[X86][SSE] Regenerate odd shuffle tests with common prefixes

llvm-svn: 280661

llvm/test/CodeGen/X86/oddshuffles.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=x86_64-pc-linux -mattr=+sse2 < %s | FileCheck %s --check-prefix=SSE2
-; RUN: llc -mtriple=x86_64-pc-linux -mattr=+sse4.2 < %s | FileCheck %s --check-prefix=SSE42
-; RUN: llc -mtriple=x86_64-pc-linux -mattr=+avx < %s | FileCheck %s --check-prefix=AVX
-; RUN: llc -mtriple=x86_64-pc-linux -mattr=+avx2 < %s | FileCheck %s --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-pc-linux -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
+; RUN: llc < %s -mtriple=x86_64-pc-linux -mattr=+sse4.2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE42
+; RUN: llc < %s -mtriple=x86_64-pc-linux -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-pc-linux -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
 
 define void @v3i64(<2 x i64> %a, <2 x i64> %b, <3 x i64>* %p) {
 ; SSE2-LABEL: v3i64:
@@ -20,12 +20,12 @@ define void @v3i64(<2 x i64> %a, <2 x i64> %b, <3 x i64>* %p) {
 ; SSE42-NEXT:    movdqa %xmm0, (%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v3i64:
-; AVX:       # BB#0:
-; AVX-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm0[0],xmm1[0]
-; AVX-NEXT:    vpextrq $1, %xmm0, 16(%rdi)
-; AVX-NEXT:    vmovapd %xmm1, (%rdi)
-; AVX-NEXT:    retq
+; AVX1-LABEL: v3i64:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpextrq $1, %xmm0, 16(%rdi)
+; AVX1-NEXT:    vmovapd %xmm1, (%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v3i64:
 ; AVX2:       # BB#0:
@@ -41,26 +41,19 @@ define void @v3i64(<2 x i64> %a, <2 x i64> %b, <3 x i64>* %p) {
   ret void
 }
 define void @v3f64(<2 x double> %a, <2 x double> %b, <3 x double>* %p) {
-; SSE2-LABEL: v3f64:
-; SSE2:       # BB#0:
-; SSE2-NEXT:    movhpd %xmm0, 16(%rdi)
-; SSE2-NEXT:    unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; SSE2-NEXT:    movapd %xmm0, (%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE42-LABEL: v3f64:
-; SSE42:       # BB#0:
-; SSE42-NEXT:    movhpd %xmm0, 16(%rdi)
-; SSE42-NEXT:    unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; SSE42-NEXT:    movapd %xmm0, (%rdi)
-; SSE42-NEXT:    retq
-;
-; AVX-LABEL: v3f64:
-; AVX:       # BB#0:
-; AVX-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm0[0],xmm1[0]
-; AVX-NEXT:    vmovhpd %xmm0, 16(%rdi)
-; AVX-NEXT:    vmovapd %xmm1, (%rdi)
-; AVX-NEXT:    retq
+; SSE-LABEL: v3f64:
+; SSE:       # BB#0:
+; SSE-NEXT:    movhpd %xmm0, 16(%rdi)
+; SSE-NEXT:    unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSE-NEXT:    movapd %xmm0, (%rdi)
+; SSE-NEXT:    retq
+;
+; AVX1-LABEL: v3f64:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vmovhpd %xmm0, 16(%rdi)
+; AVX1-NEXT:    vmovapd %xmm1, (%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v3f64:
 ; AVX2:       # BB#0:
@@ -94,13 +87,13 @@ define void @v3i32(<2 x i32> %a, <2 x i32> %b, <3 x i32>* %p) {
 ; SSE42-NEXT:    movq %xmm1, (%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v3i32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,0,1,1]
-; AVX-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
-; AVX-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
-; AVX-NEXT:    vmovq %xmm1, (%rdi)
-; AVX-NEXT:    retq
+; AVX1-LABEL: v3i32:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,0,1,1]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
+; AVX1-NEXT:    vmovq %xmm1, (%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v3i32:
 ; AVX2:       # BB#0:
@@ -148,17 +141,6 @@ define void @v5i16(<4 x i16> %a, <4 x i16> %b, <5 x i16>* %p) {
 ; AVX-NEXT:    vpextrw $6, %xmm0, 8(%rdi)
 ; AVX-NEXT:    vmovq %xmm1, (%rdi)
 ; AVX-NEXT:    retq
-;
-; AVX2-LABEL: v5i16:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,1,2,3]
-; AVX2-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
-; AVX2-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,2,2,3,4,5,6,7]
-; AVX2-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,3,2,3]
-; AVX2-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
-; AVX2-NEXT:    vpextrw $6, %xmm0, 8(%rdi)
-; AVX2-NEXT:    vmovq %xmm1, (%rdi)
-; AVX2-NEXT:    retq
   %r = shufflevector <4 x i16> %a, <4 x i16> %b, <5 x i32> <i32 0, i32 5, i32 1, i32 6, i32 3>
   store <5 x i16> %r, <5 x i16>* %p
   ret void
@@ -183,13 +165,13 @@ define void @v5i32(<4 x i32> %a, <4 x i32> %b, <5 x i32>* %p) {
 ; SSE42-NEXT:    movdqa %xmm2, (%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v5i32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vshufps {{.*#+}} xmm1 = xmm0[0,1],xmm1[1,2]
-; AVX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,1,3]
-; AVX-NEXT:    vpextrd $3, %xmm0, 16(%rdi)
-; AVX-NEXT:    vmovaps %xmm1, (%rdi)
-; AVX-NEXT:    retq
+; AVX1-LABEL: v5i32:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm0[0,1],xmm1[1,2]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,1,3]
+; AVX1-NEXT:    vpextrd $3, %xmm0, 16(%rdi)
+; AVX1-NEXT:    vmovaps %xmm1, (%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v5i32:
 ; AVX2:       # BB#0:
@@ -225,13 +207,13 @@ define void @v5f32(<4 x float> %a, <4 x float> %b, <5 x float>* %p) {
 ; SSE42-NEXT:    movaps %xmm0, (%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v5f32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vshufps {{.*#+}} xmm1 = xmm0[0,1],xmm1[1,2]
-; AVX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,1,3]
-; AVX-NEXT:    vextractps $3, %xmm0, 16(%rdi)
-; AVX-NEXT:    vmovaps %xmm1, (%rdi)
-; AVX-NEXT:    retq
+; AVX1-LABEL: v5f32:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm0[0,1],xmm1[1,2]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,1,3]
+; AVX1-NEXT:    vextractps $3, %xmm0, 16(%rdi)
+; AVX1-NEXT:    vmovaps %xmm1, (%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v5f32:
 ; AVX2:       # BB#0:
@@ -298,18 +280,6 @@ define void @v7i8(<4 x i8> %a, <4 x i8> %b, <7 x i8>* %p) {
 ; AVX-NEXT:    vpextrw $4, %xmm0, 4(%rdi)
 ; AVX-NEXT:    vmovd %xmm2, (%rdi)
 ; AVX-NEXT:    retq
-;
-; AVX2-LABEL: v7i8:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0],zero,xmm0[12],zero,xmm0[4],zero,zero,xmm0[u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpshufb {{.*#+}} xmm2 = zero,xmm1[8],zero,xmm1[8],zero,xmm1[12,0,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpor %xmm0, %xmm2, %xmm0
-; AVX2-NEXT:    vpmovzxdq {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero
-; AVX2-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
-; AVX2-NEXT:    vpextrb $0, %xmm1, 6(%rdi)
-; AVX2-NEXT:    vpextrw $4, %xmm0, 4(%rdi)
-; AVX2-NEXT:    vmovd %xmm2, (%rdi)
-; AVX2-NEXT:    retq
   %r = shufflevector <4 x i8> %a, <4 x i8> %b, <7 x i32> <i32 0, i32 6, i32 3, i32 6, i32 1, i32 7, i32 4>
   store <7 x i8> %r, <7 x i8>* %p
   ret void
@@ -352,16 +322,6 @@ define void @v7i16(<4 x i16> %a, <4 x i16> %b, <7 x i16>* %p) {
 ; AVX-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
 ; AVX-NEXT:    vmovq %xmm0, (%rdi)
 ; AVX-NEXT:    retq
-;
-; AVX2-LABEL: v7i16:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,3,1,3]
-; AVX2-NEXT:    vpshufb {{.*#+}} xmm2 = xmm1[8,9,8,9,4,5,8,9,0,1,12,13,0,1,14,15]
-; AVX2-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3],xmm0[4],xmm2[5,6,7]
-; AVX2-NEXT:    vpextrw $0, %xmm1, 12(%rdi)
-; AVX2-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
-; AVX2-NEXT:    vmovq %xmm0, (%rdi)
-; AVX2-NEXT:    retq
   %r = shufflevector <4 x i16> %a, <4 x i16> %b, <7 x i32> <i32 0, i32 6, i32 3, i32 6, i32 1, i32 7, i32 4>
   store <7 x i16> %r, <7 x i16>* %p
   ret void
@@ -393,16 +353,16 @@ define void @v7i32(<4 x i32> %a, <4 x i32> %b, <7 x i32>* %p) {
 ; SSE42-NEXT:    movdqa %xmm0, (%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v7i32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vblendps {{.*#+}} xmm2 = xmm0[0,1],xmm1[2],xmm0[3]
-; AVX-NEXT:    vpermilps {{.*#+}} xmm2 = xmm2[0,2,3,2]
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
-; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,3,0,3]
-; AVX-NEXT:    vmovd %xmm1, 24(%rdi)
-; AVX-NEXT:    vmovlps %xmm0, 16(%rdi)
-; AVX-NEXT:    vmovaps %xmm2, (%rdi)
-; AVX-NEXT:    retq
+; AVX1-LABEL: v7i32:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vblendps {{.*#+}} xmm2 = xmm0[0,1],xmm1[2],xmm0[3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm2[0,2,3,2]
+; AVX1-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,3,0,3]
+; AVX1-NEXT:    vmovd %xmm1, 24(%rdi)
+; AVX1-NEXT:    vmovlps %xmm0, 16(%rdi)
+; AVX1-NEXT:    vmovaps %xmm2, (%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v7i32:
 ; AVX2:       # BB#0:
@@ -461,15 +421,6 @@ define void @v12i8(<8 x i8> %a, <8 x i8> %b, <12 x i8>* %p) {
 ; AVX-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
 ; AVX-NEXT:    vmovq %xmm0, (%rdi)
 ; AVX-NEXT:    retq
-;
-; AVX2-LABEL: v12i8:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = zero,zero,xmm1[0],zero,zero,xmm1[2],zero,zero,xmm1[4],zero,zero,xmm1[6,u,u,u,u]
-; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,8],zero,xmm0[2,10],zero,xmm0[4,12],zero,xmm0[6,14],zero,xmm0[u,u,u,u]
-; AVX2-NEXT:    vpor %xmm1, %xmm0, %xmm0
-; AVX2-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
-; AVX2-NEXT:    vmovq %xmm0, (%rdi)
-; AVX2-NEXT:    retq
   %r = shufflevector <8 x i8> %a, <8 x i8> %b, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
   store <12 x i8> %r, <12 x i8>* %p
   ret void
@@ -511,18 +462,18 @@ define void @v12i16(<8 x i16> %a, <8 x i16> %b, <12 x i16>* %p) {
 ; SSE42-NEXT:    movq %xmm3, 16(%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v12i16:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[1,1,2,3]
-; AVX-NEXT:    vpshufd {{.*#+}} xmm3 = xmm0[3,1,2,3]
-; AVX-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[0,3,1,3,4,5,6,7]
-; AVX-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2],xmm2[3],xmm3[4,5,6,7]
-; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,3]
-; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,2,3,10,11,10,11,4,5,12,13]
-; AVX-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3,4],xmm1[5],xmm0[6,7]
-; AVX-NEXT:    vmovdqa %xmm0, (%rdi)
-; AVX-NEXT:    vmovq %xmm2, 16(%rdi)
-; AVX-NEXT:    retq
+; AVX1-LABEL: v12i16:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[1,1,2,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm0[3,1,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[0,3,1,3,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2],xmm2[3],xmm3[4,5,6,7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,3]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,2,3,10,11,10,11,4,5,12,13]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3,4],xmm1[5],xmm0[6,7]
+; AVX1-NEXT:    vmovdqa %xmm0, (%rdi)
+; AVX1-NEXT:    vmovq %xmm2, 16(%rdi)
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v12i16:
 ; AVX2:       # BB#0:
@@ -594,23 +545,23 @@ define void @v12i32(<8 x i32> %a, <8 x i32> %b, <12 x i32>* %p) {
 ; SSE42-NEXT:    movdqa %xmm0, (%rdi)
 ; SSE42-NEXT:    retq
 ;
-; AVX-LABEL: v12i32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
-; AVX-NEXT:    vmovsldup {{.*#+}} ymm2 = ymm2[0,0,2,2,4,4,6,6]
-; AVX-NEXT:    vpermilps {{.*#+}} ymm3 = ymm0[0,u,u,1,5,u,u,6]
-; AVX-NEXT:    vblendps {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2,3,4,5],ymm2[6],ymm3[7]
-; AVX-NEXT:    vmovddup {{.*#+}} xmm3 = xmm1[0,0]
-; AVX-NEXT:    vinsertf128 $1, %xmm3, %ymm3, %ymm3
-; AVX-NEXT:    vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,3],xmm3[3,3]
-; AVX-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,1]
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2],xmm1[3]
-; AVX-NEXT:    vmovaps %xmm0, 32(%rdi)
-; AVX-NEXT:    vmovaps %ymm2, (%rdi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: v12i32:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vmovsldup {{.*#+}} ymm2 = ymm2[0,0,2,2,4,4,6,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm3 = ymm0[0,u,u,1,5,u,u,6]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2,3,4,5],ymm2[6],ymm3[7]
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm3 = xmm1[0,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm3, %ymm3
+; AVX1-NEXT:    vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,3],xmm3[3,3]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,1]
+; AVX1-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2],xmm1[3]
+; AVX1-NEXT:    vmovaps %xmm0, 32(%rdi)
+; AVX1-NEXT:    vmovaps %ymm2, (%rdi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v12i32:
 ; AVX2:       # BB#0:
@@ -687,19 +638,6 @@ define void @pr29025(<4 x i8> %a, <4 x i8> %b, <4 x i8> %c, <12 x i8> *%p) {
 ; AVX-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
 ; AVX-NEXT:    vmovq %xmm0, (%rdi)
 ; AVX-NEXT:    retq
-;
-; AVX2-LABEL: pr29025:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
-; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX2-NEXT:    vpshufb %xmm3, %xmm2, %xmm1
-; AVX2-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,8,1,2,10,3,4,12,5,6,14,7,u,u,u,u]
-; AVX2-NEXT:    vpextrd $2, %xmm0, 8(%rdi)
-; AVX2-NEXT:    vmovq %xmm0, (%rdi)
-; AVX2-NEXT:    retq
   %s1 = shufflevector <4 x i8> %a, <4 x i8> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   %s2 = shufflevector <4 x i8> %c, <4 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
   %r = shufflevector <8 x i8> %s1, <8 x i8> %s2, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>