1 ; RUN: llc -O3 -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=avx2 < %s | FileCheck %s
3 define <8 x i16> @commute_fold_vpblendw_128(<8 x i16> %a, <8 x i16>* %b) #0 {
4 %1 = load <8 x i16>* %b
5 %2 = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %1, <8 x i16> %a, i8 17)
8 ;LABEL: commute_fold_vpblendw_128
9 ;CHECK: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
12 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
14 define <16 x i16> @commute_fold_vpblendw_256(<16 x i16> %a, <16 x i16>* %b) #0 {
15 %1 = load <16 x i16>* %b
16 %2 = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %1, <16 x i16> %a, i8 17)
19 ;LABEL: commute_fold_vpblendw_256
20 ;CHECK: vpblendw {{.*#+}} ymm0 = ymm0[0],mem[1,2,3],ymm0[4],mem[5,6,7],ymm0[8],mem[9,10,11],ymm0[12],mem[13,14,15]
23 declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i8) nounwind readnone
25 define <4 x i32> @commute_fold_vpblendd_128(<4 x i32> %a, <4 x i32>* %b) #0 {
26 %1 = load <4 x i32>* %b
27 %2 = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %1, <4 x i32> %a, i8 1)
30 ;LABEL: commute_fold_vpblendd_128
31 ;CHECK: vpblendd {{.*#+}} xmm0 = xmm0[0],mem[1,2,3]
34 declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i8) nounwind readnone
36 define <8 x i32> @commute_fold_vpblendd_256(<8 x i32> %a, <8 x i32>* %b) #0 {
37 %1 = load <8 x i32>* %b
38 %2 = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %1, <8 x i32> %a, i8 129)
41 ;LABEL: commute_fold_vpblendd_256
42 ;CHECK: vpblendd {{.*#+}} ymm0 = ymm0[0],mem[1,2,3,4,5,6],ymm0[7]
45 declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
47 define <4 x float> @commute_fold_vblendps_128(<4 x float> %a, <4 x float>* %b) #0 {
48 %1 = load <4 x float>* %b
49 %2 = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %1, <4 x float> %a, i8 3)
52 ;LABEL: commute_fold_vblendps_128
53 ;CHECK: vblendps {{.*#+}} xmm0 = xmm0[0,1],mem[2,3]
56 declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
58 define <8 x float> @commute_fold_vblendps_256(<8 x float> %a, <8 x float>* %b) #0 {
59 %1 = load <8 x float>* %b
60 %2 = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %1, <8 x float> %a, i8 7)
63 ;LABEL: commute_fold_vblendps_256
64 ;CHECK: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],mem[3,4,5,6,7]
67 declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
69 define <2 x double> @commute_fold_vblendpd_128(<2 x double> %a, <2 x double>* %b) #0 {
70 %1 = load <2 x double>* %b
71 %2 = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %1, <2 x double> %a, i8 1)
74 ;LABEL: commute_fold_vblendpd_128
75 ;CHECK: vblendpd {{.*#+}} xmm0 = xmm0[0],mem[1]
78 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
80 define <4 x double> @commute_fold_vblendpd_256(<4 x double> %a, <4 x double>* %b) #0 {
81 %1 = load <4 x double>* %b
82 %2 = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %1, <4 x double> %a, i8 7)
85 ;LABEL: commute_fold_vblendpd_256
86 ;CHECK: vblendpd {{.*#+}} ymm0 = ymm0[0,1,2],mem[3]
89 declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone