CodeGen peephole: fold redundant phys reg copies

[oota-llvm.git] / test / CodeGen / X86 / vector-idiv.ll

diff --git a/test/CodeGen/X86/vector-idiv.ll b/test/CodeGen/X86/vector-idiv.ll
index 06ce543e9cc477db552650ff9d07e3f2ba48c227..1117e206e5b0b084f27840295be4ddf98f5927ca 100644 (file)
--- a/test/CodeGen/X86/vector-idiv.ll
+++ b/test/CodeGen/X86/vector-idiv.ll
@@ -1,10 +1,11 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -march=x86-64 -mcpu=core2 -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=SSE41
 ; RUN: llc -march=x86-64 -mcpu=core2 < %s | FileCheck %s --check-prefix=SSE
 ; RUN: llc -march=x86-64 -mcpu=core-avx2 < %s | FileCheck %s --check-prefix=AVX
 
 target triple = "x86_64-unknown-unknown"
 
-define <4 x i32> @test1(<4 x i32> %a) {
+define <4 x i32> @test1(<4 x i32> %a) #0 {
 ; SSE41-LABEL: test1:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [613566757,613566757,613566757,613566757]
@@ -55,7 +56,7 @@ define <4 x i32> @test1(<4 x i32> %a) {
   ret <4 x i32> %div
 }
 
-define <8 x i32> @test2(<8 x i32> %a) {
+define <8 x i32> @test2(<8 x i32> %a) #0 {
 ; SSE41-LABEL: test2:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [613566757,613566757,613566757,613566757]
@@ -126,7 +127,7 @@ define <8 x i32> @test2(<8 x i32> %a) {
   ret <8 x i32> %div
 }
 
-define <8 x i16> @test3(<8 x i16> %a) {
+define <8 x i16> @test3(<8 x i16> %a) #0 {
 ; SSE41-LABEL: test3:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [9363,9363,9363,9363,9363,9363,9363,9363]
@@ -159,7 +160,7 @@ define <8 x i16> @test3(<8 x i16> %a) {
   ret <8 x i16> %div
 }
 
-define <16 x i16> @test4(<16 x i16> %a) {
+define <16 x i16> @test4(<16 x i16> %a) #0 {
 ; SSE41-LABEL: test4:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [9363,9363,9363,9363,9363,9363,9363,9363]
@@ -204,7 +205,7 @@ define <16 x i16> @test4(<16 x i16> %a) {
   ret <16 x i16> %div
 }
 
-define <8 x i16> @test5(<8 x i16> %a) {
+define <8 x i16> @test5(<8 x i16> %a) #0 {
 ; SSE41-LABEL: test5:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmulhw {{.*}}(%rip), %xmm0
@@ -234,7 +235,7 @@ define <8 x i16> @test5(<8 x i16> %a) {
   ret <8 x i16> %div
 }
 
-define <16 x i16> @test6(<16 x i16> %a) {
+define <16 x i16> @test6(<16 x i16> %a) #0 {
 ; SSE41-LABEL: test6:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [18725,18725,18725,18725,18725,18725,18725,18725]
@@ -276,7 +277,7 @@ define <16 x i16> @test6(<16 x i16> %a) {
   ret <16 x i16> %div
 }
 
-define <16 x i8> @test7(<16 x i8> %a) {
+define <16 x i8> @test7(<16 x i8> %a) #0 {
 ; SSE41-LABEL: test7:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pextrb $1, %xmm0, %eax
@@ -460,6 +461,9 @@ define <16 x i8> @test7(<16 x i8> %a) {
 ;
 ; SSE-LABEL: test7:
 ; SSE:       # BB#0:
+; SSE-NEXT:    pushq %rbp
+; SSE-NEXT:    pushq %r14
+; SSE-NEXT:    pushq %rbx
 ; SSE-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
 ; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
 ; SSE-NEXT:    imull $-109, %eax, %ecx
@@ -471,156 +475,156 @@ define <16 x i8> @test7(<16 x i8> %a) {
 ; SSE-NEXT:    addb %al, %cl
 ; SSE-NEXT:    movzbl %cl, %eax
 ; SSE-NEXT:    movd %eax, %xmm0
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %r14d
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %edx
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %r9d
 ; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
-; SSE-NEXT:    movd %eax, %xmm1
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %r11d
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %ecx
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %r8d
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %esi
+; SSE-NEXT:    imull $-109, %esi, %edi
+; SSE-NEXT:    shrl $8, %edi
+; SSE-NEXT:    addb %sil, %dil
+; SSE-NEXT:    movb %dil, %bl
+; SSE-NEXT:    shrb $7, %bl
+; SSE-NEXT:    sarb $2, %dil
+; SSE-NEXT:    addb %bl, %dil
+; SSE-NEXT:    movzbl %dil, %esi
+; SSE-NEXT:    movd %esi, %xmm1
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
+; SSE-NEXT:    imull $-109, %eax, %esi
+; SSE-NEXT:    shrl $8, %esi
+; SSE-NEXT:    addb %al, %sil
+; SSE-NEXT:    movb %sil, %al
 ; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    sarb $2, %sil
+; SSE-NEXT:    addb %al, %sil
+; SSE-NEXT:    movzbl %sil, %eax
 ; SSE-NEXT:    movd %eax, %xmm2
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %ebp
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %esi
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %r10d
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %edi
+; SSE-NEXT:    imull $-109, %edi, %ebx
+; SSE-NEXT:    shrl $8, %ebx
+; SSE-NEXT:    addb %dil, %bl
+; SSE-NEXT:    movb %bl, %al
 ; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    sarb $2, %bl
+; SSE-NEXT:    addb %al, %bl
+; SSE-NEXT:    movzbl %bl, %eax
 ; SSE-NEXT:    movd %eax, %xmm0
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
 ; SSE-NEXT:    punpcklbw {{.*#+}} 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]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %edx, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %dl, %al
+; SSE-NEXT:    movb %al, %dl
+; SSE-NEXT:    shrb $7, %dl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %dl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm1
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %esi, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %sil, %al
+; SSE-NEXT:    movb %al, %dl
+; SSE-NEXT:    shrb $7, %dl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %dl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm2
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %ecx, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movb %al, %cl
+; SSE-NEXT:    shrb $7, %cl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm3
+; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %ecx
 ; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
+; SSE-NEXT:    imull $-109, %eax, %edx
+; SSE-NEXT:    shrl $8, %edx
+; SSE-NEXT:    addb %al, %dl
+; SSE-NEXT:    movb %dl, %al
 ; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    sarb $2, %dl
+; SSE-NEXT:    addb %al, %dl
+; SSE-NEXT:    movzbl %dl, %eax
 ; SSE-NEXT:    movd %eax, %xmm1
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %r14d, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %r14b, %al
+; SSE-NEXT:    movb %al, %dl
+; SSE-NEXT:    shrb $7, %dl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %dl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm2
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %ebp, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %bpl, %al
+; SSE-NEXT:    movb %al, %dl
+; SSE-NEXT:    shrb $7, %dl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %dl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm0
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %r11d, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %r11b, %al
+; SSE-NEXT:    movb %al, %dl
+; SSE-NEXT:    shrb $7, %dl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %dl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm3
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %ecx, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movb %al, %cl
+; SSE-NEXT:    shrb $7, %cl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm2
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %r9d, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %r9b, %al
+; SSE-NEXT:    movb %al, %cl
+; SSE-NEXT:    shrb $7, %cl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm0
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %r10d, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %r10b, %al
+; SSE-NEXT:    movb %al, %cl
+; SSE-NEXT:    shrb $7, %cl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm3
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
-; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
-; SSE-NEXT:    imull $-109, %eax, %ecx
-; SSE-NEXT:    shrl $8, %ecx
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movb %cl, %al
-; SSE-NEXT:    shrb $7, %al
-; SSE-NEXT:    sarb $2, %cl
-; SSE-NEXT:    addb %al, %cl
-; SSE-NEXT:    movzbl %cl, %eax
+; SSE-NEXT:    imull $-109, %r8d, %eax
+; SSE-NEXT:    shrl $8, %eax
+; SSE-NEXT:    addb %r8b, %al
+; SSE-NEXT:    movb %al, %cl
+; SSE-NEXT:    shrb $7, %cl
+; SSE-NEXT:    sarb $2, %al
+; SSE-NEXT:    addb %cl, %al
+; SSE-NEXT:    movzbl %al, %eax
 ; SSE-NEXT:    movd %eax, %xmm4
 ; SSE-NEXT:    movsbl -{{[0-9]+}}(%rsp), %eax
 ; SSE-NEXT:    imull $-109, %eax, %ecx
@@ -636,6 +640,9 @@ define <16 x i8> @test7(<16 x i8> %a) {
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
 ; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
 ; SSE-NEXT:    punpcklbw {{.*#+}} 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]
+; SSE-NEXT:    popq %rbx
+; SSE-NEXT:    popq %r14
+; SSE-NEXT:    popq %rbp
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: test7:
@@ -821,7 +828,7 @@ define <16 x i8> @test7(<16 x i8> %a) {
   ret <16 x i8> %div
 }
 
-define <4 x i32> @test8(<4 x i32> %a) {
+define <4 x i32> @test8(<4 x i32> %a) #0 {
 ; SSE41-LABEL: test8:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [2454267027,2454267027,2454267027,2454267027]
@@ -883,7 +890,7 @@ define <4 x i32> @test8(<4 x i32> %a) {
   ret <4 x i32> %div
 }
 
-define <8 x i32> @test9(<8 x i32> %a) {
+define <8 x i32> @test9(<8 x i32> %a) #0 {
 ; SSE41-LABEL: test9:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [2454267027,2454267027,2454267027,2454267027]
@@ -977,7 +984,7 @@ define <8 x i32> @test9(<8 x i32> %a) {
   ret <8 x i32> %div
 }
 
-define <8 x i32> @test10(<8 x i32> %a) {
+define <8 x i32> @test10(<8 x i32> %a) #0 {
 ; SSE41-LABEL: test10:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [613566757,613566757,613566757,613566757]
@@ -1075,7 +1082,7 @@ define <8 x i32> @test10(<8 x i32> %a) {
   ret <8 x i32> %rem
 }
 
-define <8 x i32> @test11(<8 x i32> %a) {
+define <8 x i32> @test11(<8 x i32> %a) #0 {
 ; SSE41-LABEL: test11:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [2454267027,2454267027,2454267027,2454267027]
@@ -1188,7 +1195,7 @@ define <8 x i32> @test11(<8 x i32> %a) {
   ret <8 x i32> %rem
 }
 
-define <2 x i16> @test12() {
+define <2 x i16> @test12() #0 {
 ; SSE41-LABEL: test12:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    xorps %xmm0, %xmm0
@@ -1209,7 +1216,7 @@ define <2 x i16> @test12() {
   ret <2 x i16> %B9
 }
 
-define <4 x i32> @PR20355(<4 x i32> %a) {
+define <4 x i32> @PR20355(<4 x i32> %a) #0 {
 ; SSE41-LABEL: PR20355:
 ; SSE41:       # BB#0: # %entry
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [1431655766,1431655766,1431655766,1431655766]
@@ -1263,3 +1270,5 @@ entry:
   %sdiv = sdiv <4 x i32> %a, <i32 3, i32 3, i32 3, i32 3>
   ret <4 x i32> %sdiv
 }
+
+attributes #0 = { nounwind }