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

[SelectionDAG] Add knownbits support for EXTRACT_VECTOR_ELT opcodes 

llvm-svn: 288916
This commit is contained in:
Simon Pilgrim 2016-12-07 16:28:21 +00:00
parent 2ead2bfc12
commit 967325b373
2 changed files with 38 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -2590,6 +2590,42 @@ void SelectionDAG::computeKnownBits(SDValue Op, APInt &KnownZero,
}
break;
}
case ISD::INSERT_VECTOR_ELT: {
SDValue InVec = Op.getOperand(0);
SDValue InVal = Op.getOperand(1);
SDValue EltNo = Op.getOperand(2);
ConstantSDNode *CEltNo = dyn_cast<ConstantSDNode>(EltNo);
if (CEltNo && CEltNo->getAPIntValue().ult(NumElts)) {
// If we know the element index, split the demand between the
// source vector and the inserted element.
KnownZero = KnownOne = APInt::getAllOnesValue(BitWidth);
unsigned EltIdx = CEltNo->getZExtValue();
// If we demand the inserted element then add its common known bits.
if (DemandedElts[EltIdx]) {
computeKnownBits(InVal, KnownZero2, KnownOne2, Depth + 1);
KnownOne &= KnownOne2.zextOrTrunc(KnownOne.getBitWidth());
KnownZero &= KnownZero2.zextOrTrunc(KnownZero.getBitWidth());;
}
// If we demand the source vector then add its common known bits, ensuring
// that we don't demand the inserted element.
APInt VectorElts = DemandedElts & ~(APInt::getOneBitSet(NumElts, EltIdx));
if (!!VectorElts) {
computeKnownBits(InVec, KnownZero2, KnownOne2, VectorElts, Depth + 1);
KnownOne &= KnownOne2;
KnownZero &= KnownZero2;
}
} else {
// Unknown element index, so ignore DemandedElts and demand them all.
computeKnownBits(InVec, KnownZero, KnownOne, Depth + 1);
computeKnownBits(InVal, KnownZero2, KnownOne2, Depth + 1);
KnownOne &= KnownOne2.zextOrTrunc(KnownOne.getBitWidth());
KnownZero &= KnownZero2.zextOrTrunc(KnownZero.getBitWidth());;
}
break;
}
case ISD::BSWAP: {
computeKnownBits(Op.getOperand(0), KnownZero2, KnownOne2, DemandedElts,
Depth + 1);

12
llvm/test/CodeGen/X86/known-bits-vector.ll
View File

@ -58,11 +58,7 @@ define <4 x float> @knownbits_insert_uitofp(<4 x i32> %a0, i16 %a1, i16 %a2) nou
; X32-NEXT: vpinsrd $0, %eax, %xmm0, %xmm0
; X32-NEXT: vpinsrd $2, %ecx, %xmm0, %xmm0
; X32-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,2,2]
; X32-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X32-NEXT: vpsrld $16, %xmm0, %xmm0
; X32-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X32-NEXT: vaddps {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vaddps %xmm0, %xmm1, %xmm0
; X32-NEXT: vcvtdq2ps %xmm0, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: knownbits_insert_uitofp:
@ -72,11 +68,7 @@ define <4 x float> @knownbits_insert_uitofp(<4 x i32> %a0, i16 %a1, i16 %a2) nou
; X64-NEXT: vpinsrd $0, %eax, %xmm0, %xmm0
; X64-NEXT: vpinsrd $2, %ecx, %xmm0, %xmm0
; X64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,2,2]
; X64-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X64-NEXT: vpsrld $16, %xmm0, %xmm0
; X64-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X64-NEXT: vaddps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vaddps %xmm0, %xmm1, %xmm0
; X64-NEXT: vcvtdq2ps %xmm0, %xmm0
; X64-NEXT: retq
%1 = zext i16 %a1 to i32
%2 = zext i16 %a2 to i32