OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[X86][SSE] Test insertps instrinsic calls with masks that can't combine to something simpler 

For these basic tests of the intrinsic, make sure the mask can't simplify to movss, blend-with-zero or something else

llvm-svn: 258941
This commit is contained in:
Simon Pilgrim 2016-01-27 16:51:57 +00:00
parent 0e92f24880
commit a73a0cfaf4
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
View File

@ -1111,9 +1111,9 @@ declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i8) nounwind
define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
; CHECK-LABEL: test_x86_sse41_insertps:
; CHECK: ## BB#0:
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = zero,zero,zero,xmm0[3]
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = zero,xmm1[0],zero,xmm0[3]
; CHECK-NEXT: retl
%res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
%res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 21) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
@ -2992,7 +2992,7 @@ declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i64>) no
define <4 x double> @test_x86_avx_vpermilvar_pd_256_2(<4 x double> %a0) {
; CHECK-LABEL: test_x86_avx_vpermilvar_pd_256_2:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermilpd {{.*}}, %ymm0, %ymm0 ## ymm0 = ymm0[1,0,2,3]
; CHECK-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,3]
; CHECK-NEXT: retl
%res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> <i64 2, i64 0, i64 0, i64 2>) ; <<4 x double>> [#uses=1]
ret <4 x double> %res

6
llvm/test/CodeGen/X86/sse41.ll
View File

@ -141,14 +141,14 @@ define i32 @ext_3(<4 x i32> %v) nounwind {
define <4 x float> @insertps_1(<4 x float> %t1, <4 x float> %t2) nounwind {
; X32-LABEL: insertps_1:
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = zero,xmm0[1,2,3]
; X32-NEXT: insertps {{.*#+}} xmm0 = zero,xmm1[0],zero,xmm0[3]
; X32-NEXT: retl
;
; X64-LABEL: insertps_1:
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = zero,xmm0[1,2,3]
; X64-NEXT: insertps {{.*#+}} xmm0 = zero,xmm1[0],zero,xmm0[3]
; X64-NEXT: retq
%tmp1 = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %t1, <4 x float> %t2, i32 1) nounwind readnone
%tmp1 = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %t1, <4 x float> %t2, i32 21) nounwind readnone
ret <4 x float> %tmp1
}