forked from OSchip/llvm-project
908 lines
35 KiB
LLVM
908 lines
35 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE42
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VL
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BW
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BWVL
|
|
|
|
define void @shuffle_v16i8_to_v8i8_1(<16 x i8>* %L, <8 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,7,5,6,7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[1,0,3,2,4,5,6,7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,5,6,7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,0,3,2,4,5,6,7]
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movq %xmm0, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: movq %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
|
|
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v8i8_1:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlw $8, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovwb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
store <8 x i8> %strided.vec, <8 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v8i16_to_v4i16_1(<8 x i16>* %L, <4 x i16>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = mem[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,5,6,7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,0,3,2,4,5,6,7]
|
|
; SSE2-NEXT: movq %xmm0, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
|
|
; SSE42-NEXT: movq %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
|
|
; AVX-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
|
|
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovdw %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
|
|
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v8i16_to_v4i16_1:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovdw %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <8 x i16>, <8 x i16>* %L
|
|
%strided.vec = shufflevector <8 x i16> %vec, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
store <4 x i16> %strided.vec, <4 x i16>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v4i32_to_v2i32_1(<4 x i32>* %L, <2 x i32>* %S) nounwind {
|
|
; SSE-LABEL: shuffle_v4i32_to_v2i32_1:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: pshufd {{.*#+}} xmm0 = mem[1,3,2,3]
|
|
; SSE-NEXT: movq %xmm0, (%rsi)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v4i32_to_v2i32_1:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,3,2,3]
|
|
; AVX-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v4i32_to_v2i32_1:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,3,2,3]
|
|
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v4i32_to_v2i32_1:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,1,3,3]
|
|
; AVX512VL-NEXT: vpmovqd %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v4i32_to_v2i32_1:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,3,2,3]
|
|
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v4i32_to_v2i32_1:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,1,3,3]
|
|
; AVX512BWVL-NEXT: vpmovqd %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <4 x i32>, <4 x i32>* %L
|
|
%strided.vec = shufflevector <4 x i32> %vec, <4 x i32> undef, <2 x i32> <i32 1, i32 3>
|
|
store <2 x i32> %strided.vec, <2 x i32>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v4i8_1(<16 x i8>* %L, <4 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[1,3,2,3,4,5,6,7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: movd %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v4i8_1:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlw $8, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
|
|
store <4 x i8> %strided.vec, <4 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v4i8_2(<16 x i8>* %L, <4 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,5,6,7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,0,3,2,4,5,6,7]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: movd %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v4i8_2:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
|
|
store <4 x i8> %strided.vec, <4 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v4i8_3(<16 x i8>* %L, <4 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[3,1,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: movd %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrld $24, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v4i8_3:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrld $24, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
|
|
store <4 x i8> %strided.vec, <4 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v8i16_to_v2i16_1(<8 x i16>* %L, <2 x i16>* %S) nounwind {
|
|
; SSE-LABEL: shuffle_v8i16_to_v2i16_1:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: pshufd {{.*#+}} xmm0 = mem[0,2,2,3]
|
|
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
|
|
; SSE-NEXT: movd %xmm0, (%rsi)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v8i16_to_v2i16_1:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = mem[0,2,2,3]
|
|
; AVX-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
|
|
; AVX-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v8i16_to_v2i16_1:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = mem[0,2,2,3]
|
|
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
|
|
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v8i16_to_v2i16_1:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqw %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v8i16_to_v2i16_1:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = mem[0,2,2,3]
|
|
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
|
|
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v8i16_to_v2i16_1:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqw %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <8 x i16>, <8 x i16>* %L
|
|
%strided.vec = shufflevector <8 x i16> %vec, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
|
|
store <2 x i16> %strided.vec, <2 x i16>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v8i16_to_v2i16_2(<8 x i16>* %L, <2 x i16>* %S) nounwind {
|
|
; SSE-LABEL: shuffle_v8i16_to_v2i16_2:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: pshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
|
|
; SSE-NEXT: movd %xmm0, (%rsi)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v8i16_to_v2i16_2:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; AVX-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
|
|
; AVX-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v8i16_to_v2i16_2:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
|
|
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v8i16_to_v2i16_2:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,1,3,3]
|
|
; AVX512VL-NEXT: vpmovqw %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v8i16_to_v2i16_2:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
|
|
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v8i16_to_v2i16_2:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,1,3,3]
|
|
; AVX512BWVL-NEXT: vpmovqw %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <8 x i16>, <8 x i16>* %L
|
|
%strided.vec = shufflevector <8 x i16> %vec, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
|
|
store <2 x i16> %strided.vec, <2 x i16>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v8i16_to_v2i16_3(<8 x i16>* %L, <2 x i16>* %S) nounwind {
|
|
; SSE-LABEL: shuffle_v8i16_to_v2i16_3:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: pshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; SSE-NEXT: movd %xmm0, (%rsi)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v8i16_to_v2i16_3:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; AVX-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; AVX-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v8i16_to_v2i16_3:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v8i16_to_v2i16_3:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrlq $48, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqw %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v8i16_to_v2i16_3:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = mem[3,1,2,3]
|
|
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v8i16_to_v2i16_3:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlq $48, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqw %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <8 x i16>, <8 x i16>* %L
|
|
%strided.vec = shufflevector <8 x i16> %vec, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
|
|
store <2 x i16> %strided.vec, <2 x i16>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_1(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_1:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlw $8, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 1, i32 9>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_2(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_2:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrld $16, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 2, i32 10>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_3(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrld $24, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_3:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrld $24, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 3, i32 11>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_4(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,1,3,3]
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_4:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = mem[1,1,3,3]
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 4, i32 12>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_5(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrlq $40, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_5:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlq $40, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 5, i32 13>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_6(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
|
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrlq $48, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_6:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlq $48, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 6, i32 14>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|
|
define void @shuffle_v16i8_to_v2i8_7(<16 x i8>* %L, <2 x i8>* %S) nounwind {
|
|
; SSE2-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rsi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; SSE42: # BB#0:
|
|
; SSE42-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE42-NEXT: pshufb {{.*#+}} xmm0 = xmm0[7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; SSE42-NEXT: pextrw $0, %xmm0, (%rsi)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; AVX512F: # BB#0:
|
|
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512F-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; AVX512VL: # BB#0:
|
|
; AVX512VL-NEXT: vpsrlq $56, (%rdi), %xmm0
|
|
; AVX512VL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; AVX512BW: # BB#0:
|
|
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
|
|
; AVX512BW-NEXT: vpextrw $0, %xmm0, (%rsi)
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512BWVL-LABEL: shuffle_v16i8_to_v2i8_7:
|
|
; AVX512BWVL: # BB#0:
|
|
; AVX512BWVL-NEXT: vpsrlq $56, (%rdi), %xmm0
|
|
; AVX512BWVL-NEXT: vpmovqb %xmm0, (%rsi)
|
|
; AVX512BWVL-NEXT: retq
|
|
%vec = load <16 x i8>, <16 x i8>* %L
|
|
%strided.vec = shufflevector <16 x i8> %vec, <16 x i8> undef, <2 x i32> <i32 7, i32 15>
|
|
store <2 x i8> %strided.vec, <2 x i8>* %S
|
|
ret void
|
|
}
|
|
|