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

[X86][AVX] Add extra 'interleaved+lanepermute' shuffle test 

Possible missed opportunity to use 64-bit lane permute on AVX1 in lowerShuffleAsRepeatedMaskAndLanePermute

llvm-svn: 322628
This commit is contained in:
Simon Pilgrim 2018-01-17 10:56:54 +00:00
parent 2421b6fa5c
commit 1bea16f5d2
1 changed files with 51 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
View File

@ -927,6 +927,57 @@ define <8 x float> @shuffle_v8f32_a2u3e6f7(<8 x float> %a, <8 x float> %b) {
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_084c195d(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_084c195d:
; AVX1: # %bb.0:
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*#+}} ymm2 = ymm2[0,1,2,0,4,5,6,4]
; AVX1-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,0,2,1,4,4,6,5]
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1],ymm2[2,3,4,5],ymm1[6,7]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*#+}} ymm2 = ymm2[1,1,0,3,5,5,4,7]
; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,1,1,3,4,5,5,7]
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm2[2,3,4,5],ymm0[6,7]
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_084c195d:
; AVX2: # %bb.0:
; AVX2-NEXT: vunpcklps {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: retq
;
; AVX512VL-SLOW-LABEL: shuffle_v8f32_084c195d:
; AVX512VL-SLOW: # %bb.0:
; AVX512VL-SLOW-NEXT: vunpcklps {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
; AVX512VL-SLOW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512VL-SLOW-NEXT: retq
;
; AVX512VL-FAST-LABEL: shuffle_v8f32_084c195d:
; AVX512VL-FAST: # %bb.0:
; AVX512VL-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [0,8,4,12,1,9,5,13]
; AVX512VL-FAST-NEXT: vpermt2ps %ymm1, %ymm2, %ymm0
; AVX512VL-FAST-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 4, i32 12, i32 1, i32 9, i32 5, i32 13>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_01452367d(<8 x float> %a) {
; AVX1-LABEL: shuffle_v8f32_01452367d:
; AVX1: # %bb.0:
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilpd {{.*#+}} ymm1 = ymm1[0,0,3,2]
; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3]
; AVX1-NEXT: retq
;
; AVX2OR512VL-LABEL: shuffle_v8f32_01452367d:
; AVX2OR512VL: # %bb.0:
; AVX2OR512VL-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2OR512VL-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 0, i32 1, i32 4, i32 5, i32 2, i32 3, i32 6, i32 7>
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: