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

1 files changed, 182 insertions, 0 deletions

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
+}