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

[X86][SSE] Fold movmsk(not(x)) -> not(movmsk) 

Helps to improve folding of comparisons with movmsk results.

llvm-svn: 361056
This commit is contained in:
Simon Pilgrim 2019-05-17 17:56:25 +00:00
parent 10abc76fce
commit 065431c82b
4 changed files with 23 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -41498,6 +41498,8 @@ static SDValue combineMOVMSK(SDNode *N, SelectionDAG &DAG,
SDValue Src = N->getOperand(0);
MVT SrcVT = Src.getSimpleValueType();
MVT VT = N->getSimpleValueType(0);
unsigned NumBits = VT.getScalarSizeInBits();
unsigned NumElts = SrcVT.getVectorNumElements();
// Perform constant folding.
if (ISD::isBuildVectorOfConstantSDNodes(Src.getNode())) {
@ -41517,9 +41519,20 @@ 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
// with scalar comparisons.
if (SDValue NotSrc = IsNOT(Src, DAG)) {
SDLoc DL(N);
APInt NotMask = APInt::getLowBitsSet(NumBits, NumElts);
NotSrc = DAG.getBitcast(SrcVT, NotSrc);
return DAG.getNode(ISD::XOR, DL, VT,
DAG.getNode(X86ISD::MOVMSK, DL, VT, NotSrc),
DAG.getConstant(NotMask, DL, VT));
}
// Simplify the inputs.
const TargetLowering &TLI = DAG.getTargetLoweringInfo();
APInt DemandedMask(APInt::getAllOnesValue(VT.getScalarSizeInBits()));
APInt DemandedMask(APInt::getAllOnesValue(NumBits));
if (TLI.SimplifyDemandedBits(SDValue(N, 0), DemandedMask, DCI))
return SDValue(N, 0);

8
llvm/test/CodeGen/X86/movmsk-cmp.ll
View File

@ -4485,9 +4485,8 @@ define i1 @movmsk_v2i64(<2 x i64> %x, <2 x i64> %y) {
; SSE2-NEXT: pcmpeqd %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm1, %xmm0
; SSE2-NEXT: movmskpd %xmm0, %eax
; SSE2-NEXT: movmskpd %xmm1, %eax
; SSE2-NEXT: xorl $3, %eax
; SSE2-NEXT: cmpb $3, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
@ -4495,9 +4494,8 @@ define i1 @movmsk_v2i64(<2 x i64> %x, <2 x i64> %y) {
; AVX-LABEL: movmsk_v2i64:
; AVX: # %bb.0:
; AVX-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskpd %xmm0, %eax
; AVX-NEXT: xorl $3, %eax
; AVX-NEXT: cmpb $3, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq

8
llvm/test/CodeGen/X86/vector-compare-all_of.ll
View File

@ -1102,9 +1102,8 @@ define i1 @bool_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: bool_reduction_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
; SSE-NEXT: pxor %xmm0, %xmm1
; SSE-NEXT: movmskps %xmm1, %eax
; SSE-NEXT: movmskps %xmm0, %eax
; SSE-NEXT: xorl $15, %eax
; SSE-NEXT: cmpb $15, %al
; SSE-NEXT: sete %al
; SSE-NEXT: retq
@ -1112,9 +1111,8 @@ define i1 @bool_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
; AVX-LABEL: bool_reduction_v4i32:
; AVX: # %bb.0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskps %xmm0, %eax
; AVX-NEXT: xorl $15, %eax
; AVX-NEXT: cmpb $15, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq

10
llvm/test/CodeGen/X86/vector-compare-any_of.ll
View File

@ -1018,20 +1018,16 @@ define i1 @bool_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: bool_reduction_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: pcmpeqd %xmm1, %xmm0
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
; SSE-NEXT: pxor %xmm0, %xmm1
; SSE-NEXT: movmskps %xmm1, %eax
; SSE-NEXT: testb %al, %al
; SSE-NEXT: movmskps %xmm0, %eax
; SSE-NEXT: xorb $15, %al
; SSE-NEXT: setne %al
; SSE-NEXT: retq
;
; AVX-LABEL: bool_reduction_v4i32:
; AVX: # %bb.0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskps %xmm0, %eax
; AVX-NEXT: testb %al, %al
; AVX-NEXT: xorb $15, %al
; AVX-NEXT: setne %al
; AVX-NEXT: retq
;