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

[X86][AVX] Added combine test that should simplify to insertps 

llvm-svn: 274884
This commit is contained in:
Simon Pilgrim 2016-07-08 17:01:42 +00:00
parent cbfca9e8ef
commit b600ba3b79
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
View File

@ -186,3 +186,13 @@ define <8 x float> @combine_vpermilvar_8f32_4stage(<8 x float> %a0) {
%4 = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %3, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>)
ret <8 x float> %4
}
define <4 x float> @combine_vpermilvar_4f32_as_insertps(<4 x float> %a0) {
; ALL-LABEL: combine_vpermilvar_4f32_as_insertps:
; ALL: # BB#0:
; ALL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,6,7],zero,zero,zero,zero,xmm0[8,9,10,11],zero,zero,zero,zero
; ALL-NEXT: retq
%1 = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> <i32 3, i32 2, i32 1, i32 0>)
%2 = shufflevector <4 x float> %1, <4 x float> zeroinitializer, <4 x i32> <i32 2, i32 4, i32 1, i32 4>
ret <4 x float> %2
}