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

[X86][AVX] Add tests for v8f32/v8i32 089abcde and 0189abcd shuffles 

Mentioned in D66004
This commit is contained in:
Simon Pilgrim 2020-01-10 10:28:54 +00:00
parent 2e66405d8d
commit 3804ac63d5
1 changed files with 118 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

118
llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
View File

@ -1167,6 +1167,66 @@ define <8 x float> @shuffle_v8f32_01452367d(<8 x float> %a) {
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_089abcde(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_089abcde:
; AVX1: # %bb.0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm1[0,0,1,2]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vblendps {{.*#+}} xmm1 = xmm3[0,1,2],xmm1[3]
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,0,1,2]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_089abcde:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,0,1,2,3,4,5,6>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4,5,6,7]
; AVX2-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v8f32_089abcde:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovaps {{.*#+}} ymm2 = [8,0,1,2,3,4,5,6]
; 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 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_0189abcd(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_0189abcd:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vshufpd {{.*#+}} xmm2 = xmm1[1],xmm2[0]
; AVX1-NEXT: vmovddup {{.*#+}} xmm1 = xmm1[0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_0189abcd:
; AVX2: # %bb.0:
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,0,1,2]
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
; AVX2-NEXT: retq
;
; AVX512VL-SLOW-LABEL: shuffle_v8f32_0189abcd:
; AVX512VL-SLOW: # %bb.0:
; AVX512VL-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,0,1,2]
; AVX512VL-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
; AVX512VL-SLOW-NEXT: retq
;
; AVX512VL-FAST-LABEL: shuffle_v8f32_0189abcd:
; AVX512VL-FAST: # %bb.0:
; AVX512VL-FAST-NEXT: vmovapd {{.*#+}} ymm2 = [4,0,1,2]
; AVX512VL-FAST-NEXT: vpermi2pd %ymm0, %ymm1, %ymm2
; AVX512VL-FAST-NEXT: vmovapd %ymm2, %ymm0
; AVX512VL-FAST-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13>
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:
@ -2415,6 +2475,64 @@ define <8 x i32> @shuffle_v8i32_ba983210(<8 x i32> %a, <8 x i32> %b) {
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_089abcde(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_089abcde:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpalignr {{.*#+}} xmm2 = xmm1[12,13,14,15],xmm2[0,1,2,3,4,5,6,7,8,9,10,11]
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,1,2]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_089abcde:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,0,1,2,3,4,5,6>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4,5,6,7]
; AVX2-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v8i32_089abcde:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: valignd {{.*#+}} ymm1 = ymm1[7,0,1,2,3,4,5,6]
; AVX512VL-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4,5,6,7]
; AVX512VL-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_0189abcd(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_0189abcd:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpalignr {{.*#+}} xmm2 = xmm1[8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,1]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_0189abcd:
; AVX2: # %bb.0:
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,0,1,2]
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
; AVX2-NEXT: retq
;
; AVX512VL-SLOW-LABEL: shuffle_v8i32_0189abcd:
; AVX512VL-SLOW: # %bb.0:
; AVX512VL-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,0,1,2]
; AVX512VL-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
; AVX512VL-SLOW-NEXT: retq
;
; AVX512VL-FAST-LABEL: shuffle_v8i32_0189abcd:
; AVX512VL-FAST: # %bb.0:
; AVX512VL-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [4,0,1,2]
; AVX512VL-FAST-NEXT: vpermi2q %ymm0, %ymm1, %ymm2
; AVX512VL-FAST-NEXT: vmovdqa %ymm2, %ymm0
; AVX512VL-FAST-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_zuu8zuuc(<8 x i32> %a) {
; AVX1-LABEL: shuffle_v8i32_zuu8zuuc:
; AVX1: # %bb.0: