forked from OSchip/llvm-project
1224 lines
72 KiB
LLVM
1224 lines
72 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=AVX512,AVX512F
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VL
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512,AVX512BW
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VLBW
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi2 | FileCheck %s --check-prefixes=AVX512,AVX512VBMI2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vbmi2,+avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VLVBMI2
|
|
|
|
;
|
|
; Variable Rotates
|
|
;
|
|
|
|
define <8 x i64> @var_rotate_v8i64(<8 x i64> %a, <8 x i64> %b) nounwind {
|
|
; AVX512-LABEL: var_rotate_v8i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprolvq %zmm1, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%b64 = sub <8 x i64> <i64 64, i64 64, i64 64, i64 64, i64 64, i64 64, i64 64, i64 64>, %b
|
|
%shl = shl <8 x i64> %a, %b
|
|
%lshr = lshr <8 x i64> %a, %b64
|
|
%or = or <8 x i64> %shl, %lshr
|
|
ret <8 x i64> %or
|
|
}
|
|
|
|
define <16 x i32> @var_rotate_v16i32(<16 x i32> %a, <16 x i32> %b) nounwind {
|
|
; AVX512-LABEL: var_rotate_v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprolvd %zmm1, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%b32 = sub <16 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>, %b
|
|
%shl = shl <16 x i32> %a, %b
|
|
%lshr = lshr <16 x i32> %a, %b32
|
|
%or = or <16 x i32> %shl, %lshr
|
|
ret <16 x i32> %or
|
|
}
|
|
|
|
define <32 x i16> @var_rotate_v32i16(<32 x i16> %a, <32 x i16> %b) nounwind {
|
|
; AVX512F-LABEL: var_rotate_v32i16:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm1, %ymm3
|
|
; AVX512F-NEXT: vpsubw %ymm3, %ymm2, %ymm4
|
|
; AVX512F-NEXT: vpsubw %ymm1, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
|
|
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm5 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; AVX512F-NEXT: vpsllvd %zmm1, %zmm5, %zmm1
|
|
; AVX512F-NEXT: vpmovdw %zmm1, %ymm1
|
|
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm3 = ymm3[0],zero,ymm3[1],zero,ymm3[2],zero,ymm3[3],zero,ymm3[4],zero,ymm3[5],zero,ymm3[6],zero,ymm3[7],zero,ymm3[8],zero,ymm3[9],zero,ymm3[10],zero,ymm3[11],zero,ymm3[12],zero,ymm3[13],zero,ymm3[14],zero,ymm3[15],zero
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm0
|
|
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; AVX512F-NEXT: vpsllvd %zmm3, %zmm0, %zmm3
|
|
; AVX512F-NEXT: vpmovdw %zmm3, %ymm3
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero,ymm2[8],zero,ymm2[9],zero,ymm2[10],zero,ymm2[11],zero,ymm2[12],zero,ymm2[13],zero,ymm2[14],zero,ymm2[15],zero
|
|
; AVX512F-NEXT: vpsrlvd %zmm2, %zmm5, %zmm2
|
|
; AVX512F-NEXT: vpmovdw %zmm2, %ymm2
|
|
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm3 = ymm4[0],zero,ymm4[1],zero,ymm4[2],zero,ymm4[3],zero,ymm4[4],zero,ymm4[5],zero,ymm4[6],zero,ymm4[7],zero,ymm4[8],zero,ymm4[9],zero,ymm4[10],zero,ymm4[11],zero,ymm4[12],zero,ymm4[13],zero,ymm4[14],zero,ymm4[15],zero
|
|
; AVX512F-NEXT: vpsrlvd %zmm3, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm0, %zmm2, %zmm0
|
|
; AVX512F-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: var_rotate_v32i16:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm1, %ymm3
|
|
; AVX512VL-NEXT: vpsubw %ymm3, %ymm2, %ymm4
|
|
; AVX512VL-NEXT: vpsubw %ymm1, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
|
|
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm5 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; AVX512VL-NEXT: vpsllvd %zmm1, %zmm5, %zmm1
|
|
; AVX512VL-NEXT: vpmovdw %zmm1, %ymm1
|
|
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm3 = ymm3[0],zero,ymm3[1],zero,ymm3[2],zero,ymm3[3],zero,ymm3[4],zero,ymm3[5],zero,ymm3[6],zero,ymm3[7],zero,ymm3[8],zero,ymm3[9],zero,ymm3[10],zero,ymm3[11],zero,ymm3[12],zero,ymm3[13],zero,ymm3[14],zero,ymm3[15],zero
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm0
|
|
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; AVX512VL-NEXT: vpsllvd %zmm3, %zmm0, %zmm3
|
|
; AVX512VL-NEXT: vpmovdw %zmm3, %ymm3
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero,ymm2[8],zero,ymm2[9],zero,ymm2[10],zero,ymm2[11],zero,ymm2[12],zero,ymm2[13],zero,ymm2[14],zero,ymm2[15],zero
|
|
; AVX512VL-NEXT: vpsrlvd %zmm2, %zmm5, %zmm2
|
|
; AVX512VL-NEXT: vpmovdw %zmm2, %ymm2
|
|
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm3 = ymm4[0],zero,ymm4[1],zero,ymm4[2],zero,ymm4[3],zero,ymm4[4],zero,ymm4[5],zero,ymm4[6],zero,ymm4[7],zero,ymm4[8],zero,ymm4[9],zero,ymm4[10],zero,ymm4[11],zero,ymm4[12],zero,ymm4[13],zero,ymm4[14],zero,ymm4[15],zero
|
|
; AVX512VL-NEXT: vpsrlvd %zmm3, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vpmovdw %zmm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm0, %zmm2, %zmm0
|
|
; AVX512VL-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: var_rotate_v32i16:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm2 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
|
; AVX512BW-NEXT: vpsubw %zmm1, %zmm2, %zmm2
|
|
; AVX512BW-NEXT: vpsllvw %zmm1, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpsrlvw %zmm2, %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: var_rotate_v32i16:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vmovdqa64 {{.*#+}} zmm2 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
|
; AVX512VLBW-NEXT: vpsubw %zmm1, %zmm2, %zmm2
|
|
; AVX512VLBW-NEXT: vpsllvw %zmm1, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpsrlvw %zmm2, %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: var_rotate_v32i16:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpshldvw %zmm1, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: var_rotate_v32i16:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpshldvw %zmm1, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%b16 = sub <32 x i16> <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>, %b
|
|
%shl = shl <32 x i16> %a, %b
|
|
%lshr = lshr <32 x i16> %a, %b16
|
|
%or = or <32 x i16> %shl, %lshr
|
|
ret <32 x i16> %or
|
|
}
|
|
|
|
define <64 x i8> @var_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|
; AVX512F-LABEL: var_rotate_v64i8:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512F-NEXT: vpsubb %ymm1, %ymm3, %ymm2
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm1, %ymm4
|
|
; AVX512F-NEXT: vpsubb %ymm4, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm5
|
|
; AVX512F-NEXT: vpsllw $4, %ymm5, %ymm6
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm7 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
|
; AVX512F-NEXT: vpand %ymm7, %ymm6, %ymm6
|
|
; AVX512F-NEXT: vpsllw $5, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpblendvb %ymm4, %ymm6, %ymm5, %ymm6
|
|
; AVX512F-NEXT: vpsllw $2, %ymm6, %ymm8
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252]
|
|
; AVX512F-NEXT: vpand %ymm9, %ymm8, %ymm8
|
|
; AVX512F-NEXT: vpaddb %ymm4, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpblendvb %ymm4, %ymm8, %ymm6, %ymm6
|
|
; AVX512F-NEXT: vpaddb %ymm6, %ymm6, %ymm8
|
|
; AVX512F-NEXT: vpaddb %ymm4, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpblendvb %ymm4, %ymm8, %ymm6, %ymm4
|
|
; AVX512F-NEXT: vpsllw $4, %ymm0, %ymm6
|
|
; AVX512F-NEXT: vpand %ymm7, %ymm6, %ymm6
|
|
; AVX512F-NEXT: vpsllw $5, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpblendvb %ymm1, %ymm6, %ymm0, %ymm6
|
|
; AVX512F-NEXT: vpsllw $2, %ymm6, %ymm7
|
|
; AVX512F-NEXT: vpand %ymm7, %ymm9, %ymm7
|
|
; AVX512F-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpblendvb %ymm1, %ymm7, %ymm6, %ymm6
|
|
; AVX512F-NEXT: vpaddb %ymm6, %ymm6, %ymm7
|
|
; AVX512F-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpblendvb %ymm1, %ymm7, %ymm6, %ymm1
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm4, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vpsrlw $4, %ymm5, %ymm4
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm6 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
|
|
; AVX512F-NEXT: vpand %ymm6, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpsllw $5, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vpblendvb %ymm3, %ymm4, %ymm5, %ymm4
|
|
; AVX512F-NEXT: vpsrlw $2, %ymm4, %ymm5
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm7 = [63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63]
|
|
; AVX512F-NEXT: vpand %ymm7, %ymm5, %ymm5
|
|
; AVX512F-NEXT: vpaddb %ymm3, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vpblendvb %ymm3, %ymm5, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpsrlw $1, %ymm4, %ymm5
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm8 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
|
|
; AVX512F-NEXT: vpand %ymm5, %ymm8, %ymm5
|
|
; AVX512F-NEXT: vpaddb %ymm3, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vpblendvb %ymm3, %ymm5, %ymm4, %ymm3
|
|
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm4
|
|
; AVX512F-NEXT: vpand %ymm6, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpsllw $5, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vpblendvb %ymm2, %ymm4, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $2, %ymm0, %ymm4
|
|
; AVX512F-NEXT: vpand %ymm7, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vpblendvb %ymm2, %ymm4, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $1, %ymm0, %ymm4
|
|
; AVX512F-NEXT: vpand %ymm4, %ymm8, %ymm4
|
|
; AVX512F-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vpblendvb %ymm2, %ymm4, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: var_rotate_v64i8:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VL-NEXT: vpsubb %ymm1, %ymm3, %ymm2
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm1, %ymm4
|
|
; AVX512VL-NEXT: vpsubb %ymm4, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm5
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm5, %ymm6
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm7 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
|
; AVX512VL-NEXT: vpand %ymm7, %ymm6, %ymm6
|
|
; AVX512VL-NEXT: vpsllw $5, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpblendvb %ymm4, %ymm6, %ymm5, %ymm6
|
|
; AVX512VL-NEXT: vpsllw $2, %ymm6, %ymm8
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252]
|
|
; AVX512VL-NEXT: vpand %ymm9, %ymm8, %ymm8
|
|
; AVX512VL-NEXT: vpaddb %ymm4, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpblendvb %ymm4, %ymm8, %ymm6, %ymm6
|
|
; AVX512VL-NEXT: vpaddb %ymm6, %ymm6, %ymm8
|
|
; AVX512VL-NEXT: vpaddb %ymm4, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpblendvb %ymm4, %ymm8, %ymm6, %ymm4
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm6
|
|
; AVX512VL-NEXT: vpand %ymm7, %ymm6, %ymm6
|
|
; AVX512VL-NEXT: vpsllw $5, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm6, %ymm0, %ymm6
|
|
; AVX512VL-NEXT: vpsllw $2, %ymm6, %ymm7
|
|
; AVX512VL-NEXT: vpand %ymm7, %ymm9, %ymm7
|
|
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm7, %ymm6, %ymm6
|
|
; AVX512VL-NEXT: vpaddb %ymm6, %ymm6, %ymm7
|
|
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm7, %ymm6, %ymm1
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm4, %zmm1, %zmm1
|
|
; AVX512VL-NEXT: vpsrlw $4, %ymm5, %ymm4
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm6 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
|
|
; AVX512VL-NEXT: vpand %ymm6, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpsllw $5, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vpblendvb %ymm3, %ymm4, %ymm5, %ymm4
|
|
; AVX512VL-NEXT: vpsrlw $2, %ymm4, %ymm5
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm7 = [63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63]
|
|
; AVX512VL-NEXT: vpand %ymm7, %ymm5, %ymm5
|
|
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vpblendvb %ymm3, %ymm5, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpsrlw $1, %ymm4, %ymm5
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm8 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
|
|
; AVX512VL-NEXT: vpand %ymm5, %ymm8, %ymm5
|
|
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vpblendvb %ymm3, %ymm5, %ymm4, %ymm3
|
|
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm4
|
|
; AVX512VL-NEXT: vpand %ymm6, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpsllw $5, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $2, %ymm0, %ymm4
|
|
; AVX512VL-NEXT: vpand %ymm7, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $1, %ymm0, %ymm4
|
|
; AVX512VL-NEXT: vpand %ymm4, %ymm8, %ymm4
|
|
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: var_rotate_v64i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512BW-NEXT: vpsubb %zmm1, %zmm2, %zmm2
|
|
; AVX512BW-NEXT: vpsllw $4, %zmm0, %zmm3
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512BW-NEXT: vpsllw $5, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512BW-NEXT: vpblendmb %zmm3, %zmm0, %zmm3 {%k1}
|
|
; AVX512BW-NEXT: vpsllw $2, %zmm3, %zmm4
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm4, %zmm4
|
|
; AVX512BW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512BW-NEXT: vmovdqu8 %zmm4, %zmm3 {%k1}
|
|
; AVX512BW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512BW-NEXT: vpaddb %zmm3, %zmm3, %zmm3 {%k1}
|
|
; AVX512BW-NEXT: vpsllw $5, %zmm2, %zmm1
|
|
; AVX512BW-NEXT: vpaddb %zmm1, %zmm1, %zmm2
|
|
; AVX512BW-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k2
|
|
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k2}
|
|
; AVX512BW-NEXT: vpsrlw $2, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512BW-NEXT: vpsrlw $1, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpaddb %zmm2, %zmm2, %zmm2
|
|
; AVX512BW-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512BW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512BW-NEXT: vporq %zmm0, %zmm3, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: var_rotate_v64i8:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vmovdqa64 {{.*#+}} zmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VLBW-NEXT: vpsubb %zmm1, %zmm2, %zmm2
|
|
; AVX512VLBW-NEXT: vpsllw $4, %zmm0, %zmm3
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VLBW-NEXT: vpsllw $5, %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLBW-NEXT: vpblendmb %zmm3, %zmm0, %zmm3 {%k1}
|
|
; AVX512VLBW-NEXT: vpsllw $2, %zmm3, %zmm4
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm4, %zmm4
|
|
; AVX512VLBW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLBW-NEXT: vmovdqu8 %zmm4, %zmm3 {%k1}
|
|
; AVX512VLBW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLBW-NEXT: vpaddb %zmm3, %zmm3, %zmm3 {%k1}
|
|
; AVX512VLBW-NEXT: vpsllw $5, %zmm2, %zmm1
|
|
; AVX512VLBW-NEXT: vpaddb %zmm1, %zmm1, %zmm2
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k2
|
|
; AVX512VLBW-NEXT: vpsrlw $4, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k2}
|
|
; AVX512VLBW-NEXT: vpsrlw $2, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512VLBW-NEXT: vpsrlw $1, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vpaddb %zmm2, %zmm2, %zmm2
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512VLBW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512VLBW-NEXT: vporq %zmm0, %zmm3, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: var_rotate_v64i8:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vmovdqa64 {{.*#+}} zmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VBMI2-NEXT: vpsubb %zmm1, %zmm2, %zmm2
|
|
; AVX512VBMI2-NEXT: vpsllw $4, %zmm0, %zmm3
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VBMI2-NEXT: vpsllw $5, %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VBMI2-NEXT: vpblendmb %zmm3, %zmm0, %zmm3 {%k1}
|
|
; AVX512VBMI2-NEXT: vpsllw $2, %zmm3, %zmm4
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm4, %zmm4
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VBMI2-NEXT: vmovdqu8 %zmm4, %zmm3 {%k1}
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm3, %zmm3, %zmm3 {%k1}
|
|
; AVX512VBMI2-NEXT: vpsllw $5, %zmm2, %zmm1
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm2
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k2
|
|
; AVX512VBMI2-NEXT: vpsrlw $4, %zmm0, %zmm1
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k2}
|
|
; AVX512VBMI2-NEXT: vpsrlw $2, %zmm0, %zmm1
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512VBMI2-NEXT: vpsrlw $1, %zmm0, %zmm1
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm2, %zmm2, %zmm2
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512VBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512VBMI2-NEXT: vporq %zmm0, %zmm3, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: var_rotate_v64i8:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vmovdqa64 {{.*#+}} zmm2 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VLVBMI2-NEXT: vpsubb %zmm1, %zmm2, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpsllw $4, %zmm0, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpsllw $5, %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLVBMI2-NEXT: vpblendmb %zmm3, %zmm0, %zmm3 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpsllw $2, %zmm3, %zmm4
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm4, %zmm4
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm4, %zmm3 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm3, %zmm3, %zmm3 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpsllw $5, %zmm2, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k2
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $4, %zmm0, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k2}
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $2, %zmm0, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $1, %zmm0, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm2, %zmm2, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm2, %k1
|
|
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vporq %zmm0, %zmm3, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%b8 = sub <64 x i8> <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>, %b
|
|
%shl = shl <64 x i8> %a, %b
|
|
%lshr = lshr <64 x i8> %a, %b8
|
|
%or = or <64 x i8> %shl, %lshr
|
|
ret <64 x i8> %or
|
|
}
|
|
|
|
;
|
|
; Uniform Variable Rotates
|
|
;
|
|
|
|
define <8 x i64> @splatvar_rotate_v8i64(<8 x i64> %a, <8 x i64> %b) nounwind {
|
|
; AVX512-LABEL: splatvar_rotate_v8i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpbroadcastq %xmm1, %zmm1
|
|
; AVX512-NEXT: vprolvq %zmm1, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%splat = shufflevector <8 x i64> %b, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%splat64 = sub <8 x i64> <i64 64, i64 64, i64 64, i64 64, i64 64, i64 64, i64 64, i64 64>, %splat
|
|
%shl = shl <8 x i64> %a, %splat
|
|
%lshr = lshr <8 x i64> %a, %splat64
|
|
%or = or <8 x i64> %shl, %lshr
|
|
ret <8 x i64> %or
|
|
}
|
|
|
|
define <16 x i32> @splatvar_rotate_v16i32(<16 x i32> %a, <16 x i32> %b) nounwind {
|
|
; AVX512-LABEL: splatvar_rotate_v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpbroadcastd %xmm1, %zmm1
|
|
; AVX512-NEXT: vprolvd %zmm1, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%splat = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%splat32 = sub <16 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>, %splat
|
|
%shl = shl <16 x i32> %a, %splat
|
|
%lshr = lshr <16 x i32> %a, %splat32
|
|
%or = or <16 x i32> %shl, %lshr
|
|
ret <16 x i32> %or
|
|
}
|
|
|
|
define <32 x i16> @splatvar_rotate_v32i16(<32 x i16> %a, <32 x i16> %b) nounwind {
|
|
; AVX512F-LABEL: splatvar_rotate_v32i16:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
|
|
; AVX512F-NEXT: vpsubw %xmm1, %xmm3, %xmm1
|
|
; AVX512F-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm3
|
|
; AVX512F-NEXT: vpsllw %xmm2, %ymm3, %ymm4
|
|
; AVX512F-NEXT: vpsllw %xmm2, %ymm0, %ymm2
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm4, %zmm2, %zmm2
|
|
; AVX512F-NEXT: vpsrlw %xmm1, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: splatvar_rotate_v32i16:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
|
|
; AVX512VL-NEXT: vpsubw %xmm1, %xmm3, %xmm1
|
|
; AVX512VL-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm3
|
|
; AVX512VL-NEXT: vpsllw %xmm2, %ymm3, %ymm4
|
|
; AVX512VL-NEXT: vpsllw %xmm2, %ymm0, %ymm2
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm4, %zmm2, %zmm2
|
|
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: splatvar_rotate_v32i16:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
|
|
; AVX512BW-NEXT: vpsubw %xmm1, %xmm3, %xmm1
|
|
; AVX512BW-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512BW-NEXT: vpsllw %xmm2, %zmm0, %zmm2
|
|
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: splatvar_rotate_v32i16:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
|
|
; AVX512VLBW-NEXT: vpsubw %xmm1, %xmm3, %xmm1
|
|
; AVX512VLBW-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX512VLBW-NEXT: vpsllw %xmm2, %zmm0, %zmm2
|
|
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: splatvar_rotate_v32i16:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpbroadcastw %xmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpshldvw %zmm1, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: splatvar_rotate_v32i16:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpbroadcastw %xmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpshldvw %zmm1, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%splat = shufflevector <32 x i16> %b, <32 x i16> undef, <32 x i32> zeroinitializer
|
|
%splat16 = sub <32 x i16> <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>, %splat
|
|
%shl = shl <32 x i16> %a, %splat
|
|
%lshr = lshr <32 x i16> %a, %splat16
|
|
%or = or <32 x i16> %shl, %lshr
|
|
ret <32 x i16> %or
|
|
}
|
|
|
|
define <64 x i8> @splatvar_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|
; AVX512F-LABEL: splatvar_rotate_v64i8:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512F-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
|
; AVX512F-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm3
|
|
; AVX512F-NEXT: vpsllw %xmm2, %ymm3, %ymm4
|
|
; AVX512F-NEXT: vpsllw %xmm2, %ymm0, %ymm5
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm4, %zmm5, %zmm4
|
|
; AVX512F-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
|
; AVX512F-NEXT: vpsllw %xmm2, %xmm5, %xmm2
|
|
; AVX512F-NEXT: vpbroadcastb %xmm2, %ymm2
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm2, %zmm2, %zmm2
|
|
; AVX512F-NEXT: vpandq %zmm2, %zmm4, %zmm2
|
|
; AVX512F-NEXT: vpsrlw %xmm1, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm0, %zmm3
|
|
; AVX512F-NEXT: vpsrlw %xmm1, %xmm5, %xmm0
|
|
; AVX512F-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512F-NEXT: vpbroadcastb %xmm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: splatvar_rotate_v64i8:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VL-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
|
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm3
|
|
; AVX512VL-NEXT: vpsllw %xmm2, %ymm3, %ymm4
|
|
; AVX512VL-NEXT: vpsllw %xmm2, %ymm0, %ymm5
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm4, %zmm5, %zmm4
|
|
; AVX512VL-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
|
; AVX512VL-NEXT: vpsllw %xmm2, %xmm5, %xmm2
|
|
; AVX512VL-NEXT: vpbroadcastb %xmm2, %ymm2
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm2, %zmm2
|
|
; AVX512VL-NEXT: vpandq %zmm2, %zmm4, %zmm2
|
|
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm0, %zmm3
|
|
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm5, %xmm0
|
|
; AVX512VL-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512VL-NEXT: vpbroadcastb %xmm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: splatvar_rotate_v64i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512BW-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
|
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512BW-NEXT: vpsllw %xmm2, %zmm0, %zmm3
|
|
; AVX512BW-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
|
; AVX512BW-NEXT: vpsllw %xmm2, %xmm4, %xmm2
|
|
; AVX512BW-NEXT: vpbroadcastb %xmm2, %zmm2
|
|
; AVX512BW-NEXT: vpandq %zmm2, %zmm3, %zmm2
|
|
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
|
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
|
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512BW-NEXT: vpbroadcastb %xmm0, %zmm0
|
|
; AVX512BW-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: splatvar_rotate_v64i8:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VLBW-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
|
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VLBW-NEXT: vpsllw %xmm2, %zmm0, %zmm3
|
|
; AVX512VLBW-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
|
; AVX512VLBW-NEXT: vpsllw %xmm2, %xmm4, %xmm2
|
|
; AVX512VLBW-NEXT: vpbroadcastb %xmm2, %zmm2
|
|
; AVX512VLBW-NEXT: vpandq %zmm2, %zmm3, %zmm2
|
|
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
|
; AVX512VLBW-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
|
; AVX512VLBW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: vpbroadcastb %xmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: splatvar_rotate_v64i8:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VBMI2-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VBMI2-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
|
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VBMI2-NEXT: vpsllw %xmm2, %zmm0, %zmm3
|
|
; AVX512VBMI2-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
|
; AVX512VBMI2-NEXT: vpsllw %xmm2, %xmm4, %xmm2
|
|
; AVX512VBMI2-NEXT: vpbroadcastb %xmm2, %zmm2
|
|
; AVX512VBMI2-NEXT: vpandq %zmm2, %zmm3, %zmm2
|
|
; AVX512VBMI2-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
|
; AVX512VBMI2-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
|
; AVX512VBMI2-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512VBMI2-NEXT: vpbroadcastb %xmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: splatvar_rotate_v64i8:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VLVBMI2-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX512VLVBMI2-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
|
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
|
; AVX512VLVBMI2-NEXT: vpsllw %xmm2, %zmm0, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
|
; AVX512VLVBMI2-NEXT: vpsllw %xmm2, %xmm4, %xmm2
|
|
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm2, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpandq %zmm2, %zmm3, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%splat = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
|
|
%splat8 = sub <64 x i8> <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>, %splat
|
|
%shl = shl <64 x i8> %a, %splat
|
|
%lshr = lshr <64 x i8> %a, %splat8
|
|
%or = or <64 x i8> %shl, %lshr
|
|
ret <64 x i8> %or
|
|
}
|
|
|
|
;
|
|
; Constant Rotates
|
|
;
|
|
|
|
define <8 x i64> @constant_rotate_v8i64(<8 x i64> %a) nounwind {
|
|
; AVX512-LABEL: constant_rotate_v8i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprolvq {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%shl = shl <8 x i64> %a, <i64 4, i64 14, i64 50, i64 60, i64 4, i64 14, i64 50, i64 60>
|
|
%lshr = lshr <8 x i64> %a, <i64 60, i64 50, i64 14, i64 4, i64 60, i64 50, i64 14, i64 4>
|
|
%or = or <8 x i64> %shl, %lshr
|
|
ret <8 x i64> %or
|
|
}
|
|
|
|
define <16 x i32> @constant_rotate_v16i32(<16 x i32> %a) nounwind {
|
|
; AVX512-LABEL: constant_rotate_v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprolvd {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%shl = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
|
|
%lshr = lshr <16 x i32> %a, <i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21>
|
|
%or = or <16 x i32> %shl, %lshr
|
|
ret <16 x i32> %or
|
|
}
|
|
|
|
define <32 x i16> @constant_rotate_v32i16(<32 x i16> %a) nounwind {
|
|
; AVX512F-LABEL: constant_rotate_v32i16:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm2 = [1,2,4,8,16,32,64,128,256,512,1024,2048,4096,8192,16384,32768]
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm1, %ymm3
|
|
; AVX512F-NEXT: vpmullw %ymm2, %ymm0, %ymm4
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm4, %zmm3
|
|
; AVX512F-NEXT: vpmulhuw %ymm2, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpmulhuw %ymm2, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vporq %zmm0, %zmm3, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: constant_rotate_v32i16:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [1,2,4,8,16,32,64,128,256,512,1024,2048,4096,8192,16384,32768]
|
|
; AVX512VL-NEXT: vpmullw %ymm2, %ymm1, %ymm3
|
|
; AVX512VL-NEXT: vpmullw %ymm2, %ymm0, %ymm4
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm4, %zmm3
|
|
; AVX512VL-NEXT: vpmulhuw %ymm2, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpmulhuw %ymm2, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vporq %zmm0, %zmm3, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: constant_rotate_v32i16:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpsllvw {{.*}}(%rip), %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpsrlvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: constant_rotate_v32i16:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpsllvw {{.*}}(%rip), %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpsrlvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: constant_rotate_v32i16:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpshldvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: constant_rotate_v32i16:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpshldvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%shl = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
|
|
%lshr = lshr <32 x i16> %a, <i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1>
|
|
%or = or <32 x i16> %shl, %lshr
|
|
ret <32 x i16> %or
|
|
}
|
|
|
|
define <64 x i8> @constant_rotate_v64i8(<64 x i8> %a) nounwind {
|
|
; AVX512F-LABEL: constant_rotate_v64i8:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; AVX512F-NEXT: vpsllw $4, %ymm1, %ymm2
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm3 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
|
; AVX512F-NEXT: vpand %ymm3, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vbroadcasti128 {{.*#+}} ymm4 = [8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256]
|
|
; AVX512F-NEXT: # ymm4 = mem[0,1,0,1]
|
|
; AVX512F-NEXT: vpblendvb %ymm4, %ymm2, %ymm1, %ymm2
|
|
; AVX512F-NEXT: vpsllw $2, %ymm2, %ymm5
|
|
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm6 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252]
|
|
; AVX512F-NEXT: vpand %ymm6, %ymm5, %ymm5
|
|
; AVX512F-NEXT: vpaddb %ymm4, %ymm4, %ymm7
|
|
; AVX512F-NEXT: vpblendvb %ymm7, %ymm5, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vpaddb %ymm2, %ymm2, %ymm5
|
|
; AVX512F-NEXT: vpaddb %ymm7, %ymm7, %ymm8
|
|
; AVX512F-NEXT: vpblendvb %ymm8, %ymm5, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vpsllw $4, %ymm0, %ymm5
|
|
; AVX512F-NEXT: vpand %ymm3, %ymm5, %ymm3
|
|
; AVX512F-NEXT: vpblendvb %ymm4, %ymm3, %ymm0, %ymm3
|
|
; AVX512F-NEXT: vpsllw $2, %ymm3, %ymm4
|
|
; AVX512F-NEXT: vpand %ymm6, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpblendvb %ymm7, %ymm4, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vpaddb %ymm3, %ymm3, %ymm4
|
|
; AVX512F-NEXT: vpblendvb %ymm8, %ymm4, %ymm3, %ymm3
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm2, %zmm3, %zmm2
|
|
; AVX512F-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
|
; AVX512F-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm1[8],ymm3[8],ymm1[9],ymm3[9],ymm1[10],ymm3[10],ymm1[11],ymm3[11],ymm1[12],ymm3[12],ymm1[13],ymm3[13],ymm1[14],ymm3[14],ymm1[15],ymm3[15],ymm1[24],ymm3[24],ymm1[25],ymm3[25],ymm1[26],ymm3[26],ymm1[27],ymm3[27],ymm1[28],ymm3[28],ymm1[29],ymm3[29],ymm1[30],ymm3[30],ymm1[31],ymm3[31]
|
|
; AVX512F-NEXT: vbroadcasti128 {{.*#+}} ymm5 = [256,128,64,32,16,8,4,2,256,128,64,32,16,8,4,2]
|
|
; AVX512F-NEXT: # ymm5 = mem[0,1,0,1]
|
|
; AVX512F-NEXT: vpmullw %ymm5, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpsrlw $8, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[4],ymm3[4],ymm1[5],ymm3[5],ymm1[6],ymm3[6],ymm1[7],ymm3[7],ymm1[16],ymm3[16],ymm1[17],ymm3[17],ymm1[18],ymm3[18],ymm1[19],ymm3[19],ymm1[20],ymm3[20],ymm1[21],ymm3[21],ymm1[22],ymm3[22],ymm1[23],ymm3[23]
|
|
; AVX512F-NEXT: vbroadcasti128 {{.*#+}} ymm6 = [1,2,4,8,16,32,64,128,1,2,4,8,16,32,64,128]
|
|
; AVX512F-NEXT: # ymm6 = mem[0,1,0,1]
|
|
; AVX512F-NEXT: vpmullw %ymm6, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpsrlw $8, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpackuswb %ymm4, %ymm1, %ymm1
|
|
; AVX512F-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm0[8],ymm3[8],ymm0[9],ymm3[9],ymm0[10],ymm3[10],ymm0[11],ymm3[11],ymm0[12],ymm3[12],ymm0[13],ymm3[13],ymm0[14],ymm3[14],ymm0[15],ymm3[15],ymm0[24],ymm3[24],ymm0[25],ymm3[25],ymm0[26],ymm3[26],ymm0[27],ymm3[27],ymm0[28],ymm3[28],ymm0[29],ymm3[29],ymm0[30],ymm3[30],ymm0[31],ymm3[31]
|
|
; AVX512F-NEXT: vpmullw %ymm5, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpsrlw $8, %ymm4, %ymm4
|
|
; AVX512F-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[4],ymm3[4],ymm0[5],ymm3[5],ymm0[6],ymm3[6],ymm0[7],ymm3[7],ymm0[16],ymm3[16],ymm0[17],ymm3[17],ymm0[18],ymm3[18],ymm0[19],ymm3[19],ymm0[20],ymm3[20],ymm0[21],ymm3[21],ymm0[22],ymm3[22],ymm0[23],ymm3[23]
|
|
; AVX512F-NEXT: vpmullw %ymm6, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpackuswb %ymm4, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: constant_rotate_v64i8:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm1, %ymm2
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm3 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
|
; AVX512VL-NEXT: vpand %ymm3, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vbroadcasti128 {{.*#+}} ymm4 = [8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256]
|
|
; AVX512VL-NEXT: # ymm4 = mem[0,1,0,1]
|
|
; AVX512VL-NEXT: vpblendvb %ymm4, %ymm2, %ymm1, %ymm2
|
|
; AVX512VL-NEXT: vpsllw $2, %ymm2, %ymm5
|
|
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm6 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252]
|
|
; AVX512VL-NEXT: vpand %ymm6, %ymm5, %ymm5
|
|
; AVX512VL-NEXT: vpaddb %ymm4, %ymm4, %ymm7
|
|
; AVX512VL-NEXT: vpblendvb %ymm7, %ymm5, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm5
|
|
; AVX512VL-NEXT: vpaddb %ymm7, %ymm7, %ymm8
|
|
; AVX512VL-NEXT: vpblendvb %ymm8, %ymm5, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm5
|
|
; AVX512VL-NEXT: vpand %ymm3, %ymm5, %ymm3
|
|
; AVX512VL-NEXT: vpblendvb %ymm4, %ymm3, %ymm0, %ymm3
|
|
; AVX512VL-NEXT: vpsllw $2, %ymm3, %ymm4
|
|
; AVX512VL-NEXT: vpand %ymm6, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpblendvb %ymm7, %ymm4, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm4
|
|
; AVX512VL-NEXT: vpblendvb %ymm8, %ymm4, %ymm3, %ymm3
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm3, %zmm2
|
|
; AVX512VL-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
|
; AVX512VL-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm1[8],ymm3[8],ymm1[9],ymm3[9],ymm1[10],ymm3[10],ymm1[11],ymm3[11],ymm1[12],ymm3[12],ymm1[13],ymm3[13],ymm1[14],ymm3[14],ymm1[15],ymm3[15],ymm1[24],ymm3[24],ymm1[25],ymm3[25],ymm1[26],ymm3[26],ymm1[27],ymm3[27],ymm1[28],ymm3[28],ymm1[29],ymm3[29],ymm1[30],ymm3[30],ymm1[31],ymm3[31]
|
|
; AVX512VL-NEXT: vbroadcasti128 {{.*#+}} ymm5 = [256,128,64,32,16,8,4,2,256,128,64,32,16,8,4,2]
|
|
; AVX512VL-NEXT: # ymm5 = mem[0,1,0,1]
|
|
; AVX512VL-NEXT: vpmullw %ymm5, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpsrlw $8, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[4],ymm3[4],ymm1[5],ymm3[5],ymm1[6],ymm3[6],ymm1[7],ymm3[7],ymm1[16],ymm3[16],ymm1[17],ymm3[17],ymm1[18],ymm3[18],ymm1[19],ymm3[19],ymm1[20],ymm3[20],ymm1[21],ymm3[21],ymm1[22],ymm3[22],ymm1[23],ymm3[23]
|
|
; AVX512VL-NEXT: vbroadcasti128 {{.*#+}} ymm6 = [1,2,4,8,16,32,64,128,1,2,4,8,16,32,64,128]
|
|
; AVX512VL-NEXT: # ymm6 = mem[0,1,0,1]
|
|
; AVX512VL-NEXT: vpmullw %ymm6, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpsrlw $8, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpackuswb %ymm4, %ymm1, %ymm1
|
|
; AVX512VL-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm0[8],ymm3[8],ymm0[9],ymm3[9],ymm0[10],ymm3[10],ymm0[11],ymm3[11],ymm0[12],ymm3[12],ymm0[13],ymm3[13],ymm0[14],ymm3[14],ymm0[15],ymm3[15],ymm0[24],ymm3[24],ymm0[25],ymm3[25],ymm0[26],ymm3[26],ymm0[27],ymm3[27],ymm0[28],ymm3[28],ymm0[29],ymm3[29],ymm0[30],ymm3[30],ymm0[31],ymm3[31]
|
|
; AVX512VL-NEXT: vpmullw %ymm5, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpsrlw $8, %ymm4, %ymm4
|
|
; AVX512VL-NEXT: vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[4],ymm3[4],ymm0[5],ymm3[5],ymm0[6],ymm3[6],ymm0[7],ymm3[7],ymm0[16],ymm3[16],ymm0[17],ymm3[17],ymm0[18],ymm3[18],ymm0[19],ymm3[19],ymm0[20],ymm3[20],ymm0[21],ymm3[21],ymm0[22],ymm3[22],ymm0[23],ymm3[23]
|
|
; AVX512VL-NEXT: vpmullw %ymm6, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $8, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpackuswb %ymm4, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: constant_rotate_v64i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vbroadcasti32x4 {{.*#+}} zmm1 = [8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256]
|
|
; AVX512BW-NEXT: # zmm1 = mem[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512BW-NEXT: vpsllw $4, %zmm0, %zmm2
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
|
; AVX512BW-NEXT: vpblendmb %zmm2, %zmm0, %zmm2 {%k1}
|
|
; AVX512BW-NEXT: vpsllw $2, %zmm2, %zmm3
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512BW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512BW-NEXT: vmovdqu8 %zmm3, %zmm2 {%k1}
|
|
; AVX512BW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512BW-NEXT: vpaddb %zmm2, %zmm2, %zmm2 {%k1}
|
|
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX512BW-NEXT: vpunpckhbw {{.*#+}} zmm3 = zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[12],zmm1[12],zmm0[13],zmm1[13],zmm0[14],zmm1[14],zmm0[15],zmm1[15],zmm0[24],zmm1[24],zmm0[25],zmm1[25],zmm0[26],zmm1[26],zmm0[27],zmm1[27],zmm0[28],zmm1[28],zmm0[29],zmm1[29],zmm0[30],zmm1[30],zmm0[31],zmm1[31],zmm0[40],zmm1[40],zmm0[41],zmm1[41],zmm0[42],zmm1[42],zmm0[43],zmm1[43],zmm0[44],zmm1[44],zmm0[45],zmm1[45],zmm0[46],zmm1[46],zmm0[47],zmm1[47],zmm0[56],zmm1[56],zmm0[57],zmm1[57],zmm0[58],zmm1[58],zmm0[59],zmm1[59],zmm0[60],zmm1[60],zmm0[61],zmm1[61],zmm0[62],zmm1[62],zmm0[63],zmm1[63]
|
|
; AVX512BW-NEXT: vpsllvw {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512BW-NEXT: vpsrlw $8, %zmm3, %zmm3
|
|
; AVX512BW-NEXT: vpunpcklbw {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[16],zmm1[16],zmm0[17],zmm1[17],zmm0[18],zmm1[18],zmm0[19],zmm1[19],zmm0[20],zmm1[20],zmm0[21],zmm1[21],zmm0[22],zmm1[22],zmm0[23],zmm1[23],zmm0[32],zmm1[32],zmm0[33],zmm1[33],zmm0[34],zmm1[34],zmm0[35],zmm1[35],zmm0[36],zmm1[36],zmm0[37],zmm1[37],zmm0[38],zmm1[38],zmm0[39],zmm1[39],zmm0[48],zmm1[48],zmm0[49],zmm1[49],zmm0[50],zmm1[50],zmm0[51],zmm1[51],zmm0[52],zmm1[52],zmm0[53],zmm1[53],zmm0[54],zmm1[54],zmm0[55],zmm1[55]
|
|
; AVX512BW-NEXT: vpsllvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vpsrlw $8, %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vpackuswb %zmm3, %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: constant_rotate_v64i8:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vbroadcasti32x4 {{.*#+}} zmm1 = [8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256]
|
|
; AVX512VLBW-NEXT: # zmm1 = mem[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLBW-NEXT: vpsllw $4, %zmm0, %zmm2
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
|
; AVX512VLBW-NEXT: vpblendmb %zmm2, %zmm0, %zmm2 {%k1}
|
|
; AVX512VLBW-NEXT: vpsllw $2, %zmm2, %zmm3
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VLBW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLBW-NEXT: vmovdqu8 %zmm3, %zmm2 {%k1}
|
|
; AVX512VLBW-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLBW-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLBW-NEXT: vpaddb %zmm2, %zmm2, %zmm2 {%k1}
|
|
; AVX512VLBW-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX512VLBW-NEXT: vpunpckhbw {{.*#+}} zmm3 = zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[12],zmm1[12],zmm0[13],zmm1[13],zmm0[14],zmm1[14],zmm0[15],zmm1[15],zmm0[24],zmm1[24],zmm0[25],zmm1[25],zmm0[26],zmm1[26],zmm0[27],zmm1[27],zmm0[28],zmm1[28],zmm0[29],zmm1[29],zmm0[30],zmm1[30],zmm0[31],zmm1[31],zmm0[40],zmm1[40],zmm0[41],zmm1[41],zmm0[42],zmm1[42],zmm0[43],zmm1[43],zmm0[44],zmm1[44],zmm0[45],zmm1[45],zmm0[46],zmm1[46],zmm0[47],zmm1[47],zmm0[56],zmm1[56],zmm0[57],zmm1[57],zmm0[58],zmm1[58],zmm0[59],zmm1[59],zmm0[60],zmm1[60],zmm0[61],zmm1[61],zmm0[62],zmm1[62],zmm0[63],zmm1[63]
|
|
; AVX512VLBW-NEXT: vpsllvw {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VLBW-NEXT: vpsrlw $8, %zmm3, %zmm3
|
|
; AVX512VLBW-NEXT: vpunpcklbw {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[16],zmm1[16],zmm0[17],zmm1[17],zmm0[18],zmm1[18],zmm0[19],zmm1[19],zmm0[20],zmm1[20],zmm0[21],zmm1[21],zmm0[22],zmm1[22],zmm0[23],zmm1[23],zmm0[32],zmm1[32],zmm0[33],zmm1[33],zmm0[34],zmm1[34],zmm0[35],zmm1[35],zmm0[36],zmm1[36],zmm0[37],zmm1[37],zmm0[38],zmm1[38],zmm0[39],zmm1[39],zmm0[48],zmm1[48],zmm0[49],zmm1[49],zmm0[50],zmm1[50],zmm0[51],zmm1[51],zmm0[52],zmm1[52],zmm0[53],zmm1[53],zmm0[54],zmm1[54],zmm0[55],zmm1[55]
|
|
; AVX512VLBW-NEXT: vpsllvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vpsrlw $8, %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vpackuswb %zmm3, %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: constant_rotate_v64i8:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vbroadcasti32x4 {{.*#+}} zmm1 = [8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256]
|
|
; AVX512VBMI2-NEXT: # zmm1 = mem[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VBMI2-NEXT: vpsllw $4, %zmm0, %zmm2
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
|
; AVX512VBMI2-NEXT: vpblendmb %zmm2, %zmm0, %zmm2 {%k1}
|
|
; AVX512VBMI2-NEXT: vpsllw $2, %zmm2, %zmm3
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VBMI2-NEXT: vmovdqu8 %zmm3, %zmm2 {%k1}
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VBMI2-NEXT: vpaddb %zmm2, %zmm2, %zmm2 {%k1}
|
|
; AVX512VBMI2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX512VBMI2-NEXT: vpunpckhbw {{.*#+}} zmm3 = zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[12],zmm1[12],zmm0[13],zmm1[13],zmm0[14],zmm1[14],zmm0[15],zmm1[15],zmm0[24],zmm1[24],zmm0[25],zmm1[25],zmm0[26],zmm1[26],zmm0[27],zmm1[27],zmm0[28],zmm1[28],zmm0[29],zmm1[29],zmm0[30],zmm1[30],zmm0[31],zmm1[31],zmm0[40],zmm1[40],zmm0[41],zmm1[41],zmm0[42],zmm1[42],zmm0[43],zmm1[43],zmm0[44],zmm1[44],zmm0[45],zmm1[45],zmm0[46],zmm1[46],zmm0[47],zmm1[47],zmm0[56],zmm1[56],zmm0[57],zmm1[57],zmm0[58],zmm1[58],zmm0[59],zmm1[59],zmm0[60],zmm1[60],zmm0[61],zmm1[61],zmm0[62],zmm1[62],zmm0[63],zmm1[63]
|
|
; AVX512VBMI2-NEXT: vpsllvw {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VBMI2-NEXT: vpsrlw $8, %zmm3, %zmm3
|
|
; AVX512VBMI2-NEXT: vpunpcklbw {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[16],zmm1[16],zmm0[17],zmm1[17],zmm0[18],zmm1[18],zmm0[19],zmm1[19],zmm0[20],zmm1[20],zmm0[21],zmm1[21],zmm0[22],zmm1[22],zmm0[23],zmm1[23],zmm0[32],zmm1[32],zmm0[33],zmm1[33],zmm0[34],zmm1[34],zmm0[35],zmm1[35],zmm0[36],zmm1[36],zmm0[37],zmm1[37],zmm0[38],zmm1[38],zmm0[39],zmm1[39],zmm0[48],zmm1[48],zmm0[49],zmm1[49],zmm0[50],zmm1[50],zmm0[51],zmm1[51],zmm0[52],zmm1[52],zmm0[53],zmm1[53],zmm0[54],zmm1[54],zmm0[55],zmm1[55]
|
|
; AVX512VBMI2-NEXT: vpsllvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: vpsrlw $8, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: vpackuswb %zmm3, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: constant_rotate_v64i8:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vbroadcasti32x4 {{.*#+}} zmm1 = [8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256,8192,24640,41088,57536,57600,41152,24704,8256]
|
|
; AVX512VLVBMI2-NEXT: # zmm1 = mem[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLVBMI2-NEXT: vpsllw $4, %zmm0, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpblendmb %zmm2, %zmm0, %zmm2 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpsllw $2, %zmm2, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm3, %zmm2 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm1, %zmm1, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpmovb2m %zmm1, %k1
|
|
; AVX512VLVBMI2-NEXT: vpaddb %zmm2, %zmm2, %zmm2 {%k1}
|
|
; AVX512VLVBMI2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX512VLVBMI2-NEXT: vpunpckhbw {{.*#+}} zmm3 = zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[12],zmm1[12],zmm0[13],zmm1[13],zmm0[14],zmm1[14],zmm0[15],zmm1[15],zmm0[24],zmm1[24],zmm0[25],zmm1[25],zmm0[26],zmm1[26],zmm0[27],zmm1[27],zmm0[28],zmm1[28],zmm0[29],zmm1[29],zmm0[30],zmm1[30],zmm0[31],zmm1[31],zmm0[40],zmm1[40],zmm0[41],zmm1[41],zmm0[42],zmm1[42],zmm0[43],zmm1[43],zmm0[44],zmm1[44],zmm0[45],zmm1[45],zmm0[46],zmm1[46],zmm0[47],zmm1[47],zmm0[56],zmm1[56],zmm0[57],zmm1[57],zmm0[58],zmm1[58],zmm0[59],zmm1[59],zmm0[60],zmm1[60],zmm0[61],zmm1[61],zmm0[62],zmm1[62],zmm0[63],zmm1[63]
|
|
; AVX512VLVBMI2-NEXT: vpsllvw {{.*}}(%rip), %zmm3, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $8, %zmm3, %zmm3
|
|
; AVX512VLVBMI2-NEXT: vpunpcklbw {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[16],zmm1[16],zmm0[17],zmm1[17],zmm0[18],zmm1[18],zmm0[19],zmm1[19],zmm0[20],zmm1[20],zmm0[21],zmm1[21],zmm0[22],zmm1[22],zmm0[23],zmm1[23],zmm0[32],zmm1[32],zmm0[33],zmm1[33],zmm0[34],zmm1[34],zmm0[35],zmm1[35],zmm0[36],zmm1[36],zmm0[37],zmm1[37],zmm0[38],zmm1[38],zmm0[39],zmm1[39],zmm0[48],zmm1[48],zmm0[49],zmm1[49],zmm0[50],zmm1[50],zmm0[51],zmm1[51],zmm0[52],zmm1[52],zmm0[53],zmm1[53],zmm0[54],zmm1[54],zmm0[55],zmm1[55]
|
|
; AVX512VLVBMI2-NEXT: vpsllvw {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $8, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vpackuswb %zmm3, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vporq %zmm0, %zmm2, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%shl = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1>
|
|
%lshr = lshr <64 x i8> %a, <i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>
|
|
%or = or <64 x i8> %shl, %lshr
|
|
ret <64 x i8> %or
|
|
}
|
|
|
|
;
|
|
; Uniform Constant Rotates
|
|
;
|
|
|
|
define <8 x i64> @splatconstant_rotate_v8i64(<8 x i64> %a) nounwind {
|
|
; AVX512-LABEL: splatconstant_rotate_v8i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprolq $14, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%shl = shl <8 x i64> %a, <i64 14, i64 14, i64 14, i64 14, i64 14, i64 14, i64 14, i64 14>
|
|
%lshr = lshr <8 x i64> %a, <i64 50, i64 50, i64 50, i64 50, i64 50, i64 50, i64 50, i64 50>
|
|
%or = or <8 x i64> %shl, %lshr
|
|
ret <8 x i64> %or
|
|
}
|
|
|
|
define <16 x i32> @splatconstant_rotate_v16i32(<16 x i32> %a) nounwind {
|
|
; AVX512-LABEL: splatconstant_rotate_v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprold $4, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%shl = shl <16 x i32> %a, <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
|
|
%lshr = lshr <16 x i32> %a, <i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28>
|
|
%or = or <16 x i32> %shl, %lshr
|
|
ret <16 x i32> %or
|
|
}
|
|
|
|
define <32 x i16> @splatconstant_rotate_v32i16(<32 x i16> %a) nounwind {
|
|
; AVX512F-LABEL: splatconstant_rotate_v32i16:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vpsllw $7, %ymm0, %ymm1
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512F-NEXT: vpsllw $7, %ymm2, %ymm3
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vpsrlw $9, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $9, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: splatconstant_rotate_v32i16:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vpsllw $7, %ymm0, %ymm1
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512VL-NEXT: vpsllw $7, %ymm2, %ymm3
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512VL-NEXT: vpsrlw $9, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $9, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: splatconstant_rotate_v32i16:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpsllw $7, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpsrlw $9, %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: splatconstant_rotate_v32i16:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpsllw $7, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpsrlw $9, %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: splatconstant_rotate_v32i16:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpshldw $7, %zmm0, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: splatconstant_rotate_v32i16:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpshldw $7, %zmm0, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%shl = shl <32 x i16> %a, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
|
|
%lshr = lshr <32 x i16> %a, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
|
|
%or = or <32 x i16> %shl, %lshr
|
|
ret <32 x i16> %or
|
|
}
|
|
|
|
define <64 x i8> @splatconstant_rotate_v64i8(<64 x i8> %a) nounwind {
|
|
; AVX512F-LABEL: splatconstant_rotate_v64i8:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vpsllw $4, %ymm0, %ymm1
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512F-NEXT: vpsllw $4, %ymm2, %ymm3
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $4, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
|
; AVX512F-NEXT: vpternlogq $216, {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: splatconstant_rotate_v64i8:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm1
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm2, %ymm3
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $4, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
|
; AVX512VL-NEXT: vpternlogq $216, {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: splatconstant_rotate_v64i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm0
|
|
; AVX512BW-NEXT: vpternlogq $216, {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: splatconstant_rotate_v64i8:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpsrlw $4, %zmm0, %zmm0
|
|
; AVX512VLBW-NEXT: vpternlogq $216, {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: splatconstant_rotate_v64i8:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512VBMI2-NEXT: vpsrlw $4, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: vpternlogq $216, {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: splatconstant_rotate_v64i8:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $4, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vpternlogq $216, {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%shl = shl <64 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
|
|
%lshr = lshr <64 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
|
|
%or = or <64 x i8> %shl, %lshr
|
|
ret <64 x i8> %or
|
|
}
|
|
|
|
;
|
|
; Masked Uniform Constant Rotates
|
|
;
|
|
|
|
define <8 x i64> @splatconstant_rotate_mask_v8i64(<8 x i64> %a) nounwind {
|
|
; AVX512-LABEL: splatconstant_rotate_mask_v8i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprolq $15, %zmm0, %zmm0
|
|
; AVX512-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%shl = shl <8 x i64> %a, <i64 15, i64 15, i64 15, i64 15, i64 15, i64 15, i64 15, i64 15>
|
|
%lshr = lshr <8 x i64> %a, <i64 49, i64 49, i64 49, i64 49, i64 49, i64 49, i64 49, i64 49>
|
|
%rmask = and <8 x i64> %lshr, <i64 255, i64 127, i64 127, i64 255, i64 255, i64 127, i64 127, i64 255>
|
|
%lmask = and <8 x i64> %shl, <i64 33, i64 65, i64 129, i64 257, i64 33, i64 65, i64 129, i64 257>
|
|
%or = or <8 x i64> %lmask, %rmask
|
|
ret <8 x i64> %or
|
|
}
|
|
|
|
define <16 x i32> @splatconstant_rotate_mask_v16i32(<16 x i32> %a) nounwind {
|
|
; AVX512-LABEL: splatconstant_rotate_mask_v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vprold $4, %zmm0, %zmm0
|
|
; AVX512-NEXT: vpandd {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%shl = shl <16 x i32> %a, <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
|
|
%lshr = lshr <16 x i32> %a, <i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28, i32 28>
|
|
%rmask = and <16 x i32> %lshr, <i32 3, i32 7, i32 15, i32 31, i32 63, i32 127, i32 255, i32 511, i32 3, i32 7, i32 15, i32 31, i32 63, i32 127, i32 255, i32 511>
|
|
%lmask = and <16 x i32> %shl, <i32 511, i32 255, i32 127, i32 63, i32 31, i32 15, i32 7, i32 3, i32 511, i32 255, i32 127, i32 63, i32 31, i32 15, i32 7, i32 3>
|
|
%or = or <16 x i32> %lmask, %rmask
|
|
ret <16 x i32> %or
|
|
}
|
|
|
|
define <32 x i16> @splatconstant_rotate_mask_v32i16(<32 x i16> %a) nounwind {
|
|
; AVX512F-LABEL: splatconstant_rotate_mask_v32i16:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vpsllw $5, %ymm0, %ymm1
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512F-NEXT: vpsllw $5, %ymm2, %ymm3
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vpsrlw $11, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $11, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm2
|
|
; AVX512F-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512F-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: splatconstant_rotate_mask_v32i16:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vpsllw $5, %ymm0, %ymm1
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512VL-NEXT: vpsllw $5, %ymm2, %ymm3
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512VL-NEXT: vpsrlw $11, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $11, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm2
|
|
; AVX512VL-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: splatconstant_rotate_mask_v32i16:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpsllw $5, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpsrlw $11, %zmm0, %zmm2
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512BW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v32i16:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpsllw $5, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpsrlw $11, %zmm0, %zmm2
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VLBW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: splatconstant_rotate_mask_v32i16:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpshldw $5, %zmm0, %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: splatconstant_rotate_mask_v32i16:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpshldw $5, %zmm0, %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%shl = shl <32 x i16> %a, <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
|
|
%lshr = lshr <32 x i16> %a, <i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11>
|
|
%rmask = and <32 x i16> %lshr, <i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55>
|
|
%lmask = and <32 x i16> %shl, <i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33>
|
|
%or = or <32 x i16> %lmask, %rmask
|
|
ret <32 x i16> %or
|
|
}
|
|
|
|
define <64 x i8> @splatconstant_rotate_mask_v64i8(<64 x i8> %a) nounwind {
|
|
; AVX512F-LABEL: splatconstant_rotate_mask_v64i8:
|
|
; AVX512F: # %bb.0:
|
|
; AVX512F-NEXT: vpsllw $4, %ymm0, %ymm1
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512F-NEXT: vpsllw $4, %ymm2, %ymm3
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vpsrlw $4, %ymm0, %ymm0
|
|
; AVX512F-NEXT: vpsrlw $4, %ymm2, %ymm2
|
|
; AVX512F-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm2
|
|
; AVX512F-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512F-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: splatconstant_rotate_mask_v64i8:
|
|
; AVX512VL: # %bb.0:
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm1
|
|
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
|
; AVX512VL-NEXT: vpsllw $4, %ymm2, %ymm3
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm3, %zmm1, %zmm1
|
|
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm0
|
|
; AVX512VL-NEXT: vpsrlw $4, %ymm2, %ymm2
|
|
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm2
|
|
; AVX512VL-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512VL-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: splatconstant_rotate_mask_v64i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm2
|
|
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512BW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512BW-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v64i8:
|
|
; AVX512VLBW: # %bb.0:
|
|
; AVX512VLBW-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512VLBW-NEXT: vpsrlw $4, %zmm0, %zmm2
|
|
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VLBW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512VLBW-NEXT: retq
|
|
;
|
|
; AVX512VBMI2-LABEL: splatconstant_rotate_mask_v64i8:
|
|
; AVX512VBMI2: # %bb.0:
|
|
; AVX512VBMI2-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512VBMI2-NEXT: vpsrlw $4, %zmm0, %zmm2
|
|
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VBMI2-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512VBMI2-NEXT: retq
|
|
;
|
|
; AVX512VLVBMI2-LABEL: splatconstant_rotate_mask_v64i8:
|
|
; AVX512VLVBMI2: # %bb.0:
|
|
; AVX512VLVBMI2-NEXT: vpsllw $4, %zmm0, %zmm1
|
|
; AVX512VLVBMI2-NEXT: vpsrlw $4, %zmm0, %zmm2
|
|
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
|
; AVX512VLVBMI2-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
|
; AVX512VLVBMI2-NEXT: retq
|
|
%shl = shl <64 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
|
|
%lshr = lshr <64 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
|
|
%rmask = and <64 x i8> %lshr, <i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55>
|
|
%lmask = and <64 x i8> %shl, <i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33>
|
|
%or = or <64 x i8> %lmask, %rmask
|
|
ret <64 x i8> %or
|
|
}
|