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

[X86] Add SimplifyDemandedBitsForTargetNode support for PEXTRB/PEXTRW 

Improved constant folding for PEXTRB/PEXTRW will be added in a future commit

llvm-svn: 356324
This commit is contained in:
Simon Pilgrim 2019-03-16 14:29:50 +00:00
parent 9ea2f9079d
commit 0f472e1d01
2 changed files with 36 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -33372,6 +33372,34 @@ bool X86TargetLowering::SimplifyDemandedBitsForTargetNode(
}
break;
}
case X86ISD::PEXTRB:
case X86ISD::PEXTRW: {
SDValue Vec = Op.getOperand(0);
auto *CIdx = dyn_cast<ConstantSDNode>(Op.getOperand(1));
MVT VecVT = Vec.getSimpleValueType();
unsigned NumVecElts = VecVT.getVectorNumElements();
if (CIdx && CIdx->getAPIntValue().ult(NumVecElts)) {
unsigned Idx = CIdx->getZExtValue();
unsigned VecBitWidth = VecVT.getScalarSizeInBits();
// If we demand no bits from the vector then we must have demanded
// bits from the implict zext - simplify to zero.
APInt DemandedVecBits = OriginalDemandedBits.trunc(VecBitWidth);
if (DemandedVecBits == 0)
return TLO.CombineTo(Op, TLO.DAG.getConstant(0, SDLoc(Op), VT));
KnownBits KnownVec;
APInt DemandedVecElts = APInt::getOneBitSet(NumVecElts, Idx);
if (SimplifyDemandedBits(Vec, DemandedVecBits, DemandedVecElts,
KnownVec, TLO, Depth + 1))
return true;
Known = KnownVec.zext(BitWidth, true);
return false;
}
break;
}
case X86ISD::PINSRB:
case X86ISD::PINSRW: {
SDValue Vec = Op.getOperand(0);

12
llvm/test/CodeGen/X86/widen_load-2.ll
View File

@ -368,10 +368,12 @@ define void @rot(%i8vec3pack* nocapture sret %result, %i8vec3pack* %X, %i8vec3pa
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movdqa {{.*#+}} xmm0 = [10395294,10395294,10395294,10395294]
; X86-NEXT: pextrw $0, %xmm0, (%edx)
; X86-NEXT: movb $-98, 2(%edx)
; X86-NEXT: movw $-24930, (%edx) # imm = 0x9E9E
; X86-NEXT: movdqa {{.*#+}} xmm0 = [65793,65793,65793,65793]
; X86-NEXT: pextrw $0, %xmm0, (%ecx)
; X86-NEXT: movb $1, 2(%ecx)
; X86-NEXT: movw $257, (%ecx) # imm = 0x101
; X86-NEXT: pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
; X86-NEXT: movdqa %xmm0, %xmm1
; X86-NEXT: psrld $1, %xmm1
@ -385,10 +387,12 @@ define void @rot(%i8vec3pack* nocapture sret %result, %i8vec3pack* %X, %i8vec3pa
; X64-LABEL: rot:
; X64: # %bb.0: # %entry
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: movdqa {{.*#+}} xmm0 = [10395294,10395294,10395294,10395294]
; X64-NEXT: pextrw $0, %xmm0, (%rsi)
; X64-NEXT: movb $-98, 2(%rsi)
; X64-NEXT: movw $-24930, (%rsi) # imm = 0x9E9E
; X64-NEXT: movdqa {{.*#+}} xmm0 = [65793,65793,65793,65793]
; X64-NEXT: pextrw $0, %xmm0, (%rdx)
; X64-NEXT: movb $1, 2(%rdx)
; X64-NEXT: movw $257, (%rdx) # imm = 0x101
; X64-NEXT: pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
; X64-NEXT: movdqa %xmm0, %xmm1
; X64-NEXT: psrld $1, %xmm1