[AArch64] Regenerate and extend zip1 tests. NFC

This cleans up the existing tests and adds some extra cases that can be lowered
to zip instructions.

diff --git a/llvm/test/CodeGen/AArch64/arm64-zip.ll b/llvm/test/CodeGen/AArch64/arm64-zip.ll
index 14772e7..6d5fe17 100644 (file)
--- a/llvm/test/CodeGen/AArch64/arm64-zip.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-zip.ll
@@ -1,107 +1,280 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple | FileCheck %s
 
-define <8 x i8> @vzipi8(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipi8:
-;CHECK: zip1.8b
-;CHECK: zip2.8b
-;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 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-       %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-        %tmp5 = add <8 x i8> %tmp3, %tmp4
-       ret <8 x i8> %tmp5
-}
-
-define <4 x i16> @vzipi16(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipi16:
-;CHECK: zip1.4h
-;CHECK: zip2.4h
-;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 4, i32 1, i32 5>
-       %tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-        %tmp5 = add <4 x i16> %tmp3, %tmp4
-       ret <4 x i16> %tmp5
-}
-
-define <16 x i8> @vzipQi8(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipQi8:
-;CHECK: zip1.16b
-;CHECK: zip2.16b
-;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 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-       %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
-        %tmp5 = add <16 x i8> %tmp3, %tmp4
-       ret <16 x i8> %tmp5
-}
-
-define <8 x i16> @vzipQi16(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipQi16:
-;CHECK: zip1.8h
-;CHECK: zip2.8h
-;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 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-       %tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-        %tmp5 = add <8 x i16> %tmp3, %tmp4
-       ret <8 x i16> %tmp5
-}
-
-define <4 x i32> @vzipQi32(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipQi32:
-;CHECK: zip1.4s
-;CHECK: zip2.4s
-;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 4, i32 1, i32 5>
-       %tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-        %tmp5 = add <4 x i32> %tmp3, %tmp4
-       ret <4 x i32> %tmp5
-}
-
-define <4 x float> @vzipQf(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipQf:
-;CHECK: zip1.4s
-;CHECK: zip2.4s
-;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 4, i32 1, i32 5>
-       %tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-        %tmp5 = fadd <4 x float> %tmp3, %tmp4
-       ret <4 x float> %tmp5
+define <8 x i8> @vzipi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+; CHECK-LABEL: vzipi8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    ldr d1, [x1]
+; CHECK-NEXT:    zip1.8b v2, v0, v1
+; CHECK-NEXT:    zip2.8b v0, v0, v1
+; CHECK-NEXT:    add.8b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <8 x i8>, <8 x i8>* %A
+  %tmp2 = load <8 x i8>, <8 x i8>* %B
+  %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  %tmp5 = add <8 x i8> %tmp3, %tmp4
+  ret <8 x i8> %tmp5
+}
+
+define <4 x i16> @vzipi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+; CHECK-LABEL: vzipi16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    ldr d1, [x1]
+; CHECK-NEXT:    zip1.4h v2, v0, v1
+; CHECK-NEXT:    zip2.4h v0, v0, v1
+; CHECK-NEXT:    add.4h v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <4 x i16>, <4 x i16>* %A
+  %tmp2 = load <4 x i16>, <4 x i16>* %B
+  %tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
+  %tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
+  %tmp5 = add <4 x i16> %tmp3, %tmp4
+  ret <4 x i16> %tmp5
+}
+
+define <16 x i8> @vzipQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+; CHECK-LABEL: vzipQi8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr q0, [x0]
+; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    zip1.16b v2, v0, v1
+; CHECK-NEXT:    zip2.16b v0, v0, v1
+; CHECK-NEXT:    add.16b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <16 x i8>, <16 x i8>* %A
+  %tmp2 = load <16 x i8>, <16 x i8>* %B
+  %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+  %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
+  %tmp5 = add <16 x i8> %tmp3, %tmp4
+  ret <16 x i8> %tmp5
+}
+
+define <8 x i16> @vzipQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+; CHECK-LABEL: vzipQi16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr q0, [x0]
+; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    zip1.8h v2, v0, v1
+; CHECK-NEXT:    zip2.8h v0, v0, v1
+; CHECK-NEXT:    add.8h v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <8 x i16>, <8 x i16>* %A
+  %tmp2 = load <8 x i16>, <8 x i16>* %B
+  %tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  %tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  %tmp5 = add <8 x i16> %tmp3, %tmp4
+  ret <8 x i16> %tmp5
+}
+
+define <4 x i32> @vzipQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+; CHECK-LABEL: vzipQi32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr q0, [x0]
+; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    zip1.4s v2, v0, v1
+; CHECK-NEXT:    zip2.4s v0, v0, v1
+; CHECK-NEXT:    add.4s v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <4 x i32>, <4 x i32>* %A
+  %tmp2 = load <4 x i32>, <4 x i32>* %B
+  %tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
+  %tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
+  %tmp5 = add <4 x i32> %tmp3, %tmp4
+  ret <4 x i32> %tmp5
+}
+
+define <4 x float> @vzipQf(<4 x float>* %A, <4 x float>* %B) nounwind {
+; CHECK-LABEL: vzipQf:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr q0, [x0]
+; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    zip1.4s v2, v0, v1
+; CHECK-NEXT:    zip2.4s v0, v0, v1
+; CHECK-NEXT:    fadd.4s v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <4 x float>, <4 x float>* %A
+  %tmp2 = load <4 x float>, <4 x float>* %B
+  %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
+  %tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
+  %tmp5 = fadd <4 x float> %tmp3, %tmp4
+  ret <4 x float> %tmp5
 }
 
 ; Undef shuffle indices should not prevent matching to VZIP:
 
-define <8 x i8> @vzipi8_undef(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipi8_undef:
-;CHECK: zip1.8b
-;CHECK: zip2.8b
-;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 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11>
-       %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15>
-        %tmp5 = add <8 x i8> %tmp3, %tmp4
-       ret <8 x i8> %tmp5
-}
-
-define <16 x i8> @vzipQi8_undef(ptr %A, ptr %B) nounwind {
-;CHECK-LABEL: vzipQi8_undef:
-;CHECK: zip1.16b
-;CHECK: zip2.16b
-;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 16, i32 1, i32 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-       %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31>
-        %tmp5 = add <16 x i8> %tmp3, %tmp4
-       ret <16 x i8> %tmp5
+define <8 x i8> @vzipi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+; CHECK-LABEL: vzipi8_undef:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    ldr d1, [x1]
+; CHECK-NEXT:    zip1.8b v2, v0, v1
+; CHECK-NEXT:    zip2.8b v0, v0, v1
+; CHECK-NEXT:    add.8b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <8 x i8>, <8 x i8>* %A
+  %tmp2 = load <8 x i8>, <8 x i8>* %B
+  %tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 undef, i32 10, i32 3, i32 11>
+  %tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 undef, i32 undef, i32 15>
+  %tmp5 = add <8 x i8> %tmp3, %tmp4
+  ret <8 x i8> %tmp5
+}
+
+define <16 x i8> @vzipQi8_undef(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+; CHECK-LABEL: vzipQi8_undef:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr q0, [x0]
+; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    zip1.16b v2, v0, v1
+; CHECK-NEXT:    zip2.16b v0, v0, v1
+; CHECK-NEXT:    add.16b v0, v2, v0
+; CHECK-NEXT:    ret
+  %tmp1 = load <16 x i8>, <16 x i8>* %A
+  %tmp2 = load <16 x i8>, <16 x i8>* %B
+  %tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 undef, i32 undef, i32 undef, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+  %tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 undef, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 undef, i32 14, i32 30, i32 undef, i32 31>
+  %tmp5 = add <16 x i8> %tmp3, %tmp4
+  ret <16 x i8> %tmp5
+}
+
+define <16 x i8> @combine_v16i8(<8 x i8> %0, <8 x i8> %1) {
+; CHECK-LABEL: combine_v16i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.8b v2, v0, v1
+; CHECK-NEXT:    zip1.8b v0, v0, v1
+; CHECK-NEXT:    mov.d v0[1], v2[0]
+; CHECK-NEXT:    ret
+  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <16 x i8> %3
+}
+
+define <16 x i8> @combine2_v16i8(<8 x i8> %0, <8 x i8> %1) {
+; CHECK-LABEL: combine2_v16i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip1.8b v2, v0, v1
+; CHECK-NEXT:    zip2.8b v0, v0, v1
+; CHECK-NEXT:    mov.d v2[1], v0[0]
+; CHECK-NEXT:    mov.16b v0, v2
+; CHECK-NEXT:    ret
+  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  %4 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  %5 = shufflevector <8 x i8> %3, <8 x i8> %4, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  ret <16 x i8> %5
+}
+
+define <8 x i16> @combine_v8i16(<4 x i16> %0, <4 x i16> %1) {
+; CHECK-LABEL: combine_v8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.4h v2, v0, v1
+; CHECK-NEXT:    zip1.4h v0, v0, v1
+; CHECK-NEXT:    mov.d v0[1], v2[0]
+; CHECK-NEXT:    ret
+  %3 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
+  ret <8 x i16> %3
+}
+
+define <8 x i16> @combine2_v8i16(<4 x i16> %0, <4 x i16> %1) {
+; CHECK-LABEL: combine2_v8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip1.4h v2, v0, v1
+; CHECK-NEXT:    zip2.4h v0, v0, v1
+; CHECK-NEXT:    mov.d v2[1], v0[0]
+; CHECK-NEXT:    mov.16b v0, v2
+; CHECK-NEXT:    ret
+  %3 = shufflevector <4 x i16> %0, <4 x i16> %1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
+  %4 = shufflevector <4 x i16> %0, <4 x i16> %1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
+  %5 = shufflevector <4 x i16> %3, <4 x i16> %4, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x i16> %5
+}
+
+define <4 x i32> @combine_v4i32(<2 x i32> %0, <2 x i32> %1) {
+; CHECK-LABEL: combine_v4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.2s v2, v0, v1
+; CHECK-NEXT:    zip1.2s v0, v0, v1
+; CHECK-NEXT:    mov.d v0[1], v2[0]
+; CHECK-NEXT:    ret
+  %3 = shufflevector <2 x i32> %0, <2 x i32> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
+  ret <4 x i32> %3
+}
+
+define <4 x i32> @combine2_v4i32(<2 x i32> %0, <2 x i32> %1) {
+; CHECK-LABEL: combine2_v4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip1.2s v2, v0, v1
+; CHECK-NEXT:    zip2.2s v0, v0, v1
+; CHECK-NEXT:    mov.d v2[1], v0[0]
+; CHECK-NEXT:    mov.16b v0, v2
+; CHECK-NEXT:    ret
+  %3 = shufflevector <2 x i32> %0, <2 x i32> %1, <2 x i32> <i32 0, i32 2>
+  %4 = shufflevector <2 x i32> %0, <2 x i32> %1, <2 x i32> <i32 1, i32 3>
+  %5 = shufflevector <2 x i32> %3, <2 x i32> %4, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  ret <4 x i32> %5
+}
+
+define <16 x i8> @combine_v16i8_undef(<8 x i8> %0, <8 x i8> %1) {
+; CHECK-LABEL: combine_v16i8_undef:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.8b v2, v0, v1
+; CHECK-NEXT:    zip1.8b v0, v0, v1
+; CHECK-NEXT:    mov.d v0[1], v2[0]
+; CHECK-NEXT:    ret
+  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <16 x i8> %3
+}
+
+define <16 x i8> @combine2_v16i8_undef(<8 x i8> %0, <8 x i8> %1) {
+; CHECK-LABEL: combine2_v16i8_undef:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip1.8b v2, v0, v1
+; CHECK-NEXT:    zip2.8b v0, v0, v1
+; CHECK-NEXT:    mov.d v2[1], v0[0]
+; CHECK-NEXT:    mov.16b v0, v2
+; CHECK-NEXT:    ret
+  %3 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+  %4 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  %5 = shufflevector <8 x i8> %3, <8 x i8> %4, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  ret <16 x i8> %5
+}
+
+define <8 x i16> @combine_v8i16_undef(<4 x i16> %0, <4 x i16> %1) {
+; CHECK-LABEL: combine_v8i16_undef:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    zip2.4h v2, v0, v1
+; CHECK-NEXT:    zip1.4h v0, v0, v1
+; CHECK-NEXT:    mov.d v0[1], v2[0]
+; CHECK-NEXT:    ret
+  %3 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 undef, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
+  ret <8 x i16> %3
+}
+
+; FIXME: This could be zip1 too, 8,0,9,1... pattern is handled
+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:    adrp x8, .LCPI17_0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1_q2
+; CHECK-NEXT:    fmov d2, d0
+; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI17_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>
+  ret <16 x i8> %3
+}
+
+
+; FIXME: This could be zip1 too, 8,0,9,1... pattern is handled
+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:    adrp x8, .LCPI18_0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1_q2
+; CHECK-NEXT:    fmov d2, d0
+; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI18_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>
+  ret <16 x i8> %3
 }