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

[x86] add tests for fmul/fdiv with identity constant in select arm; NFC

This commit is contained in:
Sanjay Patel 2022-02-01 15:28:21 -05:00
parent 8191472246
commit 267400c9b0
1 changed files with 252 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

252
llvm/test/CodeGen/X86/vector-bo-select.ll
View File

@ -253,6 +253,258 @@ define <16 x float> @fsub_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef
ret <16 x float> %r
}
define <4 x float> @fmul_v4f32(<4 x i1> %b, <4 x float> noundef %x, <4 x float> noundef %y) {
; AVX2-LABEL: fmul_v4f32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
; AVX2-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fmul_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fmul_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512VL-NEXT: vmovaps %xmm2, %xmm0 {%k1}
; AVX512VL-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX512VL-NEXT: retq
%s = select <4 x i1> %b, <4 x float> %y, <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>
%r = fmul <4 x float> %x, %s
ret <4 x float> %r
}
define <8 x float> @fmul_v8f32_commute(<8 x i1> %b, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fmul_v8f32_commute:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm0, %ymm2, %ymm3, %ymm0
; AVX2-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fmul_v8f32_commute:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm2 killed $ymm2 def $zmm2
; AVX512F-NEXT: vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fmul_v8f32_commute:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512VL-NEXT: vmovaps %ymm2, %ymm0 {%k1}
; AVX512VL-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX512VL-NEXT: retq
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
%r = fmul <8 x float> %s, %x
ret <8 x float> %r
}
define <16 x float> @fmul_v16f32_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fmul_v16f32_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vmulps %ymm3, %ymm1, %ymm0
; AVX2-NEXT: vmulps %ymm4, %ymm2, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fmul_v16f32_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vbroadcastss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %zmm2 {%k1}
; AVX512-NEXT: vmulps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fmul <16 x float> %x, %s
ret <16 x float> %r
}
define <16 x float> @fmul_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fmul_v16f32_commute_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vmulps %ymm1, %ymm3, %ymm0
; AVX2-NEXT: vmulps %ymm2, %ymm4, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fmul_v16f32_commute_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vbroadcastss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %zmm2 {%k1}
; AVX512-NEXT: vmulps %zmm1, %zmm2, %zmm0
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fmul <16 x float> %s, %x
ret <16 x float> %r
}
define <4 x float> @fdiv_v4f32(<4 x i1> %b, <4 x float> noundef %x, <4 x float> noundef %y) {
; AVX2-LABEL: fdiv_v4f32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
; AVX2-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fdiv_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fdiv_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512VL-NEXT: vmovaps %xmm2, %xmm0 {%k1}
; AVX512VL-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX512VL-NEXT: retq
%s = select <4 x i1> %b, <4 x float> %y, <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>
%r = fdiv <4 x float> %x, %s
ret <4 x float> %r
}
define <8 x float> @fdiv_v8f32_commute(<8 x i1> %b, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fdiv_v8f32_commute:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm0, %ymm2, %ymm3, %ymm0
; AVX2-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fdiv_v8f32_commute:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm2 killed $ymm2 def $zmm2
; AVX512F-NEXT: vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fdiv_v8f32_commute:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512VL-NEXT: vmovaps %ymm2, %ymm0 {%k1}
; AVX512VL-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX512VL-NEXT: retq
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
%r = fdiv <8 x float> %s, %x
ret <8 x float> %r
}
define <16 x float> @fdiv_v16f32_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fdiv_v16f32_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vdivps %ymm3, %ymm1, %ymm0
; AVX2-NEXT: vdivps %ymm4, %ymm2, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fdiv_v16f32_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vbroadcastss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %zmm2 {%k1}
; AVX512-NEXT: vdivps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fdiv <16 x float> %x, %s
ret <16 x float> %r
}
define <16 x float> @fdiv_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fdiv_v16f32_commute_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vdivps %ymm1, %ymm3, %ymm0
; AVX2-NEXT: vdivps %ymm2, %ymm4, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fdiv_v16f32_commute_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vbroadcastss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %zmm2 {%k1}
; AVX512-NEXT: vdivps %zmm1, %zmm2, %zmm0
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fdiv <16 x float> %s, %x
ret <16 x float> %r
}
define <8 x float> @fadd_v8f32_cast_cond(i8 noundef zeroext %pb, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fadd_v8f32_cast_cond:
; AVX2: # %bb.0: