forked from OSchip/llvm-project
634 lines
52 KiB
LLVM
634 lines
52 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck --check-prefixes=AVX2-SLOW %s
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck --check-prefixes=AVX2-FAST,AVX2-FAST-ALL %s
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck --check-prefixes=AVX2-FAST,AVX2-FAST-PERLANE %s
|
|
|
|
; These patterns are produced by LoopVectorizer for interleaved stores.
|
|
|
|
define void @vf2(<2 x i16>* %in.vecptr0, <2 x i16>* %in.vecptr1, <2 x i16>* %in.vecptr2, <2 x i16>* %in.vecptr3, <2 x i16>* %in.vecptr4, <2 x i16>* %in.vecptr5, <12 x i16>* %out.vec) nounwind {
|
|
; AVX2-SLOW-LABEL: vf2:
|
|
; AVX2-SLOW: # %bb.0:
|
|
; AVX2-SLOW-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdx), %xmm1
|
|
; AVX2-SLOW-NEXT: vmovdqa (%r8), %xmm2
|
|
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
|
|
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[1],mem[1]
|
|
; AVX2-SLOW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],mem[0],xmm2[1],mem[1]
|
|
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm1 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,2,3,6,7,u,u,u,u,18,19,22,23,u,u,u,u,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
|
|
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} ymm0 = ymm0[1,3,2,3,4,5,6,7,9,11,10,11,12,13,14,15]
|
|
; AVX2-SLOW-NEXT: vpshufhw {{.*#+}} ymm0 = ymm0[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3],ymm0[4],ymm1[5,6,7]
|
|
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-SLOW-NEXT: vmovq %xmm1, 16(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %xmm0, (%rax)
|
|
; AVX2-SLOW-NEXT: vzeroupper
|
|
; AVX2-SLOW-NEXT: retq
|
|
;
|
|
; AVX2-FAST-LABEL: vf2:
|
|
; AVX2-FAST: # %bb.0:
|
|
; AVX2-FAST-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX2-FAST-NEXT: vmovdqa (%rdx), %xmm1
|
|
; AVX2-FAST-NEXT: vmovdqa (%r8), %xmm2
|
|
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
|
|
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[1],mem[1]
|
|
; AVX2-FAST-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],mem[0],xmm2[1],mem[1]
|
|
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX2-FAST-NEXT: vpshufb {{.*#+}} ymm1 = ymm0[0,1,4,5,8,9,12,13,u,u,u,u,2,3,6,7,u,u,u,u,18,19,22,23,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
|
|
; AVX2-FAST-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,8,9,12,13,u,u,u,u,18,19,22,23,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3],ymm0[4],ymm1[5,6,7]
|
|
; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-FAST-NEXT: vmovq %xmm1, 16(%rax)
|
|
; AVX2-FAST-NEXT: vmovdqa %xmm0, (%rax)
|
|
; AVX2-FAST-NEXT: vzeroupper
|
|
; AVX2-FAST-NEXT: retq
|
|
%in.vec0 = load <2 x i16>, <2 x i16>* %in.vecptr0, align 32
|
|
%in.vec1 = load <2 x i16>, <2 x i16>* %in.vecptr1, align 32
|
|
%in.vec2 = load <2 x i16>, <2 x i16>* %in.vecptr2, align 32
|
|
%in.vec3 = load <2 x i16>, <2 x i16>* %in.vecptr3, align 32
|
|
%in.vec4 = load <2 x i16>, <2 x i16>* %in.vecptr4, align 32
|
|
%in.vec5 = load <2 x i16>, <2 x i16>* %in.vecptr5, align 32
|
|
|
|
%concat01 = shufflevector <2 x i16> %in.vec0, <2 x i16> %in.vec1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%concat23 = shufflevector <2 x i16> %in.vec2, <2 x i16> %in.vec3, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%concat45 = shufflevector <2 x i16> %in.vec4, <2 x i16> %in.vec5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%concat0123 = shufflevector <4 x i16> %concat01, <4 x i16> %concat23, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%concat45uu = shufflevector <4 x i16> %concat45, <4 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%concat012345 = shufflevector <8 x i16> %concat0123, <8 x i16> %concat45uu, <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
|
|
%interleaved.vec = shufflevector <12 x i16> %concat012345, <12 x i16> poison, <12 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11>
|
|
|
|
store <12 x i16> %interleaved.vec, <12 x i16>* %out.vec, align 32
|
|
|
|
ret void
|
|
}
|
|
|
|
define void @vf4(<4 x i16>* %in.vecptr0, <4 x i16>* %in.vecptr1, <4 x i16>* %in.vecptr2, <4 x i16>* %in.vecptr3, <4 x i16>* %in.vecptr4, <4 x i16>* %in.vecptr5, <24 x i16>* %out.vec) nounwind {
|
|
; AVX2-SLOW-LABEL: vf4:
|
|
; AVX2-SLOW: # %bb.0:
|
|
; AVX2-SLOW-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX2-SLOW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX2-SLOW-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX2-SLOW-NEXT: vmovq {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm4
|
|
; AVX2-SLOW-NEXT: vpunpcklqdq {{.*#+}} xmm5 = xmm2[0],xmm3[0]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm6 = ymm4[0,1,8,9,u,u,u,u,u,u,u,u,2,3,10,11,18,19,26,27,u,u,u,u,u,u,u,u,20,21,28,29]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm4[2,3,0,1]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,0,1,8,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm4 = ymm6[0],ymm4[1],ymm6[2,3,4,5],ymm4[6],ymm6[7]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
|
|
; AVX2-SLOW-NEXT: vpbroadcastq %xmm2, %ymm2
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm2 = ymm4[0,1],ymm2[2],ymm4[3,4],ymm2[5],ymm4[6,7]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
|
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
|
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,1,3,1,4,5,6,7]
|
|
; AVX2-SLOW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} xmm1 = xmm5[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1,2],xmm1[3]
|
|
; AVX2-SLOW-NEXT: vmovdqa %xmm0, 32(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm2, (%rax)
|
|
; AVX2-SLOW-NEXT: vzeroupper
|
|
; AVX2-SLOW-NEXT: retq
|
|
;
|
|
; AVX2-FAST-ALL-LABEL: vf4:
|
|
; AVX2-FAST-ALL: # %bb.0:
|
|
; AVX2-FAST-ALL-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-ALL-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX2-FAST-ALL-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-FAST-ALL-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX2-FAST-ALL-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX2-FAST-ALL-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX2-FAST-ALL-NEXT: vmovq {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX2-FAST-ALL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm4
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklqdq {{.*#+}} xmm5 = xmm2[0],xmm3[0]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm6 = ymm4[0,1,8,9,u,u,u,u,u,u,u,u,2,3,10,11,18,19,26,27,u,u,u,u,u,u,u,u,20,21,28,29]
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm7 = [4,6,1,3,4,6,1,3]
|
|
; AVX2-FAST-ALL-NEXT: # ymm7 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm4, %ymm7, %ymm4
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,0,1,4,5,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,24,25,28,29,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm4 = ymm6[0],ymm4[1],ymm6[2,3,4,5],ymm4[6],ymm6[7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
|
|
; AVX2-FAST-ALL-NEXT: vpbroadcastq %xmm2, %ymm2
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm2 = ymm4[0,1],ymm2[2],ymm4[3,4],ymm2[5],ymm4[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[6,7,14,15,4,5,6,7,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[12,13,14,15,6,7,14,15,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} xmm1 = xmm5[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1,2],xmm1[3]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %xmm0, 32(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm2, (%rax)
|
|
; AVX2-FAST-ALL-NEXT: vzeroupper
|
|
; AVX2-FAST-ALL-NEXT: retq
|
|
;
|
|
; AVX2-FAST-PERLANE-LABEL: vf4:
|
|
; AVX2-FAST-PERLANE: # %bb.0:
|
|
; AVX2-FAST-PERLANE-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-PERLANE-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX2-FAST-PERLANE-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX2-FAST-PERLANE-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX2-FAST-PERLANE-NEXT: vmovq {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX2-FAST-PERLANE-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm4
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklqdq {{.*#+}} xmm5 = xmm2[0],xmm3[0]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm6 = ymm4[0,1,8,9,u,u,u,u,u,u,u,u,2,3,10,11,18,19,26,27,u,u,u,u,u,u,u,u,20,21,28,29]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm4 = ymm4[2,3,0,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,0,1,8,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm4 = ymm6[0],ymm4[1],ymm6[2,3,4,5],ymm4[6],ymm6[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq %xmm2, %ymm2
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm2 = ymm4[0,1],ymm2[2],ymm4[3,4],ymm2[5],ymm4[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[6,7,14,15,4,5,6,7,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[12,13,14,15,6,7,14,15,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} xmm1 = xmm5[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1,2],xmm1[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %xmm0, 32(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm2, (%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vzeroupper
|
|
; AVX2-FAST-PERLANE-NEXT: retq
|
|
%in.vec0 = load <4 x i16>, <4 x i16>* %in.vecptr0, align 32
|
|
%in.vec1 = load <4 x i16>, <4 x i16>* %in.vecptr1, align 32
|
|
%in.vec2 = load <4 x i16>, <4 x i16>* %in.vecptr2, align 32
|
|
%in.vec3 = load <4 x i16>, <4 x i16>* %in.vecptr3, align 32
|
|
%in.vec4 = load <4 x i16>, <4 x i16>* %in.vecptr4, align 32
|
|
%in.vec5 = load <4 x i16>, <4 x i16>* %in.vecptr5, align 32
|
|
|
|
%concat01 = shufflevector <4 x i16> %in.vec0, <4 x i16> %in.vec1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%concat23 = shufflevector <4 x i16> %in.vec2, <4 x i16> %in.vec3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%concat45 = shufflevector <4 x i16> %in.vec4, <4 x i16> %in.vec5, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%concat0123 = shufflevector <8 x i16> %concat01, <8 x i16> %concat23, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%concat45uu = shufflevector <8 x i16> %concat45, <8 x i16> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%concat012345 = shufflevector <16 x i16> %concat0123, <16 x i16> %concat45uu, <24 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
|
|
%interleaved.vec = shufflevector <24 x i16> %concat012345, <24 x i16> poison, <24 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 3, i32 7, i32 11, i32 15, i32 19, i32 23>
|
|
|
|
store <24 x i16> %interleaved.vec, <24 x i16>* %out.vec, align 32
|
|
|
|
ret void
|
|
}
|
|
|
|
define void @vf8(<8 x i16>* %in.vecptr0, <8 x i16>* %in.vecptr1, <8 x i16>* %in.vecptr2, <8 x i16>* %in.vecptr3, <8 x i16>* %in.vecptr4, <8 x i16>* %in.vecptr5, <48 x i16>* %out.vec) nounwind {
|
|
; AVX2-SLOW-LABEL: vf8:
|
|
; AVX2-SLOW: # %bb.0:
|
|
; AVX2-SLOW-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdx), %xmm1
|
|
; AVX2-SLOW-NEXT: vmovdqa (%r8), %xmm2
|
|
; AVX2-SLOW-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm1[0,2,0,2]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm3 = ymm3[u,u,u,u,0,1,8,9,u,u,u,u,u,u,u,u,18,19,26,27,u,u,u,u,u,u,u,u,20,21,28,29]
|
|
; AVX2-SLOW-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm0[0,2,0,2]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[0,1,8,9,u,u,u,u,u,u,u,u,2,3,10,11,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1],ymm4[2,3],ymm3[4],ymm4[5,6],ymm3[7]
|
|
; AVX2-SLOW-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm2[0,2,0,2]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,u,u,u,u,0,1,8,9,u,u,u,u,u,u,u,u,18,19,26,27,u,u,u,u,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm0[0,2,1,3]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u,u,u,u,u,18,19,26,27]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm5 = ymm2[0,2,1,3]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm5 = ymm5[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm4 = ymm5[0],ymm4[1],ymm5[2,3],ymm4[4],ymm5[5,6],ymm4[7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm5 = ymm1[0,2,1,3]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm5 = ymm5[u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm4 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[1,3,1,3]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm2 = ymm2[u,u,u,u,2,3,10,11,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u,u,u,u,u,22,23,30,31]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[1,3,1,3]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[2,3,10,11,u,u,u,u,u,u,u,u,4,5,12,13,u,u,u,u,u,u,u,u,22,23,30,31,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1],ymm1[2,3],ymm2[4],ymm1[5,6],ymm2[7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[1,3,1,3]
|
|
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,4,5,12,13,u,u,u,u,u,u,u,u,22,23,30,31,u,u,u,u,u,u,u,u]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3,4],ymm0[5],ymm1[6,7]
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm0, 64(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm4, 32(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm3, (%rax)
|
|
; AVX2-SLOW-NEXT: vzeroupper
|
|
; AVX2-SLOW-NEXT: retq
|
|
;
|
|
; AVX2-FAST-ALL-LABEL: vf8:
|
|
; AVX2-FAST-ALL: # %bb.0:
|
|
; AVX2-FAST-ALL-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rdx), %xmm1
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%r8), %xmm2
|
|
; AVX2-FAST-ALL-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,4,1,5,0,4,1,5]
|
|
; AVX2-FAST-ALL-NEXT: # ymm3 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm1, %ymm3, %ymm3
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm3 = ymm3[u,u,u,u,0,1,4,5,u,u,u,u,u,u,u,u,18,19,22,23,u,u,u,u,u,u,u,u,24,25,28,29]
|
|
; AVX2-FAST-ALL-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm4 = ymm0[0,2,0,2]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[0,1,8,9,u,u,u,u,u,u,u,u,2,3,10,11,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1],ymm4[2,3],ymm3[4],ymm4[5,6],ymm3[7]
|
|
; AVX2-FAST-ALL-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm4 = [0,4,4,0,0,4,4,0]
|
|
; AVX2-FAST-ALL-NEXT: # ymm4 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm2, %ymm4, %ymm4
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,u,u,u,u,12,13,8,9,u,u,u,u,u,u,u,u,18,19,22,23,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm4 = ymm0[0,2,1,3]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u,u,u,u,u,18,19,26,27]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm5 = ymm2[0,2,1,3]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm5 = ymm5[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm4 = ymm5[0],ymm4[1],ymm5[2,3],ymm4[4],ymm5[5,6],ymm4[7]
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm5 = [2,6,1,5,2,6,1,5]
|
|
; AVX2-FAST-ALL-NEXT: # ymm5 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm1, %ymm5, %ymm5
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm5 = ymm5[u,u,u,u,u,u,u,u,10,11,14,15,u,u,u,u,u,u,u,u,16,17,20,21,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm4 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm2 = ymm2[1,3,1,3]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm2 = ymm2[u,u,u,u,2,3,10,11,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u,u,u,u,u,22,23,30,31]
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm5 = [2,6,3,7,2,6,3,7]
|
|
; AVX2-FAST-ALL-NEXT: # ymm5 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm1, %ymm5, %ymm1
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[2,3,6,7,u,u,u,u,u,u,u,u,8,9,12,13,u,u,u,u,u,u,u,u,26,27,30,31,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1],ymm1[2,3],ymm2[4],ymm1[5,6],ymm2[7]
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm2 = [7,3,3,7,7,3,3,7]
|
|
; AVX2-FAST-ALL-NEXT: # ymm2 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm0, %ymm2, %ymm0
|
|
; AVX2-FAST-ALL-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,8,9,12,13,u,u,u,u,u,u,u,u,22,23,18,19,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3,4],ymm0[5],ymm1[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm0, 64(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm4, 32(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm3, (%rax)
|
|
; AVX2-FAST-ALL-NEXT: vzeroupper
|
|
; AVX2-FAST-ALL-NEXT: retq
|
|
;
|
|
; AVX2-FAST-PERLANE-LABEL: vf8:
|
|
; AVX2-FAST-PERLANE: # %bb.0:
|
|
; AVX2-FAST-PERLANE-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdx), %xmm1
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%r8), %xmm2
|
|
; AVX2-FAST-PERLANE-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm3 = ymm1[0,2,0,2]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm3 = ymm3[u,u,u,u,0,1,8,9,u,u,u,u,u,u,u,u,18,19,26,27,u,u,u,u,u,u,u,u,20,21,28,29]
|
|
; AVX2-FAST-PERLANE-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm4 = ymm0[0,2,0,2]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[0,1,8,9,u,u,u,u,u,u,u,u,2,3,10,11,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1],ymm4[2,3],ymm3[4],ymm4[5,6],ymm3[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm4 = ymm2[0,2,0,2]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,u,u,u,u,0,1,8,9,u,u,u,u,u,u,u,u,18,19,26,27,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm4 = ymm0[0,2,1,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u,u,u,u,u,18,19,26,27]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm5 = ymm2[0,2,1,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm5 = ymm5[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm4 = ymm5[0],ymm4[1],ymm5[2,3],ymm4[4],ymm5[5,6],ymm4[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm5 = ymm1[0,2,1,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm5 = ymm5[u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm4 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm2 = ymm2[1,3,1,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm2 = ymm2[u,u,u,u,2,3,10,11,u,u,u,u,u,u,u,u,20,21,28,29,u,u,u,u,u,u,u,u,22,23,30,31]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm1 = ymm1[1,3,1,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[2,3,10,11,u,u,u,u,u,u,u,u,4,5,12,13,u,u,u,u,u,u,u,u,22,23,30,31,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1],ymm1[2,3],ymm2[4],ymm1[5,6],ymm2[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm0 = ymm0[1,3,1,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,4,5,12,13,u,u,u,u,u,u,u,u,22,23,30,31,u,u,u,u,u,u,u,u]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3,4],ymm0[5],ymm1[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm0, 64(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm4, 32(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm3, (%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vzeroupper
|
|
; AVX2-FAST-PERLANE-NEXT: retq
|
|
%in.vec0 = load <8 x i16>, <8 x i16>* %in.vecptr0, align 32
|
|
%in.vec1 = load <8 x i16>, <8 x i16>* %in.vecptr1, align 32
|
|
%in.vec2 = load <8 x i16>, <8 x i16>* %in.vecptr2, align 32
|
|
%in.vec3 = load <8 x i16>, <8 x i16>* %in.vecptr3, align 32
|
|
%in.vec4 = load <8 x i16>, <8 x i16>* %in.vecptr4, align 32
|
|
%in.vec5 = load <8 x i16>, <8 x i16>* %in.vecptr5, align 32
|
|
|
|
%concat01 = shufflevector <8 x i16> %in.vec0, <8 x i16> %in.vec1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%concat23 = shufflevector <8 x i16> %in.vec2, <8 x i16> %in.vec3, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%concat45 = shufflevector <8 x i16> %in.vec4, <8 x i16> %in.vec5, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%concat0123 = shufflevector <16 x i16> %concat01, <16 x i16> %concat23, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
|
|
%concat45uu = shufflevector <16 x i16> %concat45, <16 x i16> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%concat012345 = shufflevector <32 x i16> %concat0123, <32 x i16> %concat45uu, <48 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
|
|
%interleaved.vec = shufflevector <48 x i16> %concat012345, <48 x i16> poison, <48 x i32> <i32 0, i32 8, i32 16, i32 24, i32 32, i32 40, i32 1, i32 9, i32 17, i32 25, i32 33, i32 41, i32 2, i32 10, i32 18, i32 26, i32 34, i32 42, i32 3, i32 11, i32 19, i32 27, i32 35, i32 43, i32 4, i32 12, i32 20, i32 28, i32 36, i32 44, i32 5, i32 13, i32 21, i32 29, i32 37, i32 45, i32 6, i32 14, i32 22, i32 30, i32 38, i32 46, i32 7, i32 15, i32 23, i32 31, i32 39, i32 47>
|
|
|
|
store <48 x i16> %interleaved.vec, <48 x i16>* %out.vec, align 32
|
|
|
|
ret void
|
|
}
|
|
|
|
define void @vf16(<16 x i16>* %in.vecptr0, <16 x i16>* %in.vecptr1, <16 x i16>* %in.vecptr2, <16 x i16>* %in.vecptr3, <16 x i16>* %in.vecptr4, <16 x i16>* %in.vecptr5, <96 x i16>* %out.vec) nounwind {
|
|
; AVX2-SLOW-LABEL: vf16:
|
|
; AVX2-SLOW: # %bb.0:
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm10
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rsi), %ymm11
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdx), %ymm12
|
|
; AVX2-SLOW-NEXT: vmovdqa (%r8), %ymm14
|
|
; AVX2-SLOW-NEXT: vmovdqa (%r9), %ymm15
|
|
; AVX2-SLOW-NEXT: vmovdqa (%r9), %xmm9
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm9[1,2,2,3]
|
|
; AVX2-SLOW-NEXT: vmovdqa (%r8), %xmm7
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm7[1,2,2,3]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm0[0,0,2,1]
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rsi), %xmm5
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm5[0,1,2,1]
|
|
; AVX2-SLOW-NEXT: vpshufhw {{.*#+}} xmm2 = xmm0[0,1,2,3,4,7,6,5]
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[0,1,2,1]
|
|
; AVX2-SLOW-NEXT: vpshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,7,6,5]
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} xmm2 = xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,1,0,1]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm3 = ymm1[0],ymm2[1],ymm1[2,3],ymm2[4],ymm1[5,6],ymm2[7]
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rcx), %xmm1
|
|
; AVX2-SLOW-NEXT: vpsrldq {{.*#+}} xmm4 = xmm1[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rdx), %xmm2
|
|
; AVX2-SLOW-NEXT: vpsrldq {{.*#+}} xmm6 = xmm2[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} xmm4 = xmm6[0],xmm4[0],xmm6[1],xmm4[1],xmm6[2],xmm4[2],xmm6[3],xmm4[3]
|
|
; AVX2-SLOW-NEXT: vpbroadcastq %xmm4, %ymm4
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
|
|
; AVX2-SLOW-NEXT: vmovdqu %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} xmm4 = xmm7[4],xmm9[4],xmm7[5],xmm9[5],xmm7[6],xmm9[6],xmm7[7],xmm9[7]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm4 = xmm4[2,1,2,3]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,1,0,1]
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} xmm6 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm6 = xmm6[1,2,3,3]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm6 = ymm6[0,0,2,1]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm4 = ymm6[0],ymm4[1],ymm6[2,3],ymm4[4],ymm6[5,6],ymm4[7]
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} xmm6 = xmm0[4],xmm5[4],xmm0[5],xmm5[5],xmm0[6],xmm5[6],xmm0[7],xmm5[7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm6 = ymm6[1,1,1,1]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm8 = ymm4[0,1],ymm6[2],ymm4[3,4],ymm6[5],ymm4[6,7]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm4 = ymm15[1,2,2,3,5,6,6,7]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm6 = ymm14[1,2,2,3,5,6,6,7]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} ymm4 = ymm6[0],ymm4[0],ymm6[1],ymm4[1],ymm6[2],ymm4[2],ymm6[3],ymm4[3],ymm6[8],ymm4[8],ymm6[9],ymm4[9],ymm6[10],ymm4[10],ymm6[11],ymm4[11]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm6 = ymm11[2,1,2,3,6,5,6,7]
|
|
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} ymm6 = ymm6[0,3,2,1,4,5,6,7,8,11,10,9,12,13,14,15]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm13 = ymm10[2,1,2,3,6,5,6,7]
|
|
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} ymm13 = ymm13[0,3,2,1,4,5,6,7,8,11,10,9,12,13,14,15]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} ymm6 = ymm13[0],ymm6[0],ymm13[1],ymm6[1],ymm13[2],ymm6[2],ymm13[3],ymm6[3],ymm13[8],ymm6[8],ymm13[9],ymm6[9],ymm13[10],ymm6[10],ymm13[11],ymm6[11]
|
|
; AVX2-SLOW-NEXT: vmovdqa (%rcx), %ymm13
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm4[2,2,2,3]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm6 = ymm6[2,1,2,3]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm4 = ymm4[0],ymm6[1],ymm4[2,3],ymm6[4],ymm4[5,6],ymm6[7]
|
|
; AVX2-SLOW-NEXT: vpsrldq {{.*#+}} ymm6 = ymm13[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,ymm13[22,23,24,25,26,27,28,29,30,31],zero,zero,zero,zero,zero,zero
|
|
; AVX2-SLOW-NEXT: vpsrldq {{.*#+}} ymm3 = ymm12[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,ymm12[22,23,24,25,26,27,28,29,30,31],zero,zero,zero,zero,zero,zero
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} ymm3 = ymm3[0],ymm6[0],ymm3[1],ymm6[1],ymm3[2],ymm6[2],ymm3[3],ymm6[3],ymm3[8],ymm6[8],ymm3[9],ymm6[9],ymm3[10],ymm6[10],ymm3[11],ymm6[11]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[2,2,2,2]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm4 = ymm4[0,1],ymm3[2],ymm4[3,4],ymm3[5],ymm4[6,7]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,2,1]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,0,2,2]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,1,0,1]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4],ymm0[5,6],ymm1[7]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm7[0],xmm9[0],xmm7[1],xmm9[1],xmm7[2],xmm9[2],xmm7[3],xmm9[3]
|
|
; AVX2-SLOW-NEXT: vpbroadcastq %xmm1, %ymm1
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} ymm1 = ymm10[0],ymm11[0],ymm10[1],ymm11[1],ymm10[2],ymm11[2],ymm10[3],ymm11[3],ymm10[8],ymm11[8],ymm10[9],ymm11[9],ymm10[10],ymm11[10],ymm10[11],ymm11[11]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,2,2,3]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} ymm2 = ymm12[0],ymm13[0],ymm12[1],ymm13[1],ymm12[2],ymm13[2],ymm12[3],ymm13[3],ymm12[8],ymm13[8],ymm12[9],ymm13[9],ymm12[10],ymm13[10],ymm12[11],ymm13[11]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[1,0,2,2,5,4,6,6]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,1,2,3]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1],ymm1[2,3],ymm2[4],ymm1[5,6],ymm2[7]
|
|
; AVX2-SLOW-NEXT: vpunpcklwd {{.*#+}} ymm2 = ymm14[0],ymm15[0],ymm14[1],ymm15[1],ymm14[2],ymm15[2],ymm14[3],ymm15[3],ymm14[8],ymm15[8],ymm14[9],ymm15[9],ymm14[10],ymm15[10],ymm14[11],ymm15[11]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,2,2,2]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm2[2],ymm1[3,4],ymm2[5],ymm1[6,7]
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} ymm2 = ymm14[4],ymm15[4],ymm14[5],ymm15[5],ymm14[6],ymm15[6],ymm14[7],ymm15[7],ymm14[12],ymm15[12],ymm14[13],ymm15[13],ymm14[14],ymm15[14],ymm14[15],ymm15[15]
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} ymm3 = ymm12[4],ymm13[4],ymm12[5],ymm13[5],ymm12[6],ymm13[6],ymm12[7],ymm13[7],ymm12[12],ymm13[12],ymm12[13],ymm13[13],ymm12[14],ymm13[14],ymm12[15],ymm13[15]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[2,1,2,3,6,5,6,7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,1,2,3]
|
|
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[1,2,3,3,5,6,7,7]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[2,2,2,3]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2,3],ymm2[4],ymm3[5,6],ymm2[7]
|
|
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} ymm3 = ymm10[4],ymm11[4],ymm10[5],ymm11[5],ymm10[6],ymm11[6],ymm10[7],ymm11[7],ymm10[12],ymm11[12],ymm10[13],ymm11[13],ymm10[14],ymm11[14],ymm10[15],ymm11[15]
|
|
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[3,3,3,3]
|
|
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
|
; AVX2-SLOW-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm2, 160(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm1, 96(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm0, (%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm4, 128(%rax)
|
|
; AVX2-SLOW-NEXT: vmovdqa %ymm8, 64(%rax)
|
|
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
|
; AVX2-SLOW-NEXT: vmovaps %ymm0, 32(%rax)
|
|
; AVX2-SLOW-NEXT: vzeroupper
|
|
; AVX2-SLOW-NEXT: retq
|
|
;
|
|
; AVX2-FAST-ALL-LABEL: vf16:
|
|
; AVX2-FAST-ALL: # %bb.0:
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rdi), %ymm10
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rsi), %ymm11
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rdx), %ymm14
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%r8), %ymm13
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%r9), %ymm15
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rsi), %xmm8
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa {{.*#+}} xmm0 = [0,1,2,3,4,5,6,7,8,9,6,7,4,5,10,11]
|
|
; AVX2-FAST-ALL-NEXT: vpshufb %xmm0, %xmm8, %xmm1
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rdi), %xmm7
|
|
; AVX2-FAST-ALL-NEXT: vpshufb %xmm0, %xmm7, %xmm0
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm1 = ymm0[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%r9), %xmm5
|
|
; AVX2-FAST-ALL-NEXT: vpshufd {{.*#+}} xmm2 = xmm5[1,2,2,3]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%r8), %xmm0
|
|
; AVX2-FAST-ALL-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,2,2,3]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,0,2,1]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0],ymm1[1],ymm2[2,3],ymm1[4],ymm2[5,6],ymm1[7]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rcx), %xmm1
|
|
; AVX2-FAST-ALL-NEXT: vpsrldq {{.*#+}} xmm3 = xmm1[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rdx), %xmm4
|
|
; AVX2-FAST-ALL-NEXT: vpsrldq {{.*#+}} xmm6 = xmm4[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} xmm3 = xmm6[0],xmm3[0],xmm6[1],xmm3[1],xmm6[2],xmm3[2],xmm6[3],xmm3[3]
|
|
; AVX2-FAST-ALL-NEXT: vpbroadcastq %xmm3, %ymm3
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqu %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} xmm3 = xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa {{.*#+}} ymm6 = <1,u,u,2,u,u,3,u>
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm3, %ymm6, %ymm3
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} xmm6 = xmm0[4],xmm5[4],xmm0[5],xmm5[5],xmm0[6],xmm5[6],xmm0[7],xmm5[7]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm6 = ymm6[0,1,1,1]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0],ymm6[1],ymm3[2,3],ymm6[4],ymm3[5,6],ymm6[7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} xmm6 = xmm7[4],xmm8[4],xmm7[5],xmm8[5],xmm7[6],xmm8[6],xmm7[7],xmm8[7]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm6 = ymm6[1,1,1,1]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm9 = ymm3[0,1],ymm6[2],ymm3[3,4],ymm6[5],ymm3[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa {{.*#+}} ymm3 = <u,u,u,u,4,5,10,11,u,u,u,u,u,u,u,u,24,25,22,23,20,21,26,27,u,u,u,u,u,u,u,u>
|
|
; AVX2-FAST-ALL-NEXT: vpshufb %ymm3, %ymm11, %ymm6
|
|
; AVX2-FAST-ALL-NEXT: vpshufb %ymm3, %ymm10, %ymm3
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} ymm3 = ymm3[0],ymm6[0],ymm3[1],ymm6[1],ymm3[2],ymm6[2],ymm3[3],ymm6[3],ymm3[8],ymm6[8],ymm3[9],ymm6[9],ymm3[10],ymm6[10],ymm3[11],ymm6[11]
|
|
; AVX2-FAST-ALL-NEXT: vpshufd {{.*#+}} ymm6 = ymm15[1,2,2,3,5,6,6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpshufd {{.*#+}} ymm12 = ymm13[1,2,2,3,5,6,6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} ymm6 = ymm12[0],ymm6[0],ymm12[1],ymm6[1],ymm12[2],ymm6[2],ymm12[3],ymm6[3],ymm12[8],ymm6[8],ymm12[9],ymm6[9],ymm12[10],ymm6[10],ymm12[11],ymm6[11]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa (%rcx), %ymm12
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm3 = ymm3[2,1,2,3]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm6 = ymm6[2,2,2,3]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm3 = ymm6[0],ymm3[1],ymm6[2,3],ymm3[4],ymm6[5,6],ymm3[7]
|
|
; AVX2-FAST-ALL-NEXT: vpsrldq {{.*#+}} ymm6 = ymm12[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,ymm12[22,23,24,25,26,27,28,29,30,31],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-ALL-NEXT: vpsrldq {{.*#+}} ymm2 = ymm14[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,ymm14[22,23,24,25,26,27,28,29,30,31],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} ymm2 = ymm2[0],ymm6[0],ymm2[1],ymm6[1],ymm2[2],ymm6[2],ymm2[3],ymm6[3],ymm2[8],ymm6[8],ymm2[9],ymm6[9],ymm2[10],ymm6[10],ymm2[11],ymm6[11]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,2,2,2]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm2[2],ymm3[3,4],ymm2[5],ymm3[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
|
|
; AVX2-FAST-ALL-NEXT: vbroadcasti128 {{.*#+}} ymm2 = [1,0,2,2,1,0,2,2]
|
|
; AVX2-FAST-ALL-NEXT: # ymm2 = mem[0,1,0,1]
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm1, %ymm2, %ymm1
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm7[0],xmm8[0],xmm7[1],xmm8[1],xmm7[2],xmm8[2],xmm7[3],xmm8[3]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,0,2,1]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2,3],ymm1[4],ymm2[5,6],ymm1[7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3]
|
|
; AVX2-FAST-ALL-NEXT: vpbroadcastq %xmm0, %ymm0
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3,4],ymm0[5],ymm1[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} ymm1 = ymm14[0],ymm12[0],ymm14[1],ymm12[1],ymm14[2],ymm12[2],ymm14[3],ymm12[3],ymm14[8],ymm12[8],ymm14[9],ymm12[9],ymm14[10],ymm12[10],ymm14[11],ymm12[11]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa {{.*#+}} ymm2 = <u,4,u,u,5,u,u,6>
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm1, %ymm2, %ymm1
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} ymm2 = ymm10[0],ymm11[0],ymm10[1],ymm11[1],ymm10[2],ymm11[2],ymm10[3],ymm11[3],ymm10[8],ymm11[8],ymm10[9],ymm11[9],ymm10[10],ymm11[10],ymm10[11],ymm11[11]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,2,2,3]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2,3],ymm1[4],ymm2[5,6],ymm1[7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpcklwd {{.*#+}} ymm2 = ymm13[0],ymm15[0],ymm13[1],ymm15[1],ymm13[2],ymm15[2],ymm13[3],ymm15[3],ymm13[8],ymm15[8],ymm13[9],ymm15[9],ymm13[10],ymm15[10],ymm13[11],ymm15[11]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,2,2,2]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm2[2],ymm1[3,4],ymm2[5],ymm1[6,7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} ymm2 = ymm14[4],ymm12[4],ymm14[5],ymm12[5],ymm14[6],ymm12[6],ymm14[7],ymm12[7],ymm14[12],ymm12[12],ymm14[13],ymm12[13],ymm14[14],ymm12[14],ymm14[15],ymm12[15]
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa {{.*#+}} ymm4 = <5,u,u,6,u,u,7,u>
|
|
; AVX2-FAST-ALL-NEXT: vpermd %ymm2, %ymm4, %ymm2
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} ymm4 = ymm13[4],ymm15[4],ymm13[5],ymm15[5],ymm13[6],ymm15[6],ymm13[7],ymm15[7],ymm13[12],ymm15[12],ymm13[13],ymm15[13],ymm13[14],ymm15[14],ymm13[15],ymm15[15]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm4 = ymm4[2,1,3,3]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0],ymm4[1],ymm2[2,3],ymm4[4],ymm2[5,6],ymm4[7]
|
|
; AVX2-FAST-ALL-NEXT: vpunpckhwd {{.*#+}} ymm4 = ymm10[4],ymm11[4],ymm10[5],ymm11[5],ymm10[6],ymm11[6],ymm10[7],ymm11[7],ymm10[12],ymm11[12],ymm10[13],ymm11[13],ymm10[14],ymm11[14],ymm10[15],ymm11[15]
|
|
; AVX2-FAST-ALL-NEXT: vpermq {{.*#+}} ymm4 = ymm4[3,3,3,3]
|
|
; AVX2-FAST-ALL-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3,4],ymm4[5],ymm2[6,7]
|
|
; AVX2-FAST-ALL-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm2, 160(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm1, 96(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm0, (%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm3, 128(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovdqa %ymm9, 64(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
|
; AVX2-FAST-ALL-NEXT: vmovaps %ymm0, 32(%rax)
|
|
; AVX2-FAST-ALL-NEXT: vzeroupper
|
|
; AVX2-FAST-ALL-NEXT: retq
|
|
;
|
|
; AVX2-FAST-PERLANE-LABEL: vf16:
|
|
; AVX2-FAST-PERLANE: # %bb.0:
|
|
; AVX2-FAST-PERLANE-NEXT: movq {{[0-9]+}}(%rsp), %rax
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdi), %ymm13
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rsi), %ymm15
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdx), %ymm11
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rcx), %ymm12
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%r8), %ymm14
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%r9), %ymm9
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rsi), %xmm6
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa {{.*#+}} xmm0 = [0,1,2,3,4,5,6,7,8,9,6,7,4,5,10,11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb %xmm0, %xmm6, %xmm7
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdi), %xmm1
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb %xmm0, %xmm1, %xmm0
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm7[4],xmm0[5],xmm7[5],xmm0[6],xmm7[6],xmm0[7],xmm7[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm8 = ymm0[0,1,0,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%r9), %xmm7
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} xmm2 = xmm7[1,2,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%r8), %xmm0
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,2,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,0,2,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm8 = ymm2[0],ymm8[1],ymm2[2,3],ymm8[4],ymm2[5,6],ymm8[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rcx), %xmm3
|
|
; AVX2-FAST-PERLANE-NEXT: vpsrldq {{.*#+}} xmm4 = xmm3[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa (%rdx), %xmm2
|
|
; AVX2-FAST-PERLANE-NEXT: vpsrldq {{.*#+}} xmm5 = xmm2[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} xmm4 = xmm5[0],xmm4[0],xmm5[1],xmm4[1],xmm5[2],xmm4[2],xmm5[3],xmm4[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq %xmm4, %ymm4
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm4 = ymm8[0,1],ymm4[2],ymm8[3,4],ymm4[5],ymm8[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqu %ymm4, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm0[4],xmm7[4],xmm0[5],xmm7[5],xmm0[6],xmm7[6],xmm0[7],xmm7[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} xmm5 = xmm5[2,1,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm5 = ymm5[0,1,0,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} xmm4 = xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} xmm4 = xmm4[1,2,3,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,0,2,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm4 = ymm4[0],ymm5[1],ymm4[2,3],ymm5[4],ymm4[5,6],ymm5[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm1[4],xmm6[4],xmm1[5],xmm6[5],xmm1[6],xmm6[6],xmm1[7],xmm6[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm5 = ymm5[1,1,1,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm10 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1],xmm1[2],xmm6[2],xmm1[3],xmm6[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,0,2,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,0,2,2]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,1,0,1]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1],ymm1[2,3],ymm2[4],ymm1[5,6],ymm2[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1],xmm0[2],xmm7[2],xmm0[3],xmm7[3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq %xmm0, %ymm0
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm8 = ymm1[0,1],ymm0[2],ymm1[3,4],ymm0[5],ymm1[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} ymm0 = ymm13[0],ymm15[0],ymm13[1],ymm15[1],ymm13[2],ymm15[2],ymm13[3],ymm15[3],ymm13[8],ymm15[8],ymm13[9],ymm15[9],ymm13[10],ymm15[10],ymm13[11],ymm15[11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm0 = ymm0[2,2,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} ymm1 = ymm11[0],ymm12[0],ymm11[1],ymm12[1],ymm11[2],ymm12[2],ymm11[3],ymm12[3],ymm11[8],ymm12[8],ymm11[9],ymm12[9],ymm11[10],ymm12[10],ymm11[11],ymm12[11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[1,0,2,2,5,4,6,6]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4],ymm0[5,6],ymm1[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} ymm1 = ymm14[0],ymm9[0],ymm14[1],ymm9[1],ymm14[2],ymm9[2],ymm14[3],ymm9[3],ymm14[8],ymm9[8],ymm14[9],ymm9[9],ymm14[10],ymm9[10],ymm14[11],ymm9[11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,2,2,2]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} ymm1 = ymm14[4],ymm9[4],ymm14[5],ymm9[5],ymm14[6],ymm9[6],ymm14[7],ymm9[7],ymm14[12],ymm9[12],ymm14[13],ymm9[13],ymm14[14],ymm9[14],ymm14[15],ymm9[15]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[2,1,2,3,6,5,6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} ymm2 = ymm11[4],ymm12[4],ymm11[5],ymm12[5],ymm11[6],ymm12[6],ymm11[7],ymm12[7],ymm11[12],ymm12[12],ymm11[13],ymm12[13],ymm11[14],ymm12[14],ymm11[15],ymm12[15]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[1,2,3,3,5,6,7,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,2,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2,3],ymm1[4],ymm2[5,6],ymm1[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpckhwd {{.*#+}} ymm2 = ymm13[4],ymm15[4],ymm13[5],ymm15[5],ymm13[6],ymm15[6],ymm13[7],ymm15[7],ymm13[12],ymm15[12],ymm13[13],ymm15[13],ymm13[14],ymm15[14],ymm13[15],ymm15[15]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm2 = ymm2[3,3,3,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm2[2],ymm1[3,4],ymm2[5],ymm1[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa {{.*#+}} ymm2 = <u,u,u,u,4,5,10,11,u,u,u,u,u,u,u,u,24,25,22,23,20,21,26,27,u,u,u,u,u,u,u,u>
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb %ymm2, %ymm15, %ymm3
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufb %ymm2, %ymm13, %ymm2
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} ymm2 = ymm2[0],ymm3[0],ymm2[1],ymm3[1],ymm2[2],ymm3[2],ymm2[3],ymm3[3],ymm2[8],ymm3[8],ymm2[9],ymm3[9],ymm2[10],ymm3[10],ymm2[11],ymm3[11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm2 = ymm2[2,1,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} ymm3 = ymm9[1,2,2,3,5,6,6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpshufd {{.*#+}} ymm4 = ymm14[1,2,2,3,5,6,6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} ymm3 = ymm4[0],ymm3[0],ymm4[1],ymm3[1],ymm4[2],ymm3[2],ymm4[3],ymm3[3],ymm4[8],ymm3[8],ymm4[9],ymm3[9],ymm4[10],ymm3[10],ymm4[11],ymm3[11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm3 = ymm3[2,2,2,3]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2,3],ymm2[4],ymm3[5,6],ymm2[7]
|
|
; AVX2-FAST-PERLANE-NEXT: vpsrldq {{.*#+}} ymm3 = ymm12[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,ymm12[22,23,24,25,26,27,28,29,30,31],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-PERLANE-NEXT: vpsrldq {{.*#+}} ymm4 = ymm11[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,ymm11[22,23,24,25,26,27,28,29,30,31],zero,zero,zero,zero,zero,zero
|
|
; AVX2-FAST-PERLANE-NEXT: vpunpcklwd {{.*#+}} ymm3 = ymm4[0],ymm3[0],ymm4[1],ymm3[1],ymm4[2],ymm3[2],ymm4[3],ymm3[3],ymm4[8],ymm3[8],ymm4[9],ymm3[9],ymm4[10],ymm3[10],ymm4[11],ymm3[11]
|
|
; AVX2-FAST-PERLANE-NEXT: vpermq {{.*#+}} ymm3 = ymm3[2,2,2,2]
|
|
; AVX2-FAST-PERLANE-NEXT: vpblendd {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm2, 128(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm1, 160(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm0, 96(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm8, (%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovdqa %ymm10, 64(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
|
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm0, 32(%rax)
|
|
; AVX2-FAST-PERLANE-NEXT: vzeroupper
|
|
; AVX2-FAST-PERLANE-NEXT: retq
|
|
%in.vec0 = load <16 x i16>, <16 x i16>* %in.vecptr0, align 32
|
|
%in.vec1 = load <16 x i16>, <16 x i16>* %in.vecptr1, align 32
|
|
%in.vec2 = load <16 x i16>, <16 x i16>* %in.vecptr2, align 32
|
|
%in.vec3 = load <16 x i16>, <16 x i16>* %in.vecptr3, align 32
|
|
%in.vec4 = load <16 x i16>, <16 x i16>* %in.vecptr4, align 32
|
|
%in.vec5 = load <16 x i16>, <16 x i16>* %in.vecptr5, align 32
|
|
|
|
%concat01 = shufflevector <16 x i16> %in.vec0, <16 x i16> %in.vec1, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
|
|
%concat23 = shufflevector <16 x i16> %in.vec2, <16 x i16> %in.vec3, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
|
|
%concat45 = shufflevector <16 x i16> %in.vec4, <16 x i16> %in.vec5, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
|
|
%concat0123 = shufflevector <32 x i16> %concat01, <32 x i16> %concat23, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
|
|
%concat45uu = shufflevector <32 x i16> %concat45, <32 x i16> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%concat012345 = shufflevector <64 x i16> %concat0123, <64 x i16> %concat45uu, <96 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95>
|
|
%interleaved.vec = shufflevector <96 x i16> %concat012345, <96 x i16> poison, <96 x i32> <i32 0, i32 16, i32 32, i32 48, i32 64, i32 80, i32 1, i32 17, i32 33, i32 49, i32 65, i32 81, i32 2, i32 18, i32 34, i32 50, i32 66, i32 82, i32 3, i32 19, i32 35, i32 51, i32 67, i32 83, i32 4, i32 20, i32 36, i32 52, i32 68, i32 84, i32 5, i32 21, i32 37, i32 53, i32 69, i32 85, i32 6, i32 22, i32 38, i32 54, i32 70, i32 86, i32 7, i32 23, i32 39, i32 55, i32 71, i32 87, i32 8, i32 24, i32 40, i32 56, i32 72, i32 88, i32 9, i32 25, i32 41, i32 57, i32 73, i32 89, i32 10, i32 26, i32 42, i32 58, i32 74, i32 90, i32 11, i32 27, i32 43, i32 59, i32 75, i32 91, i32 12, i32 28, i32 44, i32 60, i32 76, i32 92, i32 13, i32 29, i32 45, i32 61, i32 77, i32 93, i32 14, i32 30, i32 46, i32 62, i32 78, i32 94, i32 15, i32 31, i32 47, i32 63, i32 79, i32 95>
|
|
|
|
store <96 x i16> %interleaved.vec, <96 x i16>* %out.vec, align 32
|
|
|
|
ret void
|
|
}
|