Index: test/CodeGen/X86/avx-intrinsics-x86.ll
===================================================================
--- test/CodeGen/X86/avx-intrinsics-x86.ll
+++ test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -1943,23 +1943,29 @@
 }
 
 
-define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; AVX-LABEL: test_x86_sse42_pcmpestria128:
 ; AVX:       ## BB#0:
+; AVX-NEXT:    pushl %ebx
 ; AVX-NEXT:    movl $7, %eax
 ; AVX-NEXT:    movl $7, %edx
+; AVX-NEXT:    xorl %ebx, %ebx
 ; AVX-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX-NEXT:    seta %al
-; AVX-NEXT:    movzbl %al, %eax
+; AVX-NEXT:    seta %bl
+; AVX-NEXT:    movl %ebx, %eax
+; AVX-NEXT:    popl %ebx
 ; AVX-NEXT:    retl
 ;
 ; AVX512VL-LABEL: test_x86_sse42_pcmpestria128:
 ; AVX512VL:       ## BB#0:
+; AVX512VL-NEXT:    pushl %ebx
 ; AVX512VL-NEXT:    movl $7, %eax
 ; AVX512VL-NEXT:    movl $7, %edx
+; AVX512VL-NEXT:    xorl %ebx, %ebx
 ; AVX512VL-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX512VL-NEXT:    seta %al
-; AVX512VL-NEXT:    movzbl %al, %eax
+; AVX512VL-NEXT:    seta %bl
+; AVX512VL-NEXT:    movl %ebx, %eax
+; AVX512VL-NEXT:    popl %ebx
 ; AVX512VL-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestria128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
@@ -1991,23 +1997,29 @@
 declare i32 @llvm.x86.sse42.pcmpestric128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
 
-define i32 @test_x86_sse42_pcmpestrio128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestrio128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; AVX-LABEL: test_x86_sse42_pcmpestrio128:
 ; AVX:       ## BB#0:
+; AVX-NEXT:    pushl %ebx
 ; AVX-NEXT:    movl $7, %eax
 ; AVX-NEXT:    movl $7, %edx
+; AVX-NEXT:    xorl %ebx, %ebx
 ; AVX-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX-NEXT:    seto %al
-; AVX-NEXT:    movzbl %al, %eax
+; AVX-NEXT:    seto %bl
+; AVX-NEXT:    movl %ebx, %eax
+; AVX-NEXT:    popl %ebx
 ; AVX-NEXT:    retl
 ;
 ; AVX512VL-LABEL: test_x86_sse42_pcmpestrio128:
 ; AVX512VL:       ## BB#0:
+; AVX512VL-NEXT:    pushl %ebx
 ; AVX512VL-NEXT:    movl $7, %eax
 ; AVX512VL-NEXT:    movl $7, %edx
+; AVX512VL-NEXT:    xorl %ebx, %ebx
 ; AVX512VL-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX512VL-NEXT:    seto %al
-; AVX512VL-NEXT:    movzbl %al, %eax
+; AVX512VL-NEXT:    seto %bl
+; AVX512VL-NEXT:    movl %ebx, %eax
+; AVX512VL-NEXT:    popl %ebx
 ; AVX512VL-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
@@ -2015,23 +2027,29 @@
 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
 
-define i32 @test_x86_sse42_pcmpestris128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestris128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; AVX-LABEL: test_x86_sse42_pcmpestris128:
 ; AVX:       ## BB#0:
+; AVX-NEXT:    pushl %ebx
 ; AVX-NEXT:    movl $7, %eax
 ; AVX-NEXT:    movl $7, %edx
+; AVX-NEXT:    xorl %ebx, %ebx
 ; AVX-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX-NEXT:    sets %al
-; AVX-NEXT:    movzbl %al, %eax
+; AVX-NEXT:    sets %bl
+; AVX-NEXT:    movl %ebx, %eax
+; AVX-NEXT:    popl %ebx
 ; AVX-NEXT:    retl
 ;
 ; AVX512VL-LABEL: test_x86_sse42_pcmpestris128:
 ; AVX512VL:       ## BB#0:
+; AVX512VL-NEXT:    pushl %ebx
 ; AVX512VL-NEXT:    movl $7, %eax
 ; AVX512VL-NEXT:    movl $7, %edx
+; AVX512VL-NEXT:    xorl %ebx, %ebx
 ; AVX512VL-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX512VL-NEXT:    sets %al
-; AVX512VL-NEXT:    movzbl %al, %eax
+; AVX512VL-NEXT:    sets %bl
+; AVX512VL-NEXT:    movl %ebx, %eax
+; AVX512VL-NEXT:    popl %ebx
 ; AVX512VL-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestris128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
@@ -2039,23 +2057,29 @@
 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
 
-define i32 @test_x86_sse42_pcmpestriz128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestriz128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; AVX-LABEL: test_x86_sse42_pcmpestriz128:
 ; AVX:       ## BB#0:
+; AVX-NEXT:    pushl %ebx
 ; AVX-NEXT:    movl $7, %eax
 ; AVX-NEXT:    movl $7, %edx
+; AVX-NEXT:    xorl %ebx, %ebx
 ; AVX-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX-NEXT:    sete %al
-; AVX-NEXT:    movzbl %al, %eax
+; AVX-NEXT:    sete %bl
+; AVX-NEXT:    movl %ebx, %eax
+; AVX-NEXT:    popl %ebx
 ; AVX-NEXT:    retl
 ;
 ; AVX512VL-LABEL: test_x86_sse42_pcmpestriz128:
 ; AVX512VL:       ## BB#0:
+; AVX512VL-NEXT:    pushl %ebx
 ; AVX512VL-NEXT:    movl $7, %eax
 ; AVX512VL-NEXT:    movl $7, %edx
+; AVX512VL-NEXT:    xorl %ebx, %ebx
 ; AVX512VL-NEXT:    vpcmpestri $7, %xmm1, %xmm0
-; AVX512VL-NEXT:    sete %al
-; AVX512VL-NEXT:    movzbl %al, %eax
+; AVX512VL-NEXT:    sete %bl
+; AVX512VL-NEXT:    movl %ebx, %eax
+; AVX512VL-NEXT:    popl %ebx
 ; AVX512VL-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
Index: test/CodeGen/X86/fp128-cast.ll
===================================================================
--- test/CodeGen/X86/fp128-cast.ll
+++ test/CodeGen/X86/fp128-cast.ll
@@ -238,6 +238,7 @@
 ; X64-LABEL: TestConst128:
 ; X64:       movaps {{.*}}, %xmm1
 ; X64-NEXT:  callq __gttf2
+; X64-NEXT:  xorl
 ; X64-NEXT:  test
 ; X64:       retq
 }
Index: test/CodeGen/X86/fp128-compare.ll
===================================================================
--- test/CodeGen/X86/fp128-compare.ll
+++ test/CodeGen/X86/fp128-compare.ll
@@ -8,8 +8,9 @@
   ret i32 %conv
 ; CHECK-LABEL: TestComp128GT:
 ; CHECK:       callq __gttf2
-; CHECK:       setg  %al
-; CHECK:       movzbl %al, %eax
+; CHECK:       xorl  %ecx, %ecx
+; CHECK:       setg  %cl
+; CHECK:       movl  %ecx, %eax
 ; CHECK:       retq
 }
 
@@ -20,9 +21,10 @@
   ret i32 %conv
 ; CHECK-LABEL: TestComp128GE:
 ; CHECK:       callq __getf2
+; CHECK:       xorl  %ecx, %ecx
 ; CHECK:       testl %eax, %eax
-; CHECK:       setns %al
-; CHECK:       movzbl %al, %eax
+; CHECK:       setns %cl
+; CHECK:       movl  %ecx, %eax
 ; CHECK:       retq
 }
 
@@ -48,9 +50,10 @@
   ret i32 %conv
 ; CHECK-LABEL: TestComp128LE:
 ; CHECK:       callq __letf2
-; CHECK-NEXT:  testl %eax, %eax
-; CHECK:       setle %al
-; CHECK:       movzbl %al, %eax
+; CHECK:       xorl  %ecx, %ecx
+; CHECK:       testl %eax, %eax
+; CHECK:       setle %cl
+; CHECK:       movl  %ecx, %eax
 ; CHECK:       retq
 }
 
@@ -61,9 +64,10 @@
   ret i32 %conv
 ; CHECK-LABEL: TestComp128EQ:
 ; CHECK:       callq __eqtf2
-; CHECK-NEXT:  testl %eax, %eax
-; CHECK:       sete %al
-; CHECK:       movzbl %al, %eax
+; CHECK:       xorl  %ecx, %ecx
+; CHECK:       testl %eax, %eax
+; CHECK:       sete  %cl
+; CHECK:       movl  %ecx, %eax
 ; CHECK:       retq
 }
 
@@ -74,9 +78,10 @@
   ret i32 %conv
 ; CHECK-LABEL: TestComp128NE:
 ; CHECK:       callq __netf2
-; CHECK-NEXT:  testl %eax, %eax
-; CHECK:       setne %al
-; CHECK:       movzbl %al, %eax
+; CHECK:       xorl  %ecx, %ecx
+; CHECK:       testl %eax, %eax
+; CHECK:       setne %cl
+; CHECK:       movl  %ecx, %eax
 ; CHECK:       retq
 }
 
Index: test/CodeGen/X86/sse42-intrinsics-fast-isel.ll
===================================================================
--- test/CodeGen/X86/sse42-intrinsics-fast-isel.ll
+++ test/CodeGen/X86/sse42-intrinsics-fast-isel.ll
@@ -4,23 +4,27 @@
 
 ; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/sse42-builtins.c
 
-define i32 @test_mm_cmpestra(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) {
+define i32 @test_mm_cmpestra(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) nounwind {
 ; X32-LABEL: test_mm_cmpestra:
 ; X32:       # BB#0:
+; X32-NEXT:    pushl %ebx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    xorl %ebx, %ebx
 ; X32-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X32-NEXT:    seta %al
-; X32-NEXT:    movzbl %al, %eax
+; X32-NEXT:    seta %bl
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    popl %ebx
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_cmpestra:
 ; X64:       # BB#0:
+; X64-NEXT:    xorl %r8d, %r8d
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    movl %esi, %edx
 ; X64-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X64-NEXT:    seta %al
-; X64-NEXT:    movzbl %al, %eax
+; X64-NEXT:    seta %r8b
+; X64-NEXT:    movl %r8d, %eax
 ; X64-NEXT:    retq
   %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
   %arg2 = bitcast <2 x i64> %a2 to <16 x i8>
@@ -99,23 +103,27 @@
 }
 declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
-define i32 @test_mm_cmpestro(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) {
+define i32 @test_mm_cmpestro(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) nounwind {
 ; X32-LABEL: test_mm_cmpestro:
 ; X32:       # BB#0:
+; X32-NEXT:    pushl %ebx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    xorl %ebx, %ebx
 ; X32-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X32-NEXT:    seto %al
-; X32-NEXT:    movzbl %al, %eax
+; X32-NEXT:    seto %bl
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    popl %ebx
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_cmpestro:
 ; X64:       # BB#0:
+; X64-NEXT:    xorl %r8d, %r8d
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    movl %esi, %edx
 ; X64-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X64-NEXT:    seto %al
-; X64-NEXT:    movzbl %al, %eax
+; X64-NEXT:    seto %r8b
+; X64-NEXT:    movl %r8d, %eax
 ; X64-NEXT:    retq
   %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
   %arg2 = bitcast <2 x i64> %a2 to <16 x i8>
@@ -124,23 +132,27 @@
 }
 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
-define i32 @test_mm_cmpestrs(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) {
+define i32 @test_mm_cmpestrs(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) nounwind {
 ; X32-LABEL: test_mm_cmpestrs:
 ; X32:       # BB#0:
+; X32-NEXT:    pushl %ebx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    xorl %ebx, %ebx
 ; X32-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X32-NEXT:    sets %al
-; X32-NEXT:    movzbl %al, %eax
+; X32-NEXT:    sets %bl
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    popl %ebx
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_cmpestrs:
 ; X64:       # BB#0:
+; X64-NEXT:    xorl %r8d, %r8d
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    movl %esi, %edx
 ; X64-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X64-NEXT:    sets %al
-; X64-NEXT:    movzbl %al, %eax
+; X64-NEXT:    sets %r8b
+; X64-NEXT:    movl %r8d, %eax
 ; X64-NEXT:    retq
   %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
   %arg2 = bitcast <2 x i64> %a2 to <16 x i8>
@@ -149,23 +161,27 @@
 }
 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
-define i32 @test_mm_cmpestrz(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) {
+define i32 @test_mm_cmpestrz(<2 x i64> %a0, i32 %a1, <2 x i64> %a2, i32 %a3) nounwind {
 ; X32-LABEL: test_mm_cmpestrz:
 ; X32:       # BB#0:
+; X32-NEXT:    pushl %ebx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    xorl %ebx, %ebx
 ; X32-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X32-NEXT:    sete %al
-; X32-NEXT:    movzbl %al, %eax
+; X32-NEXT:    sete %bl
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    popl %ebx
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test_mm_cmpestrz:
 ; X64:       # BB#0:
+; X64-NEXT:    xorl %r8d, %r8d
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    movl %esi, %edx
 ; X64-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; X64-NEXT:    sete %al
-; X64-NEXT:    movzbl %al, %eax
+; X64-NEXT:    sete %r8b
+; X64-NEXT:    movl %r8d, %eax
 ; X64-NEXT:    retq
   %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
   %arg2 = bitcast <2 x i64> %a2 to <16 x i8>
Index: test/CodeGen/X86/sse42-intrinsics-x86.ll
===================================================================
--- test/CodeGen/X86/sse42-intrinsics-x86.ll
+++ test/CodeGen/X86/sse42-intrinsics-x86.ll
@@ -33,14 +33,17 @@
 }
 
 
-define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; CHECK-LABEL: test_x86_sse42_pcmpestria128:
 ; CHECK:       ## BB#0:
+; CHECK-NEXT:    pushl %ebx
 ; CHECK-NEXT:    movl $7, %eax
 ; CHECK-NEXT:    movl $7, %edx
+; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; CHECK-NEXT:    seta %al
-; CHECK-NEXT:    movzbl %al, %eax
+; CHECK-NEXT:    seta %bl
+; CHECK-NEXT:    movl %ebx, %eax
+; CHECK-NEXT:    popl %ebx
 ; CHECK-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestria128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
@@ -63,14 +66,17 @@
 declare i32 @llvm.x86.sse42.pcmpestric128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
 
-define i32 @test_x86_sse42_pcmpestrio128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestrio128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; CHECK-LABEL: test_x86_sse42_pcmpestrio128:
 ; CHECK:       ## BB#0:
+; CHECK-NEXT:    pushl %ebx
 ; CHECK-NEXT:    movl $7, %eax
 ; CHECK-NEXT:    movl $7, %edx
+; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; CHECK-NEXT:    seto %al
-; CHECK-NEXT:    movzbl %al, %eax
+; CHECK-NEXT:    seto %bl
+; CHECK-NEXT:    movl %ebx, %eax
+; CHECK-NEXT:    popl %ebx
 ; CHECK-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
@@ -78,14 +84,17 @@
 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
 
-define i32 @test_x86_sse42_pcmpestris128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestris128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; CHECK-LABEL: test_x86_sse42_pcmpestris128:
 ; CHECK:       ## BB#0:
+; CHECK-NEXT:    pushl %ebx
 ; CHECK-NEXT:    movl $7, %eax
 ; CHECK-NEXT:    movl $7, %edx
+; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; CHECK-NEXT:    sets %al
-; CHECK-NEXT:    movzbl %al, %eax
+; CHECK-NEXT:    sets %bl
+; CHECK-NEXT:    movl %ebx, %eax
+; CHECK-NEXT:    popl %ebx
 ; CHECK-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestris128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res
@@ -93,14 +102,17 @@
 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
 
 
-define i32 @test_x86_sse42_pcmpestriz128(<16 x i8> %a0, <16 x i8> %a2) {
+define i32 @test_x86_sse42_pcmpestriz128(<16 x i8> %a0, <16 x i8> %a2) nounwind {
 ; CHECK-LABEL: test_x86_sse42_pcmpestriz128:
 ; CHECK:       ## BB#0:
+; CHECK-NEXT:    pushl %ebx
 ; CHECK-NEXT:    movl $7, %eax
 ; CHECK-NEXT:    movl $7, %edx
+; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    pcmpestri $7, %xmm1, %xmm0
-; CHECK-NEXT:    sete %al
-; CHECK-NEXT:    movzbl %al, %eax
+; CHECK-NEXT:    sete %bl
+; CHECK-NEXT:    movl %ebx, %eax
+; CHECK-NEXT:    popl %ebx
 ; CHECK-NEXT:    retl
   %res = call i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
   ret i32 %res