diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index d379a28ea5523..a1c8fade7648e 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -14815,9 +14815,10 @@ SDValue AArch64TargetLowering::LowerVECTOR_SHUFFLE(SDValue Op,
     unsigned Opc = (WhichResult == 0) ? AArch64ISD::UZP1 : AArch64ISD::UZP2;
     return DAG.getNode(Opc, DL, V1.getValueType(), V1, V2);
   }
-  if (isTRNMask(ShuffleMask, NumElts, WhichResult)) {
+  if (isTRNMask(ShuffleMask, NumElts, WhichResult, OperandOrder)) {
     unsigned Opc = (WhichResult == 0) ? AArch64ISD::TRN1 : AArch64ISD::TRN2;
-    return DAG.getNode(Opc, DL, V1.getValueType(), V1, V2);
+    return DAG.getNode(Opc, DL, V1.getValueType(), OperandOrder == 0 ? V1 : V2,
+                       OperandOrder == 0 ? V2 : V1);
   }
 
   if (isZIP_v_undef_Mask(ShuffleMask, VT, WhichResult)) {
@@ -16529,7 +16530,7 @@ bool AArch64TargetLowering::isShuffleMaskLegal(ArrayRef<int> M, EVT VT) const {
           isREVMask(M, EltSize, NumElts, 16) ||
           isEXTMask(M, VT, DummyBool, DummyUnsigned) ||
           isSingletonEXTMask(M, VT, DummyUnsigned) ||
-          isTRNMask(M, NumElts, DummyUnsigned) ||
+          isTRNMask(M, NumElts, DummyUnsigned, DummyUnsigned) ||
           isUZPMask(M, NumElts, DummyUnsigned) ||
           isZIPMask(M, NumElts, DummyUnsigned, DummyUnsigned) ||
           isTRN_v_undef_Mask(M, VT, DummyUnsigned) ||
@@ -31588,10 +31589,13 @@ SDValue AArch64TargetLowering::LowerFixedLengthVECTOR_SHUFFLEToSVE(
                     OperandOrder == 0 ? Op1 : Op2,
                     OperandOrder == 0 ? Op2 : Op1));
 
-  if (isTRNMask(ShuffleMask, VT.getVectorNumElements(), WhichResult)) {
+  if (isTRNMask(ShuffleMask, VT.getVectorNumElements(), WhichResult,
+                OperandOrder)) {
     unsigned Opc = (WhichResult == 0) ? AArch64ISD::TRN1 : AArch64ISD::TRN2;
-    return convertFromScalableVector(
-        DAG, VT, DAG.getNode(Opc, DL, ContainerVT, Op1, Op2));
+    SDValue TRN =
+        DAG.getNode(Opc, DL, ContainerVT, OperandOrder == 0 ? Op1 : Op2,
+                    OperandOrder == 0 ? Op2 : Op1);
+    return convertFromScalableVector(DAG, VT, TRN);
   }
 
   if (isZIP_v_undef_Mask(ShuffleMask, VT, WhichResult) && WhichResult == 0)
diff --git a/llvm/lib/Target/AArch64/AArch64PerfectShuffle.h b/llvm/lib/Target/AArch64/AArch64PerfectShuffle.h
index ef8786d0ad0e1..c7d6b31291197 100644
--- a/llvm/lib/Target/AArch64/AArch64PerfectShuffle.h
+++ b/llvm/lib/Target/AArch64/AArch64PerfectShuffle.h
@@ -6699,33 +6699,53 @@ inline bool isUZPMask(ArrayRef<int> M, unsigned NumElts,
 }
 
 /// Return true for trn1 or trn2 masks of the form:
-///  <0, 8, 2, 10, 4, 12, 6, 14> or
-///  <1, 9, 3, 11, 5, 13, 7, 15>
+///  <0, 8, 2, 10, 4, 12, 6, 14> (WhichResultOut = 0, OperandOrderOut = 0) or
+///  <1, 9, 3, 11, 5, 13, 7, 15> (WhichResultOut = 1, OperandOrderOut = 0) or
+///  <8, 0, 10, 2, 12, 4, 14, 6> (WhichResultOut = 0, OperandOrderOut = 1) or
+///  <9, 1, 11, 3, 13, 5, 15, 7> (WhichResultOut = 1, OperandOrderOut = 1) or
 inline bool isTRNMask(ArrayRef<int> M, unsigned NumElts,
-                      unsigned &WhichResultOut) {
+                      unsigned &WhichResultOut, unsigned &OperandOrderOut) {
   if (NumElts % 2 != 0)
     return false;
-  // Check the first non-undef element for trn1 vs trn2.
-  unsigned WhichResult = 2;
+
+  // "Result" corresponds to "WhichResultOut", selecting between trn1 and trn2.
+  // "Order" corresponds to "OperandOrderOut", selecting the order of operands
+  // for the instruction (flipped or not).
+  bool Result0Order0 = true; // WhichResultOut = 0, OperandOrderOut = 0
+  bool Result1Order0 = true; // WhichResultOut = 1, OperandOrderOut = 0
+  bool Result0Order1 = true; // WhichResultOut = 0, OperandOrderOut = 1
+  bool Result1Order1 = true; // WhichResultOut = 1, OperandOrderOut = 1
+  // Check all elements match.
   for (unsigned i = 0; i != NumElts; i += 2) {
     if (M[i] >= 0) {
-      WhichResult = ((unsigned)M[i] == i ? 0 : 1);
-      break;
+      unsigned EvenElt = (unsigned)M[i];
+      if (EvenElt != i)
+        Result0Order0 = false;
+      if (EvenElt != i + 1)
+        Result1Order0 = false;
+      if (EvenElt != NumElts + i)
+        Result0Order1 = false;
+      if (EvenElt != NumElts + i + 1)
+        Result1Order1 = false;
     }
     if (M[i + 1] >= 0) {
-      WhichResult = ((unsigned)M[i + 1] == i + NumElts ? 0 : 1);
-      break;
+      unsigned OddElt = (unsigned)M[i + 1];
+      if (OddElt != NumElts + i)
+        Result0Order0 = false;
+      if (OddElt != NumElts + i + 1)
+        Result1Order0 = false;
+      if (OddElt != i)
+        Result0Order1 = false;
+      if (OddElt != i + 1)
+        Result1Order1 = false;
     }
   }
-  if (WhichResult == 2)
+
+  if (Result0Order0 + Result1Order0 + Result0Order1 + Result1Order1 != 1)
     return false;
 
-  for (unsigned i = 0; i < NumElts; i += 2) {
-    if ((M[i] >= 0 && (unsigned)M[i] != i + WhichResult) ||
-        (M[i + 1] >= 0 && (unsigned)M[i + 1] != i + NumElts + WhichResult))
-      return false;
-  }
-  WhichResultOut = WhichResult;
+  WhichResultOut = (Result0Order0 || Result0Order1) ? 0 : 1;
+  OperandOrderOut = (Result0Order0 || Result1Order0) ? 0 : 1;
   return true;
 }
 
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp b/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp
index 4fba593b3d0fb..221a7bcd881bb 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp
@@ -215,14 +215,15 @@ bool matchTRN(MachineInstr &MI, MachineRegisterInfo &MRI,
               ShuffleVectorPseudo &MatchInfo) {
   assert(MI.getOpcode() == TargetOpcode::G_SHUFFLE_VECTOR);
   unsigned WhichResult;
+  unsigned OperandOrder;
   ArrayRef<int> ShuffleMask = MI.getOperand(3).getShuffleMask();
   Register Dst = MI.getOperand(0).getReg();
   unsigned NumElts = MRI.getType(Dst).getNumElements();
-  if (!isTRNMask(ShuffleMask, NumElts, WhichResult))
+  if (!isTRNMask(ShuffleMask, NumElts, WhichResult, OperandOrder))
     return false;
   unsigned Opc = (WhichResult == 0) ? AArch64::G_TRN1 : AArch64::G_TRN2;
-  Register V1 = MI.getOperand(1).getReg();
-  Register V2 = MI.getOperand(2).getReg();
+  Register V1 = MI.getOperand(OperandOrder == 0 ? 1 : 2).getReg();
+  Register V2 = MI.getOperand(OperandOrder == 0 ? 2 : 1).getReg();
   MatchInfo = ShuffleVectorPseudo(Opc, Dst, {V1, V2});
   return true;
 }
diff --git a/llvm/test/CodeGen/AArch64/arm64-trn.ll b/llvm/test/CodeGen/AArch64/arm64-trn.ll
index fe245d01a7a6d..120c2d13a7ab7 100644
--- a/llvm/test/CodeGen/AArch64/arm64-trn.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-trn.ll
@@ -246,6 +246,63 @@ define <4 x float> @vtrnQf(ptr %A, ptr %B) nounwind {
 	ret <4 x float> %tmp5
 }
 
+define <8 x i8> @vtrni8_trn1_flipped(<8 x i8> %A, <8 x i8> %B) nounwind {
+; CHECKLE-LABEL: vtrni8_trn1_flipped:
+; CHECKLE:       // %bb.0:
+; CHECKLE-NEXT:    trn1 v0.8b, v1.8b, v0.8b
+; CHECKLE-NEXT:    ret
+;
+; CHECKBE-LABEL: vtrni8_trn1_flipped:
+; CHECKBE:       // %bb.0:
+; CHECKBE-NEXT:    rev64 v0.8b, v0.8b
+; CHECKBE-NEXT:    rev64 v1.8b, v1.8b
+; CHECKBE-NEXT:    trn1 v0.8b, v1.8b, v0.8b
+; CHECKBE-NEXT:    rev64 v0.8b, v0.8b
+; CHECKBE-NEXT:    ret
+  %tmp1 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 8, i32 0, i32 10, i32 2, i32 12, i32 4, i32 14, i32 6>
+  ret <8 x i8> %tmp1
+}
+
+define <8 x i8> @vtrni8_trn2_flipped(<8 x i8> %A, <8 x i8> %B) nounwind {
+; CHECKLE-LABEL: vtrni8_trn2_flipped:
+; CHECKLE:       // %bb.0:
+; CHECKLE-NEXT:    trn2 v0.8b, v1.8b, v0.8b
+; CHECKLE-NEXT:    ret
+;
+; CHECKBE-LABEL: vtrni8_trn2_flipped:
+; CHECKBE:       // %bb.0:
+; CHECKBE-NEXT:    rev64 v0.8b, v0.8b
+; CHECKBE-NEXT:    rev64 v1.8b, v1.8b
+; CHECKBE-NEXT:    trn2 v0.8b, v1.8b, v0.8b
+; CHECKBE-NEXT:    rev64 v0.8b, v0.8b
+; CHECKBE-NEXT:    ret
+  %tmp1 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 9, i32 1, i32 11, i32 3, i32 13, i32 5, i32 15, i32 7>
+  ret <8 x i8> %tmp1
+}
+
+define <8 x i8> @vtrni8_both_flipped_with_poison_values(<8 x i8> %A, <8 x i8> %B) nounwind {
+; CHECKLE-LABEL: vtrni8_both_flipped_with_poison_values:
+; CHECKLE:       // %bb.0:
+; CHECKLE-NEXT:    trn1 v2.8b, v1.8b, v0.8b
+; CHECKLE-NEXT:    trn2 v0.8b, v1.8b, v0.8b
+; CHECKLE-NEXT:    add v0.8b, v2.8b, v0.8b
+; CHECKLE-NEXT:    ret
+;
+; CHECKBE-LABEL: vtrni8_both_flipped_with_poison_values:
+; CHECKBE:       // %bb.0:
+; CHECKBE-NEXT:    rev64 v0.8b, v0.8b
+; CHECKBE-NEXT:    rev64 v1.8b, v1.8b
+; CHECKBE-NEXT:    trn1 v2.8b, v1.8b, v0.8b
+; CHECKBE-NEXT:    trn2 v0.8b, v1.8b, v0.8b
+; CHECKBE-NEXT:    add v0.8b, v2.8b, v0.8b
+; CHECKBE-NEXT:    rev64 v0.8b, v0.8b
+; CHECKBE-NEXT:    ret
+  %tmp1 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 poison, i32 0, i32 poison, i32 2, i32 poison, i32 4, i32 14, i32 6>
+  %tmp2 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 poison, i32 1, i32 poison, i32 3, i32 13, i32 5, i32 15, i32 poison>
+  %tmp3 = add <8 x i8> %tmp1, %tmp2
+  ret <8 x i8> %tmp3
+}
+
 ; Undef shuffle indices (even at the start of the shuffle mask) should not prevent matching to VTRN:
 
 define <8 x i8> @vtrni8_undef(ptr %A, ptr %B) nounwind {
diff --git a/llvm/test/CodeGen/AArch64/fixed-vector-deinterleave.ll b/llvm/test/CodeGen/AArch64/fixed-vector-deinterleave.ll
index 282e0503dd7be..8e75d69be5062 100644
--- a/llvm/test/CodeGen/AArch64/fixed-vector-deinterleave.ll
+++ b/llvm/test/CodeGen/AArch64/fixed-vector-deinterleave.ll
@@ -6,12 +6,10 @@ define {<2 x half>, <2 x half>} @vector_deinterleave_v2f16_v4f16(<4 x half> %vec
 ; CHECK-SD-LABEL: vector_deinterleave_v2f16_v4f16:
 ; CHECK-SD:       // %bb.0:
 ; CHECK-SD-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-SD-NEXT:    dup v2.2s, v0.s[1]
-; CHECK-SD-NEXT:    mov v1.16b, v2.16b
-; CHECK-SD-NEXT:    zip1 v2.4h, v0.4h, v2.4h
-; CHECK-SD-NEXT:    mov v1.h[0], v0.h[1]
+; CHECK-SD-NEXT:    dup v1.2s, v0.s[1]
+; CHECK-SD-NEXT:    zip1 v2.4h, v0.4h, v1.4h
+; CHECK-SD-NEXT:    trn2 v1.4h, v0.4h, v1.4h
 ; CHECK-SD-NEXT:    fmov d0, d2
-; CHECK-SD-NEXT:    // kill: def $d1 killed $d1 killed $q1
 ; CHECK-SD-NEXT:    ret
 ;
 ; CHECK-GI-LABEL: vector_deinterleave_v2f16_v4f16:
diff --git a/llvm/test/CodeGen/AArch64/reduce-shuffle.ll b/llvm/test/CodeGen/AArch64/reduce-shuffle.ll
index 072f6f4e8f73e..39beffcf85783 100644
--- a/llvm/test/CodeGen/AArch64/reduce-shuffle.ll
+++ b/llvm/test/CodeGen/AArch64/reduce-shuffle.ll
@@ -36,93 +36,93 @@ define i32 @v1(ptr nocapture noundef readonly %p1, i32 noundef %i1, ptr nocaptur
 ; CHECK-NEXT:    zip1 v5.4s, v3.4s, v0.4s
 ; CHECK-NEXT:    trn1 v6.4s, v3.4s, v0.4s
 ; CHECK-NEXT:    zip2 v0.4s, v3.4s, v0.4s
-; CHECK-NEXT:    ext v16.16b, v1.16b, v1.16b, #12
-; CHECK-NEXT:    zip2 v17.4s, v1.4s, v2.4s
-; CHECK-NEXT:    zip2 v7.4s, v2.4s, v1.4s
-; CHECK-NEXT:    zip1 v18.4s, v2.4s, v1.4s
+; CHECK-NEXT:    ext v7.16b, v1.16b, v1.16b, #12
+; CHECK-NEXT:    zip2 v16.4s, v1.4s, v2.4s
+; CHECK-NEXT:    zip1 v17.4s, v2.4s, v1.4s
+; CHECK-NEXT:    trn2 v18.4s, v2.4s, v1.4s
 ; CHECK-NEXT:    uzp2 v4.4s, v4.4s, v1.4s
 ; CHECK-NEXT:    ext v3.16b, v3.16b, v5.16b, #8
-; CHECK-NEXT:    mov v1.s[0], v2.s[1]
-; CHECK-NEXT:    ext v2.16b, v2.16b, v16.16b, #12
-; CHECK-NEXT:    mov v17.d[1], v6.d[1]
-; CHECK-NEXT:    mov v7.d[1], v6.d[1]
+; CHECK-NEXT:    zip2 v1.4s, v2.4s, v1.4s
+; CHECK-NEXT:    ext v2.16b, v2.16b, v7.16b, #12
+; CHECK-NEXT:    mov v16.d[1], v6.d[1]
+; CHECK-NEXT:    mov v18.d[1], v5.d[1]
 ; CHECK-NEXT:    mov v4.d[1], v0.d[1]
-; CHECK-NEXT:    mov v18.d[1], v3.d[1]
-; CHECK-NEXT:    mov v1.d[1], v5.d[1]
+; CHECK-NEXT:    mov v17.d[1], v3.d[1]
+; CHECK-NEXT:    mov v1.d[1], v6.d[1]
 ; CHECK-NEXT:    mov v2.d[1], v0.d[1]
-; CHECK-NEXT:    add v0.4s, v4.4s, v17.4s
-; CHECK-NEXT:    add v3.4s, v1.4s, v18.4s
-; CHECK-NEXT:    sub v1.4s, v18.4s, v1.4s
-; CHECK-NEXT:    sub v2.4s, v7.4s, v2.4s
+; CHECK-NEXT:    add v0.4s, v4.4s, v16.4s
+; CHECK-NEXT:    add v3.4s, v18.4s, v17.4s
+; CHECK-NEXT:    sub v6.4s, v17.4s, v18.4s
+; CHECK-NEXT:    sub v1.4s, v1.4s, v2.4s
 ; CHECK-NEXT:    rev64 v4.4s, v0.4s
 ; CHECK-NEXT:    rev64 v5.4s, v3.4s
-; CHECK-NEXT:    sub v6.4s, v1.4s, v2.4s
-; CHECK-NEXT:    add v1.4s, v2.4s, v1.4s
+; CHECK-NEXT:    sub v2.4s, v6.4s, v1.4s
+; CHECK-NEXT:    add v1.4s, v1.4s, v6.4s
 ; CHECK-NEXT:    mov v4.d[1], v0.d[1]
 ; CHECK-NEXT:    mov v5.d[1], v3.d[1]
-; CHECK-NEXT:    rev64 v2.4s, v6.4s
+; CHECK-NEXT:    rev64 v6.4s, v2.4s
 ; CHECK-NEXT:    rev64 v7.4s, v1.4s
 ; CHECK-NEXT:    sub v3.4s, v3.4s, v4.4s
 ; CHECK-NEXT:    add v0.4s, v0.4s, v5.4s
-; CHECK-NEXT:    sub v2.4s, v6.4s, v2.4s
+; CHECK-NEXT:    sub v4.4s, v2.4s, v6.4s
 ; CHECK-NEXT:    sub v5.4s, v1.4s, v7.4s
-; CHECK-NEXT:    addp v4.4s, v3.4s, v6.4s
+; CHECK-NEXT:    addp v2.4s, v3.4s, v2.4s
 ; CHECK-NEXT:    addp v1.4s, v0.4s, v1.4s
 ; CHECK-NEXT:    rev64 v6.4s, v0.4s
 ; CHECK-NEXT:    rev64 v7.4s, v3.4s
-; CHECK-NEXT:    ext v16.16b, v4.16b, v2.16b, #4
+; CHECK-NEXT:    ext v16.16b, v2.16b, v4.16b, #4
 ; CHECK-NEXT:    ext v17.16b, v1.16b, v5.16b, #4
 ; CHECK-NEXT:    sub v0.4s, v0.4s, v6.4s
 ; CHECK-NEXT:    sub v3.4s, v3.4s, v7.4s
-; CHECK-NEXT:    mov v7.16b, v2.16b
-; CHECK-NEXT:    zip2 v6.4s, v16.4s, v4.4s
+; CHECK-NEXT:    mov v7.16b, v4.16b
+; CHECK-NEXT:    zip2 v6.4s, v16.4s, v2.4s
 ; CHECK-NEXT:    mov v16.16b, v5.16b
 ; CHECK-NEXT:    zip2 v17.4s, v17.4s, v1.4s
 ; CHECK-NEXT:    ext v18.16b, v0.16b, v1.16b, #4
-; CHECK-NEXT:    mov v7.s[2], v4.s[3]
+; CHECK-NEXT:    mov v7.s[2], v2.s[3]
 ; CHECK-NEXT:    mov v21.16b, v3.16b
 ; CHECK-NEXT:    mov v16.s[2], v1.s[3]
 ; CHECK-NEXT:    ext v5.16b, v5.16b, v17.16b, #12
 ; CHECK-NEXT:    zip1 v17.4s, v1.4s, v1.4s
-; CHECK-NEXT:    ext v2.16b, v2.16b, v6.16b, #12
+; CHECK-NEXT:    ext v4.16b, v4.16b, v6.16b, #12
 ; CHECK-NEXT:    ext v18.16b, v18.16b, v18.16b, #4
 ; CHECK-NEXT:    mov v19.16b, v7.16b
-; CHECK-NEXT:    ext v6.16b, v3.16b, v4.16b, #8
-; CHECK-NEXT:    mov v21.s[2], v4.s[1]
+; CHECK-NEXT:    ext v6.16b, v3.16b, v2.16b, #8
+; CHECK-NEXT:    mov v21.s[2], v2.s[1]
 ; CHECK-NEXT:    mov v20.16b, v16.16b
-; CHECK-NEXT:    mov v19.s[1], v4.s[2]
+; CHECK-NEXT:    mov v19.s[1], v2.s[2]
 ; CHECK-NEXT:    trn2 v0.4s, v17.4s, v0.4s
 ; CHECK-NEXT:    sub v16.4s, v16.4s, v5.4s
 ; CHECK-NEXT:    mov v17.16b, v18.16b
 ; CHECK-NEXT:    ext v3.16b, v6.16b, v3.16b, #4
-; CHECK-NEXT:    sub v7.4s, v7.4s, v2.4s
+; CHECK-NEXT:    sub v7.4s, v7.4s, v4.4s
 ; CHECK-NEXT:    mov v20.s[1], v1.s[2]
 ; CHECK-NEXT:    mov v17.s[0], v1.s[1]
 ; CHECK-NEXT:    mov v1.16b, v21.16b
-; CHECK-NEXT:    add v2.4s, v19.4s, v2.4s
-; CHECK-NEXT:    uzp2 v3.4s, v6.4s, v3.4s
+; CHECK-NEXT:    add v4.4s, v19.4s, v4.4s
 ; CHECK-NEXT:    add v5.4s, v20.4s, v5.4s
-; CHECK-NEXT:    mov v1.s[1], v4.s[0]
-; CHECK-NEXT:    sub v4.4s, v0.4s, v18.4s
-; CHECK-NEXT:    mov v2.d[1], v7.d[1]
+; CHECK-NEXT:    mov v1.s[1], v2.s[0]
+; CHECK-NEXT:    uzp2 v2.4s, v6.4s, v3.4s
+; CHECK-NEXT:    sub v3.4s, v0.4s, v18.4s
 ; CHECK-NEXT:    add v0.4s, v0.4s, v17.4s
+; CHECK-NEXT:    mov v4.d[1], v7.d[1]
 ; CHECK-NEXT:    mov v5.d[1], v16.d[1]
-; CHECK-NEXT:    sub v6.4s, v21.4s, v3.4s
-; CHECK-NEXT:    add v1.4s, v1.4s, v3.4s
-; CHECK-NEXT:    mov v0.d[1], v4.d[1]
-; CHECK-NEXT:    cmlt v4.8h, v2.8h, #0
-; CHECK-NEXT:    cmlt v3.8h, v5.8h, #0
+; CHECK-NEXT:    sub v6.4s, v21.4s, v2.4s
+; CHECK-NEXT:    add v1.4s, v1.4s, v2.4s
+; CHECK-NEXT:    mov v0.d[1], v3.d[1]
+; CHECK-NEXT:    cmlt v3.8h, v4.8h, #0
+; CHECK-NEXT:    cmlt v2.8h, v5.8h, #0
 ; CHECK-NEXT:    mov v1.d[1], v6.d[1]
-; CHECK-NEXT:    add v2.4s, v4.4s, v2.4s
 ; CHECK-NEXT:    cmlt v6.8h, v0.8h, #0
-; CHECK-NEXT:    add v5.4s, v3.4s, v5.4s
-; CHECK-NEXT:    eor v2.16b, v2.16b, v4.16b
+; CHECK-NEXT:    add v4.4s, v3.4s, v4.4s
+; CHECK-NEXT:    add v5.4s, v2.4s, v5.4s
 ; CHECK-NEXT:    cmlt v7.8h, v1.8h, #0
 ; CHECK-NEXT:    add v0.4s, v6.4s, v0.4s
-; CHECK-NEXT:    eor v3.16b, v5.16b, v3.16b
+; CHECK-NEXT:    eor v3.16b, v4.16b, v3.16b
+; CHECK-NEXT:    eor v2.16b, v5.16b, v2.16b
 ; CHECK-NEXT:    add v1.4s, v7.4s, v1.4s
 ; CHECK-NEXT:    eor v0.16b, v0.16b, v6.16b
-; CHECK-NEXT:    add v2.4s, v3.4s, v2.4s
+; CHECK-NEXT:    add v2.4s, v2.4s, v3.4s
 ; CHECK-NEXT:    eor v1.16b, v1.16b, v7.16b
 ; CHECK-NEXT:    add v0.4s, v0.4s, v2.4s
 ; CHECK-NEXT:    add v0.4s, v0.4s, v1.4s
@@ -255,77 +255,76 @@ define i32 @v2(ptr nocapture noundef readonly %p1, i32 noundef %i1, ptr nocaptur
 ; CHECK-NEXT:    saddw v3.4s, v6.4s, v3.4h
 ; CHECK-NEXT:    saddw v2.4s, v7.4s, v2.4h
 ; CHECK-NEXT:    zip1 v4.4s, v1.4s, v0.4s
-; CHECK-NEXT:    trn1 v18.4s, v1.4s, v0.4s
+; CHECK-NEXT:    trn1 v6.4s, v1.4s, v0.4s
 ; CHECK-NEXT:    zip2 v0.4s, v1.4s, v0.4s
 ; CHECK-NEXT:    uzp2 v5.4s, v3.4s, v2.4s
-; CHECK-NEXT:    mov v7.16b, v3.16b
-; CHECK-NEXT:    zip1 v6.4s, v2.4s, v3.4s
-; CHECK-NEXT:    zip2 v16.4s, v3.4s, v2.4s
+; CHECK-NEXT:    zip1 v7.4s, v2.4s, v3.4s
+; CHECK-NEXT:    trn2 v16.4s, v2.4s, v3.4s
+; CHECK-NEXT:    ext v18.16b, v3.16b, v3.16b, #12
 ; CHECK-NEXT:    ext v17.16b, v1.16b, v4.16b, #8
-; CHECK-NEXT:    mov v7.s[0], v2.s[1]
-; CHECK-NEXT:    ext v1.16b, v3.16b, v3.16b, #12
+; CHECK-NEXT:    zip2 v1.4s, v3.4s, v2.4s
 ; CHECK-NEXT:    uzp2 v5.4s, v5.4s, v3.4s
+; CHECK-NEXT:    mov v16.d[1], v4.d[1]
 ; CHECK-NEXT:    zip2 v3.4s, v2.4s, v3.4s
-; CHECK-NEXT:    mov v16.d[1], v18.d[1]
-; CHECK-NEXT:    mov v6.d[1], v17.d[1]
-; CHECK-NEXT:    mov v7.d[1], v4.d[1]
-; CHECK-NEXT:    ext v1.16b, v2.16b, v1.16b, #12
+; CHECK-NEXT:    ext v2.16b, v2.16b, v18.16b, #12
+; CHECK-NEXT:    mov v7.d[1], v17.d[1]
+; CHECK-NEXT:    mov v1.d[1], v6.d[1]
 ; CHECK-NEXT:    mov v5.d[1], v0.d[1]
-; CHECK-NEXT:    mov v3.d[1], v18.d[1]
-; CHECK-NEXT:    add v2.4s, v7.4s, v6.4s
-; CHECK-NEXT:    mov v1.d[1], v0.d[1]
-; CHECK-NEXT:    add v4.4s, v5.4s, v16.4s
-; CHECK-NEXT:    rev64 v5.4s, v2.4s
-; CHECK-NEXT:    rev64 v0.4s, v4.4s
-; CHECK-NEXT:    sub v1.4s, v3.4s, v1.4s
-; CHECK-NEXT:    sub v3.4s, v6.4s, v7.4s
-; CHECK-NEXT:    mov v5.d[1], v2.d[1]
-; CHECK-NEXT:    add v6.4s, v1.4s, v3.4s
-; CHECK-NEXT:    sub v1.4s, v3.4s, v1.4s
-; CHECK-NEXT:    mov v0.d[1], v4.d[1]
-; CHECK-NEXT:    add v4.4s, v4.4s, v5.4s
-; CHECK-NEXT:    sub v0.4s, v2.4s, v0.4s
-; CHECK-NEXT:    zip1 v2.4s, v4.4s, v6.4s
-; CHECK-NEXT:    uzp2 v3.4s, v4.4s, v6.4s
-; CHECK-NEXT:    zip2 v16.4s, v4.4s, v6.4s
-; CHECK-NEXT:    zip1 v5.4s, v0.4s, v1.4s
-; CHECK-NEXT:    trn1 v7.4s, v0.4s, v1.4s
-; CHECK-NEXT:    zip2 v1.4s, v0.4s, v1.4s
-; CHECK-NEXT:    trn2 v2.4s, v4.4s, v2.4s
-; CHECK-NEXT:    uzp2 v3.4s, v3.4s, v4.4s
-; CHECK-NEXT:    mov v4.s[1], v6.s[1]
-; CHECK-NEXT:    ext v0.16b, v0.16b, v5.16b, #8
-; CHECK-NEXT:    mov v16.d[1], v7.d[1]
-; CHECK-NEXT:    mov v3.d[1], v1.d[1]
-; CHECK-NEXT:    mov v4.d[1], v5.d[1]
+; CHECK-NEXT:    mov v3.d[1], v6.d[1]
 ; CHECK-NEXT:    mov v2.d[1], v0.d[1]
-; CHECK-NEXT:    add v0.4s, v16.4s, v3.4s
-; CHECK-NEXT:    sub v3.4s, v3.4s, v16.4s
-; CHECK-NEXT:    add v1.4s, v4.4s, v2.4s
-; CHECK-NEXT:    sub v2.4s, v2.4s, v4.4s
+; CHECK-NEXT:    add v4.4s, v16.4s, v7.4s
+; CHECK-NEXT:    sub v6.4s, v7.4s, v16.4s
+; CHECK-NEXT:    add v1.4s, v5.4s, v1.4s
+; CHECK-NEXT:    sub v2.4s, v3.4s, v2.4s
+; CHECK-NEXT:    rev64 v5.4s, v4.4s
+; CHECK-NEXT:    rev64 v0.4s, v1.4s
+; CHECK-NEXT:    add v3.4s, v2.4s, v6.4s
+; CHECK-NEXT:    sub v2.4s, v6.4s, v2.4s
+; CHECK-NEXT:    mov v5.d[1], v4.d[1]
+; CHECK-NEXT:    mov v0.d[1], v1.d[1]
+; CHECK-NEXT:    add v1.4s, v1.4s, v5.4s
+; CHECK-NEXT:    sub v0.4s, v4.4s, v0.4s
+; CHECK-NEXT:    zip1 v4.4s, v1.4s, v3.4s
+; CHECK-NEXT:    uzp2 v5.4s, v1.4s, v3.4s
+; CHECK-NEXT:    zip2 v7.4s, v1.4s, v3.4s
+; CHECK-NEXT:    zip1 v6.4s, v0.4s, v2.4s
+; CHECK-NEXT:    trn1 v16.4s, v0.4s, v2.4s
+; CHECK-NEXT:    zip2 v2.4s, v0.4s, v2.4s
+; CHECK-NEXT:    trn2 v4.4s, v1.4s, v4.4s
+; CHECK-NEXT:    uzp2 v5.4s, v5.4s, v1.4s
+; CHECK-NEXT:    mov v1.s[1], v3.s[1]
+; CHECK-NEXT:    ext v0.16b, v0.16b, v6.16b, #8
+; CHECK-NEXT:    mov v7.d[1], v16.d[1]
+; CHECK-NEXT:    mov v5.d[1], v2.d[1]
+; CHECK-NEXT:    mov v1.d[1], v6.d[1]
+; CHECK-NEXT:    mov v4.d[1], v0.d[1]
+; CHECK-NEXT:    add v0.4s, v7.4s, v5.4s
+; CHECK-NEXT:    sub v3.4s, v5.4s, v7.4s
+; CHECK-NEXT:    add v2.4s, v1.4s, v4.4s
+; CHECK-NEXT:    sub v1.4s, v4.4s, v1.4s
 ; CHECK-NEXT:    ext v4.16b, v0.16b, v0.16b, #4
 ; CHECK-NEXT:    zip2 v6.4s, v0.4s, v3.4s
 ; CHECK-NEXT:    zip2 v7.4s, v3.4s, v0.4s
-; CHECK-NEXT:    ext v5.16b, v1.16b, v1.16b, #4
-; CHECK-NEXT:    zip2 v16.4s, v2.4s, v1.4s
-; CHECK-NEXT:    zip2 v17.4s, v1.4s, v2.4s
+; CHECK-NEXT:    ext v5.16b, v2.16b, v2.16b, #4
+; CHECK-NEXT:    zip2 v16.4s, v1.4s, v2.4s
+; CHECK-NEXT:    zip2 v17.4s, v2.4s, v1.4s
 ; CHECK-NEXT:    zip1 v0.4s, v0.4s, v3.4s
-; CHECK-NEXT:    zip1 v1.4s, v1.4s, v2.4s
 ; CHECK-NEXT:    ext v18.16b, v4.16b, v3.16b, #8
-; CHECK-NEXT:    ext v19.16b, v5.16b, v2.16b, #8
+; CHECK-NEXT:    ext v19.16b, v5.16b, v1.16b, #8
+; CHECK-NEXT:    zip1 v1.4s, v2.4s, v1.4s
 ; CHECK-NEXT:    add v2.4s, v16.4s, v7.4s
 ; CHECK-NEXT:    sub v3.4s, v6.4s, v17.4s
-; CHECK-NEXT:    sub v0.4s, v0.4s, v1.4s
 ; CHECK-NEXT:    ext v4.16b, v18.16b, v4.16b, #4
-; CHECK-NEXT:    cmlt v1.8h, v3.8h, #0
 ; CHECK-NEXT:    cmlt v6.8h, v2.8h, #0
 ; CHECK-NEXT:    ext v5.16b, v19.16b, v5.16b, #4
+; CHECK-NEXT:    sub v0.4s, v0.4s, v1.4s
+; CHECK-NEXT:    cmlt v1.8h, v3.8h, #0
 ; CHECK-NEXT:    add v2.4s, v6.4s, v2.4s
 ; CHECK-NEXT:    add v3.4s, v1.4s, v3.4s
 ; CHECK-NEXT:    add v4.4s, v5.4s, v4.4s
 ; CHECK-NEXT:    cmlt v5.8h, v0.8h, #0
-; CHECK-NEXT:    eor v1.16b, v3.16b, v1.16b
 ; CHECK-NEXT:    eor v2.16b, v2.16b, v6.16b
+; CHECK-NEXT:    eor v1.16b, v3.16b, v1.16b
 ; CHECK-NEXT:    cmlt v7.8h, v4.8h, #0
 ; CHECK-NEXT:    add v0.4s, v5.4s, v0.4s
 ; CHECK-NEXT:    add v1.4s, v2.4s, v1.4s
@@ -480,7 +479,7 @@ define i32 @v3(ptr nocapture noundef readonly %p1, i32 noundef %i1, ptr nocaptur
 ; CHECK-NEXT:    sub v3.4s, v3.4s, v7.4s
 ; CHECK-NEXT:    uzp2 v4.4s, v1.4s, v0.4s
 ; CHECK-NEXT:    uzp1 v7.4s, v1.4s, v0.4s
-; CHECK-NEXT:    mov v6.s[3], v5.s[2]
+; CHECK-NEXT:    trn1 v6.4s, v6.4s, v5.4s
 ; CHECK-NEXT:    ext v0.16b, v0.16b, v0.16b, #8
 ; CHECK-NEXT:    zip2 v17.4s, v2.4s, v3.4s
 ; CHECK-NEXT:    zip1 v2.4s, v2.4s, v3.4s