diff --git a/llvm/test/CodeGen/AArch64/arm64-uzp.ll b/llvm/test/CodeGen/AArch64/arm64-uzp.ll
index 94f86e7c88aeb..6e01ebc95a1cb 100644
--- a/llvm/test/CodeGen/AArch64/arm64-uzp.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-uzp.ll
@@ -1,107 +1,159 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
 ; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple | FileCheck %s
 
-define <8 x i8> @vuzpi8(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpi8:
-;CHECK: uzp1.8b
-;CHECK: uzp2.8b
-;CHECK-NEXT: add.8b
-	%tmp1 = load <8 x i8>, ptr %A
-	%tmp2 = load <8 x i8>, ptr %B
-	%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-	%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-        %tmp5 = add <8 x i8> %tmp3, %tmp4
-	ret <8 x i8> %tmp5
+define <8 x i8> @vuzpi8(<8 x i8> %A, <8 x i8> %B) nounwind {
+; CHECK-LABEL: vuzpi8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.8b v2, v0, v1
+; CHECK-NEXT:    uzp2.8b v0, v0, v1
+; CHECK-NEXT:    add.8b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %tmp5 = add <8 x i8> %tmp3, %tmp4
+  ret <8 x i8> %tmp5
 }
 
-define <4 x i16> @vuzpi16(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpi16:
-;CHECK: uzp1.4h
-;CHECK: uzp2.4h
-;CHECK-NEXT: add.4h
-	%tmp1 = load <4 x i16>, ptr %A
-	%tmp2 = load <4 x i16>, ptr %B
-	%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-	%tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-        %tmp5 = add <4 x i16> %tmp3, %tmp4
-	ret <4 x i16> %tmp5
+define <4 x i16> @vuzpi16(<4 x i16> %A, <4 x i16> %B) nounwind {
+; CHECK-LABEL: vuzpi16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.4h v2, v0, v1
+; CHECK-NEXT:    uzp2.4h v0, v0, v1
+; CHECK-NEXT:    add.4h v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <4 x i16> %A, <4 x i16> %B, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
+  %tmp4 = shufflevector <4 x i16> %A, <4 x i16> %B, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
+  %tmp5 = add <4 x i16> %tmp3, %tmp4
+  ret <4 x i16> %tmp5
 }
 
-define <16 x i8> @vuzpQi8(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpQi8:
-;CHECK: uzp1.16b
-;CHECK: uzp2.16b
-;CHECK-NEXT: add.16b
-	%tmp1 = load <16 x i8>, ptr %A
-	%tmp2 = load <16 x i8>, ptr %B
-	%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
-	%tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
-        %tmp5 = add <16 x i8> %tmp3, %tmp4
-	ret <16 x i8> %tmp5
+define <16 x i8> @vuzpQi8(<16 x i8> %A, <16 x i8> %B) nounwind {
+; CHECK-LABEL: vuzpQi8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.16b v2, v0, v1
+; CHECK-NEXT:    uzp2.16b v0, v0, v1
+; CHECK-NEXT:    add.16b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <16 x i8> %A, <16 x i8> %B, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
+  %tmp4 = shufflevector <16 x i8> %A, <16 x i8> %B, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
+  %tmp5 = add <16 x i8> %tmp3, %tmp4
+  ret <16 x i8> %tmp5
 }
 
-define <8 x i16> @vuzpQi16(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpQi16:
-;CHECK: uzp1.8h
-;CHECK: uzp2.8h
-;CHECK-NEXT: add.8h
-	%tmp1 = load <8 x i16>, ptr %A
-	%tmp2 = load <8 x i16>, ptr %B
-	%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-	%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-        %tmp5 = add <8 x i16> %tmp3, %tmp4
-	ret <8 x i16> %tmp5
+define <8 x i16> @vuzpQi16(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vuzpQi16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.8h v2, v0, v1
+; CHECK-NEXT:    uzp2.8h v0, v0, v1
+; CHECK-NEXT:    add.8h v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %tmp5 = add <8 x i16> %tmp3, %tmp4
+  ret <8 x i16> %tmp5
 }
 
-define <4 x i32> @vuzpQi32(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpQi32:
-;CHECK: uzp1.4s
-;CHECK: uzp2.4s
-;CHECK-NEXT: add.4s
-	%tmp1 = load <4 x i32>, ptr %A
-	%tmp2 = load <4 x i32>, ptr %B
-	%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-	%tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-        %tmp5 = add <4 x i32> %tmp3, %tmp4
-	ret <4 x i32> %tmp5
+define <4 x i32> @vuzpQi32(<4 x i32> %A, <4 x i32> %B) nounwind {
+; CHECK-LABEL: vuzpQi32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.4s v2, v0, v1
+; CHECK-NEXT:    uzp2.4s v0, v0, v1
+; CHECK-NEXT:    add.4s v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
+  %tmp4 = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
+  %tmp5 = add <4 x i32> %tmp3, %tmp4
+  ret <4 x i32> %tmp5
 }
 
-define <4 x float> @vuzpQf(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpQf:
-;CHECK: uzp1.4s
-;CHECK: uzp2.4s
-;CHECK-NEXT: fadd.4s
-	%tmp1 = load <4 x float>, ptr %A
-	%tmp2 = load <4 x float>, ptr %B
-	%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-	%tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-        %tmp5 = fadd <4 x float> %tmp3, %tmp4
-	ret <4 x float> %tmp5
+define <4 x float> @vuzpQf(<4 x float> %A, <4 x float> %B) nounwind {
+; CHECK-LABEL: vuzpQf:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.4s v2, v0, v1
+; CHECK-NEXT:    uzp2.4s v0, v0, v1
+; CHECK-NEXT:    fadd.4s v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
+  %tmp4 = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
+  %tmp5 = fadd <4 x float> %tmp3, %tmp4
+  ret <4 x float> %tmp5
 }
 
 ; Undef shuffle indices should not prevent matching to VUZP:
 
-define <8 x i8> @vuzpi8_undef(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpi8_undef:
-;CHECK: uzp1.8b
-;CHECK: uzp2.8b
-;CHECK-NEXT: add.8b
-	%tmp1 = load <8 x i8>, ptr %A
-	%tmp2 = load <8 x i8>, ptr %B
-	%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 8, i32 10, i32 12, i32 14>
-	%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 13, i32 15>
-        %tmp5 = add <8 x i8> %tmp3, %tmp4
-	ret <8 x i8> %tmp5
+define <8 x i8> @vuzpi8_undef(<8 x i8> %A, <8 x i8> %B) nounwind {
+; CHECK-LABEL: vuzpi8_undef:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.8b v2, v0, v1
+; CHECK-NEXT:    uzp2.8b v0, v0, v1
+; CHECK-NEXT:    add.8b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i8> %A, <8 x i8> %B, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 13, i32 15>
+  %tmp5 = add <8 x i8> %tmp3, %tmp4
+  ret <8 x i8> %tmp5
 }
 
-define <8 x i16> @vuzpQi16_undef(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vuzpQi16_undef:
-;CHECK: uzp1.8h
-;CHECK: uzp2.8h
-;CHECK-NEXT: add.8h
-	%tmp1 = load <8 x i16>, ptr %A
-	%tmp2 = load <8 x i16>, ptr %B
-	%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 14>
-	%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 undef, i32 undef, i32 11, i32 13, i32 15>
-        %tmp5 = add <8 x i16> %tmp3, %tmp4
-	ret <8 x i16> %tmp5
+define <8 x i16> @vuzpQi16_undef1(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vuzpQi16_undef1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    uzp1.8h v2, v0, v1
+; CHECK-NEXT:    uzp2.8h v0, v0, v1
+; CHECK-NEXT:    add.8h v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 0, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 1, i32 3, i32 5, i32 undef, i32 undef, i32 11, i32 13, i32 15>
+  %tmp5 = add <8 x i16> %tmp3, %tmp4
+  ret <8 x i16> %tmp5
+}
+
+define <8 x i16> @vuzpQi16_undef0(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vuzpQi16_undef0:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI8_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI8_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    uzp2.8h v3, v0, v1
+; CHECK-NEXT:    tbl.16b v0, { v0, v1 }, v2
+; CHECK-NEXT:    add.8h v0, v0, v3
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %tmp5 = add <8 x i16> %tmp3, %tmp4
+  ret <8 x i16> %tmp5
+}
+
+define <8 x i16> @vuzpQi16_undef01(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vuzpQi16_undef01:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI9_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI9_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    uzp2.8h v3, v0, v1
+; CHECK-NEXT:    tbl.16b v0, { v0, v1 }, v2
+; CHECK-NEXT:    add.8h v0, v0, v3
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %tmp5 = add <8 x i16> %tmp3, %tmp4
+  ret <8 x i16> %tmp5
+}
+
+define <8 x i16> @vuzpQi16_undef012(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vuzpQi16_undef012:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI10_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI10_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    uzp2.8h v3, v0, v1
+; CHECK-NEXT:    tbl.16b v0, { v0, v1 }, v2
+; CHECK-NEXT:    add.8h v0, v0, v3
+; CHECK-NEXT:    ret
+  %tmp3 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %tmp4 = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %tmp5 = add <8 x i16> %tmp3, %tmp4
+  ret <8 x i16> %tmp5
 }
diff --git a/llvm/test/CodeGen/AArch64/arm64-zip.ll b/llvm/test/CodeGen/AArch64/arm64-zip.ll
index c707265c06c5c..349751dda461f 100644
--- a/llvm/test/CodeGen/AArch64/arm64-zip.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-zip.ll
@@ -139,6 +139,90 @@ define <16 x i8> @vzipQi8_undef(ptr %A, ptr %B) nounwind {
   ret <16 x i8> %tmp5
 }
 
+define <8 x i16> @vzip1_undef_01(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip1_undef_01:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI8_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI8_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    tbl.16b v0, { v0, v1 }, v2
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip1_undef_0(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip1_undef_0:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI9_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI9_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    tbl.16b v0, { v0, v1 }, v2
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip1_undef_1(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip1_undef_1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip1.8h v0, v0, v1
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip1_undef_012(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip1_undef_012:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI11_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI11_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    tbl.16b v0, { v0, v1 }, v2
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 9, i32 2, i32 10, i32 3, i32 11>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip2_undef_01(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip2_undef_01:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.8h v0, v0, v1
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip2_undef_0(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip2_undef_0:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.8h v0, v0, v1
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip2_undef_1(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip2_undef_1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.8h v0, v0, v1
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 4, i32 undef, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <8 x i16> %s
+}
+
+define <8 x i16> @vzip2_undef_012(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK-LABEL: vzip2_undef_012:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.8h v0, v0, v1
+; CHECK-NEXT:    ret
+  %s = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <8 x i16> %s
+}
+
 define <16 x i8> @combine_v16i8(<8 x i8> %0, <8 x i8> %1) {
 ; CHECK-LABEL: combine_v16i8:
 ; CHECK:       // %bb.0:
@@ -251,9 +335,9 @@ define <16 x i8> @combine_v8i16_8first(<8 x i8> %0, <8 x i8> %1) {
 ; CHECK-LABEL: combine_v8i16_8first:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1_q2
-; CHECK-NEXT:    adrp x8, .LCPI17_0
+; CHECK-NEXT:    adrp x8, .LCPI25_0
 ; CHECK-NEXT:    fmov d2, d0
-; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI17_0]
+; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI25_0]
 ; CHECK-NEXT:    tbl.16b v0, { v1, v2 }, v3
 ; CHECK-NEXT:    ret
   %3 = shufflevector <8 x i8> %1, <8 x i8> %0, <16 x i32> <i32 8, i32 0, i32 9, i32 1, i32 10, i32 2, i32 11, i32 3, i32 12, i32 4, i32 13, i32 5, i32 14, i32 6, i32 15, i32 7>
@@ -266,9 +350,9 @@ define <16 x i8> @combine_v8i16_8firstundef(<8 x i8> %0, <8 x i8> %1) {
 ; CHECK-LABEL: combine_v8i16_8firstundef:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1_q2
-; CHECK-NEXT:    adrp x8, .LCPI18_0
+; CHECK-NEXT:    adrp x8, .LCPI26_0
 ; CHECK-NEXT:    fmov d2, d0
-; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI18_0]
+; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI26_0]
 ; CHECK-NEXT:    tbl.16b v0, { v1, v2 }, v3
 ; CHECK-NEXT:    ret
   %3 = shufflevector <8 x i8> %1, <8 x i8> %0, <16 x i32> <i32 8, i32 0, i32 9, i32 1, i32 10, i32 2, i32 11, i32 3, i32 12, i32 4, i32 13, i32 5, i32 14, i32 6, i32 15, i32 undef>