maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][SSE] Add pblendw commuted load test case 

Reduced test case for the regression caused in D57888/rL353610

llvm-svn: 354360
This commit is contained in:
Simon Pilgrim 2019-02-19 17:56:14 +00:00
parent 04e45e9311
commit e31838f88b
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/test/CodeGen/X86/commute-blend-sse41.ll
View File

@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s
define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) #0 {
define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) {
; CHECK-LABEL: commute_fold_pblendw:
; CHECK: # %bb.0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
@ -12,7 +12,7 @@ define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) #0 {
}
declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) #0 {
define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) {
; CHECK-LABEL: commute_fold_blendps:
; CHECK: # %bb.0:
; CHECK-NEXT: blendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3]
@ -23,7 +23,7 @@ define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) #0 {
}
declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) #0 {
define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) {
; CHECK-LABEL: commute_fold_blendpd:
; CHECK: # %bb.0:
; CHECK-NEXT: blendps {{.*#+}} xmm0 = xmm0[0,1],mem[2,3]
@ -33,3 +33,15 @@ define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) #0
ret <2 x double> %2
}
declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
define <4 x i32> @commute_fold_blend_v4i32(<4 x i32>* %a, <4 x i32> %b) {
; CHECK-LABEL: commute_fold_blend_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: paddd %xmm0, %xmm0 ; force integer domain
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = mem[0,1,2,3,4,5],xmm0[6,7]
; CHECK-NEXT: retq
%1 = load <4 x i32>, <4 x i32>* %a
%2 = add <4 x i32> %b, %b
%3 = shufflevector <4 x i32> %1, <4 x i32> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 7>
ret <4 x i32> %3
}