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

[X86][SSE] Match all-of bool scalar reductions into a bitcast/movmsk + cmp. 

Same as what we do for vector reductions in combineHorizontalPredicateResult, use movmsk+cmp for scalar (and(extract(x,0),extract(x,1)) reduction patterns. 

llvm-svn: 361052
This commit is contained in:
Simon Pilgrim 2019-05-17 17:25:55 +00:00
parent c05d85104d
commit 2c2f8e74b9
2 changed files with 30 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -37841,6 +37841,24 @@ static SDValue combineAnd(SDNode *N, SelectionDAG &DAG,
if (SDValue V = combineParity(N, DAG, Subtarget))
return V;
// Match all-of bool scalar reductions into a bitcast/movmsk + cmp.
// TODO: Support multiple SrcOps.
if (VT == MVT::i1) {
SmallVector<SDValue, 2> SrcOps;
if (matchBitOpReduction(SDValue(N, 0), ISD::AND, SrcOps) &&
SrcOps.size() == 1) {
SDLoc dl(N);
unsigned NumElts = SrcOps[0].getValueType().getVectorNumElements();
EVT MaskVT = EVT::getIntegerVT(*DAG.getContext(), NumElts);
SDValue Mask = combineBitcastvxi1(DAG, MaskVT, SrcOps[0], dl, Subtarget);
if (Mask) {
APInt AllBits = APInt::getAllOnesValue(NumElts);
return DAG.getSetCC(dl, MVT::i1, Mask,
DAG.getConstant(AllBits, dl, MaskVT), ISD::SETEQ);
}
}
}
if (DCI.isBeforeLegalizeOps())
return SDValue();

28
llvm/test/CodeGen/X86/movmsk-cmp.ll
View File

@ -4487,10 +4487,9 @@ define i1 @movmsk_v2i64(<2 x i64> %x, <2 x i64> %y) {
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm0
; SSE2-NEXT: movmskpd %xmm0, %ecx
; SSE2-NEXT: movl %ecx, %eax
; SSE2-NEXT: shrb %al
; SSE2-NEXT: andb %cl, %al
; SSE2-NEXT: movmskpd %xmm0, %eax
; SSE2-NEXT: cmpb $3, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; AVX-LABEL: movmsk_v2i64:
@ -4498,10 +4497,9 @@ define i1 @movmsk_v2i64(<2 x i64> %x, <2 x i64> %y) {
; AVX-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskpd %xmm0, %ecx
; AVX-NEXT: movl %ecx, %eax
; AVX-NEXT: shrb %al
; AVX-NEXT: andb %cl, %al
; AVX-NEXT: vmovmskpd %xmm0, %eax
; AVX-NEXT: cmpb $3, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; KNL-LABEL: movmsk_v2i64:
@ -4596,19 +4594,17 @@ define i1 @movmsk_v2f64(<2 x double> %x, <2 x double> %y) {
; SSE2-LABEL: movmsk_v2f64:
; SSE2: # %bb.0:
; SSE2-NEXT: cmplepd %xmm0, %xmm1
; SSE2-NEXT: movmskpd %xmm1, %ecx
; SSE2-NEXT: movl %ecx, %eax
; SSE2-NEXT: shrb %al
; SSE2-NEXT: andb %cl, %al
; SSE2-NEXT: movmskpd %xmm1, %eax
; SSE2-NEXT: cmpb $3, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; AVX-LABEL: movmsk_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vcmplepd %xmm0, %xmm1, %xmm0
; AVX-NEXT: vmovmskpd %xmm0, %ecx
; AVX-NEXT: movl %ecx, %eax
; AVX-NEXT: shrb %al
; AVX-NEXT: andb %cl, %al
; AVX-NEXT: vmovmskpd %xmm0, %eax
; AVX-NEXT: cmpb $3, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; KNL-LABEL: movmsk_v2f64: