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

[X86][SSE] Add PR30371 (shuffle constant folding) test case 

llvm-svn: 283103
This commit is contained in:
Simon Pilgrim 2016-10-03 12:16:39 +00:00
parent 2bc02892be
commit 52ab136881
1 changed files with 40 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
llvm/test/CodeGen/X86/vector-shuffle-combining.ll
View File

@ -2835,6 +2835,46 @@ define void @combine_scalar_load_with_blend_with_zero(double* %a0, <4 x float>*
ret void
}
; PR30371
define <4 x float> @combine_constant_insertion(float %f) {
; SSE2-LABEL: combine_constant_insertion:
; SSE2: # BB#0:
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: combine_constant_insertion:
; SSSE3: # BB#0:
; SSSE3-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSSE3-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSSE3-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSSE3-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: combine_constant_insertion:
; SSE41: # BB#0:
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; SSE41-NEXT: retq
;
; AVX-LABEL: combine_constant_insertion:
; AVX: # BB#0:
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; AVX-NEXT: retq
%a0 = insertelement <4 x float> undef, float %f, i32 0
%ret = shufflevector <4 x float> %a0, <4 x float> <float undef, float 4.0, float 5.0, float 3.0>, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %ret
}
define <4 x float> @PR22377(<4 x float> %a, <4 x float> %b) {
; SSE-LABEL: PR22377:
; SSE: # BB#0: # %entry