forked from OSchip/llvm-project
547 lines
24 KiB
LLVM
547 lines
24 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX1
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX2 --check-prefix=AVX2NOBW
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX2 --check-prefix=AVX512BW
|
|
|
|
;
|
|
; udiv by 7
|
|
;
|
|
|
|
define <4 x i64> @test_div7_4i64(<4 x i64> %a) nounwind {
|
|
; AVX1-LABEL: test_div7_4i64:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vpextrq $1, %xmm1, %rcx
|
|
; AVX1-NEXT: movabsq $2635249153387078803, %rsi # imm = 0x2492492492492493
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: subq %rdx, %rcx
|
|
; AVX1-NEXT: shrq %rcx
|
|
; AVX1-NEXT: addq %rdx, %rcx
|
|
; AVX1-NEXT: shrq $2, %rcx
|
|
; AVX1-NEXT: vmovq %rcx, %xmm2
|
|
; AVX1-NEXT: vmovq %xmm1, %rcx
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: subq %rdx, %rcx
|
|
; AVX1-NEXT: shrq %rcx
|
|
; AVX1-NEXT: addq %rdx, %rcx
|
|
; AVX1-NEXT: shrq $2, %rcx
|
|
; AVX1-NEXT: vmovq %rcx, %xmm1
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX1-NEXT: vpextrq $1, %xmm0, %rcx
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: subq %rdx, %rcx
|
|
; AVX1-NEXT: shrq %rcx
|
|
; AVX1-NEXT: addq %rdx, %rcx
|
|
; AVX1-NEXT: shrq $2, %rcx
|
|
; AVX1-NEXT: vmovq %rcx, %xmm2
|
|
; AVX1-NEXT: vmovq %xmm0, %rcx
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: subq %rdx, %rcx
|
|
; AVX1-NEXT: shrq %rcx
|
|
; AVX1-NEXT: addq %rdx, %rcx
|
|
; AVX1-NEXT: shrq $2, %rcx
|
|
; AVX1-NEXT: vmovq %rcx, %xmm0
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: test_div7_4i64:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-NEXT: vpextrq $1, %xmm1, %rcx
|
|
; AVX2-NEXT: movabsq $2635249153387078803, %rsi # imm = 0x2492492492492493
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: subq %rdx, %rcx
|
|
; AVX2-NEXT: shrq %rcx
|
|
; AVX2-NEXT: addq %rdx, %rcx
|
|
; AVX2-NEXT: shrq $2, %rcx
|
|
; AVX2-NEXT: vmovq %rcx, %xmm2
|
|
; AVX2-NEXT: vmovq %xmm1, %rcx
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: subq %rdx, %rcx
|
|
; AVX2-NEXT: shrq %rcx
|
|
; AVX2-NEXT: addq %rdx, %rcx
|
|
; AVX2-NEXT: shrq $2, %rcx
|
|
; AVX2-NEXT: vmovq %rcx, %xmm1
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX2-NEXT: vpextrq $1, %xmm0, %rcx
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: subq %rdx, %rcx
|
|
; AVX2-NEXT: shrq %rcx
|
|
; AVX2-NEXT: addq %rdx, %rcx
|
|
; AVX2-NEXT: shrq $2, %rcx
|
|
; AVX2-NEXT: vmovq %rcx, %xmm2
|
|
; AVX2-NEXT: vmovq %xmm0, %rcx
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: subq %rdx, %rcx
|
|
; AVX2-NEXT: shrq %rcx
|
|
; AVX2-NEXT: addq %rdx, %rcx
|
|
; AVX2-NEXT: shrq $2, %rcx
|
|
; AVX2-NEXT: vmovq %rcx, %xmm0
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
%res = udiv <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
|
|
ret <4 x i64> %res
|
|
}
|
|
|
|
define <8 x i32> @test_div7_8i32(<8 x i32> %a) nounwind {
|
|
; AVX1-LABEL: test_div7_8i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [613566757,613566757,613566757,613566757]
|
|
; AVX1-NEXT: vpmuludq %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpmuludq %xmm2, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm3[0,1],xmm1[2,3],xmm3[4,5],xmm1[6,7]
|
|
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpsrld $1, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpaddd %xmm1, %xmm3, %xmm1
|
|
; AVX1-NEXT: vpsrld $2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuludq %xmm2, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpmuludq %xmm2, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0,1],xmm3[2,3],xmm2[4,5],xmm3[6,7]
|
|
; AVX1-NEXT: vpsubd %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrld $1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpaddd %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrld $2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: test_div7_8i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [613566757,613566757,613566757,613566757,613566757,613566757,613566757,613566757]
|
|
; AVX2-NEXT: vpmuludq %ymm2, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpmuludq %ymm2, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2],ymm1[3],ymm2[4],ymm1[5],ymm2[6],ymm1[7]
|
|
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpsrld $1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpsrld $2, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
%res = udiv <8 x i32> %a, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
|
|
ret <8 x i32> %res
|
|
}
|
|
|
|
define <16 x i16> @test_div7_16i16(<16 x i16> %a) nounwind {
|
|
; AVX1-LABEL: test_div7_16i16:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [9363,9363,9363,9363,9363,9363,9363,9363]
|
|
; AVX1-NEXT: vpmulhuw %xmm1, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpsubw %xmm2, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpsrlw $1, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpaddw %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpsrlw $2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
|
|
; AVX1-NEXT: vpmulhuw %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsubw %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrlw $1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpaddw %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrlw $2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: test_div7_16i16:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpmulhuw {{.*}}(%rip), %ymm0, %ymm1
|
|
; AVX2-NEXT: vpsubw %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpsrlw $1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpaddw %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpsrlw $2, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
%res = udiv <16 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>
|
|
ret <16 x i16> %res
|
|
}
|
|
|
|
define <32 x i8> @test_div7_32i8(<32 x i8> %a) nounwind {
|
|
; AVX1-LABEL: test_div7_32i8:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [37,37,37,37,37,37,37,37]
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm4 = xmm1[2,3,0,1]
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero,xmm4[4],zero,xmm4[5],zero,xmm4[6],zero,xmm4[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpsrlw $8, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpackuswb %xmm4, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsubb %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpsrlw $1, %xmm1, %xmm1
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
|
|
; AVX1-NEXT: vpand %xmm4, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpaddb %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpsrlw $2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63]
|
|
; AVX1-NEXT: vpand %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpsrlw $8, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm0[2,3,0,1]
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm6 = xmm6[0],zero,xmm6[1],zero,xmm6[2],zero,xmm6[3],zero,xmm6[4],zero,xmm6[5],zero,xmm6[6],zero,xmm6[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm6, %xmm3
|
|
; AVX1-NEXT: vpsrlw $8, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpackuswb %xmm3, %xmm5, %xmm3
|
|
; AVX1-NEXT: vpsubb %xmm3, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrlw $1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpand %xmm4, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpaddb %xmm3, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrlw $2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpand %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2NOBW-LABEL: test_div7_32i8:
|
|
; AVX2NOBW: # %bb.0:
|
|
; AVX2NOBW-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2NOBW-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
|
|
; AVX2NOBW-NEXT: vmovdqa {{.*#+}} ymm2 = [37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37]
|
|
; AVX2NOBW-NEXT: vpmullw %ymm2, %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpmovzxbw {{.*#+}} ymm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
|
|
; AVX2NOBW-NEXT: vpmullw %ymm2, %ymm3, %ymm2
|
|
; AVX2NOBW-NEXT: vpsrlw $8, %ymm2, %ymm2
|
|
; AVX2NOBW-NEXT: vpackuswb %ymm1, %ymm2, %ymm1
|
|
; AVX2NOBW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,1,3]
|
|
; AVX2NOBW-NEXT: vpsubb %ymm1, %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: vpsrlw $1, %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: vpaddb %ymm1, %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: vpsrlw $2, %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: test_div7_32i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpmovzxbw {{.*#+}} zmm1 = 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,ymm0[16],zero,ymm0[17],zero,ymm0[18],zero,ymm0[19],zero,ymm0[20],zero,ymm0[21],zero,ymm0[22],zero,ymm0[23],zero,ymm0[24],zero,ymm0[25],zero,ymm0[26],zero,ymm0[27],zero,ymm0[28],zero,ymm0[29],zero,ymm0[30],zero,ymm0[31],zero
|
|
; AVX512BW-NEXT: vpmullw {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpsrlw $8, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
|
|
; AVX512BW-NEXT: vpsubb %ymm1, %ymm0, %ymm0
|
|
; AVX512BW-NEXT: vpsrlw $1, %ymm0, %ymm0
|
|
; AVX512BW-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
|
; AVX512BW-NEXT: vpaddb %ymm1, %ymm0, %ymm0
|
|
; AVX512BW-NEXT: vpsrlw $2, %ymm0, %ymm0
|
|
; AVX512BW-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
|
; AVX512BW-NEXT: retq
|
|
%res = udiv <32 x i8> %a, <i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7>
|
|
ret <32 x i8> %res
|
|
}
|
|
|
|
;
|
|
; urem by 7
|
|
;
|
|
|
|
define <4 x i64> @test_rem7_4i64(<4 x i64> %a) nounwind {
|
|
; AVX1-LABEL: test_rem7_4i64:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vpextrq $1, %xmm1, %rcx
|
|
; AVX1-NEXT: movabsq $2635249153387078803, %rsi # imm = 0x2492492492492493
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: shrq %rax
|
|
; AVX1-NEXT: addq %rdx, %rax
|
|
; AVX1-NEXT: shrq $2, %rax
|
|
; AVX1-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: addq %rcx, %rax
|
|
; AVX1-NEXT: vmovq %rax, %xmm2
|
|
; AVX1-NEXT: vmovq %xmm1, %rcx
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: shrq %rax
|
|
; AVX1-NEXT: addq %rdx, %rax
|
|
; AVX1-NEXT: shrq $2, %rax
|
|
; AVX1-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: addq %rcx, %rax
|
|
; AVX1-NEXT: vmovq %rax, %xmm1
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX1-NEXT: vpextrq $1, %xmm0, %rcx
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: shrq %rax
|
|
; AVX1-NEXT: addq %rdx, %rax
|
|
; AVX1-NEXT: shrq $2, %rax
|
|
; AVX1-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: addq %rcx, %rax
|
|
; AVX1-NEXT: vmovq %rax, %xmm2
|
|
; AVX1-NEXT: vmovq %xmm0, %rcx
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: mulq %rsi
|
|
; AVX1-NEXT: movq %rcx, %rax
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: shrq %rax
|
|
; AVX1-NEXT: addq %rdx, %rax
|
|
; AVX1-NEXT: shrq $2, %rax
|
|
; AVX1-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX1-NEXT: subq %rdx, %rax
|
|
; AVX1-NEXT: addq %rcx, %rax
|
|
; AVX1-NEXT: vmovq %rax, %xmm0
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: test_rem7_4i64:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-NEXT: vpextrq $1, %xmm1, %rcx
|
|
; AVX2-NEXT: movabsq $2635249153387078803, %rsi # imm = 0x2492492492492493
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: shrq %rax
|
|
; AVX2-NEXT: addq %rdx, %rax
|
|
; AVX2-NEXT: shrq $2, %rax
|
|
; AVX2-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: addq %rcx, %rax
|
|
; AVX2-NEXT: vmovq %rax, %xmm2
|
|
; AVX2-NEXT: vmovq %xmm1, %rcx
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: shrq %rax
|
|
; AVX2-NEXT: addq %rdx, %rax
|
|
; AVX2-NEXT: shrq $2, %rax
|
|
; AVX2-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: addq %rcx, %rax
|
|
; AVX2-NEXT: vmovq %rax, %xmm1
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; AVX2-NEXT: vpextrq $1, %xmm0, %rcx
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: shrq %rax
|
|
; AVX2-NEXT: addq %rdx, %rax
|
|
; AVX2-NEXT: shrq $2, %rax
|
|
; AVX2-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: addq %rcx, %rax
|
|
; AVX2-NEXT: vmovq %rax, %xmm2
|
|
; AVX2-NEXT: vmovq %xmm0, %rcx
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: mulq %rsi
|
|
; AVX2-NEXT: movq %rcx, %rax
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: shrq %rax
|
|
; AVX2-NEXT: addq %rdx, %rax
|
|
; AVX2-NEXT: shrq $2, %rax
|
|
; AVX2-NEXT: leaq (,%rax,8), %rdx
|
|
; AVX2-NEXT: subq %rdx, %rax
|
|
; AVX2-NEXT: addq %rcx, %rax
|
|
; AVX2-NEXT: vmovq %rax, %xmm0
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
%res = urem <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
|
|
ret <4 x i64> %res
|
|
}
|
|
|
|
define <8 x i32> @test_rem7_8i32(<8 x i32> %a) nounwind {
|
|
; AVX1-LABEL: test_rem7_8i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [613566757,613566757,613566757,613566757]
|
|
; AVX1-NEXT: vpmuludq %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpmuludq %xmm3, %xmm1, %xmm4
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm4[0,1],xmm2[2,3],xmm4[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpsubd %xmm2, %xmm1, %xmm4
|
|
; AVX1-NEXT: vpsrld $1, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpaddd %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpsrld $2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpslld $3, %xmm2, %xmm4
|
|
; AVX1-NEXT: vpsubd %xmm4, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpaddd %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuludq %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm3[0,1],xmm2[2,3],xmm3[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpsubd %xmm2, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpsrld $1, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpaddd %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpsrld $2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpslld $3, %xmm2, %xmm3
|
|
; AVX1-NEXT: vpsubd %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpaddd %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: test_rem7_8i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [613566757,613566757,613566757,613566757,613566757,613566757,613566757,613566757]
|
|
; AVX2-NEXT: vpmuludq %ymm2, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpmuludq %ymm2, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2],ymm1[3],ymm2[4],ymm1[5],ymm2[6],ymm1[7]
|
|
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpsrld $1, %ymm2, %ymm2
|
|
; AVX2-NEXT: vpaddd %ymm1, %ymm2, %ymm1
|
|
; AVX2-NEXT: vpsrld $2, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [7,7,7,7,7,7,7,7]
|
|
; AVX2-NEXT: vpmulld %ymm2, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
%res = urem <8 x i32> %a, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
|
|
ret <8 x i32> %res
|
|
}
|
|
|
|
define <16 x i16> @test_rem7_16i16(<16 x i16> %a) nounwind {
|
|
; AVX1-LABEL: test_rem7_16i16:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [9363,9363,9363,9363,9363,9363,9363,9363]
|
|
; AVX1-NEXT: vpmulhuw %xmm2, %xmm1, %xmm3
|
|
; AVX1-NEXT: vpsubw %xmm3, %xmm1, %xmm4
|
|
; AVX1-NEXT: vpsrlw $1, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpaddw %xmm3, %xmm4, %xmm3
|
|
; AVX1-NEXT: vpsrlw $2, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpsllw $3, %xmm3, %xmm4
|
|
; AVX1-NEXT: vpsubw %xmm4, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpaddw %xmm3, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpmulhuw %xmm2, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpsubw %xmm2, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpsrlw $1, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpaddw %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpsrlw $2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsllw $3, %xmm2, %xmm3
|
|
; AVX1-NEXT: vpsubw %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpaddw %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: test_rem7_16i16:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpmulhuw {{.*}}(%rip), %ymm0, %ymm1
|
|
; AVX2-NEXT: vpsubw %ymm1, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpsrlw $1, %ymm2, %ymm2
|
|
; AVX2-NEXT: vpaddw %ymm1, %ymm2, %ymm1
|
|
; AVX2-NEXT: vpsrlw $2, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1
|
|
; AVX2-NEXT: vpsubw %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
%res = urem <16 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>
|
|
ret <16 x i16> %res
|
|
}
|
|
|
|
define <32 x i8> @test_rem7_32i8(<32 x i8> %a) nounwind {
|
|
; AVX1-LABEL: test_rem7_32i8:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [37,37,37,37,37,37,37,37]
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm4 = xmm1[2,3,0,1]
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero,xmm4[4],zero,xmm4[5],zero,xmm4[6],zero,xmm4[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpsrlw $8, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpackuswb %xmm4, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsubb %xmm2, %xmm1, %xmm4
|
|
; AVX1-NEXT: vpsrlw $1, %xmm4, %xmm4
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm5 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
|
|
; AVX1-NEXT: vpand %xmm5, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpaddb %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpsrlw $2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = [63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63]
|
|
; AVX1-NEXT: vpand %xmm4, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsllw $3, %xmm2, %xmm6
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm7 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248]
|
|
; AVX1-NEXT: vpand %xmm7, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpsubb %xmm6, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpaddb %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm0[2,3,0,1]
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm6 = xmm6[0],zero,xmm6[1],zero,xmm6[2],zero,xmm6[3],zero,xmm6[4],zero,xmm6[5],zero,xmm6[6],zero,xmm6[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm3, %xmm6, %xmm3
|
|
; AVX1-NEXT: vpsrlw $8, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsubb %xmm2, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpsrlw $1, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpand %xmm5, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpaddb %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpsrlw $2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpand %xmm4, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpsllw $3, %xmm2, %xmm3
|
|
; AVX1-NEXT: vpand %xmm7, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpsubb %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2NOBW-LABEL: test_rem7_32i8:
|
|
; AVX2NOBW: # %bb.0:
|
|
; AVX2NOBW-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2NOBW-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
|
|
; AVX2NOBW-NEXT: vmovdqa {{.*#+}} ymm2 = [37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37]
|
|
; AVX2NOBW-NEXT: vpmullw %ymm2, %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpmovzxbw {{.*#+}} ymm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
|
|
; AVX2NOBW-NEXT: vpmullw %ymm2, %ymm3, %ymm2
|
|
; AVX2NOBW-NEXT: vpsrlw $8, %ymm2, %ymm2
|
|
; AVX2NOBW-NEXT: vpackuswb %ymm1, %ymm2, %ymm1
|
|
; AVX2NOBW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,1,3]
|
|
; AVX2NOBW-NEXT: vpsubb %ymm1, %ymm0, %ymm2
|
|
; AVX2NOBW-NEXT: vpsrlw $1, %ymm2, %ymm2
|
|
; AVX2NOBW-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
|
|
; AVX2NOBW-NEXT: vpaddb %ymm1, %ymm2, %ymm1
|
|
; AVX2NOBW-NEXT: vpsrlw $2, %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpsllw $3, %ymm1, %ymm2
|
|
; AVX2NOBW-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
|
|
; AVX2NOBW-NEXT: vpsubb %ymm2, %ymm1, %ymm1
|
|
; AVX2NOBW-NEXT: vpaddb %ymm1, %ymm0, %ymm0
|
|
; AVX2NOBW-NEXT: retq
|
|
;
|
|
; AVX512BW-LABEL: test_rem7_32i8:
|
|
; AVX512BW: # %bb.0:
|
|
; AVX512BW-NEXT: vpmovzxbw {{.*#+}} zmm1 = 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,ymm0[16],zero,ymm0[17],zero,ymm0[18],zero,ymm0[19],zero,ymm0[20],zero,ymm0[21],zero,ymm0[22],zero,ymm0[23],zero,ymm0[24],zero,ymm0[25],zero,ymm0[26],zero,ymm0[27],zero,ymm0[28],zero,ymm0[29],zero,ymm0[30],zero,ymm0[31],zero
|
|
; AVX512BW-NEXT: vpmullw {{.*}}(%rip), %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpsrlw $8, %zmm1, %zmm1
|
|
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
|
|
; AVX512BW-NEXT: vpsubb %ymm1, %ymm0, %ymm2
|
|
; AVX512BW-NEXT: vpsrlw $1, %ymm2, %ymm2
|
|
; AVX512BW-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
|
|
; AVX512BW-NEXT: vpaddb %ymm1, %ymm2, %ymm1
|
|
; AVX512BW-NEXT: vpsrlw $2, %ymm1, %ymm1
|
|
; AVX512BW-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
|
|
; AVX512BW-NEXT: vpsllw $3, %ymm1, %ymm2
|
|
; AVX512BW-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
|
|
; AVX512BW-NEXT: vpsubb %ymm2, %ymm1, %ymm1
|
|
; AVX512BW-NEXT: vpaddb %ymm1, %ymm0, %ymm0
|
|
; AVX512BW-NEXT: retq
|
|
%res = urem <32 x i8> %a, <i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7,i8 7, i8 7, i8 7, i8 7>
|
|
ret <32 x i8> %res
|
|
}
|