maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Fold MOVMSK(ICMP_SGT(X,-1)) -> NOT(MOVMSK(X))) 

Noticed while triaging PR37506
This commit is contained in:
Simon Pilgrim 2020-12-06 17:56:41 +00:00
parent d6941a1979
commit 0101fb73de
2 changed files with 17 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -47378,7 +47378,7 @@ static SDValue combineMOVMSK(SDNode *N, SelectionDAG &DAG,
Src.getOperand(0).getScalarValueSizeInBits() == EltWidth)
return DAG.getNode(X86ISD::MOVMSK, SDLoc(N), VT, Src.getOperand(0));
// Fold movmsk(not(x)) -> not(movmsk) to improve folding of movmsk results
// Fold movmsk(not(x)) -> not(movmsk(x)) to improve folding of movmsk results
// with scalar comparisons.
if (SDValue NotSrc = IsNOT(Src, DAG)) {
SDLoc DL(N);
@ -47389,6 +47389,17 @@ static SDValue combineMOVMSK(SDNode *N, SelectionDAG &DAG,
DAG.getConstant(NotMask, DL, VT));
}
// Fold movmsk(icmp_sgt(x,-1)) -> not(movmsk(x)) to improve folding of movmsk
// results with scalar comparisons.
if (Src.getOpcode() == X86ISD::PCMPGT &&
ISD::isBuildVectorAllOnes(Src.getOperand(1).getNode())) {
SDLoc DL(N);
APInt NotMask = APInt::getLowBitsSet(NumBits, NumElts);
return DAG.getNode(ISD::XOR, DL, VT,
DAG.getNode(X86ISD::MOVMSK, DL, VT, Src.getOperand(0)),
DAG.getConstant(NotMask, DL, VT));
}
// Simplify the inputs.
const TargetLowering &TLI = DAG.getTargetLoweringInfo();
APInt DemandedMask(APInt::getAllOnesValue(NumBits));

16
llvm/test/CodeGen/X86/combine-movmsk.ll
View File

@ -178,22 +178,20 @@ define i1 @pmovmskb_allof_bitcast_v4f32(<4 x float> %a0) {
ret i1 %5
}
; FIXME: MOVMSK(ICMP_SGT(X,-1)) -> NOT(MOVMSK(X)))
; MOVMSK(ICMP_SGT(X,-1)) -> NOT(MOVMSK(X)))
define i1 @movmskps_allof_v4i32_positive(<4 x i32> %a0) {
; SSE-LABEL: movmskps_allof_v4i32_positive:
; SSE: # %bb.0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
; SSE-NEXT: pcmpgtd %xmm1, %xmm0
; SSE-NEXT: movmskps %xmm0, %eax
; SSE-NEXT: xorl $15, %eax
; SSE-NEXT: cmpl $15, %eax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: movmskps_allof_v4i32_positive:
; AVX: # %bb.0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskps %xmm0, %eax
; AVX-NEXT: xorl $15, %eax
; AVX-NEXT: cmpl $15, %eax
; AVX-NEXT: sete %al
; AVX-NEXT: retq
@ -208,19 +206,15 @@ define i1 @movmskps_allof_v4i32_positive(<4 x i32> %a0) {
define i1 @pmovmskb_noneof_v16i8_positive(<16 x i8> %a0) {
; SSE-LABEL: pmovmskb_noneof_v16i8_positive:
; SSE: # %bb.0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
; SSE-NEXT: pcmpgtb %xmm1, %xmm0
; SSE-NEXT: pmovmskb %xmm0, %eax
; SSE-NEXT: testl %eax, %eax
; SSE-NEXT: xorl $65535, %eax # imm = 0xFFFF
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: pmovmskb_noneof_v16i8_positive:
; AVX: # %bb.0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpcmpgtb %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpmovmskb %xmm0, %eax
; AVX-NEXT: testl %eax, %eax
; AVX-NEXT: xorl $65535, %eax # imm = 0xFFFF
; AVX-NEXT: sete %al
; AVX-NEXT: retq
%1 = icmp sgt <16 x i8> %a0, <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>