Add tests for SSE intrinsics in non-avx mode by copying from the AVX test cases. Some of these may have been tested by other tests, but most weren't. Patch by Cameron McInally.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193309 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 1704 insertions, 0 deletions

diff --git a/test/CodeGen/X86/sse-intrinsics-x86.ll b/test/CodeGen/X86/sse-intrinsics-x86.ll
new file mode 100644
index 0000000000..65d44bfb5b
--- /dev/null
+++ b/test/CodeGen/X86/sse-intrinsics-x86.ll
@@ -0,0 +1,308 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse | FileCheck %s
+
+define <4 x float> @test_x86_sse_add_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: addss
+  %res = call <4 x float> @llvm.x86.sse.add.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.add.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_cmp_ps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: cmpordps
+  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_cmp_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: cmpordss
+  %res = call <4 x float> @llvm.x86.sse.cmp.ss(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.cmp.ss(<4 x float>, <4 x float>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse_comieq_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: comiss
+  ; CHECK: sete
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.comieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.comieq.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_comige_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: comiss
+  ; CHECK: setae
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.comige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.comige.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_comigt_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: comiss
+  ; CHECK: seta
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.comigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.comigt.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_comile_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: comiss
+  ; CHECK: setbe
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.comile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.comile.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_comilt_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: comiss
+  ; CHECK: sbb
+  %res = call i32 @llvm.x86.sse.comilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.comilt.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_comineq_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: comiss
+  ; CHECK: setne
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.comineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.comineq.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_cvtsi2ss(<4 x float> %a0) {
+  ; CHECK: movl
+  ; CHECK: cvtsi2ss
+  %res = call <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float>, i32) nounwind readnone
+
+
+define i32 @test_x86_sse_cvtss2si(<4 x float> %a0) {
+  ; CHECK: cvtss2si
+  %res = call i32 @llvm.x86.sse.cvtss2si(<4 x float> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_cvttss2si(<4 x float> %a0) {
+  ; CHECK: cvttss2si
+  %res = call i32 @llvm.x86.sse.cvttss2si(<4 x float> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_div_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: divss
+  %res = call <4 x float> @llvm.x86.sse.div.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.div.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define void @test_x86_sse_ldmxcsr(i8* %a0) {
+  ; CHECK: movl
+  ; CHECK: ldmxcsr
+  call void @llvm.x86.sse.ldmxcsr(i8* %a0)
+  ret void
+}
+declare void @llvm.x86.sse.ldmxcsr(i8*) nounwind
+
+
+
+define <4 x float> @test_x86_sse_max_ps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: maxps
+  %res = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_max_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: maxss
+  %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_min_ps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: minps
+  %res = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_min_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: minss
+  %res = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_movmsk_ps(<4 x float> %a0) {
+  ; CHECK: movmskps
+  %res = call i32 @llvm.x86.sse.movmsk.ps(<4 x float> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.movmsk.ps(<4 x float>) nounwind readnone
+
+
+
+define <4 x float> @test_x86_sse_mul_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: mulss
+  %res = call <4 x float> @llvm.x86.sse.mul.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_rcp_ps(<4 x float> %a0) {
+  ; CHECK: rcpps
+  %res = call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_rcp_ss(<4 x float> %a0) {
+  ; CHECK: rcpss
+  %res = call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_rsqrt_ps(<4 x float> %a0) {
+  ; CHECK: rsqrtps
+  %res = call <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_rsqrt_ss(<4 x float> %a0) {
+  ; CHECK: rsqrtss
+  %res = call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_sqrt_ps(<4 x float> %a0) {
+  ; CHECK: sqrtps
+  %res = call <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse_sqrt_ss(<4 x float> %a0) {
+  ; CHECK: sqrtss
+  %res = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
+
+
+define void @test_x86_sse_stmxcsr(i8* %a0) {
+  ; CHECK: movl
+  ; CHECK: stmxcsr
+  call void @llvm.x86.sse.stmxcsr(i8* %a0)
+  ret void
+}
+declare void @llvm.x86.sse.stmxcsr(i8*) nounwind
+
+
+define void @test_x86_sse_storeu_ps(i8* %a0, <4 x float> %a1) {
+  ; CHECK: movl
+  ; CHECK: movups
+  call void @llvm.x86.sse.storeu.ps(i8* %a0, <4 x float> %a1)
+  ret void
+}
+declare void @llvm.x86.sse.storeu.ps(i8*, <4 x float>) nounwind
+
+
+define <4 x float> @test_x86_sse_sub_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: subss
+  %res = call <4 x float> @llvm.x86.sse.sub.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_ucomieq_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: ucomiss
+  ; CHECK: sete
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.ucomieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.ucomieq.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_ucomige_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: ucomiss
+  ; CHECK: setae
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.ucomige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_ucomigt_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: ucomiss
+  ; CHECK: seta
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.ucomigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.ucomigt.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_ucomile_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: ucomiss
+  ; CHECK: setbe
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.ucomile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.ucomile.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_ucomilt_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: ucomiss
+  ; CHECK: sbbl
+  %res = call i32 @llvm.x86.sse.ucomilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.ucomilt.ss(<4 x float>, <4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse_ucomineq_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: ucomiss
+  ; CHECK: setne
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse.ucomineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse.ucomineq.ss(<4 x float>, <4 x float>) nounwind readnone
diff --git a/test/CodeGen/X86/sse2-intrinsics-x86.ll b/test/CodeGen/X86/sse2-intrinsics-x86.ll
new file mode 100644
index 0000000000..a6b0b90bd8
--- /dev/null
+++ b/test/CodeGen/X86/sse2-intrinsics-x86.ll
@@ -0,0 +1,711 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse2 | FileCheck %s
+
+define <2 x double> @test_x86_sse2_add_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: addsd
+  %res = call <2 x double> @llvm.x86.sse2.add.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.add.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_cmp_pd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: cmpordpd
+  %res = call <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double>, <2 x double>, i8) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_cmp_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: cmpordsd
+  %res = call <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double>, <2 x double>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse2_comieq_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: comisd
+  ; CHECK: sete
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.comieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.comieq.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_comige_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: comisd
+  ; CHECK: setae
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.comige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.comige.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_comigt_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: comisd
+  ; CHECK: seta
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.comigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.comigt.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_comile_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: comisd
+  ; CHECK: setbe
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.comile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.comile.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_comilt_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: comisd
+  ; CHECK: sbbl    %eax, %eax
+  ; CHECK: andl    $1, %eax
+  %res = call i32 @llvm.x86.sse2.comilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.comilt.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_comineq_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: comisd
+  ; CHECK: setne
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.comineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.comineq.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_cvtdq2pd(<4 x i32> %a0) {
+  ; CHECK: cvtdq2pd
+  %res = call <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32> %a0) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse2_cvtdq2ps(<4 x i32> %a0) {
+  ; CHECK: cvtdq2ps
+  %res = call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_cvtpd2dq(<2 x double> %a0) {
+  ; CHECK: cvtpd2dq
+  %res = call <4 x i32> @llvm.x86.sse2.cvtpd2dq(<2 x double> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.cvtpd2dq(<2 x double>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse2_cvtpd2ps(<2 x double> %a0) {
+  ; CHECK: cvtpd2ps
+  %res = call <4 x float> @llvm.x86.sse2.cvtpd2ps(<2 x double> %a0) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse2.cvtpd2ps(<2 x double>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_cvtps2dq(<4 x float> %a0) {
+  ; CHECK: cvtps2dq
+  %res = call <4 x i32> @llvm.x86.sse2.cvtps2dq(<4 x float> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.cvtps2dq(<4 x float>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_cvtps2pd(<4 x float> %a0) {
+  ; CHECK: cvtps2pd
+  %res = call <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float> %a0) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse2_cvtsd2si(<2 x double> %a0) {
+  ; CHECK: cvtsd2si
+  %res = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.cvtsd2si(<2 x double>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse2_cvtsd2ss(<4 x float> %a0, <2 x double> %a1) {
+  ; CHECK: cvtsd2ss 
+  %res = call <4 x float> @llvm.x86.sse2.cvtsd2ss(<4 x float> %a0, <2 x double> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse2.cvtsd2ss(<4 x float>, <2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_cvtsi2sd(<2 x double> %a0) {
+  ; CHECK: movl
+  ; CHECK: cvtsi2sd
+  %res = call <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double>, i32) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_cvtss2sd(<2 x double> %a0, <4 x float> %a1) {
+  ; CHECK: cvtss2sd
+  %res = call <2 x double> @llvm.x86.sse2.cvtss2sd(<2 x double> %a0, <4 x float> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.cvtss2sd(<2 x double>, <4 x float>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_cvttpd2dq(<2 x double> %a0) {
+  ; CHECK: cvttpd2dq
+  %res = call <4 x i32> @llvm.x86.sse2.cvttpd2dq(<2 x double> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.cvttpd2dq(<2 x double>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_cvttps2dq(<4 x float> %a0) {
+  ; CHECK: cvttps2dq
+  %res = call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float>) nounwind readnone
+
+
+define i32 @test_x86_sse2_cvttsd2si(<2 x double> %a0) {
+  ; CHECK: cvttsd2si
+  %res = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.cvttsd2si(<2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_div_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: divsd
+  %res = call <2 x double> @llvm.x86.sse2.div.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.div.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+
+define <2 x double> @test_x86_sse2_max_pd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: maxpd
+  %res = call <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.max.pd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_max_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: maxsd
+  %res = call <2 x double> @llvm.x86.sse2.max.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.max.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_min_pd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: minpd
+  %res = call <2 x double> @llvm.x86.sse2.min.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_min_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: minsd
+  %res = call <2 x double> @llvm.x86.sse2.min.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.min.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_movmsk_pd(<2 x double> %a0) {
+  ; CHECK: movmskpd
+  %res = call i32 @llvm.x86.sse2.movmsk.pd(<2 x double> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.movmsk.pd(<2 x double>) nounwind readnone
+
+
+
+
+define <2 x double> @test_x86_sse2_mul_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: test_x86_sse2_mul_sd
+  ; CHECK: mulsd
+  %res = call <2 x double> @llvm.x86.sse2.mul.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.mul.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_packssdw_128(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: packssdw
+  %res = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_packsswb_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: packsswb
+  %res = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_packuswb_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: packuswb
+  %res = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_padds_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: paddsb
+  %res = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_padds_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: paddsw
+  %res = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_paddus_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: paddusb
+  %res = call <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_paddus_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: paddusw
+  %res = call <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_pavg_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pavgb
+  %res = call <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_pavg_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pavgw
+  %res = call <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_pmadd_wd(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pmaddwd
+  %res = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %a0, <8 x i16> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_pmaxs_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pmaxsw
+  %res = call <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_pmaxu_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pmaxub
+  %res = call <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_pmins_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pminsw
+  %res = call <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_pminu_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pminub
+  %res = call <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define i32 @test_x86_sse2_pmovmskb_128(<16 x i8> %a0) {
+  ; CHECK: pmovmskb
+  %res = call i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8> %a0) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_pmulh_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pmulhw
+  %res = call <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_pmulhu_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pmulhuw
+  %res = call <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_pmulu_dq(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pmuludq
+  %res = call <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psad_bw(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: psadbw
+  %res = call <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8> %a0, <16 x i8> %a1) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_psll_d(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pslld
+  %res = call <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psll_dq(<2 x i64> %a0) {
+  ; CHECK: pslldq
+  %res = call <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64>, i32) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psll_dq_bs(<2 x i64> %a0) {
+  ; CHECK: pslldq
+  %res = call <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64>, i32) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psll_q(<2 x i64> %a0, <2 x i64> %a1) {
+  ; CHECK: psllq
+  %res = call <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64>, <2 x i64>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psll_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: psllw
+  %res = call <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_pslli_d(<4 x i32> %a0) {
+  ; CHECK: pslld
+  %res = call <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32>, i32) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_pslli_q(<2 x i64> %a0) {
+  ; CHECK: psllq
+  %res = call <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64>, i32) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_pslli_w(<8 x i16> %a0) {
+  ; CHECK: psllw
+  %res = call <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16>, i32) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_psra_d(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: psrad
+  %res = call <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psra_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: psraw
+  %res = call <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_psrai_d(<4 x i32> %a0) {
+  ; CHECK: psrad
+  %res = call <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32>, i32) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psrai_w(<8 x i16> %a0) {
+  ; CHECK: psraw
+  %res = call <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16>, i32) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_psrl_d(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: psrld
+  %res = call <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psrl_dq(<2 x i64> %a0) {
+  ; CHECK: psrldq
+  %res = call <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64>, i32) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psrl_dq_bs(<2 x i64> %a0) {
+  ; CHECK: psrldq
+  %res = call <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64>, i32) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psrl_q(<2 x i64> %a0, <2 x i64> %a1) {
+  ; CHECK: psrlq
+  %res = call <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64>, <2 x i64>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psrl_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: psrlw
+  %res = call <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse2_psrli_d(<4 x i32> %a0) {
+  ; CHECK: psrld
+  %res = call <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32>, i32) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse2_psrli_q(<2 x i64> %a0) {
+  ; CHECK: psrlq
+  %res = call <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64>, i32) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psrli_w(<8 x i16> %a0) {
+  ; CHECK: psrlw
+  %res = call <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16>, i32) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_psubs_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: psubsb
+  %res = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psubs_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: psubsw
+  %res = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse2_psubus_b(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: psubusb
+  %res = call <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse2_psubus_w(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: psubusw
+  %res = call <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_sqrt_pd(<2 x double> %a0) {
+  ; CHECK: sqrtpd
+  %res = call <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse2_sqrt_sd(<2 x double> %a0) {
+  ; CHECK: sqrtsd
+  %res = call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
+
+
+define void @test_x86_sse2_storel_dq(i8* %a0, <4 x i32> %a1) {
+  ; CHECK: test_x86_sse2_storel_dq
+  ; CHECK: movl
+  ; CHECK: movq
+  call void @llvm.x86.sse2.storel.dq(i8* %a0, <4 x i32> %a1)
+  ret void
+}
+declare void @llvm.x86.sse2.storel.dq(i8*, <4 x i32>) nounwind
+
+
+define void @test_x86_sse2_storeu_dq(i8* %a0, <16 x i8> %a1) {
+  ; CHECK: test_x86_sse2_storeu_dq
+  ; CHECK: movl
+  ; CHECK: movdqu
+  ; add operation forces the execution domain.
+  %a2 = add <16 x i8> %a1, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a2)
+  ret void
+}
+declare void @llvm.x86.sse2.storeu.dq(i8*, <16 x i8>) nounwind
+
+
+define void @test_x86_sse2_storeu_pd(i8* %a0, <2 x double> %a1) {
+  ; CHECK: test_x86_sse2_storeu_pd
+  ; CHECK: movl
+  ; CHECK: movupd
+  ; fadd operation forces the execution domain.
+  %a2 = fadd <2 x double> %a1, <double 0x0, double 0x4200000000000000>
+  call void @llvm.x86.sse2.storeu.pd(i8* %a0, <2 x double> %a2)
+  ret void
+}
+declare void @llvm.x86.sse2.storeu.pd(i8*, <2 x double>) nounwind
+
+
+define <2 x double> @test_x86_sse2_sub_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: test_x86_sse2_sub_sd
+  ; CHECK: subsd
+  %res = call <2 x double> @llvm.x86.sse2.sub.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse2.sub.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_ucomieq_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: ucomisd
+  ; CHECK: sete
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.ucomieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.ucomieq.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_ucomige_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: ucomisd
+  ; CHECK: setae
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.ucomige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.ucomige.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_ucomigt_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: ucomisd
+  ; CHECK: seta
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.ucomigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.ucomigt.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_ucomile_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: ucomisd
+  ; CHECK: setbe
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.ucomile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.ucomile.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_ucomilt_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: ucomisd
+  ; CHECK: sbbl
+  %res = call i32 @llvm.x86.sse2.ucomilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.ucomilt.sd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define i32 @test_x86_sse2_ucomineq_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: ucomisd
+  ; CHECK: setne
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse2.ucomineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse2.ucomineq.sd(<2 x double>, <2 x double>) nounwind readnone
diff --git a/test/CodeGen/X86/sse3-intrinsics-x86.ll b/test/CodeGen/X86/sse3-intrinsics-x86.ll
new file mode 100644
index 0000000000..dbd14b805f
--- /dev/null
+++ b/test/CodeGen/X86/sse3-intrinsics-x86.ll
@@ -0,0 +1,57 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse3 | FileCheck %s
+
+define <2 x double> @test_x86_sse3_addsub_pd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: addsubpd
+  %res = call <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse3_addsub_ps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: addsubps
+  %res = call <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse3_hadd_pd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: haddpd
+  %res = call <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse3_hadd_ps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: haddps
+  %res = call <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse3_hsub_pd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: hsubpd
+  %res = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double>, <2 x double>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse3_hsub_ps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: hsubps
+  %res = call <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float>, <4 x float>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse3_ldu_dq(i8* %a0) {
+  ; CHECK: movl
+  ; CHECK: lddqu
+  %res = call <16 x i8> @llvm.x86.sse3.ldu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
diff --git a/test/CodeGen/X86/sse41-intrinsics-x86.ll b/test/CodeGen/X86/sse41-intrinsics-x86.ll
new file mode 100644
index 0000000000..055eebd459
--- /dev/null
+++ b/test/CodeGen/X86/sse41-intrinsics-x86.ll
@@ -0,0 +1,326 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse41 | FileCheck %s
+
+define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: blendpd
+  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: blendps
+  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
+
+
+define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
+  ; CHECK: blendvpd
+  %res = call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) {
+  ; CHECK: blendvps
+  %res = call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: dppd
+  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: dpps
+  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: insertps
+  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
+
+
+
+define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: mpsadbw
+  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: packusdw
+  %res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse41_pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) {
+  ; CHECK: pblendvb
+  %res = call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pblendw
+  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
+  ; CHECK: phminposuw
+  %res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse41_pmaxsb(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pmaxsb
+  %res = call <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pmaxsd(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pmaxsd
+  %res = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pmaxud(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pmaxud
+  %res = call <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_pmaxuw(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pmaxuw
+  %res = call <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse41_pminsb(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pminsb
+  %res = call <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pminsd(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pminsd
+  %res = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pminud(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pminud
+  %res = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pminud(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_pminuw(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pminuw
+  %res = call <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pmovsxbd(<16 x i8> %a0) {
+  ; CHECK: pmovsxbd
+  %res = call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmovsxbq(<16 x i8> %a0) {
+  ; CHECK: pmovsxbq
+  %res = call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_pmovsxbw(<16 x i8> %a0) {
+  ; CHECK: pmovsxbw
+  %res = call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmovsxdq(<4 x i32> %a0) {
+  ; CHECK: pmovsxdq
+  %res = call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pmovsxwd(<8 x i16> %a0) {
+  ; CHECK: pmovsxwd
+  %res = call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmovsxwq(<8 x i16> %a0) {
+  ; CHECK: pmovsxwq
+  %res = call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pmovzxbd(<16 x i8> %a0) {
+  ; CHECK: pmovzxbd
+  %res = call <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmovzxbq(<16 x i8> %a0) {
+  ; CHECK: pmovzxbq
+  %res = call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_pmovzxbw(<16 x i8> %a0) {
+  ; CHECK: pmovzxbw
+  %res = call <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmovzxdq(<4 x i32> %a0) {
+  ; CHECK: pmovzxdq
+  %res = call <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32>) nounwind readnone
+
+
+define <4 x i32> @test_x86_sse41_pmovzxwd(<8 x i16> %a0) {
+  ; CHECK: pmovzxwd
+  %res = call <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmovzxwq(<8 x i16> %a0) {
+  ; CHECK: pmovzxwq
+  %res = call <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16>) nounwind readnone
+
+
+define <2 x i64> @test_x86_sse41_pmuldq(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: pmuldq
+  %res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define i32 @test_x86_sse41_ptestc(<2 x i64> %a0, <2 x i64> %a1) {
+  ; CHECK: ptest 
+  ; CHECK: sbbl
+  %res = call i32 @llvm.x86.sse41.ptestc(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse41.ptestc(<2 x i64>, <2 x i64>) nounwind readnone
+
+
+define i32 @test_x86_sse41_ptestnzc(<2 x i64> %a0, <2 x i64> %a1) {
+  ; CHECK: ptest 
+  ; CHECK: seta
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse41.ptestnzc(<2 x i64>, <2 x i64>) nounwind readnone
+
+
+define i32 @test_x86_sse41_ptestz(<2 x i64> %a0, <2 x i64> %a1) {
+  ; CHECK: ptest 
+  ; CHECK: sete
+  ; CHECK: movzbl
+  %res = call i32 @llvm.x86.sse41.ptestz(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse41.ptestz(<2 x i64>, <2 x i64>) nounwind readnone
+
+
+define <2 x double> @test_x86_sse41_round_pd(<2 x double> %a0) {
+  ; CHECK: roundpd
+  %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_round_ps(<4 x float> %a0) {
+  ; CHECK: roundps
+  %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
+
+
+define <2 x double> @test_x86_sse41_round_sd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: roundsd
+  %res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_round_ss(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: roundss
+  %res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
diff --git a/test/CodeGen/X86/sse42-intrinsics-x86.ll b/test/CodeGen/X86/sse42-intrinsics-x86.ll
new file mode 100644
index 0000000000..b262ccc7f0
--- /dev/null
+++ b/test/CodeGen/X86/sse42-intrinsics-x86.ll
@@ -0,0 +1,182 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse42 | FileCheck %s
+
+define i32 @test_x86_sse42_pcmpestri128(<16 x i8> %a0, <16 x i8> %a2) {
+  ; CHECK: movl $7
+  ; CHECK: movl $7
+  ; CHECK: pcmpestri $7
+  ; CHECK: movl
+  %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpestri128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpestri128_load(<16 x i8>* %a0, <16 x i8>* %a2) {
+  ; CHECK: movl $7
+  ; CHECK: movl $7
+  ; CHECK: pcmpestri $7, (
+  ; CHECK: movl
+  %1 = load <16 x i8>* %a0
+  %2 = load <16 x i8>* %a2
+  %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %1, i32 7, <16 x i8> %2, i32 7, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+
+
+define i32 @test_x86_sse42_pcmpestria128(<16 x i8> %a0, <16 x i8> %a2) {
+  ; CHECK: movl
+  ; CHECK: movl
+  ; CHECK: pcmpestri
+  ; CHECK: seta
+  %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
+}
+declare i32 @llvm.x86.sse42.pcmpestria128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpestric128(<16 x i8> %a0, <16 x i8> %a2) {
+  ; CHECK: movl
+  ; CHECK: movl
+  ; CHECK: pcmpestri
+  ; CHECK: sbbl
+  %res = call i32 @llvm.x86.sse42.pcmpestric128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+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) {
+  ; CHECK: movl
+  ; CHECK: movl
+  ; CHECK: pcmpestri
+  ; CHECK: seto
+  %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
+}
+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) {
+  ; CHECK: movl
+  ; CHECK: movl
+  ; CHECK: pcmpestri
+  ; CHECK: sets
+  %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
+}
+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) {
+  ; CHECK: movl
+  ; CHECK: movl
+  ; CHECK: pcmpestri
+  ; CHECK: sete
+  %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
+}
+declare i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse42_pcmpestrm128(<16 x i8> %a0, <16 x i8> %a2) {
+  ; CHECK: movl
+  ; CHECK: movl
+  ; CHECK: pcmpestrm
+  ; CHECK-NOT: vmov
+  %res = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse42_pcmpestrm128_load(<16 x i8> %a0, <16 x i8>* %a2) {
+  ; CHECK: movl $7
+  ; CHECK: movl $7
+  ; CHECK: pcmpestrm $7,
+  ; CHECK-NOT: vmov
+  %1 = load <16 x i8>* %a2
+  %res = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %a0, i32 7, <16 x i8> %1, i32 7, i8 7) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+
+
+define i32 @test_x86_sse42_pcmpistri128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistri $7
+  ; CHECK: movl
+  %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpistri128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpistri128_load(<16 x i8>* %a0, <16 x i8>* %a1) {
+  ; CHECK: pcmpistri $7, (
+  ; CHECK: movl
+  %1 = load <16 x i8>* %a0
+  %2 = load <16 x i8>* %a1
+  %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %1, <16 x i8> %2, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+
+
+define i32 @test_x86_sse42_pcmpistria128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistri
+  ; CHECK: seta
+  %res = call i32 @llvm.x86.sse42.pcmpistria128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpistria128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpistric128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistri
+  ; CHECK: sbbl
+  %res = call i32 @llvm.x86.sse42.pcmpistric128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpistric128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistri
+  ; CHECK: seto
+  %res = call i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpistris128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistri
+  ; CHECK: sets
+  %res = call i32 @llvm.x86.sse42.pcmpistris128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpistris128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define i32 @test_x86_sse42_pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistri
+  ; CHECK: sete
+  %res = call i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
+  ret i32 %res
+}
+declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse42_pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pcmpistrm $7
+  ; CHECK-NOT: vmov
+  %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8>, <16 x i8>, i8) nounwind readnone
+
+
+define <16 x i8> @test_x86_sse42_pcmpistrm128_load(<16 x i8> %a0, <16 x i8>* %a1) {
+  ; CHECK: pcmpistrm $7, (
+  ; CHECK-NOT: vmov
+  %1 = load <16 x i8>* %a1
+  %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %1, i8 7) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
diff --git a/test/CodeGen/X86/ssse3-intrinsics-x86.ll b/test/CodeGen/X86/ssse3-intrinsics-x86.ll
new file mode 100644
index 0000000000..728cbc9b60
--- /dev/null
+++ b/test/CodeGen/X86/ssse3-intrinsics-x86.ll
@@ -0,0 +1,120 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+ssse3 | FileCheck %s
+
+define <16 x i8> @test_x86_ssse3_pabs_b_128(<16 x i8> %a0) {
+  ; CHECK: pabsb
+  %res = call <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8>) nounwind readnone
+
+
+define <4 x i32> @test_x86_ssse3_pabs_d_128(<4 x i32> %a0) {
+  ; CHECK: pabsd
+  %res = call <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_pabs_w_128(<8 x i16> %a0) {
+  ; CHECK: pabsw
+  %res = call <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_ssse3_phadd_d_128(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: phaddd
+  %res = call <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_phadd_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: phaddsw
+  %res = call <8 x i16> @llvm.x86.ssse3.phadd.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.phadd.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_phadd_w_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: phaddw
+  %res = call <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <4 x i32> @test_x86_ssse3_phsub_d_128(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: phsubd
+  %res = call <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_phsub_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: phsubsw
+  %res = call <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_phsub_w_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: phsubw
+  %res = call <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_pmadd_ub_sw_128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pmaddubsw
+  %res = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8> %a0, <16 x i8> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_pmul_hr_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pmulhrsw
+  %res = call <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
+
+
+define <16 x i8> @test_x86_ssse3_pshuf_b_128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: pshufb
+  %res = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <16 x i8> @test_x86_ssse3_psign_b_128(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: psignb
+  %res = call <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8>, <16 x i8>) nounwind readnone
+
+
+define <4 x i32> @test_x86_ssse3_psign_d_128(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: psignd
+  %res = call <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32>, <4 x i32>) nounwind readnone
+
+
+define <8 x i16> @test_x86_ssse3_psign_w_128(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: psignw
+  %res = call <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16>, <8 x i16>) nounwind readnone