \\ ASIMD arith, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | UADDLVv4i16v     | uaddlv	s12, v24.4h            // UADDLV S<d>, <Vn>.4H  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UADDLVv8i16v     | uaddlv	s30, v0.8h             // UADDLV S<d>, <Vn>.8H  \\ ASIMD arith, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | UADDLVv4i32v     | uaddlv	d6, v19.4s             // UADDLV D<d>, <Vn>.4S  \\ ASIMD arith, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 14 | 14  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UADDV_VPZ_B      | uaddv	d9, p5, z1.b                   // UADDV <Dd>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UADDV_VPZ_H      | uaddv	d26, p0, z25.h                 // UADDV <Dd>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UADDV_VPZ_S      | uaddv	d4, p1, z1.s                   // UADDV <Dd>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 8  | 8   | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UADDV_VPZ_D      | uaddv	d28, p6, z6.d                  // UADDV <Dd>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UADDWv2i32_v2i64 | uaddw	v17.2d, v9.2d, v12.2s          // UADDW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UADDWv8i16_v4i32 | uaddw2	v15.4s, v13.4s, v4.8h  // UADDW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | ubfiz	w11, w6, #30, #1               // UBFIZ <Wd>, <Wn>, #<lsbs>, #<widths>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMXri          | ubfiz	x27, x15, #49, #9              // UBFIZ <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | lsl	w19, w16, #7                   // UBFM <Wd>, <Wn>, #<immrs>, #<immss>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMXri          | ubfiz	x4, x30, #5, #51               // UBFM <Xd>, <Xn>, #<immrd>, #<immsd>  \\ Bitfield move, basic  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | ubfx	w13, w18, #25, #3              // UBFX <Wd>, <Wn>, #<lsbs>, #<widths>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMXri          | lsr	x23, x26, #59                  // UBFX <Xd>, <Xn>, #<lsbd>, #<widthd>  \\ Bit field extract  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFSWHri       | ucvtf	h8, w24, #16                   // UCVTF <Hd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFSWSri       | ucvtf	s7, w16, #29                   // UCVTF <Sd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFSWDri       | ucvtf	d5, w17, #23                   // UCVTF <Dd>, <Wn>, #<sfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFSXHri       | ucvtf	h13, x17, #12                  // UCVTF <Hd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFSXSri       | ucvtf	s25, x2, #37                   // UCVTF <Sd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFSXDri       | ucvtf	d20, x11, #43                  // UCVTF <Dd>, <Xn>, #<dfbits>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFUWHri       | ucvtf	h30, w4                        // UCVTF <Hd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFUWSri       | ucvtf	s22, w8                        // UCVTF <Sd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFUWDri       | ucvtf	d8, w15                        // UCVTF <Dd>, <Wn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFUXHri       | ucvtf	h17, x12                       // UCVTF <Hd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFUXSri       | ucvtf	s8, x0                         // UCVTF <Sd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UCVTFUXDri       | ucvtf	d22, x17                       // UCVTF <Dd>, <Xn>  \\ FP convert, from gen to vec reg  \\ 1 3  3  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFh           | ucvtf	h22, h16, #11                  // UCVTF H<d>, H<n>, #<hfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFs           | ucvtf	s17, s18, #18                  // UCVTF S<d>, S<n>, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFd           | ucvtf	d19, d1, #2                    // UCVTF D<d>, D<n>, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | UCVTFv4i16_shift | ucvtf	v18.4h, v11.4h, #7             // UCVTF <Vd>.4H, <Vn>.4H, #<hfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | UCVTFv8i16_shift | ucvtf	v22.8h, v20.8h, #10            // UCVTF <Vd>.8H, <Vn>.8H, #<hfbits>  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv2i32_shift | ucvtf	v16.2s, v17.2s, #11            // UCVTF <Vd>.2S, <Vn>.2S, #<sfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | UCVTFv4i32_shift | ucvtf	v17.4s, v23.4s, #2             // UCVTF <Vd>.4S, <Vn>.4S, #<sfbits>  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv2i64_shift | ucvtf	v18.2d, v20.2d, #60            // UCVTF <Vd>.2D, <Vn>.2D, #<dfbits>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv1i16       | ucvtf	h7, h21                        // UCVTF <Hd>, <Hn>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv1i32       | ucvtf	s25, s7                        // UCVTF S<d>, S<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv1i64       | ucvtf	d30, d29                       // UCVTF D<d>, D<n>  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | UCVTFv4f16       | ucvtf	v9.4h, v25.4h                  // UCVTF <Vd>.4H, <Vn>.4H  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 6  | 6   | 0.50   | V1UnitV[4], V1UnitV02[4]                                         | UCVTFv8f16       | ucvtf	v24.8h, v31.8h                 // UCVTF <Vd>.8H, <Vn>.8H  \\ ASIMD FP convert, other, Q-form F16  \\ 1 6  6  0.5 V1UnitV02[4]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv2f32       | ucvtf	v14.2s, v2.2s                  // UCVTF <Vd>.2S, <Vn>.2S  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | UCVTFv4f32       | ucvtf	v20.4s, v0.4s                  // UCVTF <Vd>.4S, <Vn>.4S  \\ ASIMD FP convert, other, D-form F16 and Q-form F32  \\ 1 4  4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UCVTFv2f64       | ucvtf	v27.2d, v3.2d                  // UCVTF <Vd>.2D, <Vn>.2D  \\ ASIMD FP convert, other, D-form F32 and Q-form F64  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 6  | 6   | 0.25   | V1UnitV[4], V1UnitV0[4], V1UnitV01[4], V1UnitV02[4]              | UCVTF_ZPmZ_HtoH  | ucvtf	z31.h, p5/m, z30.h             // UCVTF <Zd>.H, <Pg>/M, <Zn>.H  \\ Convert to floating point, 16b to half  \\ 1 6  6  0.25 V1UnitV0[4]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | UCVTF_ZPmZ_StoH  | ucvtf	z23.h, p7/m, z9.s              // UCVTF <Zd>.H, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | UCVTF_ZPmZ_StoS  | ucvtf	z1.s, p1/m, z10.s              // UCVTF <Zd>.S, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 4  | 4   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | UCVTF_ZPmZ_StoD  | ucvtf	z24.d, p5/m, z9.s              // UCVTF <Zd>.D, <Pg>/M, <Zn>.S  \\ Convert to floating point, 32b to single or half   \\ 1 4  4  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UCVTF_ZPmZ_DtoH  | ucvtf	z30.h, p2/m, z24.d             // UCVTF <Zd>.H, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UCVTF_ZPmZ_DtoS  | ucvtf	z9.s, p5/m, z9.d               // UCVTF <Zd>.S, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 3   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UCVTF_ZPmZ_DtoD  | ucvtf	z18.d, p6/m, z19.d             // UCVTF <Zd>.D, <Pg>/M, <Zn>.D  \\ Convert to floating point, 64b to float or convert to double  \\ 1 3  3  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 12 | 12  | 0.08   | V1UnitI[12], V1UnitM[12], V1UnitM0[12]                           | UDIVWr           | udiv	w12, w17, w22                  // UDIV <Wd>, <Wn>, <Wm>  \\ Divide, W-form  \\ 1 12 12 0.08 V1UnitM0[12]
+# CHECK-NEXT:   1    | 20 | 20  | 0.05   | V1UnitI[20], V1UnitM[20], V1UnitM0[20]                           | UDIVXr           | udiv	x7, x2, x23                    // UDIV <Xd>, <Xn>, <Xm>  \\ Divide, X-form  \\ 1 20 20 0.05 V1UnitM0[20]
+# CHECK-NEXT:   1    | 12 | 12  | 0.09   | V1UnitV[11], V1UnitV0[11], V1UnitV01[11], V1UnitV02[11]          | UDIV_ZPmZ_S      | udiv	z30.s, p5/m, z30.s, z10.s      // UDIV <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+# CHECK-NEXT:   1    | 20 | 20  | 0.05   | V1UnitV[20], V1UnitV0[20], V1UnitV01[20], V1UnitV02[20]          | UDIV_ZPmZ_D      | udiv	z31.d, p5/m, z31.d, z29.d      // UDIV <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+# CHECK-NEXT:   1    | 12 | 12  | 0.09   | V1UnitV[11], V1UnitV0[11], V1UnitV01[11], V1UnitV02[11]          | UDIVR_ZPmZ_S     | udivr	z19.s, p4/m, z19.s, z8.s       // UDIVR <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Divides, 32 bit   \\ 1 12 12 0.09 V1UnitV0[11]
+# CHECK-NEXT:   1    | 20 | 20  | 0.05   | V1UnitV[20], V1UnitV0[20], V1UnitV01[20], V1UnitV02[20]          | UDIVR_ZPmZ_D     | udivr	z3.d, p5/m, z3.d, z8.d         // UDIVR <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Divides, 64 bit  \\ 1 20 20 0.05 V1UnitV0[20]
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV, V1UnitV01                                               | UDOT_ZZZI_S      | udot	z0.s, z5.b, z4.b[1]            // UDOT <Zda>.S, <Zn>.B, <Zms>.B[<imms>]  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 1   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UDOT_ZZZI_D      | udot	z19.d, z1.h, z13.h[1]          // UDOT <Zda>.D, <Zn>.H, <Zmd>.H[<immd>]  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV, V1UnitV01                                               | UDOT_ZZZ_S       | udot	z22.s, z29.b, z4.b             // UDOT <Zda>.S, <Zn>.B, <Zm>.B  \\ Dot product, 8 bit  \\ 1 3 1 2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 1   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UDOT_ZZZ_D       | udot	z9.d, z1.h, z11.h              // UDOT <Zda>.D, <Zn>.H, <Zm>.H  \\ Dot product, 16 bit  \\ 1 4 1 1.0 V1UnitV0
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | UDOTlanev8i8     | udot	v10.2s, v11.8b, v21.4b[3]      // UDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | UDOTlanev16i8    | udot	v7.4s, v21.16b, v6.4b[3]       // UDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | UDOTv8i8         | udot	v19.2s, v31.8b, v17.8b         // UDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UHADDv8i16       | uhadd	v10.8h, v7.8h, v7.8h           // UHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UHSUBv4i16       | uhsub	v12.4h, v16.4h, v28.4h         // UHSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UMADDLrrr        | umaddl	x9, w28, w9, x19       // UMADDL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UMAX_ZI_B        | umax	z8.b, z8.b, #12                // UMAX <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UMAX_ZPmZ_B      | umax	z27.b, p1/m, z27.b, z13.b      // UMAX <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UMAXv16i8        | umax	v7.16b, v11.16b, v7.16b        // UMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UMAXPv8i16       | umaxp	v15.8h, v8.8h, v12.8h          // UMAXP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UMAXVv8i8v       | umaxv	b19, v7.8b                     // UMAXV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | UMAXVv16i8v      | umaxv	b12, v10.16b                   // UMAXV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | UMAXVv4i16v      | umaxv	h27, v5.4h                     // UMAXV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UMAXVv8i16v      | umaxv	h11, v22.8h                    // UMAXV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | UMAXVv4i32v      | umaxv	s5, v25.4s                     // UMAXV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 14 | 14  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMAXV_VPZ_B      | umaxv	b9, p7, z19.b                  // UMAXV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMAXV_VPZ_H      | umaxv	h8, p7, z26.h                  // UMAXV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMAXV_VPZ_S      | umaxv	s15, p2, z28.s                 // UMAXV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 8  | 8   | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMAXV_VPZ_D      | umaxv	d11, p4, z11.d                 // UMAXV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UMIN_ZI_S        | umin	z21.s, z21.s, #139             // UMIN <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UMIN_ZPmZ_S      | umin	z31.s, p2/m, z31.s, z4.s       // UMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UMINv16i8        | umin	v0.16b, v26.16b, v2.16b        // UMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UMINPv4i32       | uminp	v28.4s, v16.4s, v15.4s         // UMINP <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD max/min, basic and pair-wise  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UMINVv8i8v       | uminv	b23, v21.8b                    // UMINV B<d>, <Vn>.8B  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV13[2]                                         | UMINVv16i8v      | uminv	b3, v10.16b                    // UMINV B<d>, <Vn>.16B  \\ ASIMD max/min, reduce, 16B  \\ 1 4  4  1.0 V1UnitV13[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | UMINVv4i16v      | uminv	h6, v22.4h                     // UMINV H<d>, <Vn>.4H  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UMINVv8i16v      | uminv	h23, v3.8h                     // UMINV H<d>, <Vn>.8H  \\ ASIMD max/min, reduce, 8B/8H  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | UMINVv4i32v      | uminv	s29, v19.4s                    // UMINV S<d>, <Vn>.4S  \\ ASIMD max/min, reduce, 4H/4S  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 14 | 14  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMINV_VPZ_B      | uminv	b2, p5, z8.b                   // UMINV B<d>, <Pg>, <Zn>.B  \\ Reduction, arithmetic, B form  \\ 1 14  14  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 12 | 12  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMINV_VPZ_H      | uminv	h28, p0, z0.h                  // UMINV H<d>, <Pg>, <Zn>.H  \\ Reduction, arithmetic, H form  \\ 1 12  12  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 10 | 10  | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMINV_VPZ_S      | uminv	s10, p1, z29.s                 // UMINV S<d>, <Pg>, <Zn>.S  \\ Reduction, arithmetic, S form  \\ 1 10  10  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 8  | 8   | 0.50   | V1UnitV[2], V1UnitV1[2], V1UnitV01[2], V1UnitV13[2]              | UMINV_VPZ_D      | uminv	d24, p5, z29.d                 // UMINV D<d>, <Pg>, <Zn>.D  \\ Reduction, arithmetic, D form  \\ 1 8  8  0.5 V1UnitV1[2]
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLALv4i16_indexed | umlal	v22.4s, v14.4h, v0.h[6]  // UMLAL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLALv2i32_indexed | umlal	v28.2d, v31.2s, v0.s[1]  // UMLAL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLALv8i16_indexed | umlal2	v31.4s, v7.8h, v15.h[5]  // UMLAL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLALv4i32_indexed | umlal2	v10.2d, v4.4s, v3.s[2]  // UMLAL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLALv4i16_v4i32 | umlal	v29.4s, v20.4h, v30.4h         // UMLAL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLALv4i32_v2i64 | umlal2	v10.2d, v28.4s, v19.4s  // UMLAL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLSLv4i16_indexed | umlsl	v21.4s, v12.4h, v7.h[5]  // UMLSL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLSLv2i32_indexed | umlsl	v20.2d, v20.2s, v2.s[0]  // UMLSL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLSLv8i16_indexed | umlsl2	v27.4s, v28.8h, v6.h[4]  // UMLSL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLSLv4i32_indexed | umlsl2	v30.2d, v23.4s, v1.s[2]  // UMLSL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLSLv2i32_v2i64 | umlsl	v11.2d, v23.2s, v1.2s          // UMLSL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV02                                               | UMLSLv16i8_v8i16 | umlsl2	v11.8h, v20.16b, v2.16b  // UMLSL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply accumulate long  \\ 1 4 1 2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | UMMLA            | ummla	v14.4s, v17.16b, v25.16b       // UMMLA <Vd>.4S, <Vn>.16B, <Vm>.16B  \\ ASIMD matrix multiply-accumulate  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | UMSUBLrrr        | umnegl	x23, w5, w23           // UMNEGL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi8_idx0     | umov	w6, v22.b[0]                   // UMOV <Wd>, <Vn>.B[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi8          | umov	w29, v0.b[11]                  // UMOV <Wd>, <Vn>.B[<indexb>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi16_idx0    | umov	w10, v25.h[0]                  // UMOV <Wd>, <Vn>.H[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi16         | umov	w6, v7.h[3]                    // UMOV <Wd>, <Vn>.H[<indexh>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi32_idx0    | mov	w8, v8.s[0]                    // UMOV <Wd>, <Vn>.S[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi32         | mov	w20, v1.s[3]                   // UMOV <Wd>, <Vn>.S[<indexs>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi64_idx0    | mov	x20, v11.d[0]                  // UMOV <Xd>, <Vn>.D[0]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV[4]                                                       | UMOVvi64         | mov	x29, v7.d[1]                   // UMOV <Xd>, <Vn>.D[<indexd>]  \\ ASIMD transfer, element to gen reg  \\ 1 2  2  1.0 V1UnitV[4]
+# CHECK-NEXT:   1    | 2  | 1   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UMSUBLrrr        | umsubl	x21, w16, w28, x6      // UMSUBL <Xd>, <Wn>, <Wm>, <Xa>  \\ Multiply accumulate long  \\ 1 2 1 1.0 V1UnitM0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UMULH_ZPmZ_B     | umulh	z20.b, p4/m, z20.b, z6.b       // UMULH <Zdn>.B, <Pg>/M, <Zdn>.B, <Zm>.B  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UMULH_ZPmZ_H     | umulh	z30.h, p6/m, z30.h, z15.h      // UMULH <Zdn>.H, <Pg>/M, <Zdn>.H, <Zm>.H  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV, V1UnitV0, V1UnitV01, V1UnitV02                          | UMULH_ZPmZ_S     | umulh	z11.s, p7/m, z11.s, z8.s       // UMULH <Zdn>.S, <Pg>/M, <Zdn>.S, <Zm>.S  \\ Multiply, B, H, S element size  \\ 1 4  4  1.0 V1UnitV0
+# CHECK-NEXT:   1    | 5  | 5   | 0.50   | V1UnitV[2], V1UnitV0[2], V1UnitV01[2], V1UnitV02[2]              | UMULH_ZPmZ_D     | umulh	z3.d, p3/m, z3.d, z2.d         // UMULH <Zdn>.D, <Pg>/M, <Zdn>.D, <Zm>.D  \\ Multiply, D element size  \\ 1 5  5  0.5 V1UnitV0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitI, V1UnitM                                                 | UMULHrr          | umulh	x23, x22, x19                  // UMULH <Xd>, <Xn>, <Xm>  \\ Multiply high  \\ 1 3  3  2.0 V1UnitM
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitI, V1UnitM                                                 | UMADDLrrr        | umull	x5, w17, w23                   // UMULL <Xd>, <Wn>, <Wm>  \\ Multiply long  \\ 1 2  2  2.0 V1UnitM
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UMULLv4i16_indexed | umull	v27.4s, v1.4h, v8.h[6]  // UMULL <Vd>.4S, <Vn>.4H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UMULLv2i32_indexed | umull	v22.2d, v28.2s, v6.s[1]  // UMULL <Vd>.2D, <Vn>.2S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UMULLv8i16_indexed | umull2	v18.4s, v26.8h, v10.h[1]  // UMULL2 <Vd>.4S, <Vn>.8H, <Vmh>.H[<indexh>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UMULLv4i32_indexed | umull2	v28.2d, v21.4s, v1.s[0]  // UMULL2 <Vd>.2D, <Vn>.4S, <Vms>.S[<indexs>]  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UMULLv4i16_v4i32 | umull	v23.4s, v26.4h, v19.4h         // UMULL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | UMULLv16i8_v8i16 | umull2	v11.8h, v29.16b, v29.16b  // UMULL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD multiply long  \\ 1 3  3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQADD_ZI_B       | uqadd	z18.b, z18.b, #14              // UQADD <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQADD_ZI_S       | uqadd	z2.s, z2.s, #14                // UQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQADD_ZI_S       | uqadd	z24.s, z24.s, #56              // UQADD <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQADD_ZZZ_H      | uqadd	z6.h, z28.h, z5.h              // UQADD <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UQADDv1i32       | uqadd	s0, s24, s30                   // UQADD <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UQADDv2i64       | uqadd	v14.2d, v22.2d, v20.2d         // UQADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECB_WPiI      | uqdecb	w10                    // UQDECB <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECB_WPiI      | uqdecb	w8, vl3                // UQDECB <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECB_WPiI      | uqdecb	w3, vl32               // UQDECB <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECB_XPiI      | uqdecb	x8                     // UQDECB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECB_XPiI      | uqdecb	x3, vl5                // UQDECB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECB_XPiI      | uqdecb	x22, mul3, mul #2      // UQDECB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECD_WPiI      | uqdecd	w11                    // UQDECD <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECD_WPiI      | uqdecd	w27, vl256             // UQDECD <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECD_WPiI      | uqdecd	w6, vl32, mul #10      // UQDECD <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECD_XPiI      | uqdecd	x1                     // UQDECD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECD_XPiI      | uqdecd	x12, vl8               // UQDECD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECD_XPiI      | uqdecd	x10, vl64, mul #10     // UQDECD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECD_ZPiI      | uqdecd	z0.d                   // UQDECD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECD_ZPiI      | uqdecd	z8.d, vl3              // UQDECD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECD_ZPiI      | uqdecd	z27.d, vl16, mul #2    // UQDECD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECH_WPiI      | uqdech	w30                    // UQDECH <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECH_WPiI      | uqdech	w28, mul3              // UQDECH <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECH_WPiI      | uqdech	w5, vl5, mul #8        // UQDECH <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECH_XPiI      | uqdech	x2                     // UQDECH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECH_XPiI      | uqdech	x15, vl7               // UQDECH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECH_XPiI      | uqdech	x17, vl256, mul #10    // UQDECH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECH_ZPiI      | uqdech	z5.h                   // UQDECH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECH_ZPiI      | uqdech	z16.h, vl128           // UQDECH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECH_ZPiI      | uqdech	z27.h, vl128, mul #15  // UQDECH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECP_WP_H      | uqdecp	w19, p5.h              // UQDECP <Wdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECP_XP_B      | uqdecp	x1, p1.b               // UQDECP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 7  | 7   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV01[2]    | UQDECP_ZP_S      | uqdecp	z20.s, p0.s            // UQDECP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECW_WPiI      | uqdecw	w17                    // UQDECW <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECW_WPiI      | uqdecw	w11, vl256             // UQDECW <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECW_WPiI      | uqdecw	w13, mul4, mul #13     // UQDECW <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECW_XPiI      | uqdecw	x7                     // UQDECW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECW_XPiI      | uqdecw	x28, vl32              // UQDECW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQDECW_XPiI      | uqdecw	x0, vl256, mul #3      // UQDECW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECW_ZPiI      | uqdecw	z29.s                  // UQDECW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECW_ZPiI      | uqdecw	z22.s, vl2             // UQDECW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQDECW_ZPiI      | uqdecw	z20.s, vl2, mul #10    // UQDECW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCB_WPiI      | uqincb	w2                     // UQINCB <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCB_WPiI      | uqincb	w21, vl128             // UQINCB <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCB_WPiI      | uqincb	w0, all, mul #13       // UQINCB <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCB_XPiI      | uqincb	x24                    // UQINCB <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCB_XPiI      | uqincb	x18, vl7               // UQINCB <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCB_XPiI      | uqincb	x13, vl256, mul #13    // UQINCB <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCD_WPiI      | uqincd	w23                    // UQINCD <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCD_WPiI      | uqincd	w27, vl4               // UQINCD <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCD_WPiI      | uqincd	w7, vl32, mul #16      // UQINCD <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCD_XPiI      | uqincd	x0                     // UQINCD <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCD_XPiI      | uqincd	x29, mul4              // UQINCD <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCD_XPiI      | uqincd	x20, pow2, mul #3      // UQINCD <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCD_ZPiI      | uqincd	z29.d                  // UQINCD <Zdn>.D  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCD_ZPiI      | uqincd	z4.d, vl64             // UQINCD <Zdn>.D, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCD_ZPiI      | uqincd	z12.d, vl6, mul #13    // UQINCD <Zdn>.D, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCH_WPiI      | uqinch	w4                     // UQINCH <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCH_WPiI      | uqinch	w23, mul3              // UQINCH <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCH_WPiI      | uqinch	w27, vl7, mul #3       // UQINCH <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCH_XPiI      | uqinch	x8                     // UQINCH <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCH_XPiI      | uqinch	x13, mul3              // UQINCH <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCH_XPiI      | uqinch	x5, mul4, mul #9       // UQINCH <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCH_ZPiI      | uqinch	z21.h                  // UQINCH <Zdn>.H  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCH_ZPiI      | uqinch	z1.h, vl8              // UQINCH <Zdn>.H, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCH_ZPiI      | uqinch	z7.h, vl7, mul #12     // UQINCH <Zdn>.H, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCP_WP_D      | uqincp	w4, p5.d               // UQINCP <Wdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCP_XP_D      | uqincp	x13, p5.d              // UQINCP <Xdn>, <Pm>.<T>  \\ Predicate counting scalar, active predicate  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   2    | 7  | 7   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2], V1UnitV[2], V1UnitV01[2]    | UQINCP_ZP_S      | uqincp	z1.s, p0.s             // UQINCP <Zdn>.<T>, <Pm>  \\ Predicate counting vector, active predicate  \\ 2 7  7  0.5 V1UnitM0[2],V1UnitV01[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCW_WPiI      | uqincw	w13                    // UQINCW <Wdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCW_WPiI      | uqincw	w26, vl8               // UQINCW <Wdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCW_WPiI      | uqincw	w3, vl16, mul #13      // UQINCW <Wdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCW_XPiI      | uqincw	x26                    // UQINCW <Xdn>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCW_XPiI      | uqincw	x13, vl256             // UQINCW <Xdn>, <pattern>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UQINCW_XPiI      | uqincw	x29, vl7, mul #6       // UQINCW <Xdn>, <pattern>, MUL #<imm>  \\ Predicate counting scalar  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCW_ZPiI      | uqincw	z26.s                  // UQINCW <Zdn>.S  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCW_ZPiI      | uqincw	z31.s, vl5             // UQINCW <Zdn>.S, <pattern>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQINCW_ZPiI      | uqincw	z12.s, vl7, mul #4     // UQINCW <Zdn>.S, <pattern>, MUL #<imm>  \\ Predicate counting vector  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHLv1i32      | uqrshl	s17, s5, s8            // UQRSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHLv8i8       | uqrshl	v25.8b, v13.8b, v23.8b  // UQRSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNb         | uqrshrn	b12, h9, #4            // UQRSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNh         | uqrshrn	h1, s28, #2            // UQRSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNs         | uqrshrn	s1, d4, #12            // UQRSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNv8i8_shift | uqrshrn	v17.8b, v24.8h, #4     // UQRSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNv4i16_shift | uqrshrn	v29.4h, v25.4s, #10    // UQRSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNv2i32_shift | uqrshrn	v16.2s, v0.2d, #10     // UQRSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNv16i8_shift | uqrshrn2	v5.16b, v28.8h, #6     // UQRSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNv8i16_shift | uqrshrn2	v28.8h, v22.4s, #15    // UQRSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQRSHRNv4i32_shift | uqrshrn2	v20.4s, v13.2d, #4     // UQRSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLb           | uqshl	b16, b25, #3                   // UQSHL B<d>, B<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLh           | uqshl	h22, h27, #3                   // UQSHL H<d>, H<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLs           | uqshl	s9, s5, #2                     // UQSHL S<d>, S<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLd           | uqshl	d25, d1, #30                   // UQSHL D<d>, D<n>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLv16i8_shift | uqshl	v25.16b, v0.16b, #7            // UQSHL <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLv4i16_shift | uqshl	v1.4h, v12.4h, #15             // UQSHL <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLv2i32_shift | uqshl	v23.2s, v4.2s, #17             // UQSHL <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLv2i64_shift | uqshl	v28.2d, v23.2d, #48            // UQSHL <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLv1i8        | uqshl	b22, b26, b2                   // UQSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHLv4i16       | uqshl	v8.4h, v17.4h, v13.4h          // UQSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNb          | uqshrn	b16, h27, #6           // UQSHRN B<d>, H<n>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNh          | uqshrn	h4, s2, #15            // UQSHRN H<d>, S<n>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNs          | uqshrn	s0, d15, #22           // UQSHRN S<d>, D<n>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNv8i8_shift | uqshrn	v19.8b, v26.8h, #3     // UQSHRN <Vd>.8B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNv4i16_shift | uqshrn	v31.4h, v17.4s, #8     // UQSHRN <Vd>.4H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNv2i32_shift | uqshrn	v1.2s, v11.2d, #9      // UQSHRN <Vd>.2S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNv16i8_shift | uqshrn2	v23.16b, v16.8h, #1    // UQSHRN2 <Vd>.16B, <Vn>.8H, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNv8i16_shift | uqshrn2	v1.8h, v12.4s, #2      // UQSHRN2 <Vd>.8H, <Vn>.4S, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQSHRNv4i32_shift | uqshrn2	v30.4s, v29.2d, #32    // UQSHRN2 <Vd>.4S, <Vn>.2D, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQSUB_ZI_B       | uqsub	z26.b, z26.b, #174             // UQSUB <Zdn>.B, <Zdn>.B, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQSUB_ZI_S       | uqsub	z19.s, z19.s, #228             // UQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQSUB_ZI_H       | uqsub	z15.h, z15.h, #26624           // UQSUB <Zdn>.<T>, <Zdn>.<T>, #<imm>, <shift>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UQSUB_ZZZ_D      | uqsub	z25.d, z13.d, z19.d            // UQSUB <Zd>.<T>, <Zn>.<T>, <Zm>.<T>  \\ Arithmetic, basic  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UQSUBv1i32       | uqsub	s16, s21, s6                   // UQSUB <V><d>, <V><n>, <V><m>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UQSUBv4i32       | uqsub	v19.4s, v0.4s, v5.4s           // UQSUB <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQXTNv1i32       | uqxtn	s3, d27                        // UQXTN <Vb><d>, <Va><n>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQXTNv2i32       | uqxtn	v26.2s, v5.2d                  // UQXTN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | UQXTNv16i8       | uqxtn2	v15.16b, v22.8h        // UQXTN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow, saturating  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | URECPEv2i32      | urecpe	v10.2s, v8.2s          // URECPE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form U32  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | URECPEv4i32      | urecpe	v1.4s, v23.4s          // URECPE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, Q-form U32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | URHADDv2i32      | urhadd	v16.2s, v19.2s, v2.2s  // URHADD <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHLv1i64       | urshl	d24, d22, d29                  // URSHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHLv8i8        | urshl	v31.8b, v5.8b, v3.8b           // URSHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHRd           | urshr	d23, d19, #62                  // URSHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHRv16i8_shift | urshr	v23.16b, v14.16b, #2           // URSHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHRv4i16_shift | urshr	v16.4h, v13.4h, #7             // URSHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHRv4i32_shift | urshr	v10.4s, v10.4s, #21            // URSHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 4   | 2.00   | V1UnitV, V1UnitV13                                               | URSHRv2i64_shift | urshr	v2.2d, v16.2d, #30             // URSHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, complex  \\ 1 4  4  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 3  | 3   | 2.00   | V1UnitV, V1UnitV02                                               | URSQRTEv2i32     | ursqrte	v15.2s, v20.2s         // URSQRTE <Vd>.2S, <Vn>.2S  \\ ASIMD reciprocal and square root estimate, D-form U32  \\ 1  3   3  2.0 V1UnitV02
+# CHECK-NEXT:   1    | 4  | 4   | 1.00   | V1UnitV[2], V1UnitV02[2]                                         | URSQRTEv4i32     | ursqrte	v31.4s, v14.4s         // URSQRTE <Vd>.4S, <Vn>.4S  \\ ASIMD reciprocal and square root estimate, Q-form U32  \\ 1  4   4  1.0 V1UnitV02[2]
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | URSRAd           | ursra	d24, d24, #48                  // URSRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | URSRAv8i8_shift  | ursra	v14.8b, v18.8b, #1             // URSRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | URSRAv4i16_shift | ursra	v9.4h, v9.4h, #16              // URSRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | URSRAv2i32_shift | ursra	v25.2s, v17.2s, #9             // URSRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | URSRAv2i64_shift | ursra	v17.2d, v16.2d, #61            // URSRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | USDOTlanev8i8    | usdot	v0.2s, v18.8b, v10.4b[3]       // USDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.4B[<index>]  \\ ASIMD dot product using signed and unsigned integers  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV[2]                                                       | USDOT_ZZZI       | usdot	z5.s, z25.b, z2.b[1]           // USDOT <Zda>.S, <Zn>.B, <Zm>.B[<imm>]  \\ Dot product, 8 bit, using signed and unsigned integers  \\ 1 3 1 2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | USDOTv8i8        | usdot	v17.2s, v0.8b, v29.8b          // USDOT <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD dot product using signed and unsigned integers  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 3  | 1   | 2.00   | V1UnitV[2]                                                       | USDOT_ZZZ        | usdot	z8.s, z6.b, z18.b              // USDOT <Zda>.S, <Zn>.B, <Zm>.B  \\ Dot product, 8 bit, using signed and unsigned integers  \\ 1 3 1 2.0 V1UnitV[2]
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLv1i64        | ushl	d7, d17, d3                    // USHL <V><d>, <V><n>, <V><m>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLv8i8         | ushl	v6.8b, v26.8b, v6.8b           // USHL <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD shift by register, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv8i8_shift  | ushll	v18.8h, v24.8b, #4             // USHLL <Vd>.8H, <Vn>.8B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv4i16_shift | ushll	v12.4s, v10.4h, #3             // USHLL <Vd>.4S, <Vn>.4H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv2i32_shift | ushll	v16.2d, v16.2s, #31            // USHLL <Vd>.2D, <Vn>.2S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv16i8_shift | ushll2	v14.8h, v3.16b, #3     // USHLL2 <Vd>.8H, <Vn>.16B, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv8i16_shift | ushll2	v18.4s, v22.8h, #13    // USHLL2 <Vd>.4S, <Vn>.8H, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv4i32_shift | ushll2	v31.2d, v12.4s, #11    // USHLL2 <Vd>.2D, <Vn>.4S, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHRd            | ushr	d23, d22, #58                  // USHR <V><d>, <V><n>, #<shift>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHRv8i8_shift   | ushr	v24.8b, v0.8b, #2              // USHR <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHRv8i16_shift  | ushr	v21.8h, v31.8h, #11            // USHR <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHRv2i32_shift  | ushr	v27.2s, v24.2s, #14            // USHR <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHRv2i64_shift  | ushr	v0.2d, v27.2d, #48             // USHR <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 3  | 1   | 4.00   | V1UnitV                                                          | USMMLA           | usmmla	v25.4s, v10.16b, v11.16b  // USMMLA <Vd>.4S, <Vn>.16B, <Vm>.16B  \\ ASIMD matrix multiply-accumulate  \\ 1 3 1 4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | USQADDv1i16      | usqadd	h14, h13               // USQADD <V><d>, <V><n>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | USQADDv2i64      | usqadd	v18.2d, v23.2d         // USQADD <Vd>.<T>, <Vn>.<T>  \\ ASIMD arith, complex  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | USRAd            | usra	d22, d24, #9                   // USRA <V><d>, <V><n>, #<shift>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | USRAv16i8_shift  | usra	v16.16b, v5.16b, #5            // USRA <Vd>.<Tb>, <Vn>.<Tb>, #<shiftb>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | USRAv4i16_shift  | usra	v18.4h, v22.4h, #11            // USRA <Vd>.<Th>, <Vn>.<Th>, #<shifth>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | USRAv2i32_shift  | usra	v13.2s, v12.2s, #24            // USRA <Vd>.<Ts>, <Vn>.<Ts>, #<shifts>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 4  | 1   | 2.00   | V1UnitV, V1UnitV13                                               | USRAv2i64_shift  | usra	v30.2d, v30.2d, #41            // USRA <Vd>.<Td>, <Vn>.<Td>, #<shiftd>  \\ ASIMD shift accumulate  \\ 1 4 1 2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | USUBLv4i16_v4i32 | usubl	v22.4s, v18.4h, v3.4h          // USUBL <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | USUBLv16i8_v8i16 | usubl2	v12.8h, v23.16b, v15.16b  // USUBL2 <Vd>.<Ta>, <Vn>.<Tb>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | USUBWv8i8_v8i16  | usubw	v30.8h, v12.8h, v20.8b         // USUBW <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | USUBWv8i16_v4i32 | usubw2	v2.4s, v0.4s, v30.8h   // USUBW2 <Vd>.<Ta>, <Vn>.<Ta>, <Vm>.<Tb>  \\ ASIMD arith, basic  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UUNPKHI_ZZ_D     | uunpkhi	z26.d, z26.s           // UUNPKHI <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV01                                               | UUNPKLO_ZZ_S     | uunpklo	z10.s, z11.h           // UUNPKLO <Zd>.<T>, <Zn>.<Tb>  \\ Unpack and extend  \\ 1 2  2  2.0 V1UnitV01
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | uxtb	w2, w23                        // UXTB <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | UXTB_ZPmZ_D      | uxtb	z1.d, p2/m, z11.d              // UXTB <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | UXTH_ZPmZ_S      | uxth	z6.s, p3/m, z18.s              // UXTH <Zd>.<T>, <Pg>/M, <Zn>.<T>  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitV, V1UnitV1, V1UnitV01, V1UnitV13                          | UXTW_ZPmZ_D      | uxtw	z23.d, p4/m, z3.d              // UXTW <Zd>.D, <Pg>/M, <Zn>.D  \\ Extend, sign or zero  \\ 1 2  2  1.0 V1UnitV1
+# CHECK-NEXT:   1    | 1  | 1   | 4.00   | V1UnitI                                                          | UBFMWri          | uxth	w7, w14                        // UXTH <Wd>, <Wn>  \\ Sign/zero extend, normal  \\ 1 1  1  4.0 V1UnitI
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv4i16_shift | ushll	v1.4s, v22.4h, #0              // UXTL <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 2.00   | V1UnitV, V1UnitV13                                               | USHLLv16i8_shift | ushll2	v14.8h, v3.16b, #0     // UXTL2 <Vd>.<Ta>, <Vn>.<Tb>  \\ ASIMD shift by immed, basic  \\ 1 2  2  2.0 V1UnitV13
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UZP1v2i32        | uzp1	v9.2s, v29.2s, v20.2s          // UZP1 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UZP1_PPP_D       | uzp1	p5.d, p3.d, p5.d               // UZP1 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | UZP2_PPP_S       | uzp2	p6.s, p0.s, p6.s               // UZP2 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | UZP2v4i32        | uzp2	v18.4s, v12.4s, v31.4s         // UZP2 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | wfe                                 // WFE  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | wfi                                 // WFI  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | WHILELE_PXX_H    | whilele	p6.h, x28, x30         // WHILELE <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | WHILELO_PXX_B    | whilelo	p3.b, x9, x7           // WHILELO <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | WHILELS_PWW_B    | whilels	p4.b, w4, w20          // WHILELS <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 3  | 3   | 0.50   | V1UnitI[2], V1UnitM[2], V1UnitM0[2]                              | WHILELT_PXX_S    | whilelt	p7.s, x20, x6          // WHILELT <Pd>.<T>, <R><n>, <R><m>  \\ Loop control, based on GPR  \\ 1 3  3  0.5 V1UnitM0[2]
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | WRFFR            | wrffr	p7.b                           // WRFFR <Pn>.B  \\ Write to first fault register  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | XTNv8i8          | xtn	v20.8b, v17.8h                 // XTN <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | XTNv16i8         | xtn2	v31.16b, v26.8h                // XTN2 <Vd>.<Tb>, <Vn>.<Ta>  \\ ASIMD extract narrow  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 1  | 1   | 15.00  |                                                                  | HINT             | yield                               // YIELD  \\ No description \\ No scheduling info
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ZIP1v2i64        | zip1	v21.2d, v4.2d, v11.2d          // ZIP1 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ZIP1_PPP_D       | zip1	p0.d, p1.d, p4.d               // ZIP1 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 1.00   | V1UnitI, V1UnitM, V1UnitM0                                       | ZIP2_PPP_S       | zip2	p3.s, p5.s, p4.s               // ZIP2 <Pd>.<T>, <Pn>.<T>, <Pm>.<T>  \\ Predicate zip/unzip  \\ 1 2  2  1.0 V1UnitM0
+# CHECK-NEXT:   1    | 2  | 2   | 4.00   | V1UnitV                                                          | ZIP2v4i32        | zip2	v2.4s, v20.4s, v5.4s           // ZIP2 <Vd>.<T>, <Vn>.<T>, <Vm>.<T>  \\ ASIMD unzip/zip  \\ 1 2  2  4.0 V1UnitV
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-sve-instructions.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-sve-instructions.s
index 6b7616d68d4cd..bc336ab90e8b4 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-sve-instructions.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-sve-instructions.s
@@ -2506,11 +2506,11 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        and	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        and	z5.b, z5.b, #0x6
 # CHECK-NEXT:  1      2     0.50                        and	z5.b, z5.b, #0xf9
-# CHECK-NEXT:  2      2     2.00                        ands	p0.b, p0/z, p0.b, p1.b
-# CHECK-NEXT:  4      12    2.00                        andv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        andv	d0, p7, z31.d
-# CHECK-NEXT:  4      12    2.00                        andv	h0, p7, z31.h
-# CHECK-NEXT:  4      12    2.00                        andv	s0, p7, z31.s
+# CHECK-NEXT:  1      2     2.00                        ands	p0.b, p0/z, p0.b, p1.b
+# CHECK-NEXT:  1      12    2.00                        andv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        andv	d0, p7, z31.d
+# CHECK-NEXT:  1      12    2.00                        andv	h0, p7, z31.h
+# CHECK-NEXT:  1      12    2.00                        andv	s0, p7, z31.s
 # CHECK-NEXT:  1      2     1.00                        asr	z0.b, p0/m, z0.b, #1
 # CHECK-NEXT:  1      2     1.00                        asr	z0.b, p0/m, z0.b, z0.b
 # CHECK-NEXT:  1      2     1.00                        asr	z0.b, p0/m, z0.b, z1.d
@@ -2573,26 +2573,26 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        bic	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        bic	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  1      2     0.50                        bic	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  2      2     2.00                        bics	p0.b, p0/z, p0.b, p0.b
-# CHECK-NEXT:  2      2     2.00                        bics	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      2     2.00                        bics	p0.b, p0/z, p0.b, p0.b
+# CHECK-NEXT:  1      2     2.00                        bics	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      2     1.00                        brka	p0.b, p15/m, p15.b
 # CHECK-NEXT:  1      2     1.00                        brka	p0.b, p15/z, p15.b
-# CHECK-NEXT:  2      3     2.00                        brkas	p0.b, p15/z, p15.b
+# CHECK-NEXT:  1      3     2.00                        brkas	p0.b, p15/z, p15.b
 # CHECK-NEXT:  1      2     1.00                        brkb	p0.b, p15/m, p15.b
 # CHECK-NEXT:  1      2     1.00                        brkb	p0.b, p15/z, p15.b
-# CHECK-NEXT:  2      3     2.00                        brkbs	p0.b, p15/z, p15.b
+# CHECK-NEXT:  1      3     2.00                        brkbs	p0.b, p15/z, p15.b
 # CHECK-NEXT:  1      2     1.00                        brkn	p0.b, p15/z, p1.b, p0.b
 # CHECK-NEXT:  1      2     1.00                        brkn	p15.b, p15/z, p15.b, p15.b
-# CHECK-NEXT:  2      3     2.00                        brkns	p0.b, p15/z, p1.b, p0.b
-# CHECK-NEXT:  2      3     2.00                        brkns	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      3     2.00                        brkns	p0.b, p15/z, p1.b, p0.b
+# CHECK-NEXT:  1      3     2.00                        brkns	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      2     1.00                        brkpa	p0.b, p15/z, p1.b, p2.b
 # CHECK-NEXT:  1      2     1.00                        brkpa	p15.b, p15/z, p15.b, p15.b
-# CHECK-NEXT:  2      3     2.00                        brkpas	p0.b, p15/z, p1.b, p2.b
-# CHECK-NEXT:  2      3     2.00                        brkpas	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      3     2.00                        brkpas	p0.b, p15/z, p1.b, p2.b
+# CHECK-NEXT:  1      3     2.00                        brkpas	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      2     1.00                        brkpb	p0.b, p15/z, p1.b, p2.b
 # CHECK-NEXT:  1      2     1.00                        brkpb	p15.b, p15/z, p15.b, p15.b
-# CHECK-NEXT:  2      3     2.00                        brkpbs	p0.b, p15/z, p1.b, p2.b
-# CHECK-NEXT:  2      3     2.00                        brkpbs	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      3     2.00                        brkpbs	p0.b, p15/z, p1.b, p2.b
+# CHECK-NEXT:  1      3     2.00                        brkpbs	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      3     1.00                        clasta	b0, p7, b0, z31.b
 # CHECK-NEXT:  1      3     1.00                        clasta	d0, p7, d0, z31.d
 # CHECK-NEXT:  1      3     1.00                        clasta	h0, p7, h0, z31.h
@@ -2840,9 +2840,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        decp	xzr, p15.d
 # CHECK-NEXT:  1      2     1.00                        decp	xzr, p15.h
 # CHECK-NEXT:  1      2     1.00                        decp	xzr, p15.s
-# CHECK-NEXT:  3      7     2.00                        decp	z31.d, p15.d
-# CHECK-NEXT:  3      7     2.00                        decp	z31.h, p15.h
-# CHECK-NEXT:  3      7     2.00                        decp	z31.s, p15.s
+# CHECK-NEXT:  2      7     2.00                        decp	z31.d, p15.d
+# CHECK-NEXT:  2      7     2.00                        decp	z31.h, p15.h
+# CHECK-NEXT:  2      7     2.00                        decp	z31.s, p15.s
 # CHECK-NEXT:  1      2     1.00                        decw	x0
 # CHECK-NEXT:  1      2     1.00                        decw	x0, #14
 # CHECK-NEXT:  1      2     1.00                        decw	x0, all, mul #16
@@ -2875,11 +2875,11 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        eor	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        eor	z5.b, z5.b, #0x6
 # CHECK-NEXT:  1      2     0.50                        eor	z5.b, z5.b, #0xf9
-# CHECK-NEXT:  2      2     2.00                        eors	p0.b, p0/z, p0.b, p1.b
-# CHECK-NEXT:  4      12    2.00                        eorv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        eorv	d0, p7, z31.d
-# CHECK-NEXT:  4      12    2.00                        eorv	h0, p7, z31.h
-# CHECK-NEXT:  4      12    2.00                        eorv	s0, p7, z31.s
+# CHECK-NEXT:  1      2     2.00                        eors	p0.b, p0/z, p0.b, p1.b
+# CHECK-NEXT:  1      12    2.00                        eorv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        eorv	d0, p7, z31.d
+# CHECK-NEXT:  1      12    2.00                        eorv	h0, p7, z31.h
+# CHECK-NEXT:  1      12    2.00                        eorv	s0, p7, z31.s
 # CHECK-NEXT:  1      2     0.50                        ext	z31.b, z31.b, z0.b, #0
 # CHECK-NEXT:  1      2     0.50                        ext	z31.b, z31.b, z0.b, #255
 # CHECK-NEXT:  1      2     0.50                        fabd	z0.d, p7/m, z0.d, z31.d
@@ -2912,12 +2912,12 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        fadd	z31.d, p7/m, z31.d, #1.0
 # CHECK-NEXT:  1      2     0.50                        fadd	z31.h, p7/m, z31.h, #1.0
 # CHECK-NEXT:  1      2     0.50                        fadd	z31.s, p7/m, z31.s, #1.0
-# CHECK-NEXT:  3      8     1.50                        fadda	d0, p7, d0, z31.d
-# CHECK-NEXT:  18     19    18.00                       fadda	h0, p7, h0, z31.h
-# CHECK-NEXT:  10     11    10.00                       fadda	s0, p7, s0, z31.s
-# CHECK-NEXT:  5      9     2.00                        faddv	d0, p7, z31.d
-# CHECK-NEXT:  6      13    3.00                        faddv	h0, p7, z31.h
-# CHECK-NEXT:  6      11    2.50                        faddv	s0, p7, z31.s
+# CHECK-NEXT:  1      8     1.50                        fadda	d0, p7, d0, z31.d
+# CHECK-NEXT:  1      19    18.00                       fadda	h0, p7, h0, z31.h
+# CHECK-NEXT:  1      11    10.00                       fadda	s0, p7, s0, z31.s
+# CHECK-NEXT:  1      9     2.00                        faddv	d0, p7, z31.d
+# CHECK-NEXT:  1      13    3.00                        faddv	h0, p7, z31.h
+# CHECK-NEXT:  1      11    2.50                        faddv	s0, p7, z31.s
 # CHECK-NEXT:  1      3     0.50                        fcadd	z0.d, p0/m, z0.d, z0.d, #90
 # CHECK-NEXT:  1      3     0.50                        fcadd	z0.h, p0/m, z0.h, z0.h, #90
 # CHECK-NEXT:  1      3     0.50                        fcadd	z0.s, p0/m, z0.s, z0.s, #90
@@ -2982,29 +2982,29 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      3     1.00                        fcvt	z0.d, p0/m, z0.h
 # CHECK-NEXT:  1      3     1.00                        fcvt	z0.d, p0/m, z0.s
 # CHECK-NEXT:  1      3     1.00                        fcvt	z0.h, p0/m, z0.d
-# CHECK-NEXT:  2      4     2.00                        fcvt	z0.h, p0/m, z0.s
+# CHECK-NEXT:  1      4     2.00                        fcvt	z0.h, p0/m, z0.s
 # CHECK-NEXT:  1      3     1.00                        fcvt	z0.s, p0/m, z0.d
-# CHECK-NEXT:  2      4     2.00                        fcvt	z0.s, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        fcvt	z0.s, p0/m, z0.h
 # CHECK-NEXT:  1      3     1.00                        fcvtzs	z0.d, p0/m, z0.d
-# CHECK-NEXT:  1      3     1.00                        fcvtzs	z0.d, p0/m, z0.h
-# CHECK-NEXT:  1      3     1.00                        fcvtzs	z0.d, p0/m, z0.s
-# CHECK-NEXT:  4      6     4.00                        fcvtzs	z0.h, p0/m, z0.h
+# CHECK-NEXT:  1      6     4.00                        fcvtzs	z0.d, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        fcvtzs	z0.d, p0/m, z0.s
+# CHECK-NEXT:  1      6     4.00                        fcvtzs	z0.h, p0/m, z0.h
 # CHECK-NEXT:  1      3     1.00                        fcvtzs	z0.s, p0/m, z0.d
-# CHECK-NEXT:  2      4     2.00                        fcvtzs	z0.s, p0/m, z0.h
-# CHECK-NEXT:  2      4     2.00                        fcvtzs	z0.s, p0/m, z0.s
+# CHECK-NEXT:  1      6     4.00                        fcvtzs	z0.s, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        fcvtzs	z0.s, p0/m, z0.s
 # CHECK-NEXT:  1      3     1.00                        fcvtzu	z0.d, p0/m, z0.d
-# CHECK-NEXT:  1      3     1.00                        fcvtzu	z0.d, p0/m, z0.h
-# CHECK-NEXT:  1      3     1.00                        fcvtzu	z0.d, p0/m, z0.s
-# CHECK-NEXT:  4      6     4.00                        fcvtzu	z0.h, p0/m, z0.h
+# CHECK-NEXT:  1      6     4.00                        fcvtzu	z0.d, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        fcvtzu	z0.d, p0/m, z0.s
+# CHECK-NEXT:  1      6     4.00                        fcvtzu	z0.h, p0/m, z0.h
 # CHECK-NEXT:  1      3     1.00                        fcvtzu	z0.s, p0/m, z0.d
-# CHECK-NEXT:  2      4     2.00                        fcvtzu	z0.s, p0/m, z0.h
-# CHECK-NEXT:  2      4     2.00                        fcvtzu	z0.s, p0/m, z0.s
-# CHECK-NEXT:  1      15    7.00                        fdiv	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  1      13    10.00                       fdiv	z0.h, p7/m, z0.h, z31.h
-# CHECK-NEXT:  1      10    7.00                        fdiv	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  1      15    7.00                        fdivr	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  1      13    10.00                       fdivr	z0.h, p7/m, z0.h, z31.h
-# CHECK-NEXT:  1      10    7.00                        fdivr	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  1      6     4.00                        fcvtzu	z0.s, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        fcvtzu	z0.s, p0/m, z0.s
+# CHECK-NEXT:  1      15    14.00                       fdiv	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      13    12.00                       fdiv	z0.h, p7/m, z0.h, z31.h
+# CHECK-NEXT:  1      10    9.00                        fdiv	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  1      15    14.00                       fdivr	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      13    12.00                       fdivr	z0.h, p7/m, z0.h, z31.h
+# CHECK-NEXT:  1      10    9.00                        fdivr	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  1      3     0.50                        fexpa	z0.d, z31.d
 # CHECK-NEXT:  1      3     0.50                        fexpa	z0.h, z31.h
 # CHECK-NEXT:  1      3     0.50                        fexpa	z0.s, z31.s
@@ -3029,12 +3029,12 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        fmaxnm	z31.d, p7/m, z31.d, #1.0
 # CHECK-NEXT:  1      2     0.50                        fmaxnm	z31.h, p7/m, z31.h, #1.0
 # CHECK-NEXT:  1      2     0.50                        fmaxnm	z31.s, p7/m, z31.s, #1.0
-# CHECK-NEXT:  5      9     2.00                        fmaxnmv	d0, p7, z31.d
-# CHECK-NEXT:  6      13    3.00                        fmaxnmv	h0, p7, z31.h
-# CHECK-NEXT:  6      11    2.50                        fmaxnmv	s0, p7, z31.s
-# CHECK-NEXT:  5      9     2.00                        fmaxv	d0, p7, z31.d
-# CHECK-NEXT:  6      13    3.00                        fmaxv	h0, p7, z31.h
-# CHECK-NEXT:  6      11    2.50                        fmaxv	s0, p7, z31.s
+# CHECK-NEXT:  1      9     2.00                        fmaxnmv	d0, p7, z31.d
+# CHECK-NEXT:  1      13    3.00                        fmaxnmv	h0, p7, z31.h
+# CHECK-NEXT:  1      11    2.50                        fmaxnmv	s0, p7, z31.s
+# CHECK-NEXT:  1      9     2.00                        fmaxv	d0, p7, z31.d
+# CHECK-NEXT:  1      13    3.00                        fmaxv	h0, p7, z31.h
+# CHECK-NEXT:  1      11    2.50                        fmaxv	s0, p7, z31.s
 # CHECK-NEXT:  1      2     0.50                        fmin	z0.d, p0/m, z0.d, #0.0
 # CHECK-NEXT:  1      2     0.50                        fmin	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        fmin	z0.h, p0/m, z0.h, #0.0
@@ -3053,12 +3053,12 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        fminnm	z31.d, p7/m, z31.d, #1.0
 # CHECK-NEXT:  1      2     0.50                        fminnm	z31.h, p7/m, z31.h, #1.0
 # CHECK-NEXT:  1      2     0.50                        fminnm	z31.s, p7/m, z31.s, #1.0
-# CHECK-NEXT:  5      9     2.00                        fminnmv	d0, p7, z31.d
-# CHECK-NEXT:  6      13    3.00                        fminnmv	h0, p7, z31.h
-# CHECK-NEXT:  6      11    2.50                        fminnmv	s0, p7, z31.s
-# CHECK-NEXT:  5      9     2.00                        fminv	d0, p7, z31.d
-# CHECK-NEXT:  6      13    3.00                        fminv	h0, p7, z31.h
-# CHECK-NEXT:  6      11    2.50                        fminv	s0, p7, z31.s
+# CHECK-NEXT:  1      9     2.00                        fminnmv	d0, p7, z31.d
+# CHECK-NEXT:  1      13    3.00                        fminnmv	h0, p7, z31.h
+# CHECK-NEXT:  1      11    2.50                        fminnmv	s0, p7, z31.s
+# CHECK-NEXT:  1      9     2.00                        fminv	d0, p7, z31.d
+# CHECK-NEXT:  1      13    3.00                        fminv	h0, p7, z31.h
+# CHECK-NEXT:  1      11    2.50                        fminv	s0, p7, z31.s
 # CHECK-NEXT:  1      4     0.50                        fmla	z0.d, p7/m, z1.d, z31.d
 # CHECK-NEXT:  1      4     0.50                        fmla	z0.d, z1.d, z7.d[1]
 # CHECK-NEXT:  1      4     0.50                        fmla	z0.h, p7/m, z1.h, z31.h
@@ -3119,8 +3119,8 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      4     0.50                        fnmsb	z0.h, p7/m, z1.h, z31.h
 # CHECK-NEXT:  1      4     0.50                        fnmsb	z0.s, p7/m, z1.s, z31.s
 # CHECK-NEXT:  1      3     1.00                        frecpe	z0.d, z31.d
-# CHECK-NEXT:  4      6     4.00                        frecpe	z0.h, z31.h
-# CHECK-NEXT:  2      4     2.00                        frecpe	z0.s, z31.s
+# CHECK-NEXT:  1      6     1.00                        frecpe	z0.h, z31.h
+# CHECK-NEXT:  1      4     1.00                        frecpe	z0.s, z31.s
 # CHECK-NEXT:  1      4     0.50                        frecps	z0.d, z1.d, z31.d
 # CHECK-NEXT:  1      4     0.50                        frecps	z0.h, z1.h, z31.h
 # CHECK-NEXT:  1      4     0.50                        frecps	z0.s, z1.s, z31.s
@@ -3149,17 +3149,17 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      6     1.00                        frintz	z31.h, p7/m, z31.h
 # CHECK-NEXT:  1      4     1.00                        frintz	z31.s, p7/m, z31.s
 # CHECK-NEXT:  1      3     1.00                        frsqrte	z0.d, z31.d
-# CHECK-NEXT:  4      6     4.00                        frsqrte	z0.h, z31.h
-# CHECK-NEXT:  2      4     2.00                        frsqrte	z0.s, z31.s
+# CHECK-NEXT:  1      6     1.00                        frsqrte	z0.h, z31.h
+# CHECK-NEXT:  1      4     1.00                        frsqrte	z0.s, z31.s
 # CHECK-NEXT:  1      4     0.50                        frsqrts	z0.d, z1.d, z31.d
 # CHECK-NEXT:  1      4     0.50                        frsqrts	z0.h, z1.h, z31.h
 # CHECK-NEXT:  1      4     0.50                        frsqrts	z0.s, z1.s, z31.s
 # CHECK-NEXT:  1      3     0.50                        fscale	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  1      3     0.50                        fscale	z0.h, p7/m, z0.h, z31.h
 # CHECK-NEXT:  1      3     0.50                        fscale	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  1      16    7.00                        fsqrt	z31.d, p7/m, z31.d
-# CHECK-NEXT:  1      13    10.00                       fsqrt	z31.h, p7/m, z31.h
-# CHECK-NEXT:  1      10    7.00                        fsqrt	z31.s, p7/m, z31.s
+# CHECK-NEXT:  1      16    14.00                       fsqrt	z31.d, p7/m, z31.d
+# CHECK-NEXT:  1      13    12.00                       fsqrt	z31.h, p7/m, z31.h
+# CHECK-NEXT:  1      10    9.00                        fsqrt	z31.s, p7/m, z31.s
 # CHECK-NEXT:  1      2     0.50                        fsub	z0.d, p0/m, z0.d, #0.5
 # CHECK-NEXT:  1      2     0.50                        fsub	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        fsub	z0.d, z1.d, z31.d
@@ -3200,15 +3200,15 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        incd	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        incd	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        incd	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        incd	z0.d
-# CHECK-NEXT:  1      2     1.00                        incd	z0.d, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        incd	z0.d
+# CHECK-NEXT:  1      2     0.50                        incd	z0.d, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        inch	x0
 # CHECK-NEXT:  1      2     1.00                        inch	x0, #14
 # CHECK-NEXT:  1      2     1.00                        inch	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        inch	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        inch	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        inch	z0.h
-# CHECK-NEXT:  1      2     1.00                        inch	z0.h, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        inch	z0.h
+# CHECK-NEXT:  1      2     0.50                        inch	z0.h, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        incp	x0, p0.b
 # CHECK-NEXT:  1      2     1.00                        incp	x0, p0.d
 # CHECK-NEXT:  1      2     1.00                        incp	x0, p0.h
@@ -3217,28 +3217,28 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        incp	xzr, p15.d
 # CHECK-NEXT:  1      2     1.00                        incp	xzr, p15.h
 # CHECK-NEXT:  1      2     1.00                        incp	xzr, p15.s
-# CHECK-NEXT:  3      7     2.00                        incp	z31.d, p15.d
-# CHECK-NEXT:  3      7     2.00                        incp	z31.h, p15.h
-# CHECK-NEXT:  3      7     2.00                        incp	z31.s, p15.s
+# CHECK-NEXT:  2      7     2.00                        incp	z31.d, p15.d
+# CHECK-NEXT:  2      7     2.00                        incp	z31.h, p15.h
+# CHECK-NEXT:  2      7     2.00                        incp	z31.s, p15.s
 # CHECK-NEXT:  1      2     1.00                        incw	x0
 # CHECK-NEXT:  1      2     1.00                        incw	x0, #14
 # CHECK-NEXT:  1      2     1.00                        incw	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        incw	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        incw	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        incw	z0.s
-# CHECK-NEXT:  1      2     1.00                        incw	z0.s, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        incw	z0.s
+# CHECK-NEXT:  1      2     0.50                        incw	z0.s, all, mul #16
 # CHECK-NEXT:  1      4     1.00                        index	z0.b, #0, #0
-# CHECK-NEXT:  2      5     2.00                        index	z0.d, #0, #0
+# CHECK-NEXT:  1      5     2.00                        index	z0.d, #0, #0
 # CHECK-NEXT:  1      4     1.00                        index	z0.h, #0, #0
 # CHECK-NEXT:  2      7     1.00                        index	z0.h, w0, w0
 # CHECK-NEXT:  1      4     1.00                        index	z0.s, #0, #0
 # CHECK-NEXT:  2      7     1.00                        index	z21.b, w10, w21
-# CHECK-NEXT:  4      8     2.00                        index	z21.d, x10, x21
+# CHECK-NEXT:  2      8     2.00                        index	z21.d, x10, x21
 # CHECK-NEXT:  2      7     1.00                        index	z21.s, w10, w21
 # CHECK-NEXT:  2      7     1.00                        index	z23.b, #13, w8
 # CHECK-NEXT:  2      7     1.00                        index	z23.b, w13, #8
-# CHECK-NEXT:  4      8     2.00                        index	z23.d, #13, x8
-# CHECK-NEXT:  4      8     2.00                        index	z23.d, x13, #8
+# CHECK-NEXT:  2      8     2.00                        index	z23.d, #13, x8
+# CHECK-NEXT:  2      8     2.00                        index	z23.d, x13, #8
 # CHECK-NEXT:  2      7     1.00                        index	z23.h, #13, w8
 # CHECK-NEXT:  2      7     1.00                        index	z23.h, w13, #8
 # CHECK-NEXT:  2      7     1.00                        index	z23.s, #13, w8
@@ -3247,10 +3247,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  2      7     1.00                        index	z31.b, #-1, wzr
 # CHECK-NEXT:  2      7     1.00                        index	z31.b, wzr, #-1
 # CHECK-NEXT:  2      7     1.00                        index	z31.b, wzr, wzr
-# CHECK-NEXT:  2      5     2.00                        index	z31.d, #-1, #-1
-# CHECK-NEXT:  4      8     2.00                        index	z31.d, #-1, xzr
-# CHECK-NEXT:  4      8     2.00                        index	z31.d, xzr, #-1
-# CHECK-NEXT:  4      8     2.00                        index	z31.d, xzr, xzr
+# CHECK-NEXT:  1      5     2.00                        index	z31.d, #-1, #-1
+# CHECK-NEXT:  2      8     2.00                        index	z31.d, #-1, xzr
+# CHECK-NEXT:  2      8     2.00                        index	z31.d, xzr, #-1
+# CHECK-NEXT:  2      8     2.00                        index	z31.d, xzr, xzr
 # CHECK-NEXT:  1      4     1.00                        index	z31.h, #-1, #-1
 # CHECK-NEXT:  2      7     1.00                        index	z31.h, #-1, wzr
 # CHECK-NEXT:  2      7     1.00                        index	z31.h, wzr, #-1
@@ -3291,66 +3291,66 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z0.b }, p0/z, [x0, x0]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z0.b }, p0/z, [x0]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1b	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z0.h }, p0/z, [x0]
-# CHECK-NEXT:  2      9     0.33    *                   ld1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *                   ld1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  2      11    0.33    *                   ld1b	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      11    4.00    *                   ld1b	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z21.b }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z21.h }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z21.s }, p5/z, [x10, x21]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z23.d }, p3/z, [x13, x8]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z31.b }, p7/z, [sp, #-1, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1b	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1b	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1b	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z31.h }, p7/z, [sp, #-1, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  2      11    0.33    *                   ld1b	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  2      11    4.00    *                   ld1b	{ z31.s }, p7/z, [z31.s, #31]
 # CHECK-NEXT:  1      6     0.50    *                   ld1b	{ z5.h }, p3/z, [x17, x16]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
+# CHECK-NEXT:  2      11    4.00    *                   ld1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
+# CHECK-NEXT:  2      11    4.00    *                   ld1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
 # CHECK-NEXT:  1      6     0.50    *                   ld1d	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1d	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  1      6     0.50    *                   ld1d	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1d	{ z23.d }, p3/z, [sp, x8, lsl #3]
 # CHECK-NEXT:  1      6     0.50    *                   ld1d	{ z23.d }, p3/z, [x13, x8, lsl #3]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
+# CHECK-NEXT:  2      11    4.00    *                   ld1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
 # CHECK-NEXT:  1      6     0.50    *                   ld1d	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1d	{ z31.d }, p7/z, [z31.d, #248]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z0.h }, p0/z, [x0]
-# CHECK-NEXT:  2      9     0.33    *                   ld1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *                   ld1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  2      11    0.33    *                   ld1h	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z21.h }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z21.s }, p5/z, [x10, #5, mul vl]
+# CHECK-NEXT:  2      9     2.00    *                   ld1d	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1d	{ z31.d }, p7/z, [z31.d, #248]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z0.d }, p0/z, [x0]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z0.h }, p0/z, [x0]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z0.s }, p0/z, [x0]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z21.d }, p5/z, [x10, #5, mul vl]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z21.h }, p5/z, [x10, #5, mul vl]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z21.s }, p5/z, [x10, x21, lsl #1]
 # CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z23.d }, p3/z, [x13, x8, lsl #1]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1h	{ z31.d }, p7/z, [z31.d, #62]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z31.h }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  1      6     0.50    *                   ld1h	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      11    0.67    *                   ld1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  4      11    0.67    *                   ld1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
-# CHECK-NEXT:  2      11    0.33    *                   ld1h	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z31.d }, p7/z, [sp, #-1, mul vl]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1h	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z31.h }, p7/z, [sp, #-1, mul vl]
+# CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z31.s }, p7/z, [sp, #-1, mul vl]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1h	{ z31.s }, p7/z, [z31.s, #62]
 # CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z5.h }, p3/z, [sp, x16, lsl #1]
 # CHECK-NEXT:  2      7     0.50    *                   ld1h	{ z5.h }, p3/z, [x17, x16, lsl #1]
 # CHECK-NEXT:  1      6     0.50    *                   ld1rb	{ z0.b }, p0/z, [x0]
@@ -3406,252 +3406,252 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      6     0.50    *                   ld1rw	{ z31.d }, p7/z, [sp, #252]
 # CHECK-NEXT:  1      6     0.50    *                   ld1rw	{ z31.s }, p7/z, [sp, #252]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sb	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sb	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z0.h }, p0/z, [sp, x0]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z0.h }, p0/z, [x0, x0]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z0.h }, p0/z, [x0]
-# CHECK-NEXT:  2      9     0.33    *                   ld1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  2      11    0.33    *                   ld1sb	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sb	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z21.h }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z21.s }, p5/z, [x10, x21]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z23.d }, p3/z, [x13, x8]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sb	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sb	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sb	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sb	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z31.h }, p7/z, [sp, #-1, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sb	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  2      11    0.33    *                   ld1sb	{ z31.s }, p7/z, [z31.s, #31]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sb	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sh	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  2      9     0.33    *                   ld1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *                   ld1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sh	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  2      11    0.33    *                   ld1sh	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sh	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  2      7     0.50    *                   ld1sh	{ z21.s }, p5/z, [sp, x21, lsl #1]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sh	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  2      7     0.50    *                   ld1sh	{ z21.s }, p5/z, [x10, x21, lsl #1]
 # CHECK-NEXT:  2      7     0.50    *                   ld1sh	{ z23.d }, p3/z, [x13, x8, lsl #1]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sh	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sh	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sh	{ z31.d }, p7/z, [z31.d, #62]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sh	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      11    0.67    *                   ld1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  4      11    0.67    *                   ld1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
-# CHECK-NEXT:  2      11    0.33    *                   ld1sh	{ z31.s }, p7/z, [z31.s, #62]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sh	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sw	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sw	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sw	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sw	{ z23.d }, p3/z, [sp, x8, lsl #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sw	{ z23.d }, p3/z, [x13, x8, lsl #2]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1sw	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1sw	{ z31.d }, p7/z, [z31.d, #124]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sw	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1sw	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  2      9     0.33    *                   ld1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *                   ld1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  2      11    0.33    *                   ld1w	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z21.s }, p5/z, [sp, x21, lsl #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z21.s }, p5/z, [x10, x21, lsl #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z23.d }, p3/z, [x13, x8, lsl #2]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  4      9     0.67    *                   ld1w	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *                   ld1w	{ z31.d }, p7/z, [z31.d, #124]
 # CHECK-NEXT:  1      6     0.50    *                   ld1w	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      11    0.67    *                   ld1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
-# CHECK-NEXT:  4      11    0.67    *                   ld1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
-# CHECK-NEXT:  2      11    0.33    *                   ld1w	{ z31.s }, p7/z, [z31.s, #124]
-# CHECK-NEXT:  4      9     1.00    *                   ld2b	{ z0.b, z1.b }, p0/z, [x0, x0]
-# CHECK-NEXT:  4      8     1.00    *                   ld2b	{ z0.b, z1.b }, p0/z, [x0]
-# CHECK-NEXT:  4      8     1.00    *                   ld2b	{ z21.b, z22.b }, p5/z, [x10, #10, mul vl]
-# CHECK-NEXT:  4      8     1.00    *                   ld2b	{ z23.b, z24.b }, p3/z, [x13, #-16, mul vl]
-# CHECK-NEXT:  4      9     1.00    *                   ld2b	{ z5.b, z6.b }, p3/z, [x17, x16]
-# CHECK-NEXT:  4      9     1.00    *                   ld2d	{ z0.d, z1.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  4      8     1.00    *                   ld2d	{ z0.d, z1.d }, p0/z, [x0]
-# CHECK-NEXT:  4      8     1.00    *                   ld2d	{ z21.d, z22.d }, p5/z, [x10, #10, mul vl]
-# CHECK-NEXT:  4      8     1.00    *                   ld2d	{ z23.d, z24.d }, p3/z, [x13, #-16, mul vl]
-# CHECK-NEXT:  4      9     1.00    *                   ld2d	{ z5.d, z6.d }, p3/z, [x17, x16, lsl #3]
-# CHECK-NEXT:  4      10    1.00    *                   ld2h	{ z0.h, z1.h }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  4      8     1.00    *                   ld2h	{ z0.h, z1.h }, p0/z, [x0]
-# CHECK-NEXT:  4      8     1.00    *                   ld2h	{ z21.h, z22.h }, p5/z, [x10, #10, mul vl]
-# CHECK-NEXT:  4      8     1.00    *                   ld2h	{ z23.h, z24.h }, p3/z, [x13, #-16, mul vl]
-# CHECK-NEXT:  4      10    1.00    *                   ld2h	{ z5.h, z6.h }, p3/z, [x17, x16, lsl #1]
-# CHECK-NEXT:  4      9     1.00    *                   ld2w	{ z0.s, z1.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  4      8     1.00    *                   ld2w	{ z0.s, z1.s }, p0/z, [x0]
-# CHECK-NEXT:  4      8     1.00    *                   ld2w	{ z21.s, z22.s }, p5/z, [x10, #10, mul vl]
-# CHECK-NEXT:  4      8     1.00    *                   ld2w	{ z23.s, z24.s }, p3/z, [x13, #-16, mul vl]
-# CHECK-NEXT:  4      9     1.00    *                   ld2w	{ z5.s, z6.s }, p3/z, [x17, x16, lsl #2]
-# CHECK-NEXT:  7      8     1.50    *                   ld3b	{ z0.b - z2.b }, p0/z, [x0, x0]
-# CHECK-NEXT:  6      11    1.50    *                   ld3b	{ z0.b - z2.b }, p0/z, [x0]
-# CHECK-NEXT:  6      11    1.50    *                   ld3b	{ z21.b - z23.b }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  6      11    1.50    *                   ld3b	{ z23.b - z25.b }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  7      8     1.50    *                   ld3b	{ z5.b - z7.b }, p3/z, [x17, x16]
-# CHECK-NEXT:  7      8     1.50    *                   ld3d	{ z0.d - z2.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  6      11    1.50    *                   ld3d	{ z0.d - z2.d }, p0/z, [x0]
-# CHECK-NEXT:  6      11    1.50    *                   ld3d	{ z21.d - z23.d }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  6      11    1.50    *                   ld3d	{ z23.d - z25.d }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  7      8     1.50    *                   ld3d	{ z5.d - z7.d }, p3/z, [x17, x16, lsl #3]
-# CHECK-NEXT:  7      8     1.50    *                   ld3h	{ z0.h - z2.h }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  6      11    1.50    *                   ld3h	{ z0.h - z2.h }, p0/z, [x0]
-# CHECK-NEXT:  6      11    1.50    *                   ld3h	{ z21.h - z23.h }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  6      11    1.50    *                   ld3h	{ z23.h - z25.h }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  7      8     1.50    *                   ld3h	{ z5.h - z7.h }, p3/z, [x17, x16, lsl #1]
-# CHECK-NEXT:  7      8     1.50    *                   ld3w	{ z0.s - z2.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  6      11    1.50    *                   ld3w	{ z0.s - z2.s }, p0/z, [x0]
-# CHECK-NEXT:  6      11    1.50    *                   ld3w	{ z21.s - z23.s }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  6      11    1.50    *                   ld3w	{ z23.s - z25.s }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  7      8     1.50    *                   ld3w	{ z5.s - z7.s }, p3/z, [x17, x16, lsl #2]
-# CHECK-NEXT:  10     13    2.00    *                   ld4b	{ z0.b - z3.b }, p0/z, [x0, x0]
-# CHECK-NEXT:  8      12    2.00    *                   ld4b	{ z0.b - z3.b }, p0/z, [x0]
-# CHECK-NEXT:  8      12    2.00    *                   ld4b	{ z21.b - z24.b }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  8      12    2.00    *                   ld4b	{ z23.b - z26.b }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  10     13    2.00    *                   ld4b	{ z5.b - z8.b }, p3/z, [x17, x16]
-# CHECK-NEXT:  10     13    2.00    *                   ld4d	{ z0.d - z3.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  8      12    2.00    *                   ld4d	{ z0.d - z3.d }, p0/z, [x0]
-# CHECK-NEXT:  8      12    2.00    *                   ld4d	{ z21.d - z24.d }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  8      12    2.00    *                   ld4d	{ z23.d - z26.d }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  10     13    2.00    *                   ld4d	{ z5.d - z8.d }, p3/z, [x17, x16, lsl #3]
-# CHECK-NEXT:  10     13    2.00    *                   ld4h	{ z0.h - z3.h }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  8      12    2.00    *                   ld4h	{ z0.h - z3.h }, p0/z, [x0]
-# CHECK-NEXT:  8      12    2.00    *                   ld4h	{ z21.h - z24.h }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  8      12    2.00    *                   ld4h	{ z23.h - z26.h }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  10     13    2.00    *                   ld4h	{ z5.h - z8.h }, p3/z, [x17, x16, lsl #1]
-# CHECK-NEXT:  10     13    2.00    *                   ld4w	{ z0.s - z3.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  8      12    2.00    *                   ld4w	{ z0.s - z3.s }, p0/z, [x0]
-# CHECK-NEXT:  8      12    2.00    *                   ld4w	{ z21.s - z24.s }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  8      12    2.00    *                   ld4w	{ z23.s - z26.s }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  10     13    2.00    *                   ld4w	{ z5.s - z8.s }, p3/z, [x17, x16, lsl #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
+# CHECK-NEXT:  2      11    4.00    *                   ld1w	{ z31.s }, p7/z, [z31.s, #124]
+# CHECK-NEXT:  2      9     1.00    *                   ld2b	{ z0.b, z1.b }, p0/z, [x0, x0]
+# CHECK-NEXT:  2      8     1.00    *                   ld2b	{ z0.b, z1.b }, p0/z, [x0]
+# CHECK-NEXT:  2      8     1.00    *                   ld2b	{ z21.b, z22.b }, p5/z, [x10, #10, mul vl]
+# CHECK-NEXT:  2      8     1.00    *                   ld2b	{ z23.b, z24.b }, p3/z, [x13, #-16, mul vl]
+# CHECK-NEXT:  2      9     1.00    *                   ld2b	{ z5.b, z6.b }, p3/z, [x17, x16]
+# CHECK-NEXT:  2      9     1.00    *                   ld2d	{ z0.d, z1.d }, p0/z, [x0, x0, lsl #3]
+# CHECK-NEXT:  2      8     1.00    *                   ld2d	{ z0.d, z1.d }, p0/z, [x0]
+# CHECK-NEXT:  2      8     1.00    *                   ld2d	{ z21.d, z22.d }, p5/z, [x10, #10, mul vl]
+# CHECK-NEXT:  2      8     1.00    *                   ld2d	{ z23.d, z24.d }, p3/z, [x13, #-16, mul vl]
+# CHECK-NEXT:  2      9     1.00    *                   ld2d	{ z5.d, z6.d }, p3/z, [x17, x16, lsl #3]
+# CHECK-NEXT:  3      10    1.00    *                   ld2h	{ z0.h, z1.h }, p0/z, [x0, x0, lsl #1]
+# CHECK-NEXT:  2      8     1.00    *                   ld2h	{ z0.h, z1.h }, p0/z, [x0]
+# CHECK-NEXT:  2      8     1.00    *                   ld2h	{ z21.h, z22.h }, p5/z, [x10, #10, mul vl]
+# CHECK-NEXT:  2      8     1.00    *                   ld2h	{ z23.h, z24.h }, p3/z, [x13, #-16, mul vl]
+# CHECK-NEXT:  3      10    1.00    *                   ld2h	{ z5.h, z6.h }, p3/z, [x17, x16, lsl #1]
+# CHECK-NEXT:  2      9     1.00    *                   ld2w	{ z0.s, z1.s }, p0/z, [x0, x0, lsl #2]
+# CHECK-NEXT:  2      8     1.00    *                   ld2w	{ z0.s, z1.s }, p0/z, [x0]
+# CHECK-NEXT:  2      8     1.00    *                   ld2w	{ z21.s, z22.s }, p5/z, [x10, #10, mul vl]
+# CHECK-NEXT:  2      8     1.00    *                   ld2w	{ z23.s, z24.s }, p3/z, [x13, #-16, mul vl]
+# CHECK-NEXT:  2      9     1.00    *                   ld2w	{ z5.s, z6.s }, p3/z, [x17, x16, lsl #2]
+# CHECK-NEXT:  3      13    3.00    *                   ld3b	{ z0.b - z2.b }, p0/z, [x0, x0]
+# CHECK-NEXT:  2      11    3.00    *                   ld3b	{ z0.b - z2.b }, p0/z, [x0]
+# CHECK-NEXT:  2      11    3.00    *                   ld3b	{ z21.b - z23.b }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  2      11    3.00    *                   ld3b	{ z23.b - z25.b }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      13    3.00    *                   ld3b	{ z5.b - z7.b }, p3/z, [x17, x16]
+# CHECK-NEXT:  3      13    3.00    *                   ld3d	{ z0.d - z2.d }, p0/z, [x0, x0, lsl #3]
+# CHECK-NEXT:  2      11    3.00    *                   ld3d	{ z0.d - z2.d }, p0/z, [x0]
+# CHECK-NEXT:  2      11    3.00    *                   ld3d	{ z21.d - z23.d }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  2      11    3.00    *                   ld3d	{ z23.d - z25.d }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      13    3.00    *                   ld3d	{ z5.d - z7.d }, p3/z, [x17, x16, lsl #3]
+# CHECK-NEXT:  3      13    3.00    *                   ld3h	{ z0.h - z2.h }, p0/z, [x0, x0, lsl #1]
+# CHECK-NEXT:  2      11    3.00    *                   ld3h	{ z0.h - z2.h }, p0/z, [x0]
+# CHECK-NEXT:  2      11    3.00    *                   ld3h	{ z21.h - z23.h }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  2      11    3.00    *                   ld3h	{ z23.h - z25.h }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      13    3.00    *                   ld3h	{ z5.h - z7.h }, p3/z, [x17, x16, lsl #1]
+# CHECK-NEXT:  3      13    3.00    *                   ld3w	{ z0.s - z2.s }, p0/z, [x0, x0, lsl #2]
+# CHECK-NEXT:  2      11    3.00    *                   ld3w	{ z0.s - z2.s }, p0/z, [x0]
+# CHECK-NEXT:  2      11    3.00    *                   ld3w	{ z21.s - z23.s }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  2      11    3.00    *                   ld3w	{ z23.s - z25.s }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      13    3.00    *                   ld3w	{ z5.s - z7.s }, p3/z, [x17, x16, lsl #2]
+# CHECK-NEXT:  3      13    4.00    *                   ld4b	{ z0.b - z3.b }, p0/z, [x0, x0]
+# CHECK-NEXT:  2      12    4.00    *                   ld4b	{ z0.b - z3.b }, p0/z, [x0]
+# CHECK-NEXT:  2      12    4.00    *                   ld4b	{ z21.b - z24.b }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  2      12    4.00    *                   ld4b	{ z23.b - z26.b }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      13    4.00    *                   ld4b	{ z5.b - z8.b }, p3/z, [x17, x16]
+# CHECK-NEXT:  3      13    4.00    *                   ld4d	{ z0.d - z3.d }, p0/z, [x0, x0, lsl #3]
+# CHECK-NEXT:  2      12    4.00    *                   ld4d	{ z0.d - z3.d }, p0/z, [x0]
+# CHECK-NEXT:  2      12    4.00    *                   ld4d	{ z21.d - z24.d }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  2      12    4.00    *                   ld4d	{ z23.d - z26.d }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      13    4.00    *                   ld4d	{ z5.d - z8.d }, p3/z, [x17, x16, lsl #3]
+# CHECK-NEXT:  3      13    4.00    *                   ld4h	{ z0.h - z3.h }, p0/z, [x0, x0, lsl #1]
+# CHECK-NEXT:  2      12    4.00    *                   ld4h	{ z0.h - z3.h }, p0/z, [x0]
+# CHECK-NEXT:  2      12    4.00    *                   ld4h	{ z21.h - z24.h }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  2      12    4.00    *                   ld4h	{ z23.h - z26.h }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      13    4.00    *                   ld4h	{ z5.h - z8.h }, p3/z, [x17, x16, lsl #1]
+# CHECK-NEXT:  3      13    4.00    *                   ld4w	{ z0.s - z3.s }, p0/z, [x0, x0, lsl #2]
+# CHECK-NEXT:  2      12    4.00    *                   ld4w	{ z0.s - z3.s }, p0/z, [x0]
+# CHECK-NEXT:  2      12    4.00    *                   ld4w	{ z21.s - z24.s }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  2      12    4.00    *                   ld4w	{ z23.s - z26.s }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      13    4.00    *                   ld4w	{ z5.s - z8.s }, p3/z, [x17, x16, lsl #2]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z0.d }, p0/z, [x0, x0]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1b	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z0.h }, p0/z, [x0, x0]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z0.s }, p0/z, [x0, x0]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1b	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1b	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z31.b }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1b	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1b	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1b	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z31.h }, p7/z, [sp]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1b	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1b	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1b	{ z31.s }, p7/z, [z31.s, #31]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1d	{ z0.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1d	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1d	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1d	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1d	{ z31.d }, p7/z, [z31.d, #248]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1d	{ z31.d }, p7/z, [z31.d, #248]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1h	{ z0.d }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1h	{ z0.h }, p0/z, [x0, x0, lsl #1]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1h	{ z0.s }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1h	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1h	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1h	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1h	{ z31.d }, p7/z, [z31.d, #62]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1h	{ z31.h }, p7/z, [sp]
-# CHECK-NEXT:  4      11    0.67    *             U     ldff1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  4      11    0.67    *             U     ldff1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1h	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1h	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1h	{ z31.s }, p7/z, [z31.s, #62]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sb	{ z0.d }, p0/z, [x0, x0]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sb	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sb	{ z0.h }, p0/z, [x0, x0]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sb	{ z0.s }, p0/z, [x0, x0]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1sb	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1sb	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sb	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sb	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sb	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sb	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sb	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sb	{ z31.h }, p7/z, [sp]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sb	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1sb	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sb	{ z31.s }, p7/z, [z31.s, #31]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1sh	{ z0.d }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1sh	{ z0.s }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1sh	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1sh	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sh	{ z31.d }, p7/z, [z31.d, #62]
-# CHECK-NEXT:  4      11    0.67    *             U     ldff1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  4      11    0.67    *             U     ldff1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sh	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
 # CHECK-NEXT:  2      7     0.50    *             U     ldff1sh	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1sh	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sh	{ z31.s }, p7/z, [z31.s, #62]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sw	{ z0.d }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sw	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sw	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1sw	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1sw	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1sw	{ z31.d }, p7/z, [z31.d, #124]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1w	{ z0.d }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1w	{ z0.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  2      9     0.33    *             U     ldff1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1w	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1w	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  4      9     0.67    *             U     ldff1w	{ z31.d }, p7/z, [z31.d, #124]
-# CHECK-NEXT:  4      11    0.67    *             U     ldff1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
-# CHECK-NEXT:  4      11    0.67    *             U     ldff1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
+# CHECK-NEXT:  2      9     2.00    *             U     ldff1w	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
 # CHECK-NEXT:  2      6     0.50    *             U     ldff1w	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  2      11    0.33    *             U     ldff1w	{ z31.s }, p7/z, [z31.s, #124]
+# CHECK-NEXT:  2      11    4.00    *             U     ldff1w	{ z31.s }, p7/z, [z31.s, #124]
 # CHECK-NEXT:  1      6     0.50    *             U     ldnf1b	{ z0.b }, p0/z, [x0]
 # CHECK-NEXT:  1      6     0.50    *             U     ldnf1b	{ z0.d }, p0/z, [x0]
 # CHECK-NEXT:  1      6     0.50    *             U     ldnf1b	{ z0.h }, p0/z, [x0]
@@ -3782,9 +3782,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        lsrr	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT:  1      2     1.00                        lsrr	z0.h, p0/m, z0.h, z0.h
 # CHECK-NEXT:  1      2     1.00                        lsrr	z0.s, p0/m, z0.s, z0.s
-# CHECK-NEXT:  2      5     2.00                        mad	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT:  2      5     2.00                        mla	z0.d, p0/m, z0.d, z0.d
-# CHECK-NEXT:  2      5     2.00                        mls	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT:  1      5     2.00                        mad	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT:  1      5     2.00                        mla	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT:  1      5     2.00                        mls	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT:  1      1     1.00                        mov	p0.b, p0.b
 # CHECK-NEXT:  1      1     1.00                        mov	p0.b, p0/m, p0.b
 # CHECK-NEXT:  1      1     1.00                        mov	p0.b, p0/z, p0.b
@@ -3888,36 +3888,36 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        mov	z5.h, #-6
 # CHECK-NEXT:  1      2     0.50                        mov	z5.q, z17.q[3]
 # CHECK-NEXT:  1      2     0.50                        mov	z5.s, #-6
-# CHECK-NEXT:  2      2     2.00                        movs	p0.b, p0.b
-# CHECK-NEXT:  2      2     2.00                        movs	p0.b, p0/z, p0.b
-# CHECK-NEXT:  2      2     2.00                        movs	p15.b, p15.b
-# CHECK-NEXT:  2      2     2.00                        movs	p15.b, p15/z, p15.b
+# CHECK-NEXT:  1      2     2.00                        movs	p0.b, p0.b
+# CHECK-NEXT:  1      2     2.00                        movs	p0.b, p0/z, p0.b
+# CHECK-NEXT:  1      2     2.00                        movs	p15.b, p15.b
+# CHECK-NEXT:  1      2     2.00                        movs	p15.b, p15/z, p15.b
 # CHECK-NEXT:  1      1     0.07                  U     mrs	x3, ID_AA64ZFR0_EL1
 # CHECK-NEXT:  1      1     0.07                  U     mrs	x3, ZCR_EL1
 # CHECK-NEXT:  1      1     0.07                  U     mrs	x3, ZCR_EL12
 # CHECK-NEXT:  1      1     0.07                  U     mrs	x3, ZCR_EL2
 # CHECK-NEXT:  1      1     0.07                  U     mrs	x3, ZCR_EL3
 # CHECK-NEXT:  1      1     0.07                  U     msr	ZCR_EL1, x3
-# CHECK-NEXT:  2      5     2.00                        msb	z0.d, p0/m, z0.d, z0.d
+# CHECK-NEXT:  1      5     2.00                        msb	z0.d, p0/m, z0.d, z0.d
 # CHECK-NEXT:  1      1     0.07                  U     msr	ZCR_EL12, x3
 # CHECK-NEXT:  1      1     0.07                  U     msr	ZCR_EL2, x3
 # CHECK-NEXT:  1      1     0.07                  U     msr	ZCR_EL3, x3
 # CHECK-NEXT:  1      4     1.00                        mul	z0.b, p7/m, z0.b, z31.b
-# CHECK-NEXT:  2      5     2.00                        mul	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      5     2.00                        mul	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  1      4     1.00                        mul	z0.h, p7/m, z0.h, z31.h
 # CHECK-NEXT:  1      4     1.00                        mul	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  1      4     1.00                        mul	z31.b, z31.b, #-128
 # CHECK-NEXT:  1      4     1.00                        mul	z31.b, z31.b, #127
-# CHECK-NEXT:  2      5     2.00                        mul	z31.d, z31.d, #-128
-# CHECK-NEXT:  2      5     2.00                        mul	z31.d, z31.d, #127
+# CHECK-NEXT:  1      5     2.00                        mul	z31.d, z31.d, #-128
+# CHECK-NEXT:  1      5     2.00                        mul	z31.d, z31.d, #127
 # CHECK-NEXT:  1      4     1.00                        mul	z31.h, z31.h, #-128
 # CHECK-NEXT:  1      4     1.00                        mul	z31.h, z31.h, #127
 # CHECK-NEXT:  1      4     1.00                        mul	z31.s, z31.s, #-128
 # CHECK-NEXT:  1      4     1.00                        mul	z31.s, z31.s, #127
 # CHECK-NEXT:  1      1     1.00                        nand	p0.b, p0/z, p0.b, p0.b
 # CHECK-NEXT:  1      1     1.00                        nand	p15.b, p15/z, p15.b, p15.b
-# CHECK-NEXT:  2      2     2.00                        nands	p0.b, p0/z, p0.b, p0.b
-# CHECK-NEXT:  2      2     2.00                        nands	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      2     2.00                        nands	p0.b, p0/z, p0.b, p0.b
+# CHECK-NEXT:  1      2     2.00                        nands	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      2     0.50                        neg	z0.b, p0/m, z0.b
 # CHECK-NEXT:  1      2     0.50                        neg	z0.d, p0/m, z0.d
 # CHECK-NEXT:  1      2     0.50                        neg	z0.h, p0/m, z0.h
@@ -3928,20 +3928,20 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        neg	z31.s, p7/m, z31.s
 # CHECK-NEXT:  1      1     1.00                        nor	p0.b, p0/z, p0.b, p0.b
 # CHECK-NEXT:  1      1     1.00                        nor	p15.b, p15/z, p15.b, p15.b
-# CHECK-NEXT:  2      2     2.00                        nors	p0.b, p0/z, p0.b, p0.b
-# CHECK-NEXT:  2      2     2.00                        nors	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      2     2.00                        nors	p0.b, p0/z, p0.b, p0.b
+# CHECK-NEXT:  1      2     2.00                        nors	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      1     1.00                        not	p0.b, p0/z, p0.b
 # CHECK-NEXT:  1      1     1.00                        not	p15.b, p15/z, p15.b
 # CHECK-NEXT:  1      2     0.50                        not	z31.b, p7/m, z31.b
 # CHECK-NEXT:  1      2     0.50                        not	z31.d, p7/m, z31.d
 # CHECK-NEXT:  1      2     0.50                        not	z31.h, p7/m, z31.h
 # CHECK-NEXT:  1      2     0.50                        not	z31.s, p7/m, z31.s
-# CHECK-NEXT:  2      2     2.00                        nots	p0.b, p0/z, p0.b
-# CHECK-NEXT:  2      2     2.00                        nots	p15.b, p15/z, p15.b
+# CHECK-NEXT:  1      2     2.00                        nots	p0.b, p0/z, p0.b
+# CHECK-NEXT:  1      2     2.00                        nots	p15.b, p15/z, p15.b
 # CHECK-NEXT:  1      1     1.00                        orn	p0.b, p0/z, p0.b, p0.b
 # CHECK-NEXT:  1      1     1.00                        orn	p15.b, p15/z, p15.b, p15.b
-# CHECK-NEXT:  2      2     2.00                        orns	p0.b, p0/z, p0.b, p0.b
-# CHECK-NEXT:  2      2     2.00                        orns	p15.b, p15/z, p15.b, p15.b
+# CHECK-NEXT:  1      2     2.00                        orns	p0.b, p0/z, p0.b, p0.b
+# CHECK-NEXT:  1      2     2.00                        orns	p15.b, p15/z, p15.b, p15.b
 # CHECK-NEXT:  1      1     1.00                        orr	p0.b, p0/z, p0.b, p1.b
 # CHECK-NEXT:  1      2     0.50                        orr	z0.d, z0.d, #0x6
 # CHECK-NEXT:  1      2     0.50                        orr	z0.d, z0.d, #0xfffffffffffffff9
@@ -3956,11 +3956,11 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        orr	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        orr	z5.b, z5.b, #0x6
 # CHECK-NEXT:  1      2     0.50                        orr	z5.b, z5.b, #0xf9
-# CHECK-NEXT:  2      2     2.00                        orrs	p0.b, p0/z, p0.b, p1.b
-# CHECK-NEXT:  4      12    2.00                        orv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        orv	d0, p7, z31.d
-# CHECK-NEXT:  4      12    2.00                        orv	h0, p7, z31.h
-# CHECK-NEXT:  4      12    2.00                        orv	s0, p7, z31.s
+# CHECK-NEXT:  1      2     2.00                        orrs	p0.b, p0/z, p0.b, p1.b
+# CHECK-NEXT:  1      12    2.00                        orv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        orv	d0, p7, z31.d
+# CHECK-NEXT:  1      12    2.00                        orv	h0, p7, z31.h
+# CHECK-NEXT:  1      12    2.00                        orv	s0, p7, z31.s
 # CHECK-NEXT:  1      2     1.00                        pfalse	p15.b
 # CHECK-NEXT:  1      2     1.00                        pfirst	p0.b, p15, p0.b
 # CHECK-NEXT:  1      2     1.00                        pfirst	p15.b, p15, p15.b
@@ -4010,45 +4010,45 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        ptrue	p7.s, vl64
 # CHECK-NEXT:  1      2     1.00                        ptrue	p7.s, vl7
 # CHECK-NEXT:  1      2     1.00                        ptrue	p7.s, vl8
-# CHECK-NEXT:  2      3     2.00                        ptrues	p0.b, pow2
-# CHECK-NEXT:  2      3     2.00                        ptrues	p0.d, pow2
-# CHECK-NEXT:  2      3     2.00                        ptrues	p0.h, pow2
-# CHECK-NEXT:  2      3     2.00                        ptrues	p0.s, pow2
-# CHECK-NEXT:  2      3     2.00                        ptrues	p15.b
-# CHECK-NEXT:  2      3     2.00                        ptrues	p15.d
-# CHECK-NEXT:  2      3     2.00                        ptrues	p15.h
-# CHECK-NEXT:  2      3     2.00                        ptrues	p15.s
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #14
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #15
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #16
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #17
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #18
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #19
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #20
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #21
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #22
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #23
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #24
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #25
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #26
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #27
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, #28
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, mul3
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, mul4
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl1
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl128
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl16
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl2
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl256
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl3
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl32
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl4
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl5
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl6
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl64
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl7
-# CHECK-NEXT:  2      3     2.00                        ptrues	p7.s, vl8
+# CHECK-NEXT:  1      3     2.00                        ptrues	p0.b, pow2
+# CHECK-NEXT:  1      3     2.00                        ptrues	p0.d, pow2
+# CHECK-NEXT:  1      3     2.00                        ptrues	p0.h, pow2
+# CHECK-NEXT:  1      3     2.00                        ptrues	p0.s, pow2
+# CHECK-NEXT:  1      3     2.00                        ptrues	p15.b
+# CHECK-NEXT:  1      3     2.00                        ptrues	p15.d
+# CHECK-NEXT:  1      3     2.00                        ptrues	p15.h
+# CHECK-NEXT:  1      3     2.00                        ptrues	p15.s
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #14
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #15
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #16
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #17
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #18
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #19
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #20
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #21
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #22
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #23
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #24
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #25
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #26
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #27
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, #28
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, mul3
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, mul4
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl1
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl128
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl16
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl2
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl256
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl3
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl32
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl4
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl5
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl6
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl64
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl7
+# CHECK-NEXT:  1      3     2.00                        ptrues	p7.s, vl8
 # CHECK-NEXT:  1      2     1.00                        punpkhi	p0.h, p0.b
 # CHECK-NEXT:  1      2     1.00                        punpkhi	p15.h, p15.b
 # CHECK-NEXT:  1      2     1.00                        punpklo	p0.h, p0.b
@@ -4058,11 +4058,11 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        rbit	z0.h, p7/m, z31.h
 # CHECK-NEXT:  1      2     0.50                        rbit	z0.s, p7/m, z31.s
 # CHECK-NEXT:  1      2     1.00    *             U     rdffr	p0.b
-# CHECK-NEXT:  2      3     2.00    *             U     rdffr	p0.b, p0/z
+# CHECK-NEXT:  1      3     2.00    *             U     rdffr	p0.b, p0/z
 # CHECK-NEXT:  1      2     1.00    *             U     rdffr	p15.b
-# CHECK-NEXT:  2      3     2.00    *             U     rdffr	p15.b, p15/z
-# CHECK-NEXT:  1      4     0.50                  U     rdffrs	p0.b, p0/z
-# CHECK-NEXT:  1      4     0.50                  U     rdffrs	p15.b, p15/z
+# CHECK-NEXT:  1      3     2.00    *             U     rdffr	p15.b, p15/z
+# CHECK-NEXT:  1      4     3.00                  U     rdffrs	p0.b, p0/z
+# CHECK-NEXT:  1      4     3.00                  U     rdffrs	p15.b, p15/z
 # CHECK-NEXT:  1      2     1.00                        rdvl	x0, #0
 # CHECK-NEXT:  1      2     1.00                        rdvl	x21, #-32
 # CHECK-NEXT:  1      2     1.00                        rdvl	x23, #31
@@ -4081,18 +4081,18 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        sabd	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        sabd	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  1      2     0.50                        sabd	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  5      14    2.00                        saddv	d0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        saddv	d0, p7, z31.h
-# CHECK-NEXT:  4      10    2.00                        saddv	d0, p7, z31.s
+# CHECK-NEXT:  1      14    2.00                        saddv	d0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        saddv	d0, p7, z31.h
+# CHECK-NEXT:  1      10    2.00                        saddv	d0, p7, z31.s
 # CHECK-NEXT:  1      3     1.00                        scvtf	z0.d, p0/m, z0.d
-# CHECK-NEXT:  4      6     4.00                        scvtf	z0.h, p0/m, z0.h
-# CHECK-NEXT:  2      4     2.00                        scvtf	z0.h, p0/m, z0.s
+# CHECK-NEXT:  1      6     4.00                        scvtf	z0.h, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        scvtf	z0.h, p0/m, z0.s
 # CHECK-NEXT:  1      3     1.00                        scvtf	z0.s, p0/m, z0.d
-# CHECK-NEXT:  2      4     2.00                        scvtf	z0.s, p0/m, z0.s
-# CHECK-NEXT:  1      20    7.00                        sdiv	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  1      12    7.00                        sdiv	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  1      20    7.00                        sdivr	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  1      12    7.00                        sdivr	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  1      4     2.00                        scvtf	z0.s, p0/m, z0.s
+# CHECK-NEXT:  1      20    20.00                       sdiv	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      12    11.00                       sdiv	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  1      20    20.00                       sdivr	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      12    11.00                       sdivr	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  1      4     1.00                        sdot	z0.d, z1.h, z15.h[1]
 # CHECK-NEXT:  1      4     1.00                        sdot	z0.d, z1.h, z31.h
 # CHECK-NEXT:  1      3     0.50                        sdot	z0.s, z1.b, z31.b
@@ -4114,9 +4114,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        smax	z31.h, z31.h, #127
 # CHECK-NEXT:  1      2     0.50                        smax	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        smax	z31.s, z31.s, #127
-# CHECK-NEXT:  5      14    2.00                        smaxv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        smaxv	h0, p7, z31.h
-# CHECK-NEXT:  4      10    2.00                        smaxv	s0, p7, z31.s
+# CHECK-NEXT:  1      14    2.00                        smaxv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        smaxv	h0, p7, z31.h
+# CHECK-NEXT:  1      10    2.00                        smaxv	s0, p7, z31.s
 # CHECK-NEXT:  1      2     0.50                        smin	z0.b, z0.b, #-128
 # CHECK-NEXT:  1      2     0.50                        smin	z0.d, z0.d, #-128
 # CHECK-NEXT:  1      2     0.50                        smin	z0.h, z0.h, #-128
@@ -4129,12 +4129,12 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        smin	z31.h, z31.h, #127
 # CHECK-NEXT:  1      2     0.50                        smin	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        smin	z31.s, z31.s, #127
-# CHECK-NEXT:  5      14    2.00                        sminv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        sminv	h0, p7, z31.h
-# CHECK-NEXT:  4      10    2.00                        sminv	s0, p7, z31.s
+# CHECK-NEXT:  1      14    2.00                        sminv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        sminv	h0, p7, z31.h
+# CHECK-NEXT:  1      10    2.00                        sminv	s0, p7, z31.s
 # CHECK-NEXT:  1      3     0.50                        smmla	z0.s, z1.b, z2.b
 # CHECK-NEXT:  1      4     1.00                        smulh	z0.b, p7/m, z0.b, z31.b
-# CHECK-NEXT:  2      5     2.00                        smulh	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      5     2.00                        smulh	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  1      4     1.00                        smulh	z0.h, p7/m, z0.h, z31.h
 # CHECK-NEXT:  1      4     1.00                        smulh	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  1      3     1.00                        splice	z31.b, p7, z31.b, z31.b
@@ -4174,10 +4174,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqdecd	x0, w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqdecd	x0, w0, pow2
 # CHECK-NEXT:  1      2     1.00                        sqdecd	x0, w0, pow2, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqdecd	z0.d
-# CHECK-NEXT:  1      2     1.00                        sqdecd	z0.d, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqdecd	z0.d, pow2
-# CHECK-NEXT:  1      2     1.00                        sqdecd	z0.d, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqdecd	z0.d
+# CHECK-NEXT:  1      2     0.50                        sqdecd	z0.d, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqdecd	z0.d, pow2
+# CHECK-NEXT:  1      2     0.50                        sqdecd	z0.d, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqdech	x0
 # CHECK-NEXT:  1      2     1.00                        sqdech	x0, #14
 # CHECK-NEXT:  1      2     1.00                        sqdech	x0, all, mul #16
@@ -4187,10 +4187,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqdech	x0, w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqdech	x0, w0, pow2
 # CHECK-NEXT:  1      2     1.00                        sqdech	x0, w0, pow2, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqdech	z0.h
-# CHECK-NEXT:  1      2     1.00                        sqdech	z0.h, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqdech	z0.h, pow2
-# CHECK-NEXT:  1      2     1.00                        sqdech	z0.h, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqdech	z0.h
+# CHECK-NEXT:  1      2     0.50                        sqdech	z0.h, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqdech	z0.h, pow2
+# CHECK-NEXT:  1      2     0.50                        sqdech	z0.h, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqdecp	x0, p0.b
 # CHECK-NEXT:  1      2     1.00                        sqdecp	x0, p0.d
 # CHECK-NEXT:  1      2     1.00                        sqdecp	x0, p0.h
@@ -4199,9 +4199,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqdecp	xzr, p15.d, wzr
 # CHECK-NEXT:  1      2     1.00                        sqdecp	xzr, p15.h, wzr
 # CHECK-NEXT:  1      2     1.00                        sqdecp	xzr, p15.s, wzr
-# CHECK-NEXT:  3      7     2.00                        sqdecp	z0.d, p0.d
-# CHECK-NEXT:  3      7     2.00                        sqdecp	z0.h, p0.h
-# CHECK-NEXT:  3      7     2.00                        sqdecp	z0.s, p0.s
+# CHECK-NEXT:  2      7     2.00                        sqdecp	z0.d, p0.d
+# CHECK-NEXT:  2      7     2.00                        sqdecp	z0.h, p0.h
+# CHECK-NEXT:  2      7     2.00                        sqdecp	z0.s, p0.s
 # CHECK-NEXT:  1      2     1.00                        sqdecw	x0
 # CHECK-NEXT:  1      2     1.00                        sqdecw	x0, #14
 # CHECK-NEXT:  1      2     1.00                        sqdecw	x0, all, mul #16
@@ -4211,10 +4211,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqdecw	x0, w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqdecw	x0, w0, pow2
 # CHECK-NEXT:  1      2     1.00                        sqdecw	x0, w0, pow2, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqdecw	z0.s
-# CHECK-NEXT:  1      2     1.00                        sqdecw	z0.s, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqdecw	z0.s, pow2
-# CHECK-NEXT:  1      2     1.00                        sqdecw	z0.s, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqdecw	z0.s
+# CHECK-NEXT:  1      2     0.50                        sqdecw	z0.s, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqdecw	z0.s, pow2
+# CHECK-NEXT:  1      2     0.50                        sqdecw	z0.s, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqincb	x0
 # CHECK-NEXT:  1      2     1.00                        sqincb	x0, #14
 # CHECK-NEXT:  1      2     1.00                        sqincb	x0, all, mul #16
@@ -4233,10 +4233,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqincd	x0, w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqincd	x0, w0, pow2
 # CHECK-NEXT:  1      2     1.00                        sqincd	x0, w0, pow2, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqincd	z0.d
-# CHECK-NEXT:  1      2     1.00                        sqincd	z0.d, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqincd	z0.d, pow2
-# CHECK-NEXT:  1      2     1.00                        sqincd	z0.d, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqincd	z0.d
+# CHECK-NEXT:  1      2     0.50                        sqincd	z0.d, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqincd	z0.d, pow2
+# CHECK-NEXT:  1      2     0.50                        sqincd	z0.d, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqinch	x0
 # CHECK-NEXT:  1      2     1.00                        sqinch	x0, #14
 # CHECK-NEXT:  1      2     1.00                        sqinch	x0, all, mul #16
@@ -4246,10 +4246,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqinch	x0, w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqinch	x0, w0, pow2
 # CHECK-NEXT:  1      2     1.00                        sqinch	x0, w0, pow2, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqinch	z0.h
-# CHECK-NEXT:  1      2     1.00                        sqinch	z0.h, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqinch	z0.h, pow2
-# CHECK-NEXT:  1      2     1.00                        sqinch	z0.h, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqinch	z0.h
+# CHECK-NEXT:  1      2     0.50                        sqinch	z0.h, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqinch	z0.h, pow2
+# CHECK-NEXT:  1      2     0.50                        sqinch	z0.h, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqincp	x0, p0.b
 # CHECK-NEXT:  1      2     1.00                        sqincp	x0, p0.d
 # CHECK-NEXT:  1      2     1.00                        sqincp	x0, p0.h
@@ -4258,9 +4258,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqincp	xzr, p15.d, wzr
 # CHECK-NEXT:  1      2     1.00                        sqincp	xzr, p15.h, wzr
 # CHECK-NEXT:  1      2     1.00                        sqincp	xzr, p15.s, wzr
-# CHECK-NEXT:  3      7     2.00                        sqincp	z0.d, p0.d
-# CHECK-NEXT:  3      7     2.00                        sqincp	z0.h, p0.h
-# CHECK-NEXT:  3      7     2.00                        sqincp	z0.s, p0.s
+# CHECK-NEXT:  2      7     2.00                        sqincp	z0.d, p0.d
+# CHECK-NEXT:  2      7     2.00                        sqincp	z0.h, p0.h
+# CHECK-NEXT:  2      7     2.00                        sqincp	z0.s, p0.s
 # CHECK-NEXT:  1      2     1.00                        sqincw	x0
 # CHECK-NEXT:  1      2     1.00                        sqincw	x0, #14
 # CHECK-NEXT:  1      2     1.00                        sqincw	x0, all, mul #16
@@ -4270,10 +4270,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        sqincw	x0, w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        sqincw	x0, w0, pow2
 # CHECK-NEXT:  1      2     1.00                        sqincw	x0, w0, pow2, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqincw	z0.s
-# CHECK-NEXT:  1      2     1.00                        sqincw	z0.s, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        sqincw	z0.s, pow2
-# CHECK-NEXT:  1      2     1.00                        sqincw	z0.s, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqincw	z0.s
+# CHECK-NEXT:  1      2     0.50                        sqincw	z0.s, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        sqincw	z0.s, pow2
+# CHECK-NEXT:  1      2     0.50                        sqincw	z0.s, pow2, mul #16
 # CHECK-NEXT:  1      2     0.50                        sqsub	z0.b, z0.b, #0
 # CHECK-NEXT:  1      2     0.50                        sqsub	z0.b, z0.b, z0.b
 # CHECK-NEXT:  1      2     0.50                        sqsub	z0.d, z0.d, #0
@@ -4292,148 +4292,148 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.b }, p0, [x0, x0]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.b }, p0, [x0]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.d }, p0, [x0, x0]
-# CHECK-NEXT:  2      6     0.50           *            st1b	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1b	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1b	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1b	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1b	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1b	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  2      6     0.50           *            st1b	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1b	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.h }, p0, [x0, x0]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.h }, p0, [x0]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.s }, p0, [x0, x0]
-# CHECK-NEXT:  4      10    1.00           *            st1b	{ z0.s }, p0, [x0, z0.s, sxtw]
-# CHECK-NEXT:  4      10    1.00           *            st1b	{ z0.s }, p0, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      10    4.00           *            st1b	{ z0.s }, p0, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      10    4.00           *            st1b	{ z0.s }, p0, [x0, z0.s, uxtw]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z0.s }, p0, [x0]
-# CHECK-NEXT:  4      10    1.00           *            st1b	{ z0.s }, p7, [z0.s]
+# CHECK-NEXT:  2      10    4.00           *            st1b	{ z0.s }, p7, [z0.s]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z21.b }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z21.h }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z21.s }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z31.b }, p7, [sp, #-1, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  2      6     0.50           *            st1b	{ z31.d }, p7, [z31.d, #31]
+# CHECK-NEXT:  2      6     2.00           *            st1b	{ z31.d }, p7, [z31.d, #31]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z31.h }, p7, [sp, #-1, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1b	{ z31.s }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      10    1.00           *            st1b	{ z31.s }, p7, [z31.s, #31]
+# CHECK-NEXT:  2      10    4.00           *            st1b	{ z31.s }, p7, [z31.s, #31]
 # CHECK-NEXT:  2      2     0.50           *            st1d	{ z0.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p0, [x0, z0.d, lsl #3]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p0, [x0, z0.d, sxtw #3]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p0, [x0, z0.d, uxtw #3]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p0, [x0, z0.d, lsl #3]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p0, [x0, z0.d, sxtw #3]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p0, [x0, z0.d, uxtw #3]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1d	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1d	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1d	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  2      6     0.50           *            st1d	{ z31.d }, p7, [z31.d, #248]
+# CHECK-NEXT:  2      6     2.00           *            st1d	{ z31.d }, p7, [z31.d, #248]
 # CHECK-NEXT:  3      2     0.50           *            st1h	{ z0.d }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p0, [x0, z0.d, lsl #1]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p0, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p0, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p0, [x0, z0.d, lsl #1]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p0, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p0, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  3      2     0.50           *            st1h	{ z0.h }, p0, [x0, x0, lsl #1]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z0.h }, p0, [x0]
 # CHECK-NEXT:  3      2     0.50           *            st1h	{ z0.s }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  4      10    1.00           *            st1h	{ z0.s }, p0, [x0, z0.s, sxtw #1]
-# CHECK-NEXT:  4      10    1.00           *            st1h	{ z0.s }, p0, [x0, z0.s, sxtw]
-# CHECK-NEXT:  4      10    1.00           *            st1h	{ z0.s }, p0, [x0, z0.s, uxtw #1]
-# CHECK-NEXT:  4      10    1.00           *            st1h	{ z0.s }, p0, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      10    4.00           *            st1h	{ z0.s }, p0, [x0, z0.s, sxtw #1]
+# CHECK-NEXT:  2      10    4.00           *            st1h	{ z0.s }, p0, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      10    4.00           *            st1h	{ z0.s }, p0, [x0, z0.s, uxtw #1]
+# CHECK-NEXT:  2      10    4.00           *            st1h	{ z0.s }, p0, [x0, z0.s, uxtw]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z0.s }, p0, [x0]
-# CHECK-NEXT:  4      10    1.00           *            st1h	{ z0.s }, p7, [z0.s]
+# CHECK-NEXT:  2      10    4.00           *            st1h	{ z0.s }, p7, [z0.s]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z21.h }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z21.s }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  2      6     0.50           *            st1h	{ z31.d }, p7, [z31.d, #62]
+# CHECK-NEXT:  2      6     2.00           *            st1h	{ z31.d }, p7, [z31.d, #62]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z31.h }, p7, [sp, #-1, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1h	{ z31.s }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      10    1.00           *            st1h	{ z31.s }, p7, [z31.s, #62]
+# CHECK-NEXT:  2      10    4.00           *            st1h	{ z31.s }, p7, [z31.s, #62]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z0.d }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p0, [x0, z0.d, lsl #2]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p0, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p0, [x0, z0.d, uxtw #2]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p0, [x0, z0.d, lsl #2]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p0, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p0, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z0.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  4      10    1.00           *            st1w	{ z0.s }, p0, [x0, z0.s, sxtw #2]
-# CHECK-NEXT:  4      10    1.00           *            st1w	{ z0.s }, p0, [x0, z0.s, sxtw]
-# CHECK-NEXT:  4      10    1.00           *            st1w	{ z0.s }, p0, [x0, z0.s, uxtw #2]
-# CHECK-NEXT:  4      10    1.00           *            st1w	{ z0.s }, p0, [x0, z0.s, uxtw]
+# CHECK-NEXT:  2      10    4.00           *            st1w	{ z0.s }, p0, [x0, z0.s, sxtw #2]
+# CHECK-NEXT:  2      10    4.00           *            st1w	{ z0.s }, p0, [x0, z0.s, sxtw]
+# CHECK-NEXT:  2      10    4.00           *            st1w	{ z0.s }, p0, [x0, z0.s, uxtw #2]
+# CHECK-NEXT:  2      10    4.00           *            st1w	{ z0.s }, p0, [x0, z0.s, uxtw]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z0.s }, p0, [x0]
-# CHECK-NEXT:  4      10    1.00           *            st1w	{ z0.s }, p7, [z0.s]
+# CHECK-NEXT:  2      10    4.00           *            st1w	{ z0.s }, p7, [z0.s]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z21.s }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  2      6     0.50           *            st1w	{ z31.d }, p7, [z31.d, #124]
+# CHECK-NEXT:  2      6     2.00           *            st1w	{ z31.d }, p7, [z31.d, #124]
 # CHECK-NEXT:  2      2     0.50           *            st1w	{ z31.s }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  4      10    1.00           *            st1w	{ z31.s }, p7, [z31.s, #124]
-# CHECK-NEXT:  2      4     0.50           *            st2b	{ z0.b, z1.b }, p0, [x0, x0]
-# CHECK-NEXT:  2      4     0.50           *            st2b	{ z0.b, z1.b }, p0, [x0]
-# CHECK-NEXT:  2      4     0.50           *            st2b	{ z21.b, z22.b }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2b	{ z23.b, z24.b }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2b	{ z5.b, z6.b }, p3, [x17, x16]
-# CHECK-NEXT:  2      4     0.50           *            st2d	{ z0.d, z1.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  2      4     0.50           *            st2d	{ z0.d, z1.d }, p0, [x0]
-# CHECK-NEXT:  2      4     0.50           *            st2d	{ z21.d, z22.d }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2d	{ z23.d, z24.d }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2d	{ z5.d, z6.d }, p3, [x17, x16, lsl #3]
-# CHECK-NEXT:  3      4     0.50           *            st2h	{ z0.h, z1.h }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  2      4     0.50           *            st2h	{ z0.h, z1.h }, p0, [x0]
-# CHECK-NEXT:  2      4     0.50           *            st2h	{ z21.h, z22.h }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2h	{ z23.h, z24.h }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  3      4     0.50           *            st2h	{ z5.h, z6.h }, p3, [x17, x16, lsl #1]
-# CHECK-NEXT:  2      4     0.50           *            st2w	{ z0.s, z1.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  2      4     0.50           *            st2w	{ z0.s, z1.s }, p0, [x0]
-# CHECK-NEXT:  2      4     0.50           *            st2w	{ z21.s, z22.s }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2w	{ z23.s, z24.s }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  2      4     0.50           *            st2w	{ z5.s, z6.s }, p3, [x17, x16, lsl #2]
-# CHECK-NEXT:  15     7     2.50           *            st3b	{ z0.b - z2.b }, p0, [x0, x0]
-# CHECK-NEXT:  10     7     2.50           *            st3b	{ z0.b - z2.b }, p0, [x0]
-# CHECK-NEXT:  10     7     2.50           *            st3b	{ z21.b - z23.b }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  10     7     2.50           *            st3b	{ z23.b - z25.b }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  15     7     2.50           *            st3b	{ z5.b - z7.b }, p3, [x17, x16]
-# CHECK-NEXT:  15     7     2.50           *            st3d	{ z0.d - z2.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  10     7     2.50           *            st3d	{ z0.d - z2.d }, p0, [x0]
-# CHECK-NEXT:  10     7     2.50           *            st3d	{ z21.d - z23.d }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  10     7     2.50           *            st3d	{ z23.d - z25.d }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  15     7     2.50           *            st3d	{ z5.d - z7.d }, p3, [x17, x16, lsl #3]
-# CHECK-NEXT:  15     7     2.50           *            st3h	{ z0.h - z2.h }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  10     7     2.50           *            st3h	{ z0.h - z2.h }, p0, [x0]
-# CHECK-NEXT:  10     7     2.50           *            st3h	{ z21.h - z23.h }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  10     7     2.50           *            st3h	{ z23.h - z25.h }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  15     7     2.50           *            st3h	{ z5.h - z7.h }, p3, [x17, x16, lsl #1]
-# CHECK-NEXT:  15     7     2.50           *            st3w	{ z0.s - z2.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  10     7     2.50           *            st3w	{ z0.s - z2.s }, p0, [x0]
-# CHECK-NEXT:  10     7     2.50           *            st3w	{ z21.s - z23.s }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  10     7     2.50           *            st3w	{ z23.s - z25.s }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  15     7     2.50           *            st3w	{ z5.s - z7.s }, p3, [x17, x16, lsl #2]
-# CHECK-NEXT:  27     11    4.50           *            st4b	{ z0.b - z3.b }, p0, [x0, x0]
-# CHECK-NEXT:  18     19    4.50           *            st4b	{ z0.b - z3.b }, p0, [x0]
-# CHECK-NEXT:  18     19    4.50           *            st4b	{ z21.b - z24.b }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  18     19    4.50           *            st4b	{ z23.b - z26.b }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  27     11    4.50           *            st4b	{ z5.b - z8.b }, p3, [x17, x16]
-# CHECK-NEXT:  27     11    4.50           *            st4d	{ z0.d - z3.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  18     19    4.50           *            st4d	{ z0.d - z3.d }, p0, [x0]
-# CHECK-NEXT:  18     19    4.50           *            st4d	{ z21.d - z24.d }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  18     19    4.50           *            st4d	{ z23.d - z26.d }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  27     11    4.50           *            st4d	{ z5.d - z8.d }, p3, [x17, x16, lsl #3]
-# CHECK-NEXT:  27     11    4.50           *            st4h	{ z0.h - z3.h }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  18     19    4.50           *            st4h	{ z0.h - z3.h }, p0, [x0]
-# CHECK-NEXT:  18     19    4.50           *            st4h	{ z21.h - z24.h }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  18     19    4.50           *            st4h	{ z23.h - z26.h }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  27     11    4.50           *            st4h	{ z5.h - z8.h }, p3, [x17, x16, lsl #1]
-# CHECK-NEXT:  27     11    4.50           *            st4w	{ z0.s - z3.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  18     19    4.50           *            st4w	{ z0.s - z3.s }, p0, [x0]
-# CHECK-NEXT:  18     19    4.50           *            st4w	{ z21.s - z24.s }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  18     19    4.50           *            st4w	{ z23.s - z26.s }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  27     11    4.50           *            st4w	{ z5.s - z8.s }, p3, [x17, x16, lsl #2]
+# CHECK-NEXT:  2      10    4.00           *            st1w	{ z31.s }, p7, [z31.s, #124]
+# CHECK-NEXT:  2      4     1.00           *            st2b	{ z0.b, z1.b }, p0, [x0, x0]
+# CHECK-NEXT:  2      4     1.00           *            st2b	{ z0.b, z1.b }, p0, [x0]
+# CHECK-NEXT:  2      4     1.00           *            st2b	{ z21.b, z22.b }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2b	{ z23.b, z24.b }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2b	{ z5.b, z6.b }, p3, [x17, x16]
+# CHECK-NEXT:  2      4     1.00           *            st2d	{ z0.d, z1.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  2      4     1.00           *            st2d	{ z0.d, z1.d }, p0, [x0]
+# CHECK-NEXT:  2      4     1.00           *            st2d	{ z21.d, z22.d }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2d	{ z23.d, z24.d }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2d	{ z5.d, z6.d }, p3, [x17, x16, lsl #3]
+# CHECK-NEXT:  3      4     1.00           *            st2h	{ z0.h, z1.h }, p0, [x0, x0, lsl #1]
+# CHECK-NEXT:  2      4     1.00           *            st2h	{ z0.h, z1.h }, p0, [x0]
+# CHECK-NEXT:  2      4     1.00           *            st2h	{ z21.h, z22.h }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2h	{ z23.h, z24.h }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  3      4     1.00           *            st2h	{ z5.h, z6.h }, p3, [x17, x16, lsl #1]
+# CHECK-NEXT:  2      4     1.00           *            st2w	{ z0.s, z1.s }, p0, [x0, x0, lsl #2]
+# CHECK-NEXT:  2      4     1.00           *            st2w	{ z0.s, z1.s }, p0, [x0]
+# CHECK-NEXT:  2      4     1.00           *            st2w	{ z21.s, z22.s }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2w	{ z23.s, z24.s }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  2      4     1.00           *            st2w	{ z5.s, z6.s }, p3, [x17, x16, lsl #2]
+# CHECK-NEXT:  3      7     4.50           *            st3b	{ z0.b - z2.b }, p0, [x0, x0]
+# CHECK-NEXT:  2      7     4.50           *            st3b	{ z0.b - z2.b }, p0, [x0]
+# CHECK-NEXT:  2      7     4.50           *            st3b	{ z21.b - z23.b }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  2      7     4.50           *            st3b	{ z23.b - z25.b }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      7     4.50           *            st3b	{ z5.b - z7.b }, p3, [x17, x16]
+# CHECK-NEXT:  3      7     4.50           *            st3d	{ z0.d - z2.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  2      7     4.50           *            st3d	{ z0.d - z2.d }, p0, [x0]
+# CHECK-NEXT:  2      7     4.50           *            st3d	{ z21.d - z23.d }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  2      7     4.50           *            st3d	{ z23.d - z25.d }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      7     4.50           *            st3d	{ z5.d - z7.d }, p3, [x17, x16, lsl #3]
+# CHECK-NEXT:  3      7     4.50           *            st3h	{ z0.h - z2.h }, p0, [x0, x0, lsl #1]
+# CHECK-NEXT:  2      7     4.50           *            st3h	{ z0.h - z2.h }, p0, [x0]
+# CHECK-NEXT:  2      7     4.50           *            st3h	{ z21.h - z23.h }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  2      7     4.50           *            st3h	{ z23.h - z25.h }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      7     4.50           *            st3h	{ z5.h - z7.h }, p3, [x17, x16, lsl #1]
+# CHECK-NEXT:  3      7     4.50           *            st3w	{ z0.s - z2.s }, p0, [x0, x0, lsl #2]
+# CHECK-NEXT:  2      7     4.50           *            st3w	{ z0.s - z2.s }, p0, [x0]
+# CHECK-NEXT:  2      7     4.50           *            st3w	{ z21.s - z23.s }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  2      7     4.50           *            st3w	{ z23.s - z25.s }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  3      7     4.50           *            st3w	{ z5.s - z7.s }, p3, [x17, x16, lsl #2]
+# CHECK-NEXT:  3      11    9.00           *            st4b	{ z0.b - z3.b }, p0, [x0, x0]
+# CHECK-NEXT:  2      11    9.00           *            st4b	{ z0.b - z3.b }, p0, [x0]
+# CHECK-NEXT:  2      11    9.00           *            st4b	{ z21.b - z24.b }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  2      11    9.00           *            st4b	{ z23.b - z26.b }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      11    9.00           *            st4b	{ z5.b - z8.b }, p3, [x17, x16]
+# CHECK-NEXT:  3      11    9.00           *            st4d	{ z0.d - z3.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  2      11    9.00           *            st4d	{ z0.d - z3.d }, p0, [x0]
+# CHECK-NEXT:  2      11    9.00           *            st4d	{ z21.d - z24.d }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  2      11    9.00           *            st4d	{ z23.d - z26.d }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      11    9.00           *            st4d	{ z5.d - z8.d }, p3, [x17, x16, lsl #3]
+# CHECK-NEXT:  3      11    9.00           *            st4h	{ z0.h - z3.h }, p0, [x0, x0, lsl #1]
+# CHECK-NEXT:  2      11    9.00           *            st4h	{ z0.h - z3.h }, p0, [x0]
+# CHECK-NEXT:  2      11    9.00           *            st4h	{ z21.h - z24.h }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  2      11    9.00           *            st4h	{ z23.h - z26.h }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      11    9.00           *            st4h	{ z5.h - z8.h }, p3, [x17, x16, lsl #1]
+# CHECK-NEXT:  3      11    9.00           *            st4w	{ z0.s - z3.s }, p0, [x0, x0, lsl #2]
+# CHECK-NEXT:  2      11    9.00           *            st4w	{ z0.s - z3.s }, p0, [x0]
+# CHECK-NEXT:  2      11    9.00           *            st4w	{ z21.s - z24.s }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  2      11    9.00           *            st4w	{ z23.s - z26.s }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  3      11    9.00           *            st4w	{ z5.s - z8.s }, p3, [x17, x16, lsl #2]
 # CHECK-NEXT:  2      2     0.50           *            stnt1b	{ z0.b }, p0, [x0, x0]
 # CHECK-NEXT:  2      2     0.50           *            stnt1b	{ z0.b }, p0, [x0]
 # CHECK-NEXT:  2      2     0.50           *            stnt1b	{ z21.b }, p5, [x10, #7, mul vl]
@@ -4514,7 +4514,7 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        subr	z31.d, z31.d, #65280
 # CHECK-NEXT:  1      2     0.50                        subr	z31.h, z31.h, #65280
 # CHECK-NEXT:  1      2     0.50                        subr	z31.s, z31.s, #65280
-# CHECK-NEXT:  1      3     0.25                        sudot	z0.s, z1.b, z7.b[3]
+# CHECK-NEXT:  1      3     0.50                        sudot	z0.s, z1.b, z7.b[3]
 # CHECK-NEXT:  1      2     0.50                        sunpkhi	z31.d, z31.s
 # CHECK-NEXT:  1      2     0.50                        sunpkhi	z31.h, z31.b
 # CHECK-NEXT:  1      2     0.50                        sunpkhi	z31.s, z31.h
@@ -4557,18 +4557,18 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        uabd	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        uabd	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  1      2     0.50                        uabd	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  5      14    2.00                        uaddv	d0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        uaddv	d0, p7, z31.h
-# CHECK-NEXT:  4      10    2.00                        uaddv	d0, p7, z31.s
+# CHECK-NEXT:  1      14    2.00                        uaddv	d0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        uaddv	d0, p7, z31.h
+# CHECK-NEXT:  1      10    2.00                        uaddv	d0, p7, z31.s
 # CHECK-NEXT:  1      3     1.00                        ucvtf	z0.d, p0/m, z0.d
-# CHECK-NEXT:  4      6     4.00                        ucvtf	z0.h, p0/m, z0.h
-# CHECK-NEXT:  2      4     2.00                        ucvtf	z0.h, p0/m, z0.s
+# CHECK-NEXT:  1      6     4.00                        ucvtf	z0.h, p0/m, z0.h
+# CHECK-NEXT:  1      4     2.00                        ucvtf	z0.h, p0/m, z0.s
 # CHECK-NEXT:  1      3     1.00                        ucvtf	z0.s, p0/m, z0.d
-# CHECK-NEXT:  2      4     2.00                        ucvtf	z0.s, p0/m, z0.s
-# CHECK-NEXT:  1      20    7.00                        udiv	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  1      12    7.00                        udiv	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  1      20    7.00                        udivr	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  1      12    7.00                        udivr	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  1      4     2.00                        ucvtf	z0.s, p0/m, z0.s
+# CHECK-NEXT:  1      20    20.00                       udiv	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      12    11.00                       udiv	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  1      20    20.00                       udivr	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      12    11.00                       udivr	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  1      4     1.00                        udot	z0.d, z1.h, z15.h[1]
 # CHECK-NEXT:  1      4     1.00                        udot	z0.d, z1.h, z31.h
 # CHECK-NEXT:  1      3     0.50                        udot	z0.s, z1.b, z31.b
@@ -4579,21 +4579,21 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        umax	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        umax	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  1      2     0.50                        umax	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  5      14    2.00                        umaxv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        umaxv	h0, p7, z31.h
-# CHECK-NEXT:  4      10    2.00                        umaxv	s0, p7, z31.s
+# CHECK-NEXT:  1      14    2.00                        umaxv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        umaxv	h0, p7, z31.h
+# CHECK-NEXT:  1      10    2.00                        umaxv	s0, p7, z31.s
 # CHECK-NEXT:  1      2     0.50                        umin	z0.b, z0.b, #0
 # CHECK-NEXT:  1      2     0.50                        umin	z31.b, p7/m, z31.b, z31.b
 # CHECK-NEXT:  1      2     0.50                        umin	z31.b, z31.b, #255
 # CHECK-NEXT:  1      2     0.50                        umin	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        umin	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  1      2     0.50                        umin	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  5      14    2.00                        uminv	b0, p7, z31.b
-# CHECK-NEXT:  4      12    2.00                        uminv	h0, p7, z31.h
-# CHECK-NEXT:  4      10    2.00                        uminv	s0, p7, z31.s
+# CHECK-NEXT:  1      14    2.00                        uminv	b0, p7, z31.b
+# CHECK-NEXT:  1      12    2.00                        uminv	h0, p7, z31.h
+# CHECK-NEXT:  1      10    2.00                        uminv	s0, p7, z31.s
 # CHECK-NEXT:  1      3     0.50                        ummla	z0.s, z1.b, z2.b
 # CHECK-NEXT:  1      4     1.00                        umulh	z0.b, p7/m, z0.b, z31.b
-# CHECK-NEXT:  2      5     2.00                        umulh	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  1      5     2.00                        umulh	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  1      4     1.00                        umulh	z0.h, p7/m, z0.h, z31.h
 # CHECK-NEXT:  1      4     1.00                        umulh	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        uqadd	z0.b, z0.b, #0
@@ -4629,10 +4629,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqdecd	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdecd	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        uqdecd	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        uqdecd	z0.d
-# CHECK-NEXT:  1      2     1.00                        uqdecd	z0.d, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        uqdecd	z0.d, pow2
-# CHECK-NEXT:  1      2     1.00                        uqdecd	z0.d, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqdecd	z0.d
+# CHECK-NEXT:  1      2     0.50                        uqdecd	z0.d, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqdecd	z0.d, pow2
+# CHECK-NEXT:  1      2     0.50                        uqdecd	z0.d, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdech	w0
 # CHECK-NEXT:  1      2     1.00                        uqdech	w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdech	w0, pow2
@@ -4642,10 +4642,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqdech	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdech	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        uqdech	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        uqdech	z0.h
-# CHECK-NEXT:  1      2     1.00                        uqdech	z0.h, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        uqdech	z0.h, pow2
-# CHECK-NEXT:  1      2     1.00                        uqdech	z0.h, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqdech	z0.h
+# CHECK-NEXT:  1      2     0.50                        uqdech	z0.h, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqdech	z0.h, pow2
+# CHECK-NEXT:  1      2     0.50                        uqdech	z0.h, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdecp	wzr, p15.b
 # CHECK-NEXT:  1      2     1.00                        uqdecp	wzr, p15.d
 # CHECK-NEXT:  1      2     1.00                        uqdecp	wzr, p15.h
@@ -4654,9 +4654,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqdecp	x0, p0.d
 # CHECK-NEXT:  1      2     1.00                        uqdecp	x0, p0.h
 # CHECK-NEXT:  1      2     1.00                        uqdecp	x0, p0.s
-# CHECK-NEXT:  3      7     2.00                        uqdecp	z0.d, p0.d
-# CHECK-NEXT:  3      7     2.00                        uqdecp	z0.h, p0.h
-# CHECK-NEXT:  3      7     2.00                        uqdecp	z0.s, p0.s
+# CHECK-NEXT:  2      7     2.00                        uqdecp	z0.d, p0.d
+# CHECK-NEXT:  2      7     2.00                        uqdecp	z0.h, p0.h
+# CHECK-NEXT:  2      7     2.00                        uqdecp	z0.s, p0.s
 # CHECK-NEXT:  1      2     1.00                        uqdecw	w0
 # CHECK-NEXT:  1      2     1.00                        uqdecw	w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdecw	w0, pow2
@@ -4666,10 +4666,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqdecw	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqdecw	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        uqdecw	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        uqdecw	z0.s
-# CHECK-NEXT:  1      2     1.00                        uqdecw	z0.s, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        uqdecw	z0.s, pow2
-# CHECK-NEXT:  1      2     1.00                        uqdecw	z0.s, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqdecw	z0.s
+# CHECK-NEXT:  1      2     0.50                        uqdecw	z0.s, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqdecw	z0.s, pow2
+# CHECK-NEXT:  1      2     0.50                        uqdecw	z0.s, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqincb	w0
 # CHECK-NEXT:  1      2     1.00                        uqincb	w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqincb	w0, pow2
@@ -4688,10 +4688,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqincd	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqincd	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        uqincd	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        uqincd	z0.d
-# CHECK-NEXT:  1      2     1.00                        uqincd	z0.d, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        uqincd	z0.d, pow2
-# CHECK-NEXT:  1      2     1.00                        uqincd	z0.d, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqincd	z0.d
+# CHECK-NEXT:  1      2     0.50                        uqincd	z0.d, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqincd	z0.d, pow2
+# CHECK-NEXT:  1      2     0.50                        uqincd	z0.d, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqinch	w0
 # CHECK-NEXT:  1      2     1.00                        uqinch	w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqinch	w0, pow2
@@ -4701,10 +4701,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqinch	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqinch	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        uqinch	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        uqinch	z0.h
-# CHECK-NEXT:  1      2     1.00                        uqinch	z0.h, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        uqinch	z0.h, pow2
-# CHECK-NEXT:  1      2     1.00                        uqinch	z0.h, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqinch	z0.h
+# CHECK-NEXT:  1      2     0.50                        uqinch	z0.h, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqinch	z0.h, pow2
+# CHECK-NEXT:  1      2     0.50                        uqinch	z0.h, pow2, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqincp	wzr, p15.b
 # CHECK-NEXT:  1      2     1.00                        uqincp	wzr, p15.d
 # CHECK-NEXT:  1      2     1.00                        uqincp	wzr, p15.h
@@ -4713,9 +4713,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqincp	x0, p0.d
 # CHECK-NEXT:  1      2     1.00                        uqincp	x0, p0.h
 # CHECK-NEXT:  1      2     1.00                        uqincp	x0, p0.s
-# CHECK-NEXT:  3      7     2.00                        uqincp	z0.d, p0.d
-# CHECK-NEXT:  3      7     2.00                        uqincp	z0.h, p0.h
-# CHECK-NEXT:  3      7     2.00                        uqincp	z0.s, p0.s
+# CHECK-NEXT:  2      7     2.00                        uqincp	z0.d, p0.d
+# CHECK-NEXT:  2      7     2.00                        uqincp	z0.h, p0.h
+# CHECK-NEXT:  2      7     2.00                        uqincp	z0.s, p0.s
 # CHECK-NEXT:  1      2     1.00                        uqincw	w0
 # CHECK-NEXT:  1      2     1.00                        uqincw	w0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqincw	w0, pow2
@@ -4725,10 +4725,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     1.00                        uqincw	x0, all, mul #16
 # CHECK-NEXT:  1      2     1.00                        uqincw	x0, pow2
 # CHECK-NEXT:  1      2     1.00                        uqincw	x0, vl1
-# CHECK-NEXT:  1      2     1.00                        uqincw	z0.s
-# CHECK-NEXT:  1      2     1.00                        uqincw	z0.s, all, mul #16
-# CHECK-NEXT:  1      2     1.00                        uqincw	z0.s, pow2
-# CHECK-NEXT:  1      2     1.00                        uqincw	z0.s, pow2, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqincw	z0.s
+# CHECK-NEXT:  1      2     0.50                        uqincw	z0.s, all, mul #16
+# CHECK-NEXT:  1      2     0.50                        uqincw	z0.s, pow2
+# CHECK-NEXT:  1      2     0.50                        uqincw	z0.s, pow2, mul #16
 # CHECK-NEXT:  1      2     0.50                        uqsub	z0.b, z0.b, #0
 # CHECK-NEXT:  1      2     0.50                        uqsub	z0.b, z0.b, z0.b
 # CHECK-NEXT:  1      2     0.50                        uqsub	z0.d, z0.d, #0
@@ -4744,8 +4744,8 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        uqsub	z31.d, z31.d, #65280
 # CHECK-NEXT:  1      2     0.50                        uqsub	z31.h, z31.h, #65280
 # CHECK-NEXT:  1      2     0.50                        uqsub	z31.s, z31.s, #65280
-# CHECK-NEXT:  1      3     0.25                        usdot	z0.s, z1.b, z31.b
-# CHECK-NEXT:  1      3     0.25                        usdot	z0.s, z1.b, z7.b[3]
+# CHECK-NEXT:  1      3     0.50                        usdot	z0.s, z1.b, z31.b
+# CHECK-NEXT:  1      3     0.50                        usdot	z0.s, z1.b, z7.b[3]
 # CHECK-NEXT:  1      3     0.50                        usmmla	z0.s, z1.b, z2.b
 # CHECK-NEXT:  1      2     0.50                        uunpkhi	z31.d, z31.s
 # CHECK-NEXT:  1      2     0.50                        uunpkhi	z31.h, z31.b
@@ -4781,10 +4781,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  1      2     0.50                        uzp2	z31.d, z31.d, z31.d
 # CHECK-NEXT:  1      2     0.50                        uzp2	z31.h, z31.h, z31.h
 # CHECK-NEXT:  1      2     0.50                        uzp2	z31.s, z31.s, z31.s
-# CHECK-NEXT:  2      3     2.00                        whilele	p0.b, w30, wzr
-# CHECK-NEXT:  2      3     2.00                        whilelo	p15.d, xzr, x30
-# CHECK-NEXT:  2      3     2.00                        whilels	p0.h, w30, wzr
-# CHECK-NEXT:  2      3     2.00                        whilelt	p15.s, xzr, x30
+# CHECK-NEXT:  1      3     2.00                        whilele	p0.b, w30, wzr
+# CHECK-NEXT:  1      3     2.00                        whilelo	p15.d, xzr, x30
+# CHECK-NEXT:  1      3     2.00                        whilels	p0.h, w30, wzr
+# CHECK-NEXT:  1      3     2.00                        whilelt	p15.s, xzr, x30
 # CHECK-NEXT:  1      2     1.00           *      U     wrffr	p0.b
 # CHECK-NEXT:  1      2     1.00           *      U     wrffr	p15.b
 # CHECK-NEXT:  1      2     1.00                        zip1	p0.b, p0.b, p0.b
@@ -4842,7 +4842,7 @@ zip2	z31.s, z31.s, z31.s
 
 # CHECK:      Resource pressure per iteration:
 # CHECK-NEXT: [0.0]  [0.1]  [1.0]  [1.1]  [2.0]  [2.1]  [2.2]  [3]    [4.0]  [4.1]  [5]    [6]    [7.0]  [7.1]  [8]    [9]    [10]   [11]
-# CHECK-NEXT:  -      -      -      -      -      -      -     88.67  500.67 500.67 797.50 2.50   92.50  92.50  1252.00 921.00 178.50 181.50
+# CHECK-NEXT:  -      -      -      -      -      -      -     427.00 1140.50 1140.50 802.50 7.50 196.00 196.00 1778.25 1363.25 541.75 541.75
 
 # CHECK:      Resource pressure by instruction:
 # CHECK-NEXT: [0.0]  [0.1]  [1.0]  [1.1]  [2.0]  [2.1]  [2.2]  [3]    [4.0]  [4.1]  [5]    [6]    [7.0]  [7.1]  [8]    [9]    [10]   [11]   Instructions:
@@ -5271,9 +5271,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     decp	xzr, p15.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     decp	xzr, p15.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     decp	xzr, p15.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     decp	z31.d, p15.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     decp	z31.h, p15.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     decp	z31.s, p15.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     decp	z31.d, p15.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     decp	z31.h, p15.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     decp	z31.s, p15.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     decw	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     decw	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     decw	x0, all, mul #16
@@ -5346,9 +5346,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.50   1.50    -      -     fadda	d0, p7, d0, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     18.00   -      -      -     fadda	h0, p7, h0, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     10.00   -      -      -     fadda	s0, p7, s0, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.25   2.25   0.25   0.25   faddv	d0, p7, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00   2.00    -      -     faddv	d0, p7, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -     faddv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.75   2.75   0.25   0.25   faddv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     faddv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fcadd	z0.d, p0/m, z0.d, z0.d, #90
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fcadd	z0.h, p0/m, z0.h, z0.h, #90
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fcadd	z0.s, p0/m, z0.s, z0.s, #90
@@ -5417,25 +5417,25 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvt	z0.s, p0/m, z0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvt	z0.s, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	z0.d, p0/m, z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	z0.d, p0/m, z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	z0.d, p0/m, z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     fcvtzs	z0.d, p0/m, z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvtzs	z0.d, p0/m, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     fcvtzs	z0.h, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzs	z0.s, p0/m, z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvtzs	z0.s, p0/m, z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     fcvtzs	z0.s, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvtzs	z0.s, p0/m, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	z0.d, p0/m, z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	z0.d, p0/m, z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	z0.d, p0/m, z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     fcvtzu	z0.d, p0/m, z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvtzu	z0.d, p0/m, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     fcvtzu	z0.h, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     fcvtzu	z0.s, p0/m, z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvtzu	z0.s, p0/m, z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     fcvtzu	z0.s, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     fcvtzu	z0.s, p0/m, z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     fdiv	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     10.00   -      -      -     fdiv	z0.h, p7/m, z0.h, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     fdiv	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     fdivr	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     10.00   -      -      -     fdivr	z0.h, p7/m, z0.h, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     fdivr	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     14.00   -      -      -     fdiv	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     12.00   -      -      -     fdiv	z0.h, p7/m, z0.h, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     9.00    -      -      -     fdiv	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     14.00   -      -      -     fdivr	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     12.00   -      -      -     fdivr	z0.h, p7/m, z0.h, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     9.00    -      -      -     fdivr	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fexpa	z0.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fexpa	z0.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fexpa	z0.s, z31.s
@@ -5460,12 +5460,12 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmaxnm	z31.d, p7/m, z31.d, #1.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmaxnm	z31.h, p7/m, z31.h, #1.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmaxnm	z31.s, p7/m, z31.s, #1.0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.25   2.25   0.25   0.25   fmaxnmv	d0, p7, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00   2.00    -      -     fmaxnmv	d0, p7, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -     fmaxnmv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.75   2.75   0.25   0.25   fmaxnmv	s0, p7, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.25   2.25   0.25   0.25   fmaxv	d0, p7, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     fmaxnmv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00   2.00    -      -     fmaxv	d0, p7, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -     fmaxv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.75   2.75   0.25   0.25   fmaxv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     fmaxv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmin	z0.d, p0/m, z0.d, #0.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmin	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmin	z0.h, p0/m, z0.h, #0.0
@@ -5484,12 +5484,12 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fminnm	z31.d, p7/m, z31.d, #1.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fminnm	z31.h, p7/m, z31.h, #1.0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fminnm	z31.s, p7/m, z31.s, #1.0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.25   2.25   0.25   0.25   fminnmv	d0, p7, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00   2.00    -      -     fminnmv	d0, p7, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -     fminnmv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.75   2.75   0.25   0.25   fminnmv	s0, p7, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.25   2.25   0.25   0.25   fminv	d0, p7, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     fminnmv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00   2.00    -      -     fminv	d0, p7, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -     fminv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.75   2.75   0.25   0.25   fminv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.50   2.50    -      -     fminv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmla	z0.d, p7/m, z1.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmla	z0.d, z1.d, z7.d[1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fmla	z0.h, p7/m, z1.h, z31.h
@@ -5550,8 +5550,8 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fnmsb	z0.h, p7/m, z1.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fnmsb	z0.s, p7/m, z1.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frecpe	z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     frecpe	z0.h, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     frecpe	z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frecpe	z0.h, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frecpe	z0.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     frecps	z0.d, z1.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     frecps	z0.h, z1.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     frecps	z0.s, z1.s, z31.s
@@ -5580,17 +5580,17 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frintz	z31.h, p7/m, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frintz	z31.s, p7/m, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frsqrte	z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     frsqrte	z0.h, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     frsqrte	z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frsqrte	z0.h, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     frsqrte	z0.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     frsqrts	z0.d, z1.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     frsqrts	z0.h, z1.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     frsqrts	z0.s, z1.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fscale	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fscale	z0.h, p7/m, z0.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fscale	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     fsqrt	z31.d, p7/m, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     10.00   -      -      -     fsqrt	z31.h, p7/m, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     fsqrt	z31.s, p7/m, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     14.00   -      -      -     fsqrt	z31.d, p7/m, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     12.00   -      -      -     fsqrt	z31.h, p7/m, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     9.00    -      -      -     fsqrt	z31.s, p7/m, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fsub	z0.d, p0/m, z0.d, #0.5
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fsub	z0.d, p7/m, z0.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     fsub	z0.d, z1.d, z31.d
@@ -5631,15 +5631,15 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incd	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incd	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incd	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     incd	z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     incd	z0.d, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     incd	z0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     incd	z0.d, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     inch	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     inch	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     inch	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     inch	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     inch	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     inch	z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     inch	z0.h, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     inch	z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     inch	z0.h, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incp	x0, p0.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incp	x0, p0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incp	x0, p0.h
@@ -5648,48 +5648,48 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incp	xzr, p15.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incp	xzr, p15.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incp	xzr, p15.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     incp	z31.d, p15.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     incp	z31.h, p15.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     incp	z31.s, p15.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     incp	z31.d, p15.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     incp	z31.h, p15.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     incp	z31.s, p15.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incw	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incw	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incw	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incw	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     incw	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     incw	z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     incw	z0.s, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     incw	z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     incw	z0.s, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     index	z0.b, #0, #0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     index	z0.d, #0, #0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     index	z0.h, #0, #0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z0.h, w0, w0
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z0.h, w0, w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     index	z0.s, #0, #0
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z21.b, w10, w21
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z21.b, w10, w21
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     2.00    -      -      -     index	z21.d, x10, x21
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z21.s, w10, w21
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z23.b, #13, w8
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z23.b, w13, #8
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z21.s, w10, w21
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z23.b, #13, w8
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z23.b, w13, #8
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     2.00    -      -      -     index	z23.d, #13, x8
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     2.00    -      -      -     index	z23.d, x13, #8
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z23.h, #13, w8
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z23.h, w13, #8
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z23.s, #13, w8
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z23.s, w13, #8
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z23.h, #13, w8
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z23.h, w13, #8
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z23.s, #13, w8
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z23.s, w13, #8
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     index	z31.b, #-1, #-1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.b, #-1, wzr
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.b, wzr, #-1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.b, wzr, wzr
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.b, #-1, wzr
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.b, wzr, #-1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.b, wzr, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     index	z31.d, #-1, #-1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     2.00    -      -      -     index	z31.d, #-1, xzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     2.00    -      -      -     index	z31.d, xzr, #-1
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     2.00    -      -      -     index	z31.d, xzr, xzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     index	z31.h, #-1, #-1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.h, #-1, wzr
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.h, wzr, #-1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.h, wzr, wzr
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.h, #-1, wzr
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.h, wzr, #-1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.h, wzr, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     index	z31.s, #-1, #-1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.s, #-1, wzr
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.s, wzr, #-1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     index	z31.s, wzr, wzr
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.s, #-1, wzr
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.s, wzr, #-1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     1.00    -      -      -     index	z31.s, wzr, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     insr	z0.b, w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     insr	z0.d, x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -     1.00    -      -     insr	z0.h, w0
@@ -5722,66 +5722,66 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z0.b }, p0/z, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z0.b }, p0/z, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1b	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z0.h }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1b	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1b	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z21.b }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z21.h }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z21.s }, p5/z, [x10, x21]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z23.d }, p3/z, [x13, x8]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z31.b }, p7/z, [sp, #-1, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1b	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1b	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1b	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z31.h }, p7/z, [sp, #-1, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1b	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1b	{ z31.s }, p7/z, [z31.s, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1b	{ z5.h }, p3/z, [x17, x16]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1d	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1d	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1d	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1d	{ z23.d }, p3/z, [sp, x8, lsl #3]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1d	{ z23.d }, p3/z, [x13, x8, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1d	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1d	{ z31.d }, p7/z, [z31.d, #248]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z0.h }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1h	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z21.h }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z21.s }, p5/z, [x10, #5, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1d	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1d	{ z31.d }, p7/z, [z31.d, #248]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z0.d }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z0.h }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z0.s }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z21.d }, p5/z, [x10, #5, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z21.h }, p5/z, [x10, #5, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z21.s }, p5/z, [x10, x21, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z23.d }, p3/z, [x13, x8, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z31.d }, p7/z, [z31.d, #62]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z31.h }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1h	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1h	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z31.d }, p7/z, [sp, #-1, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1h	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z31.h }, p7/z, [sp, #-1, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z31.s }, p7/z, [sp, #-1, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1h	{ z31.s }, p7/z, [z31.s, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z5.h }, p3/z, [sp, x16, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1h	{ z5.h }, p3/z, [x17, x16, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1rb	{ z0.b }, p0/z, [x0]
@@ -5837,85 +5837,85 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1rw	{ z31.d }, p7/z, [sp, #252]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1rw	{ z31.s }, p7/z, [sp, #252]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sb	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sb	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z0.h }, p0/z, [sp, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z0.h }, p0/z, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z0.h }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sb	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sb	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z21.h }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z21.s }, p5/z, [x10, x21]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z23.d }, p3/z, [x13, x8]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sb	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sb	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sb	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sb	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z31.h }, p7/z, [sp, #-1, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sb	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sb	{ z31.s }, p7/z, [z31.s, #31]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sb	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sh	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sh	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sh	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sh	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1sh	{ z21.s }, p5/z, [sp, x21, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sh	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1sh	{ z21.s }, p5/z, [x10, x21, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ld1sh	{ z23.d }, p3/z, [x13, x8, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sh	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sh	{ z31.d }, p7/z, [z31.d, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sh	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1sh	{ z31.s }, p7/z, [z31.s, #62]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sh	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sw	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sw	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sw	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sw	{ z23.d }, p3/z, [sp, x8, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sw	{ z23.d }, p3/z, [x13, x8, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1sw	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1sw	{ z31.d }, p7/z, [z31.d, #124]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sw	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1sw	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z0.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z0.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1w	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z0.s }, p0/z, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z21.d }, p5/z, [x10, #5, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z21.s }, p5/z, [sp, x21, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z21.s }, p5/z, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z21.s }, p5/z, [x10, x21, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z23.d }, p3/z, [x13, x8, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z31.d }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z31.d }, p7/z, [sp, z31.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ld1w	{ z31.d }, p7/z, [z31.d, #124]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ld1w	{ z31.s }, p7/z, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ld1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ld1w	{ z31.s }, p7/z, [z31.s, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ld1w	{ z31.s }, p7/z, [z31.s, #124]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2b	{ z0.b, z1.b }, p0/z, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2b	{ z0.b, z1.b }, p0/z, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2b	{ z21.b, z22.b }, p5/z, [x10, #10, mul vl]
@@ -5926,163 +5926,163 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2d	{ z21.d, z22.d }, p5/z, [x10, #10, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2d	{ z23.d, z24.d }, p3/z, [x13, #-16, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2d	{ z5.d, z6.d }, p3/z, [x17, x16, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2h	{ z0.h, z1.h }, p0/z, [x0, x0, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -     1.00   1.00   1.00   1.00    -      -     ld2h	{ z0.h, z1.h }, p0/z, [x0, x0, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2h	{ z0.h, z1.h }, p0/z, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2h	{ z21.h, z22.h }, p5/z, [x10, #10, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2h	{ z23.h, z24.h }, p3/z, [x13, #-16, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2h	{ z5.h, z6.h }, p3/z, [x17, x16, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -     1.00   1.00   1.00   1.00    -      -     ld2h	{ z5.h, z6.h }, p3/z, [x17, x16, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2w	{ z0.s, z1.s }, p0/z, [x0, x0, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2w	{ z0.s, z1.s }, p0/z, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2w	{ z21.s, z22.s }, p5/z, [x10, #10, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2w	{ z23.s, z24.s }, p3/z, [x13, #-16, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     1.00   1.00    -      -     ld2w	{ z5.s, z6.s }, p3/z, [x17, x16, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3b	{ z0.b - z2.b }, p0/z, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3b	{ z0.b - z2.b }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3b	{ z21.b - z23.b }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3b	{ z23.b - z25.b }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3b	{ z5.b - z7.b }, p3/z, [x17, x16]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3d	{ z0.d - z2.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3d	{ z0.d - z2.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3d	{ z21.d - z23.d }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3d	{ z23.d - z25.d }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3d	{ z5.d - z7.d }, p3/z, [x17, x16, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3h	{ z0.h - z2.h }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3h	{ z0.h - z2.h }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3h	{ z21.h - z23.h }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3h	{ z23.h - z25.h }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3h	{ z5.h - z7.h }, p3/z, [x17, x16, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3w	{ z0.s - z2.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3w	{ z0.s - z2.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3w	{ z21.s - z23.s }, p5/z, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -      -      -     1.50   1.50    -      -     ld3w	{ z23.s - z25.s }, p3/z, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.50   1.50    -      -     0.50   0.50   1.50   1.50    -      -     ld3w	{ z5.s - z7.s }, p3/z, [x17, x16, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4b	{ z0.b - z3.b }, p0/z, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4b	{ z0.b - z3.b }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4b	{ z21.b - z24.b }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4b	{ z23.b - z26.b }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4b	{ z5.b - z8.b }, p3/z, [x17, x16]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4d	{ z0.d - z3.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4d	{ z0.d - z3.d }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4d	{ z21.d - z24.d }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4d	{ z23.d - z26.d }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4d	{ z5.d - z8.d }, p3/z, [x17, x16, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4h	{ z0.h - z3.h }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4h	{ z0.h - z3.h }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4h	{ z21.h - z24.h }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4h	{ z23.h - z26.h }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4h	{ z5.h - z8.h }, p3/z, [x17, x16, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4w	{ z0.s - z3.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4w	{ z0.s - z3.s }, p0/z, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4w	{ z21.s - z24.s }, p5/z, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -      -     ld4w	{ z23.s - z26.s }, p3/z, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -     1.00   1.00   2.00   2.00    -      -     ld4w	{ z5.s - z8.s }, p3/z, [x17, x16, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3b	{ z0.b - z2.b }, p0/z, [x0, x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3b	{ z0.b - z2.b }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3b	{ z21.b - z23.b }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3b	{ z23.b - z25.b }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3b	{ z5.b - z7.b }, p3/z, [x17, x16]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3d	{ z0.d - z2.d }, p0/z, [x0, x0, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3d	{ z0.d - z2.d }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3d	{ z21.d - z23.d }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3d	{ z23.d - z25.d }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3d	{ z5.d - z7.d }, p3/z, [x17, x16, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3h	{ z0.h - z2.h }, p0/z, [x0, x0, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3h	{ z0.h - z2.h }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3h	{ z21.h - z23.h }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3h	{ z23.h - z25.h }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3h	{ z5.h - z7.h }, p3/z, [x17, x16, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3w	{ z0.s - z2.s }, p0/z, [x0, x0, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3w	{ z0.s - z2.s }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3w	{ z21.s - z23.s }, p5/z, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -     3.00   3.00    -      -     ld3w	{ z23.s - z25.s }, p3/z, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     3.00   3.00    -      -     3.00   3.00   3.00   3.00    -      -     ld3w	{ z5.s - z7.s }, p3/z, [x17, x16, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4b	{ z0.b - z3.b }, p0/z, [x0, x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4b	{ z0.b - z3.b }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4b	{ z21.b - z24.b }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4b	{ z23.b - z26.b }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4b	{ z5.b - z8.b }, p3/z, [x17, x16]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4d	{ z0.d - z3.d }, p0/z, [x0, x0, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4d	{ z0.d - z3.d }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4d	{ z21.d - z24.d }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4d	{ z23.d - z26.d }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4d	{ z5.d - z8.d }, p3/z, [x17, x16, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4h	{ z0.h - z3.h }, p0/z, [x0, x0, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4h	{ z0.h - z3.h }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4h	{ z21.h - z24.h }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4h	{ z23.h - z26.h }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4h	{ z5.h - z8.h }, p3/z, [x17, x16, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4w	{ z0.s - z3.s }, p0/z, [x0, x0, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4w	{ z0.s - z3.s }, p0/z, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4w	{ z21.s - z24.s }, p5/z, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     4.00   4.00    -      -     ld4w	{ z23.s - z26.s }, p3/z, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -     4.00   4.00   4.00   4.00    -      -     ld4w	{ z5.s - z8.s }, p3/z, [x17, x16, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z0.d }, p0/z, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1b	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z0.h }, p0/z, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z0.s }, p0/z, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1b	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1b	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z21.d }, p5/z, [x10, z21.d, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z31.b }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1b	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1b	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1b	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z31.h }, p7/z, [sp]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1b	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1b	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1b	{ z31.s }, p7/z, [z31.s, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1d	{ z0.d }, p0/z, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1d	{ z0.d }, p0/z, [x0, z0.d, sxtw #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1d	{ z0.d }, p0/z, [x0, z0.d, uxtw #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1d	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1d	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1d	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1d	{ z23.d }, p3/z, [x13, z8.d, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1d	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1d	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1d	{ z31.d }, p7/z, [z31.d, #248]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1d	{ z31.d }, p7/z, [z31.d, #248]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1h	{ z0.d }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1h	{ z0.h }, p0/z, [x0, x0, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1h	{ z0.s }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1h	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1h	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1h	{ z31.d }, p7/z, [z31.d, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1h	{ z31.h }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1h	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1h	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1h	{ z31.s }, p7/z, [z31.s, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sb	{ z0.d }, p0/z, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sb	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sb	{ z0.h }, p0/z, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sb	{ z0.s }, p0/z, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sb	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sb	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sb	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sb	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sb	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sb	{ z31.d }, p7/z, [z31.d, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sb	{ z31.d }, p7/z, [z31.d, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sb	{ z31.h }, p7/z, [sp]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sb	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sb	{ z31.s }, p7/z, [z31.s, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sb	{ z31.s }, p7/z, [z31.s, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sh	{ z0.d }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z0.d }, p0/z, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z0.d }, p0/z, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sh	{ z0.s }, p0/z, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sh	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z23.d }, p3/z, [x13, z8.d, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sh	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z31.d }, p7/z, [z31.d, #62]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sh	{ z31.d }, p7/z, [z31.d, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z31.s }, p7/z, [sp, z31.s, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z31.s }, p7/z, [sp, z31.s, uxtw #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sh	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1sh	{ z31.s }, p7/z, [z31.s, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sh	{ z31.s }, p7/z, [z31.s, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sw	{ z0.d }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z0.d }, p0/z, [z0.d]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sw	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sw	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sw	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sw	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sw	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1sw	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sw	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1sw	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1sw	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1sw	{ z31.d }, p7/z, [z31.d, #124]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1w	{ z0.d }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z0.d }, p0/z, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z0.d }, p0/z, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z0.d }, p0/z, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z0.d }, p0/z, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1w	{ z0.s }, p0/z, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1w	{ z0.s }, p0/z, [z0.s]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z31.d }, p7/z, [sp, z31.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z0.s }, p0/z, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z0.s }, p0/z, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z0.s }, p0/z, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z21.d }, p5/z, [x10, z21.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z21.d }, p5/z, [x10, z21.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z23.d }, p3/z, [x13, z8.d, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z31.d }, p7/z, [sp, z31.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1w	{ z31.d }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z31.d }, p7/z, [z31.d, #124]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.67   0.67   0.67    -      -      -      -     0.50   0.50   0.50   0.50   ldff1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     2.00   2.00   2.00    -      -      -      -     1.50   1.50   1.50   1.50   ldff1w	{ z31.d }, p7/z, [z31.d, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z31.s }, p7/z, [sp, z31.s, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z31.s }, p7/z, [sp, z31.s, uxtw #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50    -      -      -      -     ldff1w	{ z31.s }, p7/z, [sp]
-# CHECK-NEXT:  -      -      -      -      -      -      -     0.33   0.33   0.33    -      -      -      -     0.25   0.25   0.25   0.25   ldff1w	{ z31.s }, p7/z, [z31.s, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -     4.00   4.00   4.00    -      -      -      -     3.00   3.00   3.00   3.00   ldff1w	{ z31.s }, p7/z, [z31.s, #124]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ldnf1b	{ z0.b }, p0/z, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ldnf1b	{ z0.d }, p0/z, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -      -      -     ldnf1b	{ z0.h }, p0/z, [x0]
@@ -6492,8 +6492,8 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -      -      -      -      -     rdffr	p0.b, p0/z
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     rdffr	p15.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -      -      -      -      -     rdffr	p15.b, p15/z
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     rdffrs	p0.b, p0/z
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -      -      -     rdffrs	p15.b, p15/z
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -      -      -     rdffrs	p0.b, p0/z
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     3.00   3.00    -      -      -      -      -      -     rdffrs	p15.b, p15/z
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     rdvl	x0, #0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     rdvl	x21, #-32
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     rdvl	x23, #31
@@ -6512,18 +6512,18 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sabd	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sabd	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sabd	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.25   2.75   0.25   0.75   saddv	d0, p7, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   saddv	d0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   saddv	d0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     saddv	d0, p7, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     saddv	d0, p7, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     saddv	d0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     scvtf	z0.d, p0/m, z0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     scvtf	z0.h, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     scvtf	z0.h, p0/m, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     scvtf	z0.s, p0/m, z0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     scvtf	z0.s, p0/m, z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     sdiv	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     sdiv	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     sdivr	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     sdivr	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     20.00   -      -      -     sdiv	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     11.00   -      -      -     sdiv	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     20.00   -      -      -     sdivr	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     11.00   -      -      -     sdivr	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sdot	z0.d, z1.h, z15.h[1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sdot	z0.d, z1.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sdot	z0.s, z1.b, z31.b
@@ -6545,9 +6545,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smax	z31.h, z31.h, #127
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smax	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smax	z31.s, z31.s, #127
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.25   2.75   0.25   0.75   smaxv	b0, p7, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   smaxv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   smaxv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     smaxv	b0, p7, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     smaxv	h0, p7, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     smaxv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smin	z0.b, z0.b, #-128
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smin	z0.d, z0.d, #-128
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smin	z0.h, z0.h, #-128
@@ -6560,9 +6560,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smin	z31.h, z31.h, #127
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smin	z31.s, p7/m, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smin	z31.s, z31.s, #127
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.25   2.75   0.25   0.75   sminv	b0, p7, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   sminv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   sminv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     sminv	b0, p7, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     sminv	h0, p7, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     sminv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     smmla	z0.s, z1.b, z2.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     smulh	z0.b, p7/m, z0.b, z31.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     smulh	z0.d, p7/m, z0.d, z31.d
@@ -6605,10 +6605,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecd	x0, w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecd	x0, w0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecd	x0, w0, pow2, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecd	z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecd	z0.d, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecd	z0.d, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecd	z0.d, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecd	z0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecd	z0.d, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecd	z0.d, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecd	z0.d, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdech	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdech	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdech	x0, all, mul #16
@@ -6618,10 +6618,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdech	x0, w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdech	x0, w0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdech	x0, w0, pow2, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdech	z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdech	z0.h, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdech	z0.h, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdech	z0.h, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdech	z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdech	z0.h, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdech	z0.h, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdech	z0.h, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecp	x0, p0.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecp	x0, p0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecp	x0, p0.h
@@ -6630,9 +6630,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecp	xzr, p15.d, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecp	xzr, p15.h, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecp	xzr, p15.s, wzr
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     sqdecp	z0.d, p0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     sqdecp	z0.h, p0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     sqdecp	z0.s, p0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     sqdecp	z0.d, p0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     sqdecp	z0.h, p0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     sqdecp	z0.s, p0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecw	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecw	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecw	x0, all, mul #16
@@ -6642,10 +6642,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecw	x0, w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecw	x0, w0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqdecw	x0, w0, pow2, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecw	z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecw	z0.s, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecw	z0.s, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqdecw	z0.s, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecw	z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecw	z0.s, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecw	z0.s, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqdecw	z0.s, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincb	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincb	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincb	x0, all, mul #16
@@ -6664,10 +6664,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincd	x0, w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincd	x0, w0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincd	x0, w0, pow2, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincd	z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincd	z0.d, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincd	z0.d, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincd	z0.d, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincd	z0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincd	z0.d, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincd	z0.d, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincd	z0.d, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqinch	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqinch	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqinch	x0, all, mul #16
@@ -6677,10 +6677,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqinch	x0, w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqinch	x0, w0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqinch	x0, w0, pow2, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqinch	z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqinch	z0.h, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqinch	z0.h, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqinch	z0.h, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqinch	z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqinch	z0.h, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqinch	z0.h, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqinch	z0.h, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincp	x0, p0.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincp	x0, p0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincp	x0, p0.h
@@ -6689,9 +6689,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincp	xzr, p15.d, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincp	xzr, p15.h, wzr
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincp	xzr, p15.s, wzr
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     sqincp	z0.d, p0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     sqincp	z0.h, p0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     sqincp	z0.s, p0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     sqincp	z0.d, p0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     sqincp	z0.h, p0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     sqincp	z0.s, p0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincw	x0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincw	x0, #14
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincw	x0, all, mul #16
@@ -6701,10 +6701,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincw	x0, w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincw	x0, w0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     sqincw	x0, w0, pow2, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincw	z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincw	z0.s, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincw	z0.s, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     sqincw	z0.s, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincw	z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincw	z0.s, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincw	z0.s, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqincw	z0.s, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqsub	z0.b, z0.b, #0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqsub	z0.b, z0.b, z0.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sqsub	z0.d, z0.d, #0
@@ -6723,148 +6723,148 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.b }, p0, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.b }, p0, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.d }, p0, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1b	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1b	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1b	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1b	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.h }, p0, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.h }, p0, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.s }, p0, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1b	{ z0.s }, p0, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1b	{ z0.s }, p0, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1b	{ z0.s }, p0, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1b	{ z0.s }, p0, [x0, z0.s, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z0.s }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1b	{ z0.s }, p7, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1b	{ z0.s }, p7, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z21.b }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z21.h }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z21.s }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z31.b }, p7, [sp, #-1, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z31.d }, p7, [z31.d, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1b	{ z31.d }, p7, [z31.d, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z31.h }, p7, [sp, #-1, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1b	{ z31.s }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1b	{ z31.s }, p7, [z31.s, #31]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1b	{ z31.s }, p7, [z31.s, #31]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, z0.d, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, z0.d, sxtw #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, z0.d, uxtw #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p0, [x0, z0.d, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p0, [x0, z0.d, sxtw #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p0, [x0, z0.d, uxtw #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1d	{ z31.d }, p7, [z31.d, #248]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1d	{ z31.d }, p7, [z31.d, #248]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50   0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, z0.d, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, z0.d, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, z0.d, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p0, [x0, z0.d, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p0, [x0, z0.d, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p0, [x0, z0.d, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50   0.25   0.25   0.25   0.25   st1h	{ z0.h }, p0, [x0, x0, lsl #1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.h }, p0, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50   0.25   0.25   0.25   0.25   st1h	{ z0.s }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1h	{ z0.s }, p0, [x0, z0.s, sxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1h	{ z0.s }, p0, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1h	{ z0.s }, p0, [x0, z0.s, uxtw #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1h	{ z0.s }, p0, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1h	{ z0.s }, p0, [x0, z0.s, sxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1h	{ z0.s }, p0, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1h	{ z0.s }, p0, [x0, z0.s, uxtw #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1h	{ z0.s }, p0, [x0, z0.s, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z0.s }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1h	{ z0.s }, p7, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1h	{ z0.s }, p7, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z21.h }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z21.s }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z31.d }, p7, [z31.d, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1h	{ z31.d }, p7, [z31.d, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z31.h }, p7, [sp, #-1, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1h	{ z31.s }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1h	{ z31.s }, p7, [z31.s, #62]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1h	{ z31.s }, p7, [z31.s, #62]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, z0.d, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, z0.d, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, z0.d, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, z0.d, uxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, z0.d, uxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0, z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p0, [x0, z0.d, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p0, [x0, z0.d, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p0, [x0, z0.d, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p0, [x0, z0.d, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p0, [x0, z0.d, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p0, [x0, z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.d }, p7, [z0.d]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z0.d }, p7, [z0.d]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1w	{ z0.s }, p0, [x0, z0.s, sxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1w	{ z0.s }, p0, [x0, z0.s, sxtw]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1w	{ z0.s }, p0, [x0, z0.s, uxtw #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1w	{ z0.s }, p0, [x0, z0.s, uxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1w	{ z0.s }, p0, [x0, z0.s, sxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1w	{ z0.s }, p0, [x0, z0.s, sxtw]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1w	{ z0.s }, p0, [x0, z0.s, uxtw #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1w	{ z0.s }, p0, [x0, z0.s, uxtw]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z0.s }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1w	{ z0.s }, p7, [z0.s]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1w	{ z0.s }, p7, [z0.s]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z21.d }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z21.s }, p5, [x10, #5, mul vl]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z31.d }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z31.d }, p7, [z31.d, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.00   2.00    -      -      -      -     1.00   1.00   1.00   1.00   st1w	{ z31.d }, p7, [z31.d, #124]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st1w	{ z31.s }, p7, [sp, #-1, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st1w	{ z31.s }, p7, [z31.s, #124]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2b	{ z0.b, z1.b }, p0, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2b	{ z0.b, z1.b }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2b	{ z21.b, z22.b }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2b	{ z23.b, z24.b }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2b	{ z5.b, z6.b }, p3, [x17, x16]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2d	{ z0.d, z1.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2d	{ z0.d, z1.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2d	{ z21.d, z22.d }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2d	{ z23.d, z24.d }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2d	{ z5.d, z6.d }, p3, [x17, x16, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50   0.25   0.25   0.25   0.25   st2h	{ z0.h, z1.h }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2h	{ z0.h, z1.h }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2h	{ z21.h, z22.h }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2h	{ z23.h, z24.h }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -     0.50   0.50   0.25   0.25   0.25   0.25   st2h	{ z5.h, z6.h }, p3, [x17, x16, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2w	{ z0.s, z1.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2w	{ z0.s, z1.s }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2w	{ z21.s, z22.s }, p5, [x10, #10, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2w	{ z23.s, z24.s }, p3, [x13, #-16, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   st2w	{ z5.s, z6.s }, p3, [x17, x16, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3b	{ z0.b - z2.b }, p0, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3b	{ z0.b - z2.b }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3b	{ z21.b - z23.b }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3b	{ z23.b - z25.b }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3b	{ z5.b - z7.b }, p3, [x17, x16]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3d	{ z0.d - z2.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3d	{ z0.d - z2.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3d	{ z21.d - z23.d }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3d	{ z23.d - z25.d }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3d	{ z5.d - z7.d }, p3, [x17, x16, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3h	{ z0.h - z2.h }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3h	{ z0.h - z2.h }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3h	{ z21.h - z23.h }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3h	{ z23.h - z25.h }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3h	{ z5.h - z7.h }, p3, [x17, x16, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3w	{ z0.s - z2.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3w	{ z0.s - z2.s }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3w	{ z21.s - z23.s }, p5, [x10, #15, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -      -      -     1.25   1.25   1.25   1.25   st3w	{ z23.s - z25.s }, p3, [x13, #-24, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     2.50   2.50    -      -     2.50   2.50   1.25   1.25   1.25   1.25   st3w	{ z5.s - z7.s }, p3, [x17, x16, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4b	{ z0.b - z3.b }, p0, [x0, x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4b	{ z0.b - z3.b }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4b	{ z21.b - z24.b }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4b	{ z23.b - z26.b }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4b	{ z5.b - z8.b }, p3, [x17, x16]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4d	{ z0.d - z3.d }, p0, [x0, x0, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4d	{ z0.d - z3.d }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4d	{ z21.d - z24.d }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4d	{ z23.d - z26.d }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4d	{ z5.d - z8.d }, p3, [x17, x16, lsl #3]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4h	{ z0.h - z3.h }, p0, [x0, x0, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4h	{ z0.h - z3.h }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4h	{ z21.h - z24.h }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4h	{ z23.h - z26.h }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4h	{ z5.h - z8.h }, p3, [x17, x16, lsl #1]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4w	{ z0.s - z3.s }, p0, [x0, x0, lsl #2]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4w	{ z0.s - z3.s }, p0, [x0]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4w	{ z21.s - z24.s }, p5, [x10, #20, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st4w	{ z23.s - z26.s }, p3, [x13, #-32, mul vl]
-# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st4w	{ z5.s - z8.s }, p3, [x17, x16, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.00   4.00    -      -      -      -     2.00   2.00   2.00   2.00   st1w	{ z31.s }, p7, [z31.s, #124]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2b	{ z0.b, z1.b }, p0, [x0, x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2b	{ z0.b, z1.b }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2b	{ z21.b, z22.b }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2b	{ z23.b, z24.b }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2b	{ z5.b, z6.b }, p3, [x17, x16]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2d	{ z0.d, z1.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2d	{ z0.d, z1.d }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2d	{ z21.d, z22.d }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2d	{ z23.d, z24.d }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2d	{ z5.d, z6.d }, p3, [x17, x16, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -     1.00   1.00   0.50   0.50   0.50   0.50   st2h	{ z0.h, z1.h }, p0, [x0, x0, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2h	{ z0.h, z1.h }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2h	{ z21.h, z22.h }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2h	{ z23.h, z24.h }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -     1.00   1.00   0.50   0.50   0.50   0.50   st2h	{ z5.h, z6.h }, p3, [x17, x16, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2w	{ z0.s, z1.s }, p0, [x0, x0, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2w	{ z0.s, z1.s }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2w	{ z21.s, z22.s }, p5, [x10, #10, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2w	{ z23.s, z24.s }, p3, [x13, #-16, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.00   1.00    -      -      -      -     0.50   0.50   0.50   0.50   st2w	{ z5.s, z6.s }, p3, [x17, x16, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3b	{ z0.b - z2.b }, p0, [x0, x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3b	{ z0.b - z2.b }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3b	{ z21.b - z23.b }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3b	{ z23.b - z25.b }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3b	{ z5.b - z7.b }, p3, [x17, x16]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3d	{ z0.d - z2.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3d	{ z0.d - z2.d }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3d	{ z21.d - z23.d }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3d	{ z23.d - z25.d }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3d	{ z5.d - z7.d }, p3, [x17, x16, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3h	{ z0.h - z2.h }, p0, [x0, x0, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3h	{ z0.h - z2.h }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3h	{ z21.h - z23.h }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3h	{ z23.h - z25.h }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3h	{ z5.h - z7.h }, p3, [x17, x16, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3w	{ z0.s - z2.s }, p0, [x0, x0, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3w	{ z0.s - z2.s }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3w	{ z21.s - z23.s }, p5, [x10, #15, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -      -      -     2.25   2.25   2.25   2.25   st3w	{ z23.s - z25.s }, p3, [x13, #-24, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     4.50   4.50    -      -     4.50   4.50   2.25   2.25   2.25   2.25   st3w	{ z5.s - z7.s }, p3, [x17, x16, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4b	{ z0.b - z3.b }, p0, [x0, x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4b	{ z0.b - z3.b }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4b	{ z21.b - z24.b }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4b	{ z23.b - z26.b }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4b	{ z5.b - z8.b }, p3, [x17, x16]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4d	{ z0.d - z3.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4d	{ z0.d - z3.d }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4d	{ z21.d - z24.d }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4d	{ z23.d - z26.d }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4d	{ z5.d - z8.d }, p3, [x17, x16, lsl #3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4h	{ z0.h - z3.h }, p0, [x0, x0, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4h	{ z0.h - z3.h }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4h	{ z21.h - z24.h }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4h	{ z23.h - z26.h }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4h	{ z5.h - z8.h }, p3, [x17, x16, lsl #1]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4w	{ z0.s - z3.s }, p0, [x0, x0, lsl #2]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4w	{ z0.s - z3.s }, p0, [x0]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4w	{ z21.s - z24.s }, p5, [x10, #20, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -      -      -     4.50   4.50   4.50   4.50   st4w	{ z23.s - z26.s }, p3, [x13, #-32, mul vl]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -     9.00   9.00    -      -     9.00   9.00   4.50   4.50   4.50   4.50   st4w	{ z5.s - z8.s }, p3, [x17, x16, lsl #2]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   stnt1b	{ z0.b }, p0, [x0, x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   stnt1b	{ z0.b }, p0, [x0]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -     0.50   0.50    -      -      -      -     0.25   0.25   0.25   0.25   stnt1b	{ z21.b }, p5, [x10, #7, mul vl]
@@ -6945,7 +6945,7 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     subr	z31.d, z31.d, #65280
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     subr	z31.h, z31.h, #65280
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     subr	z31.s, z31.s, #65280
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   sudot	z0.s, z1.b, z7.b[3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50   0.50   0.50   sudot	z0.s, z1.b, z7.b[3]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sunpkhi	z31.d, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sunpkhi	z31.h, z31.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     sunpkhi	z31.s, z31.h
@@ -6988,18 +6988,18 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uabd	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uabd	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uabd	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.25   2.75   0.25   0.75   uaddv	d0, p7, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   uaddv	d0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   uaddv	d0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     uaddv	d0, p7, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     uaddv	d0, p7, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     uaddv	d0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     ucvtf	z0.d, p0/m, z0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     4.00    -      -      -     ucvtf	z0.h, p0/m, z0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     ucvtf	z0.h, p0/m, z0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     ucvtf	z0.s, p0/m, z0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     ucvtf	z0.s, p0/m, z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     udiv	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     udiv	z0.s, p7/m, z0.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     udivr	z0.d, p7/m, z0.d, z31.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     7.00    -      -      -     udivr	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     20.00   -      -      -     udiv	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     11.00   -      -      -     udiv	z0.s, p7/m, z0.s, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     20.00   -      -      -     udivr	z0.d, p7/m, z0.d, z31.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     11.00   -      -      -     udivr	z0.s, p7/m, z0.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     udot	z0.d, z1.h, z15.h[1]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     udot	z0.d, z1.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     udot	z0.s, z1.b, z31.b
@@ -7010,18 +7010,18 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umax	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umax	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umax	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.25   2.75   0.25   0.75   umaxv	b0, p7, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   umaxv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   umaxv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     umaxv	b0, p7, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     umaxv	h0, p7, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     umaxv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umin	z0.b, z0.b, #0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umin	z31.b, p7/m, z31.b, z31.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umin	z31.b, z31.b, #255
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umin	z31.d, p7/m, z31.d, z31.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umin	z31.h, p7/m, z31.h, z31.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     umin	z31.s, p7/m, z31.s, z31.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.25   2.75   0.25   0.75   uminv	b0, p7, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   uminv	h0, p7, z31.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.75   2.75   0.25   0.25   uminv	s0, p7, z31.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     uminv	b0, p7, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     uminv	h0, p7, z31.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -     uminv	s0, p7, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     ummla	z0.s, z1.b, z2.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     umulh	z0.b, p7/m, z0.b, z31.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     umulh	z0.d, p7/m, z0.d, z31.d
@@ -7060,10 +7060,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecd	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecd	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecd	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecd	z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecd	z0.d, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecd	z0.d, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecd	z0.d, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecd	z0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecd	z0.d, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecd	z0.d, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecd	z0.d, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdech	w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdech	w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdech	w0, pow2
@@ -7073,10 +7073,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdech	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdech	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdech	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdech	z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdech	z0.h, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdech	z0.h, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdech	z0.h, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdech	z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdech	z0.h, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdech	z0.h, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdech	z0.h, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecp	wzr, p15.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecp	wzr, p15.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecp	wzr, p15.h
@@ -7085,9 +7085,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecp	x0, p0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecp	x0, p0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecp	x0, p0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     uqdecp	z0.d, p0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     uqdecp	z0.h, p0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     uqdecp	z0.s, p0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     uqdecp	z0.d, p0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     uqdecp	z0.h, p0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     uqdecp	z0.s, p0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecw	w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecw	w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecw	w0, pow2
@@ -7097,10 +7097,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecw	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecw	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqdecw	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecw	z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecw	z0.s, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecw	z0.s, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqdecw	z0.s, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecw	z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecw	z0.s, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecw	z0.s, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqdecw	z0.s, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincb	w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincb	w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincb	w0, pow2
@@ -7119,10 +7119,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincd	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincd	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincd	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincd	z0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincd	z0.d, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincd	z0.d, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincd	z0.d, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincd	z0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincd	z0.d, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincd	z0.d, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincd	z0.d, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqinch	w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqinch	w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqinch	w0, pow2
@@ -7132,10 +7132,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqinch	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqinch	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqinch	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqinch	z0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqinch	z0.h, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqinch	z0.h, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqinch	z0.h, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqinch	z0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqinch	z0.h, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqinch	z0.h, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqinch	z0.h, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincp	wzr, p15.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincp	wzr, p15.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincp	wzr, p15.h
@@ -7144,9 +7144,9 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincp	x0, p0.d
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincp	x0, p0.h
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincp	x0, p0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     uqincp	z0.d, p0.d
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     uqincp	z0.h, p0.h
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     0.50   0.50    -      -     uqincp	z0.s, p0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     uqincp	z0.d, p0.d
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     uqincp	z0.h, p0.h
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     2.00    -      -      -     1.00   1.00    -      -     uqincp	z0.s, p0.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincw	w0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincw	w0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincw	w0, pow2
@@ -7156,10 +7156,10 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincw	x0, all, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincw	x0, pow2
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     1.00    -      -      -      -      -      -      -     uqincw	x0, vl1
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincw	z0.s
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincw	z0.s, all, mul #16
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincw	z0.s, pow2
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     1.00    -      -      -     uqincw	z0.s, pow2, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincw	z0.s
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincw	z0.s, all, mul #16
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincw	z0.s, pow2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqincw	z0.s, pow2, mul #16
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqsub	z0.b, z0.b, #0
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqsub	z0.b, z0.b, z0.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqsub	z0.d, z0.d, #0
@@ -7175,8 +7175,8 @@ zip2	z31.s, z31.s, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqsub	z31.d, z31.d, #65280
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqsub	z31.h, z31.h, #65280
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uqsub	z31.s, z31.s, #65280
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usdot	z0.s, z1.b, z31.b
-# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.25   0.25   0.25   0.25   usdot	z0.s, z1.b, z7.b[3]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50   0.50   0.50   usdot	z0.s, z1.b, z31.b
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50   0.50   0.50   usdot	z0.s, z1.b, z7.b[3]
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     usmmla	z0.s, z1.b, z2.b
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uunpkhi	z31.d, z31.s
 # CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -      -     uunpkhi	z31.h, z31.b
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s
index 264ad8bccc58e..ecf43fd3d9c94 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-writeback.s
@@ -1301,10 +1301,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        1900
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.74
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 3.0
 
@@ -1320,8 +1320,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.2s, v2.2s }, [x27], #16
 # CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1338,19 +1338,19 @@ add x0, x27, 1
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.2s, v2.2s }, [x27], #16
 # CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.4h, v2.4h }, [x27], #16
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.3    0.1    2.0       <total>
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.4h, v2.4h }, [x27], #16
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [4] Code Region - G05
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.94
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 3.3
 
@@ -1365,9 +1365,9 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1383,20 +1383,20 @@ add x0, x27, 1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.16b, v2.16b }, [x27], #32
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.2    0.1    2.0       <total>
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.1d, v2.1d }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [5] Code Region - G06
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.94
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 3.3
 
@@ -1411,9 +1411,9 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1429,20 +1429,20 @@ add x0, x27, 1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.8b, v2.8b }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.2    0.1    2.0       <total>
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [6] Code Region - G07
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        2300
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.53
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 4.3
 
@@ -1456,10 +1456,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
 # CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1474,21 +1474,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.1d, v2.1d, v3.1d }, [x27], #24
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    2.0       <total>
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [7] Code Region - G08
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.92
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -1502,10 +1502,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1520,21 +1520,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    2.0       <total>
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [8] Code Region - G09
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.92
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -1548,10 +1548,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeER .   ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
 # CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1566,21 +1566,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.2s, v2.2s, v3.2s }, [x27], x28
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    2.0       <total>
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [9] Code Region - G10
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      608
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.11
+# CHECK-NEXT: uOps Per Cycle:    2.47
 # CHECK-NEXT: IPC:               1.64
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -1594,10 +1594,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE----R.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeER  .   ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,5]     D===eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,9]     .D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,7]     D====eE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeeER   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,9]     D=====eE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1612,21 +1612,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: 9.     1     5.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    2.1       <total>
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: 9.     1     6.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.1       <total>
 
 # CHECK:      [10] Code Region - G11
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      509
-# CHECK-NEXT: Total uOps:        2400
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.72
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.96
 # CHECK-NEXT: Block RThroughput: 4.7
 
@@ -1640,10 +1640,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE----R.  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeER .   ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,5]     D===eE-----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,7]     .D===eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,9]     .D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,7]     D====eE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeeER   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,9]     D=====eE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1658,21 +1658,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: 5.     1     4.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: 9.     1     5.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    2.2       <total>
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: 9.     1     6.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.2       <total>
 
 # CHECK:      [11] Code Region - G12
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        2400
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.72
+# CHECK-NEXT: uOps Per Cycle:    2.95
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 4.7
 
@@ -1685,11 +1685,11 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D=eeeeeeER. .   ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeER.   ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,5]     D===eE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER.   ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,7]     D====eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeeER   ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,9]     D=====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -1703,22 +1703,22 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.0    0.1    2.2       <total>
+# CHECK-NEXT: 5.     1     4.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ld1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.2       <total>
 
 # CHECK:      [12] Code Region - G13
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      1110
-# CHECK-NEXT: Total uOps:        2600
+# CHECK-NEXT: Total uOps:        1600
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    2.34
+# CHECK-NEXT: uOps Per Cycle:    1.44
 # CHECK-NEXT: IPC:               0.90
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -1731,10 +1731,10 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D=eeeeeeER.    .    .   ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE----R.    .    .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeER   .    .   ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE-----R   .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeER  .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,7]     .D===eE-----R  .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D=========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,5]     D===eE-----R   .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeER  .    .   ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,7]     D====eE-----R  .    .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D==========eeeeeeeeER   ld1	{ v1.b }[0], [x27], #1
 # CHECK-NEXT: [0,9]     .D==========eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
@@ -1749,12 +1749,12 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: 7.     1     4.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     10.0   0.0    0.0       ld1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: 5.     1     4.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: 7.     1     5.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     11.0   0.0    0.0       ld1	{ v1.b }[0], [x27], #1
 # CHECK-NEXT: 9.     1     11.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     4.2    0.1    2.5       <total>
+# CHECK-NEXT:        1     4.6    0.1    2.5       <total>
 
 # CHECK:      [13] Code Region - G14
 
@@ -1991,10 +1991,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        2400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.71
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
 # CHECK-NEXT: Block RThroughput: 2.5
 
@@ -2008,7 +2008,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2	{ v1.2d, v2.2d }, [x27], #32
 # CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld2	{ v1.2s, v2.2s }, [x27], #16
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2	{ v1.4h, v2.4h }, [x27], #16
 # CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
@@ -2026,21 +2026,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld2	{ v1.2d, v2.2d }, [x27], #32
 # CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld2	{ v1.2s, v2.2s }, [x27], #16
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld2	{ v1.2s, v2.2s }, [x27], #16
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld2	{ v1.4h, v2.4h }, [x27], #16
 # CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    3.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [19] Code Region - G20
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        2900
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.69
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
 # CHECK-NEXT: Block RThroughput: 3.0
 
@@ -2052,12 +2052,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.8b, v2.8b }, [x27], #16
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld2	{ v1.16b, v2.16b }, [x27], #32
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2070,23 +2070,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld2	{ v1.8b, v2.8b }, [x27], #16
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld2	{ v1.8h, v2.8h }, [x27], #32
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld2	{ v1.16b, v2.16b }, [x27], #32
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld2	{ v1.8h, v2.8h }, [x27], #32
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld2	{ v1.16b, v2.16b }, [x27], #32
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ld2	{ v1.2d, v2.2d }, [x27], x28
-# CHECK-NEXT: 9.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.7    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld2	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [20] Code Region - G21
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        2700
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.29
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
 # CHECK-NEXT: Block RThroughput: 2.5
 
@@ -2099,8 +2099,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld2	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld2	{ v1.8b, v2.8b }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
@@ -2117,24 +2117,24 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld2	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld2	{ v1.4s, v2.4s }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld2	{ v1.8b, v2.8b }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld2	{ v1.8b, v2.8b }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld2	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.0    0.1    3.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [21] Code Region - G22
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      3310
-# CHECK-NEXT: Total uOps:        2600
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.79
+# CHECK-NEXT: uOps Per Cycle:    0.60
 # CHECK-NEXT: IPC:               0.30
-# CHECK-NEXT: Block RThroughput: 2.5
+# CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456789          0123456789
@@ -2145,8 +2145,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld2	{ v1.b, v2.b }[0], [x27], #2
 # CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld2	{ v1.b, v2.b }[0], [x27], x28
 # CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld2	{ v1.b, v2.b }[8], [x27], x28
 # CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
@@ -2163,24 +2163,24 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     9.0    0.0    0.0       ld2	{ v1.b, v2.b }[0], [x27], #2
 # CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld2	{ v1.b, v2.b }[8], [x27], #2
-# CHECK-NEXT: 5.     1     17.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     24.0   0.0    0.0       ld2	{ v1.b, v2.b }[0], [x27], x28
+# CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     25.0   0.0    0.0       ld2	{ v1.b, v2.b }[0], [x27], x28
 # CHECK-NEXT: 7.     1     25.0   0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     32.0   0.0    0.0       ld2	{ v1.b, v2.b }[8], [x27], x28
 # CHECK-NEXT: 9.     1     33.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     17.0   0.1    3.0       <total>
+# CHECK-NEXT:        1     17.2   0.1    3.0       <total>
 
 # CHECK:      [22] Code Region - G23
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      4003
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.62
+# CHECK-NEXT: uOps Per Cycle:    0.50
 # CHECK-NEXT: IPC:               0.25
-# CHECK-NEXT: Block RThroughput: 2.5
+# CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456789          0123456789
@@ -2192,7 +2192,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld2	{ v1.h, v2.h }[0], [x27], x28
 # CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld2	{ v1.h, v2.h }[4], [x27], x28
 # CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld2	{ v1.s, v2.s }[0], [x27], #8
 # CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
@@ -2210,23 +2210,23 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld2	{ v1.h, v2.h }[0], [x27], x28
 # CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     24.0   0.0    0.0       ld2	{ v1.h, v2.h }[4], [x27], x28
+# CHECK-NEXT: 6.     1     25.0   0.0    0.0       ld2	{ v1.h, v2.h }[4], [x27], x28
 # CHECK-NEXT: 7.     1     25.0   0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     32.0   0.0    0.0       ld2	{ v1.s, v2.s }[0], [x27], #8
 # CHECK-NEXT: 9.     1     33.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     17.1   0.1    3.0       <total>
+# CHECK-NEXT:        1     17.2   0.1    3.0       <total>
 
 # CHECK:      [23] Code Region - G24
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      2603
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.96
+# CHECK-NEXT: uOps Per Cycle:    0.77
 # CHECK-NEXT: IPC:               0.38
-# CHECK-NEXT: Block RThroughput: 2.5
+# CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456789
@@ -2238,7 +2238,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D=========eE------R .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D================eeeeeeeeER .   ld2	{ v1.d, v2.d }[0], [x27], x28
 # CHECK-NEXT: [0,5]     D=================eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D================eeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: [0,6]     D=================eeeeeeeeER.   ld2r	{ v1.1d, v2.1d }, [x27], #16
 # CHECK-NEXT: [0,7]     .D=================eE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D=================eeeeeeeeER   ld2r	{ v1.2d, v2.2d }, [x27], #16
 # CHECK-NEXT: [0,9]     .D==================eE------R   add	x0, x27, #1
@@ -2256,23 +2256,23 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld2	{ v1.d, v2.d }[0], [x27], x28
 # CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     17.0   0.0    0.0       ld2r	{ v1.1d, v2.1d }, [x27], #16
+# CHECK-NEXT: 6.     1     18.0   0.0    0.0       ld2r	{ v1.1d, v2.1d }, [x27], #16
 # CHECK-NEXT: 7.     1     18.0   0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     18.0   0.0    0.0       ld2r	{ v1.2d, v2.2d }, [x27], #16
 # CHECK-NEXT: 9.     1     19.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     12.9   0.1    3.0       <total>
+# CHECK-NEXT:        1     13.0   0.1    3.0       <total>
 
 # CHECK:      [24] Code Region - G25
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.90
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 2.5
+# CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2284,7 +2284,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2r	{ v1.4s, v2.4s }, [x27], #8
 # CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld2r	{ v1.8b, v2.8b }, [x27], #2
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2r	{ v1.8h, v2.8h }, [x27], #4
 # CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
@@ -2302,23 +2302,23 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld2r	{ v1.4s, v2.4s }, [x27], #8
 # CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld2r	{ v1.8b, v2.8b }, [x27], #2
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld2r	{ v1.8b, v2.8b }, [x27], #2
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld2r	{ v1.8h, v2.8h }, [x27], #4
 # CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    3.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [25] Code Region - G26
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        2500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.90
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 2.5
+# CHECK-NEXT: Block RThroughput: 3.3
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2330,7 +2330,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2r	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld2r	{ v1.2s, v2.2s }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld2r	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
@@ -2348,23 +2348,23 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld2r	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld2r	{ v1.2s, v2.2s }, [x27], x28
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld2r	{ v1.2s, v2.2s }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld2r	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    3.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [26] Code Region - G27
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        2800
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.49
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 2.8
+# CHECK-NEXT: Block RThroughput: 3.7
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2376,7 +2376,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld2r	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld2r	{ v1.16b, v2.16b }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
@@ -2394,23 +2394,23 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld2r	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld2r	{ v1.16b, v2.16b }, [x27], x28
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld2r	{ v1.16b, v2.16b }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld3	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    3.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [27] Code Region - G28
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        3700
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    7.25
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 4.0
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2420,12 +2420,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2438,25 +2438,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld3	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: 9.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.7    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [28] Code Region - G29
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        3800
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    7.45
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 4.3
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2465,13 +2465,13 @@ add x0, x27, 1
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2483,26 +2483,26 @@ add x0, x27, 1
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld3	{ v1.2s, v2.2s, v3.2s }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: 9.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.6    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [29] Code Region - G30
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      1910
-# CHECK-NEXT: Total uOps:        3700
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    1.94
+# CHECK-NEXT: uOps Per Cycle:    1.05
 # CHECK-NEXT: IPC:               0.52
-# CHECK-NEXT: Block RThroughput: 4.0
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456789
@@ -2512,12 +2512,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R    .    .    .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER   .    .    .  .   ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE------R   .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER  .    .    .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R  .    .    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=========eeeeeeeeER    .  .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER  .    .    .  .   ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R  .    .    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D==========eeeeeeeeER    .  .   ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
 # CHECK-NEXT: [0,7]     .D==========eE------R    .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D================eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,9]     . D=================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D=================eeeeeeeeER   ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,9]     .D==================eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2530,25 +2530,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     10.0   0.0    0.0       ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld3	{ v1.16b, v2.16b, v3.16b }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     11.0   0.0    0.0       ld3	{ v1.b, v2.b, v3.b }[0], [x27], #3
 # CHECK-NEXT: 7.     1     11.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     17.0   0.0    0.0       ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: 9.     1     18.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     6.9    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     18.0   0.0    0.0       ld3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: 9.     1     19.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     7.4    0.1    3.0       <total>
 
 # CHECK:      [30] Code Region - G31
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      4003
-# CHECK-NEXT: Total uOps:        3500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.87
+# CHECK-NEXT: uOps Per Cycle:    0.50
 # CHECK-NEXT: IPC:               0.25
-# CHECK-NEXT: Block RThroughput: 3.8
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456789          0123456789
@@ -2558,12 +2558,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
 # CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
 # CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2576,25 +2576,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     9.0    0.0    0.0       ld3	{ v1.b, v2.b, v3.b }[8], [x27], x28
 # CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     16.0   0.0    0.0       ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
-# CHECK-NEXT: 5.     1     17.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     24.0   0.0    0.0       ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
+# CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld3	{ v1.h, v2.h, v3.h }[0], [x27], #6
+# CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     25.0   0.0    0.0       ld3	{ v1.h, v2.h, v3.h }[4], [x27], #6
 # CHECK-NEXT: 7.     1     25.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     31.0   0.0    0.0       ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: 9.     1     32.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     16.7   0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     32.0   0.0    0.0       ld3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: 9.     1     33.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     17.2   0.1    3.0       <total>
 
 # CHECK:      [31] Code Region - G32
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      4003
-# CHECK-NEXT: Total uOps:        3500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    0.87
+# CHECK-NEXT: uOps Per Cycle:    0.50
 # CHECK-NEXT: IPC:               0.25
-# CHECK-NEXT: Block RThroughput: 3.8
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456789          0123456789
@@ -2604,12 +2604,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
 # CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===============eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D================eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D=======================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
 # CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==============================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D===============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2622,25 +2622,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     9.0    0.0    0.0       ld3	{ v1.s, v2.s, v3.s }[0], [x27], #12
 # CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     16.0   0.0    0.0       ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
-# CHECK-NEXT: 5.     1     17.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     24.0   0.0    0.0       ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
+# CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld3	{ v1.s, v2.s, v3.s }[0], [x27], x28
+# CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     25.0   0.0    0.0       ld3	{ v1.d, v2.d, v3.d }[0], [x27], #24
 # CHECK-NEXT: 7.     1     25.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     31.0   0.0    0.0       ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: 9.     1     32.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     16.7   0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     32.0   0.0    0.0       ld3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: 9.     1     33.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     17.2   0.1    3.0       <total>
 
 # CHECK:      [32] Code Region - G33
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        3500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    6.86
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 3.8
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2650,12 +2650,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2668,25 +2668,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], #24
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld3r	{ v1.2s, v2.2s, v3.2s }, [x27], #12
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], #6
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
-# CHECK-NEXT: 9.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.7    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], #12
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [33] Code Region - G34
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        3500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    6.86
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 3.8
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2696,12 +2696,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2714,25 +2714,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], #6
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], #3
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld3r	{ v1.1d, v2.1d, v3.1d }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: 9.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.7    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld3r	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [34] Code Region - G35
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        3500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    6.86
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
-# CHECK-NEXT: Block RThroughput: 3.8
+# CHECK-NEXT: Block RThroughput: 5.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01234
@@ -2742,12 +2742,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2760,25 +2760,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld3r	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld3r	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld3r	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: 9.     1     4.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.7    0.1    3.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld3r	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [35] Code Region - G36
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      611
-# CHECK-NEXT: Total uOps:        4500
+# CHECK-NEXT: Total Cycles:      710
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    7.36
-# CHECK-NEXT: IPC:               1.64
-# CHECK-NEXT: Block RThroughput: 5.3
+# CHECK-NEXT: uOps Per Cycle:    2.82
+# CHECK-NEXT: IPC:               1.41
+# CHECK-NEXT: Block RThroughput: 7.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456
@@ -2786,14 +2786,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeeeER  ..   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-------R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeeeER  ..   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,5]     . D=eE------R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  DeeeeeeeeER ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D=eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D==eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeeeER  ..   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,3]     D==eE-------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER  ..   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,5]     D===eE------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,7]     .D===eE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeeeeeeeeER   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,9]     .D=====eE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2804,42 +2804,42 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld3r	{ v1.16b, v2.16b, v3.16b }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: 3.     1     2.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: 5.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     1.0    0.0    0.0       ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: 7.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     2.0    1.0    0.0       ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: 9.     1     3.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT:        1     1.7    0.2    3.2       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: 3.     1     3.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    1.0    0.0       ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: 9.     1     6.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.4    0.2    3.2       <total>
 
 # CHECK:      [36] Code Region - G37
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      610
-# CHECK-NEXT: Total uOps:        4800
+# CHECK-NEXT: Total Cycles:      810
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    7.87
-# CHECK-NEXT: IPC:               1.64
-# CHECK-NEXT: Block RThroughput: 6.0
+# CHECK-NEXT: uOps Per Cycle:    2.47
+# CHECK-NEXT: IPC:               1.23
+# CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
-# CHECK-NEXT:                     012345
+# CHECK-NEXT:                     01234567
 # CHECK-NEXT: Index     0123456789
 
-# CHECK:      [0,0]     DeeeeeeeeER    .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE------R    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeeeER  .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeeeeER .   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,5]     . D=eE-------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  DeeeeeeeeeER.   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE------R   add	x0, x27, #1
+# CHECK:      [0,0]     DeeeeeeeeER    . .   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,1]     D=eE------R    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeeeER  . .   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,3]     D==eE-------R  . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeeER . .   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,5]     D===eE-------R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeeER. .   ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,7]     .D===eE-------R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D======eeeeeeeeER   ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=======eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2850,27 +2850,27 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: 3.     1     2.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: 5.     1     2.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     1.0    0.0    0.0       ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: 7.     1     2.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     2.0    1.0    0.0       ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: 9.     1     3.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     1.7    0.2    3.3       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: 3.     1     3.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: 5.     1     4.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: 7.     1     4.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     7.0    3.0    0.0       ld4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: 9.     1     8.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.8    0.4    3.3       <total>
 
 # CHECK:      [37] Code Region - G38
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      660
-# CHECK-NEXT: Total uOps:        4800
+# CHECK-NEXT: Total Cycles:      809
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    7.27
-# CHECK-NEXT: IPC:               1.52
-# CHECK-NEXT: Block RThroughput: 6.0
+# CHECK-NEXT: uOps Per Cycle:    2.47
+# CHECK-NEXT: IPC:               1.24
+# CHECK-NEXT: Block RThroughput: 8.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     0123456
@@ -2878,14 +2878,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER    ..   ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
 # CHECK-NEXT: [0,1]     D=eE------R    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeeeER  ..   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-------R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeeeER  ..   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE------R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  DeeeeeeeeeER..   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE-------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=eeeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D==eE-------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeeeER  ..   ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eE-------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER  ..   ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeeER..   ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,7]     .D===eE-------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeeeeeeeeER   ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=====eE-------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2896,25 +2896,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: 5.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     1.0    0.0    0.0       ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: 7.     1     2.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     2.0    1.0    0.0       ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: 9.     1     3.0    0.0    7.0       add	x0, x27, #1
-# CHECK-NEXT:        1     1.7    0.2    3.3       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: 7.     1     4.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    1.0    0.0       ld4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    7.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.4    0.2    3.3       <total>
 
 # CHECK:      [38] Code Region - G39
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      4003
-# CHECK-NEXT: Total uOps:        4500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    1.12
+# CHECK-NEXT: uOps Per Cycle:    0.50
 # CHECK-NEXT: IPC:               0.25
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -2924,14 +2924,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
 # CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2942,25 +2942,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     8.0    0.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: 3.     1     9.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     15.0   0.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: 5.     1     16.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     22.0   0.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
-# CHECK-NEXT: 7.     1     23.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     29.0   0.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: 9.     1     30.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     15.5   0.1    3.0       <total>
+# CHECK-NEXT: 2.     1     9.0    0.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     25.0   0.0    0.0       ld4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
+# CHECK-NEXT: 7.     1     25.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     32.0   0.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
+# CHECK-NEXT: 9.     1     33.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     17.2   0.1    3.0       <total>
 
 # CHECK:      [39] Code Region - G40
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      4003
-# CHECK-NEXT: Total uOps:        4500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    1.12
+# CHECK-NEXT: uOps Per Cycle:    0.50
 # CHECK-NEXT: IPC:               0.25
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -2970,14 +2970,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
 # CHECK-NEXT: [0,1]     D=eE------R    .    .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R .    .    .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D==============eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,5]     . D===============eE------R   .    .    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=====================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,7]     .  D======================eE------R.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D============================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .   D=============================eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D========eeeeeeeeER .    .    .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,3]     D=========eE------R .    .    .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D================eeeeeeeeER   .    .    . .   ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,5]     D=================eE------R   .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D========================eeeeeeeeER.    . .   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,7]     .D========================eE------R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===============================eeeeeeeeER   ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .D================================eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -2988,25 +2988,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     8.0    0.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: 3.     1     9.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     15.0   0.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: 5.     1     16.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     22.0   0.0    0.0       ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: 7.     1     23.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     29.0   0.0    0.0       ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: 9.     1     30.0   0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     15.5   0.1    3.0       <total>
+# CHECK-NEXT: 2.     1     9.0    0.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     17.0   0.0    0.0       ld4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: 5.     1     18.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     25.0   0.0    0.0       ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: 7.     1     25.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     32.0   0.0    0.0       ld4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: 9.     1     33.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     17.2   0.1    3.0       <total>
 
 # CHECK:      [40] Code Region - G41
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      1903
-# CHECK-NEXT: Total uOps:        4500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    2.36
+# CHECK-NEXT: uOps Per Cycle:    1.05
 # CHECK-NEXT: IPC:               0.53
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -3016,14 +3016,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER    .    ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
 # CHECK-NEXT: [0,1]     D=eE------R    .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .D=======eeeeeeeeER ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D========eE------R ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D=======eeeeeeeeER..   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: [0,5]     . D========eE------R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D=======eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: [0,7]     .  D========eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D=======eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: [0,9]     .   D========eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D========eeeeeeeeER ..   ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,3]     D=========eE------R ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D=========eeeeeeeeER..   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: [0,5]     D==========eE------R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D==========eeeeeeeeER.   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: [0,7]     .D==========eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D==========eeeeeeeeER   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: [0,9]     .D===========eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3034,25 +3034,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     8.0    0.0    0.0       ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: 3.     1     9.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     8.0    0.0    0.0       ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
-# CHECK-NEXT: 5.     1     9.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     8.0    0.0    0.0       ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
-# CHECK-NEXT: 7.     1     9.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     8.0    0.0    0.0       ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
-# CHECK-NEXT: 9.     1     9.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     7.1    0.1    3.0       <total>
+# CHECK-NEXT: 2.     1     9.0    0.0    0.0       ld4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: 3.     1     10.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     10.0   0.0    0.0       ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
+# CHECK-NEXT: 5.     1     11.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     11.0   0.0    0.0       ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #32
+# CHECK-NEXT: 7.     1     11.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     11.0   0.0    0.0       ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #16
+# CHECK-NEXT: 9.     1     12.0   0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     8.8    0.1    3.0       <total>
 
 # CHECK:      [41] Code Region - G42
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        4500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    8.82
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -3062,14 +3062,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #8
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeeER  .   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeeeER .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
-# CHECK-NEXT: [0,5]     . D=eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  DeeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
-# CHECK-NEXT: [0,7]     .  D=eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   DeeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
-# CHECK-NEXT: [0,9]     .   D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
+# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
+# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3080,25 +3080,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #8
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
-# CHECK-NEXT: 3.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
-# CHECK-NEXT: 5.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     1.0    0.0    0.0       ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
-# CHECK-NEXT: 7.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     1.0    0.0    0.0       ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
-# CHECK-NEXT: 9.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     1.5    0.1    3.0       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #16
+# CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #4
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #8
+# CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #4
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [42] Code Region - G43
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      510
-# CHECK-NEXT: Total uOps:        4500
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    8.82
+# CHECK-NEXT: uOps Per Cycle:    3.92
 # CHECK-NEXT: IPC:               1.96
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -3108,14 +3108,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER   .   ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 # CHECK-NEXT: [0,1]     D=eE------R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeeER  .   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeeeER .   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  DeeeeeeeeER.   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,7]     .  D=eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   DeeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,9]     .   D=eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeeER  .   ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eE------R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER .   ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeeeER.   ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,7]     .D===eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeeeER   ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,9]     .D====eE------R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3126,25 +3126,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4r	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: 5.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     1.0    0.0    0.0       ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: 7.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     1.0    0.0    0.0       ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: 9.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT:        1     1.5    0.1    3.0       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld4r	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld4r	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       ld4r	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: 7.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ld4r	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: 9.     1     5.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    3.0       <total>
 
 # CHECK:      [43] Code Region - G44
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        3300
+# CHECK-NEXT: Total uOps:        1800
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    6.50
+# CHECK-NEXT: uOps Per Cycle:    3.54
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 3.7
 
@@ -3154,14 +3154,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeeeeeeeER .   ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 # CHECK-NEXT: [0,1]     D=eE------R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE------R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     . D=eE------R   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeE-R   ldp	s1, s2, [x27], #248
-# CHECK-NEXT: [0,7]     . D==eE-----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   ldp	d1, d2, [x27], #496
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeeER.   ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eE------R.   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeeeER   ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE------R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeE-R   ldp	s1, s2, [x27], #248
+# CHECK-NEXT: [0,7]     D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeER   ldp	d1, d2, [x27], #496
+# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3172,25 +3172,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       ld4r	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: 5.     1     2.0    0.0    6.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     2.0    0.0    1.0       ldp	s1, s2, [x27], #248
-# CHECK-NEXT: 7.     1     3.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       ldp	d1, d2, [x27], #496
-# CHECK-NEXT: 9.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.1    0.1    2.8       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       ld4r	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       ld4r	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    6.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    1.0       ldp	s1, s2, [x27], #248
+# CHECK-NEXT: 7.     1     5.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ldp	d1, d2, [x27], #496
+# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.3    0.1    2.8       <total>
 
 # CHECK:      [44] Code Region - G45
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      507
-# CHECK-NEXT: Total uOps:        1700
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.35
+# CHECK-NEXT: uOps Per Cycle:    2.96
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 2.5
 
@@ -3206,8 +3206,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,5]     D===eE----R.   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     D===eeeeeeER   ldp	q1, q2, [x27, #992]!
 # CHECK-NEXT: [0,7]     D====eE----R   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeE-R   ldp	w1, w2, [x27], #248
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeE-R   ldp	w1, w2, [x27], #248
+# CHECK-NEXT: [0,9]     D=====eE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3224,21 +3224,21 @@ add x0, x27, 1
 # CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       ldp	q1, q2, [x27, #992]!
 # CHECK-NEXT: 7.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    1.0       ldp	w1, w2, [x27], #248
-# CHECK-NEXT: 9.     1     5.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.3    0.1    2.0       <total>
+# CHECK-NEXT: 8.     1     5.0    0.0    1.0       ldp	w1, w2, [x27], #248
+# CHECK-NEXT: 9.     1     6.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    2.0       <total>
 
 # CHECK:      [45] Code Region - G46
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      507
-# CHECK-NEXT: Total uOps:        1900
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.75
+# CHECK-NEXT: uOps Per Cycle:    2.96
 # CHECK-NEXT: IPC:               1.97
-# CHECK-NEXT: Block RThroughput: 3.0
+# CHECK-NEXT: Block RThroughput: 4.3
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     01
@@ -3252,8 +3252,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,5]     D===eE--R ..   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     D===eeeeeER.   ldpsw	x1, x2, [x27], #248
 # CHECK-NEXT: [0,7]     D====eE---R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeeeeER   ldpsw	x1, x2, [x27, #248]!
-# CHECK-NEXT: [0,9]     .D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D====eeeeeER   ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: [0,9]     D=====eE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3270,9 +3270,9 @@ add x0, x27, 1
 # CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       ldpsw	x1, x2, [x27], #248
 # CHECK-NEXT: 7.     1     5.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       ldpsw	x1, x2, [x27, #248]!
-# CHECK-NEXT: 9.     1     5.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.3    0.1    1.2       <total>
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       ldpsw	x1, x2, [x27, #248]!
+# CHECK-NEXT: 9.     1     6.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.5    0.1    1.2       <total>
 
 # CHECK:      [46] Code Region - G47
 
@@ -3689,10 +3689,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.76
+# CHECK-NEXT: uOps Per Cycle:    3.97
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 3.5
 
@@ -3705,7 +3705,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.4h, v2.4h }, [x27], #16
 # CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: [0,6]     D===eeER.   st1	{ v1.4s, v2.4s }, [x27], #32
 # CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.8b, v2.8b }, [x27], #16
 # CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
@@ -3723,21 +3723,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       st1	{ v1.4h, v2.4h }, [x27], #16
 # CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st1	{ v1.4s, v2.4s }, [x27], #32
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st1	{ v1.4s, v2.4s }, [x27], #32
 # CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       st1	{ v1.8b, v2.8b }, [x27], #16
 # CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    0.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
 
 # CHECK:      [56] Code Region - G57
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2600
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.16
+# CHECK-NEXT: uOps Per Cycle:    3.97
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 4.0
 
@@ -3749,8 +3749,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D=eeER  .   st1	{ v1.16b, v2.16b }, [x27], #32
 # CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeER.   st1	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.2s, v2.2s }, [x27], x28
 # CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
@@ -3767,22 +3767,22 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.16b, v2.16b }, [x27], #32
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       st1	{ v1.1d, v2.1d }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st1	{ v1.2d, v2.2d }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st1	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       st1	{ v1.2s, v2.2s }, [x27], x28
 # CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.0    0.1    0.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
 
 # CHECK:      [57] Code Region - G58
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2600
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.16
+# CHECK-NEXT: uOps Per Cycle:    3.97
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 4.0
 
@@ -3795,7 +3795,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeER .   st1	{ v1.8b, v2.8b }, [x27], x28
 # CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: [0,6]     D===eeER.   st1	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeER   st1	{ v1.16b, v2.16b }, [x27], x28
 # CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
@@ -3813,21 +3813,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       st1	{ v1.8b, v2.8b }, [x27], x28
 # CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st1	{ v1.8h, v2.8h }, [x27], x28
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st1	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       st1	{ v1.16b, v2.16b }, [x27], x28
 # CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    0.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
 
 # CHECK:      [58] Code Region - G59
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      703
-# CHECK-NEXT: Total uOps:        3400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.84
+# CHECK-NEXT: uOps Per Cycle:    2.84
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 6.0
 
@@ -3838,12 +3838,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,4]     D==eeER  .   st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: [0,5]     D===eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeER.   st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 # CHECK-NEXT: [0,7]     .D====eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: [0,9]     . D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeER   st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: [0,9]     .D=====eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3856,23 +3856,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.2d, v2.2d, v3.2d }, [x27], #48
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
-# CHECK-NEXT: 5.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    1.0    0.0       st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st1	{ v1.2s, v2.2s, v3.2s }, [x27], #24
+# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    1.0    0.0       st1	{ v1.4h, v2.4h, v3.4h }, [x27], #24
 # CHECK-NEXT: 7.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
-# CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.2    0.0       <total>
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       st1	{ v1.4s, v2.4s, v3.4s }, [x27], #48
+# CHECK-NEXT: 9.     1     6.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.6    0.2    0.0       <total>
 
 # CHECK:      [59] Code Region - G60
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      703
-# CHECK-NEXT: Total uOps:        3600
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.12
+# CHECK-NEXT: uOps Per Cycle:    2.84
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 6.5
 
@@ -3883,12 +3883,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
 # CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: [0,4]     D==eeER  .   st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,5]     D===eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeER.   st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
 # CHECK-NEXT: [0,7]     .D====eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeER   st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=====eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3901,23 +3901,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.8h, v2.8h, v3.8h }, [x27], #48
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: 5.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    1.0    0.0       st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st1	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    1.0    0.0       st1	{ v1.1d, v2.1d, v3.1d }, [x27], x28
 # CHECK-NEXT: 7.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.2    0.0       <total>
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       st1	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.6    0.2    0.0       <total>
 
 # CHECK:      [60] Code Region - G61
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      703
-# CHECK-NEXT: Total uOps:        3400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.84
+# CHECK-NEXT: uOps Per Cycle:    2.84
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 6.0
 
@@ -3928,12 +3928,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     D==eeER  .   st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeER .   st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeER   st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=====eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3946,23 +3946,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st1	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st1	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    1.0    0.0       st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.9    0.2    0.0       <total>
+# CHECK-NEXT: 8.     1     5.0    1.0    0.0       st1	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.4    0.2    0.0       <total>
 
 # CHECK:      [61] Code Region - G62
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      704
-# CHECK-NEXT: Total uOps:        3600
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.11
+# CHECK-NEXT: uOps Per Cycle:    2.84
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 6.5
 
@@ -3974,12 +3974,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eER.    .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeER    .   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
 # CHECK-NEXT: [0,3]     D==eER    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,5]     .D===eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,7]     . D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,9]     . D=====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D===eeER  .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,5]     D====eER  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeER .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,7]     .D====eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D=====eeER   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,9]     .D======eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -3992,23 +3992,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], #32
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     5.0    1.0    0.0       st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: 9.     1     6.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.4    0.3    0.0       <total>
+# CHECK-NEXT: 4.     1     4.0    1.0    0.0       st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: 5.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    0.0    0.0       st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: 7.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     6.0    1.0    0.0       st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: 9.     1     7.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     4.0    0.3    0.0       <total>
 
 # CHECK:      [62] Code Region - G63
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      804
-# CHECK-NEXT: Total uOps:        4200
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.22
+# CHECK-NEXT: uOps Per Cycle:    2.49
 # CHECK-NEXT: IPC:               1.24
 # CHECK-NEXT: Block RThroughput: 8.0
 
@@ -4019,13 +4019,13 @@ add x0, x27, 1
 # CHECK:      [0,0]     DeeER.    ..   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: [0,1]     D=eER.    ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeER    ..   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,3]     .D=eER    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,5]     .D===eER  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D==eeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,7]     . D===eER ..   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D=====eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D=====eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     D==eER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D===eeER  ..   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,5]     D====eER  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeER ..   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,7]     .D====eER ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D======eeER   st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=======eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4037,24 +4037,24 @@ add x0, x27, 1
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: 3.     1     2.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     6.0    2.0    0.0       st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
-# CHECK-NEXT: 9.     1     6.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.3    0.4    0.0       <total>
+# CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     4.0    1.0    0.0       st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: 5.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    0.0    0.0       st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: 7.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     7.0    2.0    0.0       st1	{ v1.1d, v2.1d, v3.1d, v4.1d }, [x27], x28
+# CHECK-NEXT: 9.     1     8.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     4.2    0.4    0.0       <total>
 
 # CHECK:      [63] Code Region - G64
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      703
-# CHECK-NEXT: Total uOps:        3800
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.41
+# CHECK-NEXT: uOps Per Cycle:    2.84
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 7.0
 
@@ -4064,13 +4064,13 @@ add x0, x27, 1
 # CHECK:      [0,0]     DeeER.   .   st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: [0,1]     D=eER.   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeER   .   st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     .D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D==eeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     . D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D===eER   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     D==eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D===eeER .   st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     D====eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeER.   st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .D====eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeER   st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=====eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4082,24 +4082,24 @@ add x0, x27, 1
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st1	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: 9.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.9    0.2    0.0       <total>
+# CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     4.0    1.0    0.0       st1	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: 5.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    0.0    0.0       st1	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: 7.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       st1	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.8    0.2    0.0       <total>
 
 # CHECK:      [64] Code Region - G65
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      706
-# CHECK-NEXT: Total uOps:        3200
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.53
+# CHECK-NEXT: uOps Per Cycle:    2.83
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 5.5
 
@@ -4109,14 +4109,14 @@ add x0, x27, 1
 
 # CHECK:      [0,0]     DeeER.    . .   st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: [0,1]     D=eER.    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeER    . .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eER    . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===eeeeER .   st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: [0,5]     .D====eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeER.   st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: [0,7]     . D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eeeeER   st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     . D=====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeER    . .   st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eER    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D====eeeeER .   st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: [0,5]     D=====eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D=====eeeeER.   st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: [0,7]     .D=====eE--R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D=====eeeeER   st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .D======eE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4127,15 +4127,15 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st1	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     4.0    2.0    0.0       st1	{ v1.b }[0], [x27], #1
-# CHECK-NEXT: 5.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st1	{ v1.b }[8], [x27], #1
-# CHECK-NEXT: 7.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     5.0    0.0    0.0       st1	{ v1.b }[0], [x27], x28
-# CHECK-NEXT: 9.     1     6.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.5    0.3    0.6       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       st1	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     5.0    2.0    0.0       st1	{ v1.b }[0], [x27], #1
+# CHECK-NEXT: 5.     1     6.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     6.0    0.0    0.0       st1	{ v1.b }[8], [x27], #1
+# CHECK-NEXT: 7.     1     6.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     6.0    0.0    0.0       st1	{ v1.b }[0], [x27], x28
+# CHECK-NEXT: 9.     1     7.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT:        1     4.4    0.3    0.6       <total>
 
 # CHECK:      [65] Code Region - G66
 
@@ -4188,10 +4188,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      506
-# CHECK-NEXT: Total uOps:        2200
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.35
+# CHECK-NEXT: uOps Per Cycle:    3.95
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 3.0
 
@@ -4234,10 +4234,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      506
-# CHECK-NEXT: Total uOps:        2400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.74
+# CHECK-NEXT: uOps Per Cycle:    3.95
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 3.5
 
@@ -4251,7 +4251,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.4s, v2.4s }, [x27], #32
 # CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: [0,6]     D===eeeeER.   st2	{ v1.8b, v2.8b }, [x27], #16
 # CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
@@ -4269,21 +4269,21 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       st2	{ v1.4s, v2.4s }, [x27], #32
 # CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st2	{ v1.8b, v2.8b }, [x27], #16
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st2	{ v1.8b, v2.8b }, [x27], #16
 # CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       st2	{ v1.8h, v2.8h }, [x27], #32
 # CHECK-NEXT: 9.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    1.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    1.0       <total>
 
 # CHECK:      [68] Code Region - G69
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      506
-# CHECK-NEXT: Total uOps:        2600
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.14
+# CHECK-NEXT: uOps Per Cycle:    3.95
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 4.0
 
@@ -4296,8 +4296,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeER.   st2	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.4s, v2.4s }, [x27], x28
 # CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
@@ -4314,22 +4314,22 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st2	{ v1.2d, v2.2d }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       st2	{ v1.2s, v2.2s }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st2	{ v1.4h, v2.4h }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st2	{ v1.4h, v2.4h }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       st2	{ v1.4s, v2.4s }, [x27], x28
 # CHECK-NEXT: 9.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.0    0.1    1.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    1.0       <total>
 
 # CHECK:      [69] Code Region - G70
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      506
-# CHECK-NEXT: Total uOps:        2400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.74
+# CHECK-NEXT: uOps Per Cycle:    3.95
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 3.5
 
@@ -4342,8 +4342,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,2]     D=eeeeER  .   st2	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeeeER .   st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeER.   st2	{ v1.b, v2.b }[0], [x27], #2
 # CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eeeeER   st2	{ v1.b, v2.b }[8], [x27], #2
 # CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
@@ -4360,12 +4360,12 @@ add x0, x27, 1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st2	{ v1.8h, v2.8h }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       st2	{ v1.16b, v2.16b }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st2	{ v1.b, v2.b }[0], [x27], #2
+# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st2	{ v1.b, v2.b }[0], [x27], #2
 # CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       st2	{ v1.b, v2.b }[8], [x27], #2
 # CHECK-NEXT: 9.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.0    0.1    1.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    1.0       <total>
 
 # CHECK:      [70] Code Region - G71
 
@@ -4464,10 +4464,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      600
 # CHECK-NEXT: Total Cycles:      406
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total uOps:        1200
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.93
+# CHECK-NEXT: uOps Per Cycle:    2.96
 # CHECK-NEXT: IPC:               1.48
 # CHECK-NEXT: Block RThroughput: 3.5
 
@@ -4478,8 +4478,8 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE---R .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeER .   st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
 # CHECK-NEXT: [0,3]     D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: [0,5]     .D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D===eeeeER   st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: [0,5]     D====eE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4492,19 +4492,19 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    3.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st3	{ v1.2s, v2.2s, v3.2s }, [x27], #24
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
-# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.5    0.3    1.2       <total>
+# CHECK-NEXT: 4.     1     4.0    1.0    0.0       st3	{ v1.4h, v2.4h, v3.4h }, [x27], #24
+# CHECK-NEXT: 5.     1     5.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT:        1     2.8    0.3    1.2       <total>
 
 # CHECK:      [73] Code Region - G74
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      707
-# CHECK-NEXT: Total uOps:        3800
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.37
+# CHECK-NEXT: uOps Per Cycle:    2.83
 # CHECK-NEXT: IPC:               1.41
 # CHECK-NEXT: Block RThroughput: 7.0
 
@@ -4516,12 +4516,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE---R  .  .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeER  .  .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: [0,3]     D==eE--R  .  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeeER  .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: [0,5]     .D===eE---R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: [0,7]     . D===eE---R .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D====eeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: [0,9]     . D=====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D===eeeeeER  .   st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: [0,5]     D====eE---R  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeeeeER .   st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: [0,7]     .D====eE---R .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D=====eeeeeER   st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: [0,9]     .D======eE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4534,23 +4534,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    3.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st3	{ v1.8b, v2.8b, v3.8b }, [x27], #24
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
-# CHECK-NEXT: 5.     1     4.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
-# CHECK-NEXT: 7.     1     4.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     5.0    1.0    0.0       st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
-# CHECK-NEXT: 9.     1     6.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.4    0.3    1.4       <total>
+# CHECK-NEXT: 4.     1     4.0    1.0    0.0       st3	{ v1.8h, v2.8h, v3.8h }, [x27], #48
+# CHECK-NEXT: 5.     1     5.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    0.0    0.0       st3	{ v1.16b, v2.16b, v3.16b }, [x27], #48
+# CHECK-NEXT: 7.     1     5.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     6.0    1.0    0.0       st3	{ v1.2d, v2.2d, v3.2d }, [x27], x28
+# CHECK-NEXT: 9.     1     7.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT:        1     4.0    0.3    1.4       <total>
 
 # CHECK:      [74] Code Region - G75
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      706
-# CHECK-NEXT: Total uOps:        3400
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.82
+# CHECK-NEXT: uOps Per Cycle:    2.83
 # CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 6.0
 
@@ -4562,12 +4562,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE--R   . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeER  . .   st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: [0,3]     D==eE--R  . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeER. .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE---R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER. .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: [0,4]     D==eeeeeER. .   st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: [0,5]     D===eE---R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeER. .   st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: [0,9]     . D====eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeeeeER   st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=====eE---R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4580,23 +4580,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st3	{ v1.4h, v2.4h, v3.4h }, [x27], x28
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st3	{ v1.4s, v2.4s, v3.4s }, [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st3	{ v1.8b, v2.8b, v3.8b }, [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    1.0    0.0       st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    3.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.9    0.2    1.2       <total>
+# CHECK-NEXT: 8.     1     5.0    1.0    0.0       st3	{ v1.8h, v2.8h, v3.8h }, [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    3.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.4    0.2    1.2       <total>
 
 # CHECK:      [75] Code Region - G76
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      606
-# CHECK-NEXT: Total uOps:        3200
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.28
+# CHECK-NEXT: uOps Per Cycle:    3.30
 # CHECK-NEXT: IPC:               1.65
 # CHECK-NEXT: Block RThroughput: 5.5
 
@@ -4608,12 +4608,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE---R  ..   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeER  ..   st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
 # CHECK-NEXT: [0,3]     D==eE--R  ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeER..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: [0,5]     .D===eE--R..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: [0,4]     D===eeeeER..   st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: [0,5]     D====eE--R..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D====eeeeER.   st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
 # CHECK-NEXT: [0,7]     .D====eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D===eeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: [0,9]     . D====eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeeeER   st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: [0,9]     .D=====eE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4626,23 +4626,23 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    3.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st3	{ v1.b, v2.b, v3.b }[0], [x27], #3
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
-# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
+# CHECK-NEXT: 4.     1     4.0    1.0    0.0       st3	{ v1.b, v2.b, v3.b }[8], [x27], #3
+# CHECK-NEXT: 5.     1     5.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     5.0    0.0    0.0       st3	{ v1.b, v2.b, v3.b }[0], [x27], x28
 # CHECK-NEXT: 7.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.3    0.2    1.1       <total>
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       st3	{ v1.b, v2.b, v3.b }[8], [x27], x28
+# CHECK-NEXT: 9.     1     6.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.8    0.2    1.1       <total>
 
 # CHECK:      [76] Code Region - G77
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      506
-# CHECK-NEXT: Total uOps:        3000
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.93
+# CHECK-NEXT: uOps Per Cycle:    3.95
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -4654,12 +4654,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE--R   .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeER  .   st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
 # CHECK-NEXT: [0,3]     D==eE--R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: [0,4]     D==eeeeER .   st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: [0,5]     D===eE--R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeER.   st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
 # CHECK-NEXT: [0,7]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: [0,9]     . D===eE--R   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeER   st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: [0,9]     .D====eE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4672,25 +4672,25 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st3	{ v1.h, v2.h, v3.h }[4], [x27], #6
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st3	{ v1.h, v2.h, v3.h }[0], [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st3	{ v1.h, v2.h, v3.h }[4], [x27], x28
 # CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
-# CHECK-NEXT: 9.     1     4.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.7    0.1    1.0       <total>
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st3	{ v1.s, v2.s, v3.s }[0], [x27], #12
+# CHECK-NEXT: 9.     1     5.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    1.0       <total>
 
 # CHECK:      [77] Code Region - G78
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      706
-# CHECK-NEXT: Total uOps:        3600
+# CHECK-NEXT: Total Cycles:      1003
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.10
-# CHECK-NEXT: IPC:               1.42
-# CHECK-NEXT: Block RThroughput: 6.5
+# CHECK-NEXT: uOps Per Cycle:    1.99
+# CHECK-NEXT: IPC:               1.00
+# CHECK-NEXT: Block RThroughput: 10.0
 
 # CHECK:      Timeline view:
 # CHECK-NEXT:                     012
@@ -4700,12 +4700,12 @@ add x0, x27, 1
 # CHECK-NEXT: [0,1]     D=eE--R   . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeER  . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
 # CHECK-NEXT: [0,3]     D==eE--R  . .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeER . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: [0,5]     .D==eE--R . .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeeeER. .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: [0,7]     . D==eE--R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: [0,9]     . D===eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeER . .   st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: [0,5]     D===eE--R . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeER. .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: [0,7]     .D===eE--R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeER   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4718,40 +4718,40 @@ add x0, x27, 1
 # CHECK-NEXT: 1.     1     2.0    0.0    2.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st3	{ v1.d, v2.d, v3.d }[0], [x27], #24
 # CHECK-NEXT: 3.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
-# CHECK-NEXT: 5.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
-# CHECK-NEXT: 7.     1     3.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
-# CHECK-NEXT: 9.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.6    0.1    1.2       <total>
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st3	{ v1.d, v2.d, v3.d }[0], [x27], x28
+# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], #64
+# CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], #32
+# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    1.2       <total>
 
 # CHECK:      [78] Code Region - G79
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      1205
-# CHECK-NEXT: Total uOps:        5800
+# CHECK-NEXT: Total Cycles:      2399
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.81
-# CHECK-NEXT: IPC:               0.83
-# CHECK-NEXT: Block RThroughput: 12.0
+# CHECK-NEXT: uOps Per Cycle:    0.83
+# CHECK-NEXT: IPC:               0.42
+# CHECK-NEXT: Block RThroughput: 24.0
 
 # CHECK:      Timeline view:
-# CHECK-NEXT:                     0123456
-# CHECK-NEXT: Index     0123456789
-
-# CHECK:      [0,0]     DeeeeeeER .    ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
-# CHECK-NEXT: [0,1]     D=eE----R .    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeER    ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: [0,3]     .D=eE-----R    ..   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . D=eeeeeeER   ..   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: [0,5]     . D==eE----R   ..   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .  D===eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: [0,7]     .  D====eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .   D===eeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: [0,9]     .   D====eE-----R   add	x0, x27, #1
+# CHECK-NEXT:                     0123456789
+# CHECK-NEXT: Index     0123456789          012
+
+# CHECK:      [0,0]     DeeeeeeER .    .    . .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
+# CHECK-NEXT: [0,1]     D=eE----R .    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeER    .    . .   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: [0,3]     D==eE-----R    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D======eeeeeeER.    . .   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: [0,5]     D=======eE----R.    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D============eeeeeeeER.   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: [0,7]     .D============eE-----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D============eeeeeeeER   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: [0,9]     .D=============eE-----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4762,42 +4762,42 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], #32
 # CHECK-NEXT: 1.     1     2.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
-# CHECK-NEXT: 3.     1     2.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    1.0    0.0       st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
-# CHECK-NEXT: 5.     1     3.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    2.0    0.0       st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
-# CHECK-NEXT: 7.     1     5.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
-# CHECK-NEXT: 9.     1     5.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.9    0.4    2.3       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], #64
+# CHECK-NEXT: 3.     1     3.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     7.0    4.0    0.0       st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], #32
+# CHECK-NEXT: 5.     1     8.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     13.0   5.0    0.0       st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], #64
+# CHECK-NEXT: 7.     1     13.0   0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     13.0   0.0    0.0       st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], #64
+# CHECK-NEXT: 9.     1     14.0   0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT:        1     7.6    1.0    2.3       <total>
 
 # CHECK:      [79] Code Region - G80
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      1006
-# CHECK-NEXT: Total uOps:        4800
+# CHECK-NEXT: Total Cycles:      1903
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.77
-# CHECK-NEXT: IPC:               0.99
-# CHECK-NEXT: Block RThroughput: 9.5
+# CHECK-NEXT: uOps Per Cycle:    1.05
+# CHECK-NEXT: IPC:               0.53
+# CHECK-NEXT: Block RThroughput: 19.0
 
 # CHECK:      Timeline view:
-# CHECK-NEXT:                     012345
-# CHECK-NEXT: Index     0123456789
+# CHECK-NEXT:                     0123456789
+# CHECK-NEXT: Index     0123456789          01
 
-# CHECK:      [0,0]     DeeeeER   .    .   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE--R   .    .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeER.    .   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.    .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D===eeeeeeER  .   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: [0,5]     . D===eE----R  .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeeeeER.   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: [0,7]     . D====eE-----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D====eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: [0,9]     .  D=====eE----R   add	x0, x27, #1
+# CHECK:      [0,0]     DeeeeER   .    .    ..   st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
+# CHECK-NEXT: [0,1]     D=eE--R   .    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeER.    .    ..   st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eE----R.    .    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D=======eeeeeeER    ..   st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: [0,5]     D========eE----R    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D========eeeeeeeER  ..   st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: [0,7]     .D========eE-----R  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D============eeeeeeER   st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: [0,9]     .D=============eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4808,42 +4808,42 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st4	{ v1.2d, v2.2d, v3.2d, v4.2d }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     4.0    2.0    0.0       st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
-# CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
-# CHECK-NEXT: 7.     1     5.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     5.0    1.0    0.0       st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
-# CHECK-NEXT: 9.     1     6.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.4    0.4    1.9       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       st4	{ v1.2s, v2.2s, v3.2s, v4.2s }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     8.0    5.0    0.0       st4	{ v1.4h, v2.4h, v3.4h, v4.4h }, [x27], x28
+# CHECK-NEXT: 5.     1     9.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     9.0    0.0    0.0       st4	{ v1.4s, v2.4s, v3.4s, v4.4s }, [x27], x28
+# CHECK-NEXT: 7.     1     9.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     13.0   4.0    0.0       st4	{ v1.8b, v2.8b, v3.8b, v4.8b }, [x27], x28
+# CHECK-NEXT: 9.     1     14.0   0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     7.0    1.0    1.9       <total>
 
 # CHECK:      [80] Code Region - G81
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      807
-# CHECK-NEXT: Total uOps:        5200
+# CHECK-NEXT: Total Cycles:      1508
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    6.44
-# CHECK-NEXT: IPC:               1.24
-# CHECK-NEXT: Block RThroughput: 6.0
+# CHECK-NEXT: uOps Per Cycle:    1.33
+# CHECK-NEXT: IPC:               0.66
+# CHECK-NEXT: Block RThroughput: 15.0
 
 # CHECK:      Timeline view:
-# CHECK-NEXT:                     01234
-# CHECK-NEXT: Index     0123456789
-
-# CHECK:      [0,0]     DeeeeeeeER.   .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
-# CHECK-NEXT: [0,1]     D=eE-----R.   .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     .DeeeeeeeER   .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE-----R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     . DeeeeeeER   .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: [0,5]     . D=eE----R   .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D===eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: [0,7]     .  D===eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .  D===eeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: [0,9]     .  D====eE----R   add	x0, x27, #1
+# CHECK-NEXT:                     0123456789
+# CHECK-NEXT: Index     0123456789          012
+
+# CHECK:      [0,0]     DeeeeeeeER.    .    . .   st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
+# CHECK-NEXT: [0,1]     D=eE-----R.    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeeER    .    . .   st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: [0,3]     D==eE-----R    .    . .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D============eeeeeeER .   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
+# CHECK-NEXT: [0,5]     D=============eE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D=============eeeeeeER.   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: [0,7]     .D=============eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D=============eeeeeeER   st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: [0,9]     .D==============eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4854,25 +4854,25 @@ add x0, x27, 1
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st4	{ v1.8h, v2.8h, v3.8h, v4.8h }, [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     1.0    0.0    0.0       st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    5.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     1.0    0.0    0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
-# CHECK-NEXT: 5.     1     2.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    2.0    0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
-# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
-# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.6    0.3    2.2       <total>
+# CHECK-NEXT: 2.     1     2.0    0.0    0.0       st4	{ v1.16b, v2.16b, v3.16b, v4.16b }, [x27], x28
+# CHECK-NEXT: 3.     1     3.0    0.0    5.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     13.0   10.0   0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], #4
+# CHECK-NEXT: 5.     1     14.0   0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     14.0   0.0    0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], #4
+# CHECK-NEXT: 7.     1     14.0   0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     14.0   0.0    0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[0], [x27], x28
+# CHECK-NEXT: 9.     1     15.0   0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     9.2    1.1    2.2       <total>
 
 # CHECK:      [81] Code Region - G82
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      508
-# CHECK-NEXT: Total uOps:        4000
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    7.87
+# CHECK-NEXT: uOps Per Cycle:    3.94
 # CHECK-NEXT: IPC:               1.97
 # CHECK-NEXT: Block RThroughput: 5.0
 
@@ -4883,13 +4883,13 @@ add x0, x27, 1
 # CHECK:      [0,0]     DeeeeeeER . .   st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
 # CHECK-NEXT: [0,1]     D=eE----R . .   add	x0, x27, #1
 # CHECK-NEXT: [0,2]     D=eeeeeeER. .   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: [0,3]     .D=eE----R. .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D=eeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: [0,5]     .D==eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     . D=eeeeeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: [0,7]     . D==eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     . D==eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: [0,9]     .  D==eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,3]     D==eE----R. .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeeeER .   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
+# CHECK-NEXT: [0,5]     D===eE----R .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeeeER.   st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .D===eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D===eeeeeeER   st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: [0,9]     .D====eE----R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4901,39 +4901,38 @@ add x0, x27, 1
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st4	{ v1.b, v2.b, v3.b, v4.b }[8], [x27], x28
 # CHECK-NEXT: 1.     1     2.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], #8
-# CHECK-NEXT: 3.     1     2.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     2.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
-# CHECK-NEXT: 5.     1     3.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     2.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
-# CHECK-NEXT: 7.     1     3.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     3.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
-# CHECK-NEXT: 9.     1     3.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.3    0.1    2.0       <total>
+# CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], #8
+# CHECK-NEXT: 5.     1     4.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[0], [x27], x28
+# CHECK-NEXT: 7.     1     4.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     4.0    0.0    0.0       st4	{ v1.h, v2.h, v3.h, v4.h }[4], [x27], x28
+# CHECK-NEXT: 9.     1     5.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.2    0.1    2.0       <total>
 
 # CHECK:      [82] Code Region - G83
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      800
-# CHECK-NEXT: Total Cycles:      506
-# CHECK-NEXT: Total uOps:        2800
+# CHECK-NEXT: Total Cycles:      406
+# CHECK-NEXT: Total uOps:        1600
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    5.53
-# CHECK-NEXT: IPC:               1.58
-# CHECK-NEXT: Block RThroughput: 2.0
+# CHECK-NEXT: uOps Per Cycle:    3.94
+# CHECK-NEXT: IPC:               1.97
+# CHECK-NEXT: Block RThroughput: 4.0
 
 # CHECK:      Timeline view:
-# CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
-# CHECK:      [0,0]     DeeeeeeER .   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
-# CHECK-NEXT: [0,1]     D=eE----R .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: [0,3]     .D=eE----R.   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     .D==eeeeER.   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: [0,5]     .D===eE--R.   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D===eeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: [0,7]     .D====eE--R   add	x0, x27, #1
+# CHECK:      [0,0]     DeeeeeeER.   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
+# CHECK-NEXT: [0,1]     D=eE----R.   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eeeeeeER   st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
+# CHECK-NEXT: [0,3]     D==eE----R   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eeeeE-R   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
+# CHECK-NEXT: [0,5]     D===eE---R   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeeeER   st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
+# CHECK-NEXT: [0,7]     .D===eE--R   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -4945,12 +4944,12 @@ add x0, x27, 1
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], #16
 # CHECK-NEXT: 1.     1     2.0    0.0    4.0       add	x0, x27, #1
 # CHECK-NEXT: 2.     1     2.0    0.0    0.0       st4	{ v1.s, v2.s, v3.s, v4.s }[0], [x27], x28
-# CHECK-NEXT: 3.     1     2.0    0.0    4.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    1.0    0.0       st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
-# CHECK-NEXT: 5.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT: 3.     1     3.0    0.0    4.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     3.0    0.0    1.0       st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], #32
+# CHECK-NEXT: 5.     1     4.0    0.0    3.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       st4	{ v1.d, v2.d, v3.d, v4.d }[0], [x27], x28
-# CHECK-NEXT: 7.     1     5.0    0.0    2.0       add	x0, x27, #1
-# CHECK-NEXT:        1     2.9    0.3    1.5       <total>
+# CHECK-NEXT: 7.     1     4.0    0.0    2.0       add	x0, x27, #1
+# CHECK-NEXT:        1     2.9    0.1    1.8       <total>
 
 # CHECK:      [83] Code Region - G84
 
@@ -4990,10 +4989,10 @@ add x0, x27, 1
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2200
+# CHECK-NEXT: Total uOps:        2000
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    4.37
+# CHECK-NEXT: uOps Per Cycle:    3.97
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 3.5
 
@@ -5006,7 +5005,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
 # CHECK-NEXT: [0,4]     D==eeER .   stp	d1, d2, [x27, #496]!
 # CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     .D==eeER.   stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: [0,6]     D===eeER.   stp	q1, q2, [x27, #992]!
 # CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eER.   stp	w1, w2, [x27], #248
 # CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
@@ -5024,37 +5023,38 @@ add x0, x27, 1
 # CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       stp	d1, d2, [x27, #496]!
 # CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     3.0    0.0    0.0       stp	q1, q2, [x27, #992]!
+# CHECK-NEXT: 6.     1     4.0    0.0    0.0       stp	q1, q2, [x27, #992]!
 # CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       stp	w1, w2, [x27], #248
 # CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.1    0.1    0.0       <total>
+# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
 
 # CHECK:      [85] Code Region - G86
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total Cycles:      704
+# CHECK-NEXT: Total uOps:        1800
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.97
-# CHECK-NEXT: IPC:               1.98
+# CHECK-NEXT: uOps Per Cycle:    2.56
+# CHECK-NEXT: IPC:               1.42
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
-# CHECK-NEXT: Index     012345678
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
 
-# CHECK:      [0,0]     DeER .  .   stp	x1, x2, [x27], #496
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eER.  .   stp	w1, w2, [x27, #248]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eER  .   stp	x1, x2, [x27, #496]!
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   str	b1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   str	h1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK:      [0,0]     DeER .    .   stp	x1, x2, [x27], #496
+# CHECK-NEXT: [0,1]     D=eER.    .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D=eER.    .   stp	w1, w2, [x27, #248]!
+# CHECK-NEXT: [0,3]     D==eER    .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D==eER    .   stp	x1, x2, [x27, #496]!
+# CHECK-NEXT: [0,5]     D===eER   .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D===eeER  .   str	b1, [x27], #254
+# CHECK-NEXT: [0,7]     D=====eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     .D====eeER.   str	h1, [x27], #254
+# CHECK-NEXT: [0,9]     .D======eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5070,36 +5070,37 @@ add x0, x27, 1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       stp	x1, x2, [x27, #496]!
 # CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       str	b1, [x27], #254
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       str	h1, [x27], #254
-# CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
+# CHECK-NEXT: 7.     1     6.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     5.0    0.0    0.0       str	h1, [x27], #254
+# CHECK-NEXT: 9.     1     7.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     3.7    0.1    0.0       <total>
 
 # CHECK:      [86] Code Region - G87
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total Cycles:      1004
+# CHECK-NEXT: Total uOps:        1500
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.97
-# CHECK-NEXT: IPC:               1.98
+# CHECK-NEXT: uOps Per Cycle:    1.49
+# CHECK-NEXT: IPC:               1.00
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
-# CHECK-NEXT: Index     012345678
+# CHECK-NEXT:                     0123
+# CHECK-NEXT: Index     0123456789
 
-# CHECK:      [0,0]     DeeER.  .   str	s1, [x27], #254
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27], #254
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   str	q1, [x27], #254
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eeER.   str	b1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eeER   str	h1, [x27, #254]!
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK:      [0,0]     DeeER.    .  .   str	s1, [x27], #254
+# CHECK-NEXT: [0,1]     D==eER    .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D==eeER   .  .   str	d1, [x27], #254
+# CHECK-NEXT: [0,3]     D====eER  .  .   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D====eeER .  .   str	q1, [x27], #254
+# CHECK-NEXT: [0,5]     D======eER.  .   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D======eeER  .   str	b1, [x27, #254]!
+# CHECK-NEXT: [0,7]     D========eER .   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D========eeER.   str	h1, [x27, #254]!
+# CHECK-NEXT: [0,9]     D==========eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5109,42 +5110,43 @@ add x0, x27, 1
 
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       str	s1, [x27], #254
-# CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     2.0    0.0    0.0       str	d1, [x27], #254
-# CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    0.0    0.0       str	q1, [x27], #254
-# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       str	b1, [x27, #254]!
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       str	h1, [x27, #254]!
-# CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
+# CHECK-NEXT: 1.     1     3.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 2.     1     3.0    0.0    0.0       str	d1, [x27], #254
+# CHECK-NEXT: 3.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     5.0    0.0    0.0       str	q1, [x27], #254
+# CHECK-NEXT: 5.     1     7.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     7.0    0.0    0.0       str	b1, [x27, #254]!
+# CHECK-NEXT: 7.     1     9.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     9.0    0.0    0.0       str	h1, [x27, #254]!
+# CHECK-NEXT: 9.     1     11.0   0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     6.0    0.1    0.0       <total>
 
 # CHECK:      [87] Code Region - G88
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
-# CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total Cycles:      804
+# CHECK-NEXT: Total uOps:        1600
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.97
-# CHECK-NEXT: IPC:               1.98
+# CHECK-NEXT: uOps Per Cycle:    1.99
+# CHECK-NEXT: IPC:               1.24
 # CHECK-NEXT: Block RThroughput: 2.5
 
 # CHECK:      Timeline view:
-# CHECK-NEXT: Index     012345678
+# CHECK-NEXT:                     01
+# CHECK-NEXT: Index     0123456789
 
-# CHECK:      [0,0]     DeeER.  .   str	s1, [x27, #254]!
-# CHECK-NEXT: [0,1]     D=eER.  .   add	x0, x27, #1
-# CHECK-NEXT: [0,2]     D=eeER  .   str	d1, [x27, #254]!
-# CHECK-NEXT: [0,3]     D==eER  .   add	x0, x27, #1
-# CHECK-NEXT: [0,4]     D==eeER .   str	q1, [x27, #254]!
-# CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
-# CHECK-NEXT: [0,6]     D===eER .   str	w1, [x27], #254
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
-# CHECK-NEXT: [0,8]     .D===eER.   str	x1, [x27], #254
-# CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
+# CHECK:      [0,0]     DeeER.    ..   str	s1, [x27, #254]!
+# CHECK-NEXT: [0,1]     D==eER    ..   add	x0, x27, #1
+# CHECK-NEXT: [0,2]     D==eeER   ..   str	d1, [x27, #254]!
+# CHECK-NEXT: [0,3]     D====eER  ..   add	x0, x27, #1
+# CHECK-NEXT: [0,4]     D====eeER ..   str	q1, [x27, #254]!
+# CHECK-NEXT: [0,5]     D======eER..   add	x0, x27, #1
+# CHECK-NEXT: [0,6]     D======eER..   str	w1, [x27], #254
+# CHECK-NEXT: [0,7]     D=======eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,8]     D=======eER.   str	x1, [x27], #254
+# CHECK-NEXT: [0,9]     .D=======eER   add	x0, x27, #1
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
@@ -5154,26 +5156,26 @@ add x0, x27, 1
 
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     1     1.0    1.0    0.0       str	s1, [x27, #254]!
-# CHECK-NEXT: 1.     1     2.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 2.     1     2.0    0.0    0.0       str	d1, [x27, #254]!
-# CHECK-NEXT: 3.     1     3.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 4.     1     3.0    0.0    0.0       str	q1, [x27, #254]!
-# CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 6.     1     4.0    0.0    0.0       str	w1, [x27], #254
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT: 8.     1     4.0    0.0    0.0       str	x1, [x27], #254
-# CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
+# CHECK-NEXT: 1.     1     3.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 2.     1     3.0    0.0    0.0       str	d1, [x27, #254]!
+# CHECK-NEXT: 3.     1     5.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 4.     1     5.0    0.0    0.0       str	q1, [x27, #254]!
+# CHECK-NEXT: 5.     1     7.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 6.     1     7.0    0.0    0.0       str	w1, [x27], #254
+# CHECK-NEXT: 7.     1     8.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 8.     1     8.0    0.0    0.0       str	x1, [x27], #254
+# CHECK-NEXT: 9.     1     8.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT:        1     5.5    0.1    0.0       <total>
 
 # CHECK:      [88] Code Region - G89
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      1000
 # CHECK-NEXT: Total Cycles:      504
-# CHECK-NEXT: Total uOps:        2000
+# CHECK-NEXT: Total uOps:        1900
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.97
+# CHECK-NEXT: uOps Per Cycle:    3.77
 # CHECK-NEXT: IPC:               1.98
 # CHECK-NEXT: Block RThroughput: 2.5
 
@@ -5187,7 +5189,7 @@ add x0, x27, 1
 # CHECK-NEXT: [0,4]     D==eER  .   strb	w1, [x27], #254
 # CHECK-NEXT: [0,5]     D===eER .   add	x0, x27, #1
 # CHECK-NEXT: [0,6]     D===eER .   strb	w1, [x27, #254]!
-# CHECK-NEXT: [0,7]     .D===eER.   add	x0, x27, #1
+# CHECK-NEXT: [0,7]     D====eER.   add	x0, x27, #1
 # CHECK-NEXT: [0,8]     .D===eER.   strh	w1, [x27], #254
 # CHECK-NEXT: [0,9]     .D====eER   add	x0, x27, #1
 
@@ -5205,10 +5207,10 @@ add x0, x27, 1
 # CHECK-NEXT: 4.     1     3.0    0.0    0.0       strb	w1, [x27], #254
 # CHECK-NEXT: 5.     1     4.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 6.     1     4.0    0.0    0.0       strb	w1, [x27, #254]!
-# CHECK-NEXT: 7.     1     4.0    0.0    0.0       add	x0, x27, #1
+# CHECK-NEXT: 7.     1     5.0    0.0    0.0       add	x0, x27, #1
 # CHECK-NEXT: 8.     1     4.0    0.0    0.0       strh	w1, [x27], #254
 # CHECK-NEXT: 9.     1     5.0    0.0    0.0       add	x0, x27, #1
-# CHECK-NEXT:        1     3.2    0.1    0.0       <total>
+# CHECK-NEXT:        1     3.3    0.1    0.0       <total>
 
 # CHECK:      [89] Code Region - G90
 
diff --git a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s
index 8b1c8a4e4ca55..03cd932e24186 100644
--- a/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s
+++ b/llvm/test/tools/llvm-mca/AArch64/Neoverse/V1-zero-dependency.s
@@ -7,10 +7,10 @@ cmp x0, #4
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      200
 # CHECK-NEXT: Total Cycles:      54
-# CHECK-NEXT: Total uOps:        200
+# CHECK-NEXT: Total uOps:        300
 
 # CHECK:      Dispatch Width:    15
-# CHECK-NEXT: uOps Per Cycle:    3.70
+# CHECK-NEXT: uOps Per Cycle:    5.56
 # CHECK-NEXT: IPC:               3.70
 # CHECK-NEXT: Block RThroughput: 0.5
 
@@ -24,7 +24,7 @@ cmp x0, #4
 
 # CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
 # CHECK-NEXT:  1      1     0.25                        mov	x0, x1
-# CHECK-NEXT:  1      1     0.33                        cmp	x0, #4
+# CHECK-NEXT:  2      1     0.33                        cmp	x0, #4
 
 # CHECK:      Resources:
 # CHECK-NEXT: [0.0] - V1UnitB