forked from OSchip/llvm-project
[X86][SSE] Combine combineLogicBlendIntoConditionalNegate for VSELECT nodes (PR43660)
Attempt to use combineLogicBlendIntoConditionalNegate for (select M, (sub 0, X), X) -> (sub (xor X, M), M) We limit this to cases that can't easily replace the VSELECT with a shuffle (non-constant masks) or where a BLENDV is likely to occur (which tends to result in slower codegen).
This commit is contained in:
Simon Pilgrim
parent
6a6e6f04ec
commit
e3bd011890
|
|
@ -37697,10 +37697,21 @@ static SDValue combineSelect(SDNode *N, SelectionDAG &DAG,
|
|||
EVT VT = LHS.getValueType();
|
||||
EVT CondVT = Cond.getValueType();
|
||||
const TargetLowering &TLI = DAG.getTargetLoweringInfo();
|
||||
bool CondConstantVector = ISD::isBuildVectorOfConstantSDNodes(Cond.getNode());
|
||||
|
||||
// Attempt to combine (select M, (sub 0, X), X) -> (sub (xor X, M), M).
|
||||
// Limit this to cases of non-constant masks that createShuffleMaskFromVSELECT
|
||||
// can't catch, plus vXi8 cases where we'd likely end up with BLENDV.
|
||||
if (CondVT.isVector() && CondVT.isInteger() &&
|
||||
CondVT.getScalarSizeInBits() == VT.getScalarSizeInBits() &&
|
||||
(!CondConstantVector || CondVT.getScalarType() == MVT::i8) &&
|
||||
DAG.ComputeNumSignBits(Cond) == CondVT.getScalarSizeInBits())
|
||||
if (SDValue V = combineLogicBlendIntoConditionalNegate(VT, Cond, RHS, LHS,
|
||||
DL, DAG, Subtarget))
|
||||
return V;
|
||||
|
||||
// Convert vselects with constant condition into shuffles.
|
||||
if (ISD::isBuildVectorOfConstantSDNodes(Cond.getNode()) &&
|
||||
DCI.isBeforeLegalizeOps()) {
|
||||
if (CondConstantVector && DCI.isBeforeLegalizeOps()) {
|
||||
SmallVector<int, 64> Mask;
|
||||
if (createShuffleMaskFromVSELECT(Mask, Cond))
|
||||
return DAG.getVectorShuffle(VT, DL, LHS, RHS, Mask);
|
||||
|
|
|
|||
|
|
@ -2104,46 +2104,32 @@ define <4 x i32> @combine_vec_sdiv_by_pow2b_undef3(<4 x i32> %x) {
|
|||
|
||||
; PR37119
|
||||
define <16 x i8> @non_splat_minus_one_divisor_0(<16 x i8> %A) {
|
||||
; SSE2-LABEL: non_splat_minus_one_divisor_0:
|
||||
; SSE2: # %bb.0:
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pxor %xmm1, %xmm0
|
||||
; SSE2-NEXT: psubb %xmm0, %xmm1
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: non_splat_minus_one_divisor_0:
|
||||
; SSE41: # %bb.0:
|
||||
; SSE41-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm2, %xmm2
|
||||
; SSE41-NEXT: psubb %xmm0, %xmm2
|
||||
; SSE41-NEXT: movaps {{.*#+}} xmm0 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; SSE41-NEXT: pblendvb %xmm0, %xmm1, %xmm2
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
||||
; SSE41-NEXT: retq
|
||||
; SSE-LABEL: non_splat_minus_one_divisor_0:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,0,0,0]
|
||||
; SSE-NEXT: pxor %xmm1, %xmm0
|
||||
; SSE-NEXT: psubb %xmm1, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: non_splat_minus_one_divisor_0:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX1-NEXT: vpblendvb %xmm2, %xmm0, %xmm1, %xmm0
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,0,0,0]
|
||||
; AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: non_splat_minus_one_divisor_0:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX2-NEXT: vpblendvb %xmm2, %xmm0, %xmm1, %xmm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,0,0,0]
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: non_splat_minus_one_divisor_0:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX512F-NEXT: vpblendvb %xmm2, %xmm0, %xmm1, %xmm0
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,0,0,0]
|
||||
; AVX512F-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: non_splat_minus_one_divisor_0:
|
||||
|
|
@ -2156,10 +2142,9 @@ define <16 x i8> @non_splat_minus_one_divisor_0(<16 x i8> %A) {
|
|||
;
|
||||
; XOP-LABEL: non_splat_minus_one_divisor_0:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; XOP-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; XOP-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; XOP-NEXT: vpblendvb %xmm2, %xmm0, %xmm1, %xmm0
|
||||
; XOP-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,0,0,0]
|
||||
; XOP-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
%div = sdiv <16 x i8> %A, <i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
|
||||
ret <16 x i8> %div
|
||||
|
|
@ -2203,38 +2188,38 @@ define <16 x i8> @non_splat_minus_one_divisor_1(<16 x i8> %A) {
|
|||
; SSE41-LABEL: non_splat_minus_one_divisor_1:
|
||||
; SSE41: # %bb.0:
|
||||
; SSE41-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm2, %xmm2
|
||||
; SSE41-NEXT: pxor %xmm0, %xmm0
|
||||
; SSE41-NEXT: pcmpgtb %xmm1, %xmm0
|
||||
; SSE41-NEXT: pxor %xmm3, %xmm3
|
||||
; SSE41-NEXT: pcmpgtb %xmm1, %xmm3
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm4
|
||||
; SSE41-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
|
||||
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
||||
; SSE41-NEXT: psllw $1, %xmm3
|
||||
; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm4[0,1],xmm3[2],xmm4[3,4,5],xmm3[6],xmm4[7]
|
||||
; SSE41-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
|
||||
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm2 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero,xmm3[4],zero,xmm3[5],zero,xmm3[6],zero,xmm3[7],zero
|
||||
; SSE41-NEXT: psllw $1, %xmm2
|
||||
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm4[0,1],xmm2[2],xmm4[3,4,5],xmm2[6],xmm4[7]
|
||||
; SSE41-NEXT: psrlw $8, %xmm2
|
||||
; SSE41-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm0[8],xmm3[9],xmm0[9],xmm3[10],xmm0[10],xmm3[11],xmm0[11],xmm3[12],xmm0[12],xmm3[13],xmm0[13],xmm3[14],xmm0[14],xmm3[15],xmm0[15]
|
||||
; SSE41-NEXT: pmullw {{.*}}(%rip), %xmm3
|
||||
; SSE41-NEXT: psrlw $8, %xmm3
|
||||
; SSE41-NEXT: packuswb %xmm3, %xmm2
|
||||
; SSE41-NEXT: paddb %xmm1, %xmm2
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
||||
; SSE41-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8],xmm2[8],xmm0[9],xmm2[9],xmm0[10],xmm2[10],xmm0[11],xmm2[11],xmm0[12],xmm2[12],xmm0[13],xmm2[13],xmm0[14],xmm2[14],xmm0[15],xmm2[15]
|
||||
; SSE41-NEXT: pmullw {{.*}}(%rip), %xmm0
|
||||
; SSE41-NEXT: psrlw $8, %xmm0
|
||||
; SSE41-NEXT: packuswb %xmm0, %xmm3
|
||||
; SSE41-NEXT: paddb %xmm1, %xmm3
|
||||
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
||||
; SSE41-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8],xmm3[8],xmm0[9],xmm3[9],xmm0[10],xmm3[10],xmm0[11],xmm3[11],xmm0[12],xmm3[12],xmm0[13],xmm3[13],xmm0[14],xmm3[14],xmm0[15],xmm3[15]
|
||||
; SSE41-NEXT: psraw $8, %xmm0
|
||||
; SSE41-NEXT: movdqa %xmm0, %xmm4
|
||||
; SSE41-NEXT: psllw $1, %xmm4
|
||||
; SSE41-NEXT: movdqa %xmm0, %xmm3
|
||||
; SSE41-NEXT: psllw $1, %xmm3
|
||||
; SSE41-NEXT: psllw $7, %xmm0
|
||||
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4],xmm4[5],xmm0[6],xmm4[7]
|
||||
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4],xmm3[5],xmm0[6],xmm3[7]
|
||||
; SSE41-NEXT: psrlw $8, %xmm0
|
||||
; SSE41-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
||||
; SSE41-NEXT: psraw $8, %xmm3
|
||||
; SSE41-NEXT: psllw $7, %xmm3
|
||||
; SSE41-NEXT: psrlw $8, %xmm3
|
||||
; SSE41-NEXT: packuswb %xmm0, %xmm3
|
||||
; SSE41-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
||||
; SSE41-NEXT: psraw $8, %xmm2
|
||||
; SSE41-NEXT: psllw $7, %xmm2
|
||||
; SSE41-NEXT: psrlw $8, %xmm2
|
||||
; SSE41-NEXT: packuswb %xmm0, %xmm2
|
||||
; SSE41-NEXT: movaps {{.*#+}} xmm0 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
|
||||
; SSE41-NEXT: psubb %xmm1, %xmm2
|
||||
; SSE41-NEXT: movaps {{.*#+}} xmm0 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; SSE41-NEXT: pblendvb %xmm0, %xmm2, %xmm1
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; SSE41-NEXT: pxor %xmm0, %xmm1
|
||||
; SSE41-NEXT: psubb %xmm0, %xmm1
|
||||
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
|
|
@ -2247,68 +2232,68 @@ define <16 x i8> @non_splat_minus_one_divisor_1(<16 x i8> %A) {
|
|||
; AVX1-NEXT: vpsllw $1, %xmm4, %xmm4
|
||||
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm3[0,1],xmm4[2],xmm3[3,4,5],xmm4[6],xmm3[7]
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
||||
; AVX1-NEXT: vpmullw {{.*}}(%rip), %xmm2, %xmm2
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
|
||||
; AVX1-NEXT: vpackuswb %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpaddb %xmm2, %xmm0, %xmm2
|
||||
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm3 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
||||
; AVX1-NEXT: vpsraw $8, %xmm3, %xmm3
|
||||
; AVX1-NEXT: vpsllw $1, %xmm3, %xmm4
|
||||
; AVX1-NEXT: vpsllw $7, %xmm3, %xmm3
|
||||
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm3[0,1,2,3,4],xmm4[5],xmm3[6],xmm4[7]
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX1-NEXT: vpunpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
||||
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm1 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
|
||||
; AVX1-NEXT: vpmullw {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpackuswb %xmm1, %xmm3, %xmm1
|
||||
; AVX1-NEXT: vpaddb %xmm1, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm2 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
||||
; AVX1-NEXT: vpsraw $8, %xmm2, %xmm2
|
||||
; AVX1-NEXT: vpsllw $1, %xmm2, %xmm3
|
||||
; AVX1-NEXT: vpsllw $7, %xmm2, %xmm2
|
||||
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0,1,2,3,4],xmm3[5],xmm2[6],xmm3[7]
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
|
||||
; AVX1-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX1-NEXT: vpblendvb %xmm3, %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; AVX1-NEXT: vpunpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
||||
; AVX1-NEXT: vpsraw $8, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsllw $7, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX1-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: non_splat_minus_one_divisor_1:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm2
|
||||
; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero
|
||||
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm2, %ymm2
|
||||
; AVX2-NEXT: vpsrlw $8, %ymm2, %ymm2
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
|
||||
; AVX2-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
|
||||
; AVX2-NEXT: vpaddb %xmm2, %xmm0, %xmm2
|
||||
; AVX2-NEXT: vpmovsxbw %xmm2, %ymm2
|
||||
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm2, %ymm2
|
||||
; AVX2-NEXT: vpsrlw $8, %ymm2, %ymm2
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
|
||||
; AVX2-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX2-NEXT: vpblendvb %xmm3, %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; AVX2-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm1
|
||||
; AVX2-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
|
||||
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpaddb %xmm1, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm1
|
||||
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX2-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: non_splat_minus_one_divisor_1:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm2
|
||||
; AVX512F-NEXT: vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
|
||||
; AVX512F-NEXT: vpsrlvd {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512F-NEXT: vpmovdb %zmm2, %xmm2
|
||||
; AVX512F-NEXT: vpaddb %xmm2, %xmm0, %xmm2
|
||||
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
||||
; AVX512F-NEXT: vpsravd {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512F-NEXT: vpmovdb %zmm2, %xmm2
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX512F-NEXT: vpblendvb %xmm3, %xmm2, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; AVX512F-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
|
||||
; AVX512F-NEXT: vpsrlvd {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
|
||||
; AVX512F-NEXT: vpaddb %xmm1, %xmm0, %xmm1
|
||||
; AVX512F-NEXT: vpmovsxbd %xmm1, %zmm1
|
||||
; AVX512F-NEXT: vpsravd {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; AVX512F-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; AVX512F-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
|
|
@ -2336,15 +2321,15 @@ define <16 x i8> @non_splat_minus_one_divisor_1(<16 x i8> %A) {
|
|||
; XOP-LABEL: non_splat_minus_one_divisor_1:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; XOP-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm2
|
||||
; XOP-NEXT: vpshlb {{.*}}(%rip), %xmm2, %xmm2
|
||||
; XOP-NEXT: vpaddb %xmm2, %xmm0, %xmm2
|
||||
; XOP-NEXT: vpshab {{.*}}(%rip), %xmm2, %xmm2
|
||||
; XOP-NEXT: vmovdqa {{.*#+}} xmm3 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; XOP-NEXT: vpblendvb %xmm3, %xmm2, %xmm0, %xmm0
|
||||
; XOP-NEXT: vpsubb %xmm0, %xmm1, %xmm1
|
||||
; XOP-NEXT: vmovdqa {{.*#+}} xmm2 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; XOP-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm1
|
||||
; XOP-NEXT: vpshlb {{.*}}(%rip), %xmm1, %xmm1
|
||||
; XOP-NEXT: vpaddb %xmm1, %xmm0, %xmm1
|
||||
; XOP-NEXT: vpshab {{.*}}(%rip), %xmm1, %xmm1
|
||||
; XOP-NEXT: vmovdqa {{.*#+}} xmm2 = [0,0,255,0,0,0,255,0,0,255,255,255,255,255,255,255]
|
||||
; XOP-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,0,255,255,255,0,255,255,0,0,0,0,255,0,255]
|
||||
; XOP-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
%div = sdiv <16 x i8> %A, <i8 -1, i8 -1, i8 2, i8 -1, i8 -1, i8 -1, i8 2, i8 -1, i8 -1, i8 2, i8 2, i8 2, i8 2, i8 -128, i8 2, i8 -128>
|
||||
ret <16 x i8> %div
|
||||
|
|
|
|||
|
|
@ -922,37 +922,19 @@ entry:
|
|||
}
|
||||
|
||||
define <4 x i32> @blend_neg_logic_v4i32_2(<4 x i32> %v, <4 x i32> %c) {
|
||||
; SSE2-LABEL: blend_neg_logic_v4i32_2:
|
||||
; SSE2: # %bb.0: # %entry
|
||||
; SSE2-NEXT: psrad $31, %xmm1
|
||||
; SSE2-NEXT: pxor %xmm1, %xmm0
|
||||
; SSE2-NEXT: psubd %xmm0, %xmm1
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: blend_neg_logic_v4i32_2:
|
||||
; SSSE3: # %bb.0: # %entry
|
||||
; SSSE3-NEXT: psrad $31, %xmm1
|
||||
; SSSE3-NEXT: pxor %xmm1, %xmm0
|
||||
; SSSE3-NEXT: psubd %xmm0, %xmm1
|
||||
; SSSE3-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSSE3-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: blend_neg_logic_v4i32_2:
|
||||
; SSE41: # %bb.0: # %entry
|
||||
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
||||
; SSE41-NEXT: pxor %xmm3, %xmm3
|
||||
; SSE41-NEXT: psubd %xmm0, %xmm3
|
||||
; SSE41-NEXT: movaps %xmm1, %xmm0
|
||||
; SSE41-NEXT: blendvps %xmm0, %xmm2, %xmm3
|
||||
; SSE41-NEXT: movaps %xmm3, %xmm0
|
||||
; SSE41-NEXT: retq
|
||||
; SSE-LABEL: blend_neg_logic_v4i32_2:
|
||||
; SSE: # %bb.0: # %entry
|
||||
; SSE-NEXT: psrad $31, %xmm1
|
||||
; SSE-NEXT: pxor %xmm1, %xmm0
|
||||
; SSE-NEXT: psubd %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: blend_neg_logic_v4i32_2:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; AVX-NEXT: vpsubd %xmm0, %xmm2, %xmm2
|
||||
; AVX-NEXT: vblendvps %xmm1, %xmm0, %xmm2, %xmm0
|
||||
; AVX-NEXT: vpsrad $31, %xmm1, %xmm1
|
||||
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsubd %xmm0, %xmm1, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
entry:
|
||||
%0 = ashr <4 x i32> %c, <i32 31, i32 31, i32 31, i32 31>
|
||||
|
|
|
|||
Loading…
Reference in New Issue