1 ; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=knl < %s | FileCheck %s -check-prefix=AVX512
2 ; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=core-avx2 < %s | FileCheck %s -check-prefix=AVX2
5 ; AVX512: vmovdqu32 (%rdi), %zmm0 {%k1} {z}
8 ; AVX2: vpmaskmovd 32(%rdi)
9 ; AVX2: vpmaskmovd (%rdi)
12 define <16 x i32> @test1(<16 x i32> %trigger, i8* %addr) {
13 %mask = icmp eq <16 x i32> %trigger, zeroinitializer
14 %res = call <16 x i32> @llvm.masked.load.v16i32(i8* %addr, <16 x i32>undef, i32 4, <16 x i1>%mask)
19 ; AVX512: vmovdqu32 (%rdi), %zmm0 {%k1} {z}
22 ; AVX2: vpmaskmovd {{.*}}(%rdi)
23 ; AVX2: vpmaskmovd {{.*}}(%rdi)
25 define <16 x i32> @test2(<16 x i32> %trigger, i8* %addr) {
26 %mask = icmp eq <16 x i32> %trigger, zeroinitializer
27 %res = call <16 x i32> @llvm.masked.load.v16i32(i8* %addr, <16 x i32>zeroinitializer, i32 4, <16 x i1>%mask)
32 ; AVX512: vmovdqu32 %zmm1, (%rdi) {%k1}
34 define void @test3(<16 x i32> %trigger, i8* %addr, <16 x i32> %val) {
35 %mask = icmp eq <16 x i32> %trigger, zeroinitializer
36 call void @llvm.masked.store.v16i32(i8* %addr, <16 x i32>%val, i32 4, <16 x i1>%mask)
41 ; AVX512: vmovups (%rdi), %zmm{{.*{%k[1-7]}}}
44 ; AVX2: vpmaskmovd {{.*}}(%rdi)
45 ; AVX2: vpmaskmovd {{.*}}(%rdi)
47 define <16 x float> @test4(<16 x i32> %trigger, i8* %addr, <16 x float> %dst) {
48 %mask = icmp eq <16 x i32> %trigger, zeroinitializer
49 %res = call <16 x float> @llvm.masked.load.v16f32(i8* %addr, <16 x float>%dst, i32 4, <16 x i1>%mask)
54 ; AVX512: vmovupd (%rdi), %zmm1 {%k1}
61 define <8 x double> @test5(<8 x i32> %trigger, i8* %addr, <8 x double> %dst) {
62 %mask = icmp eq <8 x i32> %trigger, zeroinitializer
63 %res = call <8 x double> @llvm.masked.load.v8f64(i8* %addr, <8 x double>%dst, i32 4, <8 x i1>%mask)
67 declare <16 x i32> @llvm.masked.load.v16i32(i8*, <16 x i32>, i32, <16 x i1>)
68 declare void @llvm.masked.store.v16i32(i8*, <16 x i32>, i32, <16 x i1>)
69 declare <16 x float> @llvm.masked.load.v16f32(i8*, <16 x float>, i32, <16 x i1>)
70 declare void @llvm.masked.store.v16f32(i8*, <16 x float>, i32, <16 x i1>)
71 declare <8 x double> @llvm.masked.load.v8f64(i8*, <8 x double>, i32, <8 x i1>)
72 declare void @llvm.masked.store.v8f64(i8*, <8 x double>, i32, <8 x i1>)