1 ; RUN: llc -O3 -mtriple=x86_64-unknown -mcpu=corei7 < %s | FileCheck %s 2 3 define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) #0 { 4 %1 = load <8 x i16>, <8 x i16>* %b 5 %2 = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %1, <8 x i16> %a, i8 17) 6 ret <8 x i16> %2 7 8 ;LABEL: commute_fold_pblendw 9 ;CHECK: pblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7] 10 ;CHECK-NEXT: retq 11 } 12 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone 13 14 define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) #0 { 15 %1 = load <4 x float>, <4 x float>* %b 16 %2 = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %1, <4 x float> %a, i8 5) 17 ret <4 x float> %2 18 19 ;LABEL: commute_fold_blendps 20 ;CHECK: blendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3] 21 ;CHECK-NEXT: retq 22 } 23 declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone 24 25 define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) #0 { 26 %1 = load <2 x double>, <2 x double>* %b 27 %2 = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %1, <2 x double> %a, i8 1) 28 ret <2 x double> %2 29 30 ;LABEL: commute_fold_vblendpd 31 ;CHECK: blendpd {{.*#+}} xmm0 = xmm0[0],mem[1] 32 ;CHECK-NEXT: retq 33 } 34 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone 35