replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[X86][SSE] Fix insertps load combine test name 

The existing test was called extract_lane_insertps_5123 but it was in fact doing a <6,1,2,3> shuffle. I've fixed the name and added the <5,1,2,3> test case as well.

llvm-svn: 342328
This commit is contained in:
Simon Pilgrim 2018-09-15 16:57:04 +00:00
parent fe0b973fbf
commit fc4c26485c
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
llvm/test/CodeGen/X86/insertps-combine.ll
View File

@ -274,6 +274,22 @@ define float @extract_lane_insertps_5123(<4 x float> %a0, <4 x float> *%p1) {
; AVX-LABEL: extract_lane_insertps_5123:
; AVX: # %bb.0:
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT: retq
%a1 = load <4 x float>, <4 x float> *%p1
%res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 64)
%ext = extractelement <4 x float> %res, i32 0
ret float %ext
}
define float @extract_lane_insertps_6123(<4 x float> %a0, <4 x float> *%p1) {
; SSE-LABEL: extract_lane_insertps_6123:
; SSE: # %bb.0:
; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: retq
;
; AVX-LABEL: extract_lane_insertps_6123:
; AVX: # %bb.0:
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT: retq
%a1 = load <4 x float>, <4 x float> *%p1
%res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 128)