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

[X86][AVX] Add v8f32/v8i32 01289abc test case 

Blend Insertion + Element Rotation pattern similar to Issue #53124
This commit is contained in:
Simon Pilgrim 2022-01-13 11:37:37 +00:00
parent 7c56458616
commit 4f19bb6f28
1 changed files with 67 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
View File

@ -1399,6 +1399,34 @@ define <8 x float> @shuffle_v8f32_0189abcd(<8 x float> %a, <8 x float> %b) {
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_01289abc(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_01289abc:
; AVX1: # %bb.0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm1[0,0,0,0]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vblendps {{.*#+}} xmm1 = xmm3[0],xmm1[1,2,3]
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[1,2,3,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_01289abc:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,u,0,1,2,3,4>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
; AVX2-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v8f32_01289abc:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovaps {{.*#+}} ymm2 = [8,9,10,0,1,2,3,4]
; AVX512VL-NEXT: vpermi2ps %ymm0, %ymm1, %ymm2
; AVX512VL-NEXT: vmovaps %ymm2, %ymm0
; AVX512VL-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 9, i32 10, i32 11, i32 12>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_uuuu1111(<8 x float> %a, <8 x float> %b) {
; ALL-LABEL: shuffle_v8f32_uuuu1111:
; ALL: # %bb.0:
@ -2923,6 +2951,45 @@ define <8 x i32> @shuffle_v8i32_0189abcd(<8 x i32> %a, <8 x i32> %b) {
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_01289abc(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_01289abc:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpalignr {{.*#+}} xmm2 = xmm1[4,5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3]
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_01289abc:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,u,0,1,2,3,4>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
; AVX2-NEXT: retq
;
; AVX512VL-SLOW-LABEL: shuffle_v8i32_01289abc:
; AVX512VL-SLOW: # %bb.0:
; AVX512VL-SLOW-NEXT: valignd {{.*#+}} ymm1 = ymm1[5,6,7,0,1,2,3,4]
; AVX512VL-SLOW-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
; AVX512VL-SLOW-NEXT: retq
;
; AVX512VL-FAST-ALL-LABEL: shuffle_v8i32_01289abc:
; AVX512VL-FAST-ALL: # %bb.0:
; AVX512VL-FAST-ALL-NEXT: vmovdqa {{.*#+}} ymm2 = [8,9,10,0,1,2,3,4]
; AVX512VL-FAST-ALL-NEXT: vpermi2d %ymm0, %ymm1, %ymm2
; AVX512VL-FAST-ALL-NEXT: vmovdqa %ymm2, %ymm0
; AVX512VL-FAST-ALL-NEXT: retq
;
; AVX512VL-FAST-PERLANE-LABEL: shuffle_v8i32_01289abc:
; AVX512VL-FAST-PERLANE: # %bb.0:
; AVX512VL-FAST-PERLANE-NEXT: valignd {{.*#+}} ymm1 = ymm1[5,6,7,0,1,2,3,4]
; AVX512VL-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
; AVX512VL-FAST-PERLANE-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 9, i32 10, i32 11, i32 12>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_zuu8zuuc(<8 x i32> %a) {
; AVX1-LABEL: shuffle_v8i32_zuu8zuuc:
; AVX1: # %bb.0: