Masked Load/Store - fixed a bug in type legalization.

llvm-svn: 225441

1 files changed, 49 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/masked_memop.ll b/llvm/test/CodeGen/X86/masked_memop.ll
index 1a28098bd1c..cce2d909120 100644
--- a/llvm/test/CodeGen/X86/masked_memop.ll
+++ b/llvm/test/CodeGen/X86/masked_memop.ll
@@ -149,16 +149,65 @@ define void @test13(<16 x i32> %trigger, <16 x float>* %addr, <16 x float> %val)
   ret void
 }
 
+; AVX2-LABEL: test14
+; AVX2: vshufps $-24
+; AVX2: vmaskmovps
+define void @test14(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
+  ret void
+}
+
+; AVX2-LABEL: test15
+; AVX2: vpmaskmovq
+define void @test15(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
+  ret void
+}
+
+; AVX2-LABEL: test16
+; AVX2: vmaskmovps
+; AVX2: vblendvps
+define <2 x float> @test16(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
+  ret <2 x float> %res
+}
+
+; AVX2-LABEL: test17
+; AVX2: vpmaskmovq
+; AVX2: vblendvpd
+define <2 x i32> @test17(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  %res = call <2 x i32> @llvm.masked.load.v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
+  ret <2 x i32> %res
+}
+
+; AVX2-LABEL: test18
+; AVX2: vmaskmovps
+; AVX2-NOT: blend
+define <2 x float> @test18(<2 x i32> %trigger, <2 x float>* %addr) {
+  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+  %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>undef)
+  ret <2 x float> %res
+}
+
+
 declare <16 x i32> @llvm.masked.load.v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>) 
 declare <4 x i32> @llvm.masked.load.v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+declare <2 x i32> @llvm.masked.load.v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
 declare void @llvm.masked.store.v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
 declare void @llvm.masked.store.v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
 declare void @llvm.masked.store.v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
 declare void @llvm.masked.store.v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>) 
 declare void @llvm.masked.store.v16f32p(<16 x float>*, <16 x float>**, i32, <16 x i1>) 
 declare <16 x float> @llvm.masked.load.v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
 declare <8 x float> @llvm.masked.load.v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
 declare <4 x float> @llvm.masked.load.v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.load.v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
 declare <8 x double> @llvm.masked.load.v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
 declare <4 x double> @llvm.masked.load.v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
 declare <2 x double> @llvm.masked.load.v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)