void Lint::visitInsertElementInst(InsertElementInst &I) {
if (ConstantInt *CI =
dyn_cast<ConstantInt>(findValue(I.getOperand(2),
/*OffsetOk=*/false)))
Assert1(CI->getValue().ult(I.getType()->getNumElements()),
"Undefined result: insertelement index out of range", &I);
}
// Return component I, creating a new Value for it if necessary.
Value *Scatterer::operator[](unsigned I) {
ValueVector &CV = (CachePtr ? *CachePtr : Tmp);
// Try to reuse a previous value.
if (CV[I])
return CV[I];
IRBuilder<> Builder(BB, BBI);
if (PtrTy) {
if (!CV[0]) {
Type *Ty =
PointerType::get(PtrTy->getElementType()->getVectorElementType(),
PtrTy->getAddressSpace());
CV[0] = Builder.CreateBitCast(V, Ty, V->getName() + ".i0");
}
if (I != 0)
CV[I] = Builder.CreateConstGEP1_32(nullptr, CV[0], I,
V->getName() + ".i" + Twine(I));
} else {
// Search through a chain of InsertElementInsts looking for element I.
// Record other elements in the cache. The new V is still suitable
// for all uncached indices.
for (;;) {
InsertElementInst *Insert = dyn_cast<InsertElementInst>(V);
if (!Insert)
break;
ConstantInt *Idx = dyn_cast<ConstantInt>(Insert->getOperand(2));
if (!Idx)
break;
unsigned J = Idx->getZExtValue();
V = Insert->getOperand(0);
if (I == J) {
CV[J] = Insert->getOperand(1);
return CV[J];
} else if (!CV[J]) {
// Only cache the first entry we find for each index we're not actively
// searching for. This prevents us from going too far up the chain and
// caching incorrect entries.
CV[J] = Insert->getOperand(1);
}
}
CV[I] = Builder.CreateExtractElement(V, Builder.getInt32(I),
V->getName() + ".i" + Twine(I));
}
return CV[I];
}
// This function is *almost* as-is from instcombine, avoiding silly
// cases that should already have been optimized.
bool BackendCanonicalize::visitInsertElementInst(InsertElementInst &IE) {
Value *ScalarOp = IE.getOperand(1);
Value *IdxOp = IE.getOperand(2);
// If the inserted element was extracted from some other vector, and if the
// indexes are constant, try to turn this into a shufflevector operation.
if (ExtractElementInst *EI = dyn_cast<ExtractElementInst>(ScalarOp)) {
if (isa<ConstantInt>(EI->getOperand(1)) && isa<ConstantInt>(IdxOp)) {
unsigned NumInsertVectorElts = IE.getType()->getNumElements();
unsigned NumExtractVectorElts =
EI->getOperand(0)->getType()->getVectorNumElements();
unsigned ExtractedIdx =
cast<ConstantInt>(EI->getOperand(1))->getZExtValue();
unsigned InsertedIdx = cast<ConstantInt>(IdxOp)->getZExtValue();
if (ExtractedIdx >= NumExtractVectorElts) // Out of range extract.
return false;
if (InsertedIdx >= NumInsertVectorElts) // Out of range insert.
return false;
// If this insertelement isn't used by some other insertelement, turn it
// (and any insertelements it points to), into one big shuffle.
if (!IE.hasOneUse() || !isa<InsertElementInst>(IE.user_back())) {
typedef SmallVector<Constant *, 16> MaskT;
MaskT Mask;
Value *LHS, *RHS;
std::tie(LHS, RHS) = CollectShuffleElements(&IE, Mask, nullptr);
if (!RHS)
RHS = UndefValue::get(LHS->getType());
// We now have a shuffle of LHS, RHS, Mask.
if (isa<UndefValue>(LHS) && !isa<UndefValue>(RHS)) {
// Canonicalize shufflevector to always have undef on the RHS,
// and adjust the mask.
std::swap(LHS, RHS);
for (MaskT::iterator I = Mask.begin(), E = Mask.end(); I != E; ++I) {
unsigned Idx = cast<ConstantInt>(*I)->getZExtValue();
unsigned NewIdx = Idx >= NumInsertVectorElts
? Idx - NumInsertVectorElts
: Idx + NumInsertVectorElts;
*I = ConstantInt::get(Type::getInt32Ty(RHS->getContext()), NewIdx);
}
}
IRBuilder<> IRB(&IE);
IE.replaceAllUsesWith(
IRB.CreateShuffleVector(LHS, RHS, ConstantVector::get(Mask)));
// The chain of now-dead insertelement / extractelement
// instructions can be deleted.
Kill.push_back(&IE);
return true;
}
}
}
return false;
}
unsigned CostModelAnalysis::getInstructionCost(Instruction *I) const {
if (!VTTI)
return -1;
switch (I->getOpcode()) {
case Instruction::Ret:
case Instruction::PHI:
case Instruction::Br: {
return VTTI->getCFInstrCost(I->getOpcode());
}
case Instruction::Add:
case Instruction::FAdd:
case Instruction::Sub:
case Instruction::FSub:
case Instruction::Mul:
case Instruction::FMul:
case Instruction::UDiv:
case Instruction::SDiv:
case Instruction::FDiv:
case Instruction::URem:
case Instruction::SRem:
case Instruction::FRem:
case Instruction::Shl:
case Instruction::LShr:
case Instruction::AShr:
case Instruction::And:
case Instruction::Or:
case Instruction::Xor: {
return VTTI->getArithmeticInstrCost(I->getOpcode(), I->getType());
}
case Instruction::Select: {
SelectInst *SI = cast<SelectInst>(I);
Type *CondTy = SI->getCondition()->getType();
return VTTI->getCmpSelInstrCost(I->getOpcode(), I->getType(), CondTy);
}
case Instruction::ICmp:
case Instruction::FCmp: {
Type *ValTy = I->getOperand(0)->getType();
return VTTI->getCmpSelInstrCost(I->getOpcode(), ValTy);
}
case Instruction::Store: {
StoreInst *SI = cast<StoreInst>(I);
Type *ValTy = SI->getValueOperand()->getType();
return VTTI->getMemoryOpCost(I->getOpcode(), ValTy,
SI->getAlignment(),
SI->getPointerAddressSpace());
}
case Instruction::Load: {
LoadInst *LI = cast<LoadInst>(I);
return VTTI->getMemoryOpCost(I->getOpcode(), I->getType(),
LI->getAlignment(),
LI->getPointerAddressSpace());
}
case Instruction::ZExt:
case Instruction::SExt:
case Instruction::FPToUI:
case Instruction::FPToSI:
case Instruction::FPExt:
case Instruction::PtrToInt:
case Instruction::IntToPtr:
case Instruction::SIToFP:
case Instruction::UIToFP:
case Instruction::Trunc:
case Instruction::FPTrunc:
case Instruction::BitCast: {
Type *SrcTy = I->getOperand(0)->getType();
return VTTI->getCastInstrCost(I->getOpcode(), I->getType(), SrcTy);
}
case Instruction::ExtractElement: {
ExtractElementInst * EEI = cast<ExtractElementInst>(I);
ConstantInt *CI = dyn_cast<ConstantInt>(I->getOperand(1));
unsigned Idx = -1;
if (CI)
Idx = CI->getZExtValue();
return VTTI->getVectorInstrCost(I->getOpcode(),
EEI->getOperand(0)->getType(), Idx);
}
case Instruction::InsertElement: {
InsertElementInst * IE = cast<InsertElementInst>(I);
ConstantInt *CI = dyn_cast<ConstantInt>(IE->getOperand(2));
unsigned Idx = -1;
if (CI)
Idx = CI->getZExtValue();
return VTTI->getVectorInstrCost(I->getOpcode(),
IE->getType(), Idx);
}
default:
// We don't have any information on this instruction.
return -1;
}
}
void Lint::visitInsertElementInst(InsertElementInst &I) {
if (ConstantInt *CI =
dyn_cast<ConstantInt>(I.getOperand(2)->stripPointerCasts()))
Assert1(CI->getValue().ult(I.getType()->getNumElements()),
"Undefined result: insertelement index out of range", &I);
}
