Fix a broadcast related regression on the vector shuffle lowering.

[oota-llvm.git] / test / CodeGen / X86 / avx-intrinsics-x86.ll

diff --git a/test/CodeGen/X86/avx-intrinsics-x86.ll b/test/CodeGen/X86/avx-intrinsics-x86.ll
index c44beb4bc2b8e03470704b966f4098c4e1b7eb9f..a957d10cc2b282ea32fc8cef6fc1f70062b2676b 100644 (file)
--- a/test/CodeGen/X86/avx-intrinsics-x86.ll
+++ b/test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -671,7 +671,9 @@ define void @test_x86_sse2_storeu_dq(i8* %a0, <16 x i8> %a1) {
   ; CHECK: test_x86_sse2_storeu_dq
   ; CHECK: movl
   ; CHECK: vmovdqu
-  call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a1)
+  ; 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
@@ -681,6 +683,7 @@ define void @test_x86_sse2_storeu_pd(i8* %a0, <2 x double> %a1) {
   ; CHECK: test_x86_sse2_storeu_pd
   ; CHECK: movl
   ; CHECK: vmovupd
+  ; 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
@@ -815,18 +818,18 @@ declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
 
 define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
   ; CHECK: vblendpd
-  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.sse41.blendpd(<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.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
+declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vblendps
-  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.blendps(<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.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
@@ -847,35 +850,35 @@ declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x floa
 
 define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
   ; CHECK: vdppd
-  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.sse41.dppd(<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.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
+declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vdpps
-  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.dpps(<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.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vinsertps
-  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.insertps(<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.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 
 define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
   ; CHECK: vmpsadbw
-  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i8 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
+declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i8) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
@@ -896,10 +899,10 @@ declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) noun
 
 define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
   ; CHECK: vpblendw
-  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i8 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
+declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
@@ -1140,9 +1143,9 @@ declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) noun
 
 
 define i32 @test_x86_sse42_pcmpestri128(<16 x i8> %a0, <16 x i8> %a2) {
-  ; CHECK: movl
-  ; CHECK: movl
-  ; CHECK: vpcmpestri
+  ; CHECK: movl $7
+  ; CHECK: movl $7
+  ; CHECK: vpcmpestri $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
@@ -1150,6 +1153,18 @@ define i32 @test_x86_sse42_pcmpestri128(<16 x i8> %a0, <16 x i8> %a2) {
 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: vpcmpestri $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
@@ -1216,8 +1231,19 @@ define <16 x i8> @test_x86_sse42_pcmpestrm128(<16 x i8> %a0, <16 x i8> %a2) {
 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: vpcmpestrm $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: vpcmpistri
+  ; CHECK: vpcmpistri $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
@@ -1225,6 +1251,16 @@ define i32 @test_x86_sse42_pcmpistri128(<16 x i8> %a0, <16 x i8> %a1) {
 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: vpcmpistri $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: vpcmpistri
   ; CHECK: seta
@@ -1271,7 +1307,7 @@ declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind rea
 
 
 define <16 x i8> @test_x86_sse42_pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1) {
-  ; CHECK: vpcmpistrm
+  ; CHECK: vpcmpistrm $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
@@ -1279,6 +1315,15 @@ define <16 x i8> @test_x86_sse42_pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1) {
 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: vpcmpistrm $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
+}
+
+
 define <4 x float> @test_x86_sse_add_ss(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vaddss
   %res = call <4 x float> @llvm.x86.sse.add.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
@@ -1725,18 +1770,18 @@ declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwi
 
 define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
   ; CHECK: vblendpd
-  %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
+  %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
   ret <4 x double> %res
 }
-declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
+declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
 
 
 define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
   ; CHECK: vblendps
-  %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
+  %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
   ret <8 x float> %res
 }
-declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
+declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
 
 
 define <4 x double> @test_x86_avx_blendv_pd_256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) {
@@ -1905,10 +1950,10 @@ declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone
 
 define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
   ; CHECK: vdpps
-  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
+  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
   ret <8 x float> %res
 }
-declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
+declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
 
 
 define <4 x double> @test_x86_avx_hadd_pd_256(<4 x double> %a0, <4 x double> %a1) {
@@ -2174,14 +2219,6 @@ define void @test_x86_avx_storeu_ps_256(i8* %a0, <8 x float> %a1) {
 declare void @llvm.x86.avx.storeu.ps.256(i8*, <8 x float>) nounwind
 
 
-define <4 x double> @test_x86_avx_vbroadcast_sd_256(i8* %a0) {
-  ; CHECK: vbroadcastsd
-  %res = call <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8* %a0) ; <<4 x double>> [#uses=1]
-  ret <4 x double> %res
-}
-declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*) nounwind readonly
-
-
 define <4 x double> @test_x86_avx_vbroadcastf128_pd_256(i8* %a0) {
   ; CHECK: vbroadcastf128
   %res = call <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
@@ -2198,22 +2235,6 @@ define <8 x float> @test_x86_avx_vbroadcastf128_ps_256(i8* %a0) {
 declare <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8*) nounwind readonly
 
 
-define <4 x float> @test_x86_avx_vbroadcast_ss(i8* %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <4 x float> @llvm.x86.avx.vbroadcast.ss(i8* %a0) ; <<4 x float>> [#uses=1]
-  ret <4 x float> %res
-}
-declare <4 x float> @llvm.x86.avx.vbroadcast.ss(i8*) nounwind readonly
-
-
-define <8 x float> @test_x86_avx_vbroadcast_ss_256(i8* %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8* %a0) ; <<8 x float>> [#uses=1]
-  ret <8 x float> %res
-}
-declare <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8*) nounwind readonly
-
-
 define <2 x double> @test_x86_avx_vextractf128_pd_256(<4 x double> %a0) {
   ; CHECK: vextractf128
   %res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
@@ -2288,7 +2309,7 @@ declare <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32>, <8 x i32>, i8) noun
 
 define <2 x double> @test_x86_avx_vpermil_pd(<2 x double> %a0) {
   ; CHECK: vpermilpd
-  %res = call <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double> %a0, i8 1) ; <<2 x double>> [#uses=1]
   ret <2 x double> %res
 }
 declare <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double>, i8) nounwind readnone