bool Scalarizer::visitSelectInst(SelectInst &SI) {
VectorType *VT = dyn_cast<VectorType>(SI.getType());
if (!VT)
return false;
unsigned NumElems = VT->getNumElements();
IRBuilder<> Builder(SI.getParent(), &SI);
Scatterer Op1 = scatter(&SI, SI.getOperand(1));
Scatterer Op2 = scatter(&SI, SI.getOperand(2));
assert(Op1.size() == NumElems && "Mismatched select");
assert(Op2.size() == NumElems && "Mismatched select");
ValueVector Res;
Res.resize(NumElems);
if (SI.getOperand(0)->getType()->isVectorTy()) {
Scatterer Op0 = scatter(&SI, SI.getOperand(0));
assert(Op0.size() == NumElems && "Mismatched select");
for (unsigned I = 0; I < NumElems; ++I)
Res[I] = Builder.CreateSelect(Op0[I], Op1[I], Op2[I],
SI.getName() + ".i" + Twine(I));
} else {
Value *Op0 = SI.getOperand(0);
for (unsigned I = 0; I < NumElems; ++I)
Res[I] = Builder.CreateSelect(Op0, Op1[I], Op2[I],
SI.getName() + ".i" + Twine(I));
}
gather(&SI, Res);
return true;
}
bool Scalarizer::visitStoreInst(StoreInst &SI) {
if (!ScalarizeLoadStore)
return false;
if (!SI.isSimple())
return false;
VectorLayout Layout;
Value *FullValue = SI.getValueOperand();
if (!getVectorLayout(FullValue->getType(), SI.getAlignment(), Layout))
return false;
unsigned NumElems = Layout.VecTy->getNumElements();
IRBuilder<> Builder(SI.getParent(), &SI);
Scatterer Ptr = scatter(&SI, SI.getPointerOperand());
Scatterer Val = scatter(&SI, FullValue);
ValueVector Stores;
Stores.resize(NumElems);
for (unsigned I = 0; I < NumElems; ++I) {
unsigned Align = Layout.getElemAlign(I);
Stores[I] = Builder.CreateAlignedStore(Val[I], Ptr[I], Align);
}
transferMetadata(&SI, Stores);
return true;
}
bool Scalarizer::visitGetElementPtrInst(GetElementPtrInst &GEPI) {
VectorType *VT = dyn_cast<VectorType>(GEPI.getType());
if (!VT)
return false;
IRBuilder<> Builder(&GEPI);
unsigned NumElems = VT->getNumElements();
unsigned NumIndices = GEPI.getNumIndices();
Scatterer Base = scatter(&GEPI, GEPI.getOperand(0));
SmallVector<Scatterer, 8> Ops;
Ops.resize(NumIndices);
for (unsigned I = 0; I < NumIndices; ++I)
Ops[I] = scatter(&GEPI, GEPI.getOperand(I + 1));
ValueVector Res;
Res.resize(NumElems);
for (unsigned I = 0; I < NumElems; ++I) {
SmallVector<Value *, 8> Indices;
Indices.resize(NumIndices);
for (unsigned J = 0; J < NumIndices; ++J)
Indices[J] = Ops[J][I];
Res[I] = Builder.CreateGEP(GEPI.getSourceElementType(), Base[I], Indices,
GEPI.getName() + ".i" + Twine(I));
if (GEPI.isInBounds())
if (GetElementPtrInst *NewGEPI = dyn_cast<GetElementPtrInst>(Res[I]))
NewGEPI->setIsInBounds();
}
gather(&GEPI, Res);
return true;
}
bool Scalarizer::visitBitCastInst(BitCastInst &BCI) {
VectorType *DstVT = dyn_cast<VectorType>(BCI.getDestTy());
VectorType *SrcVT = dyn_cast<VectorType>(BCI.getSrcTy());
if (!DstVT || !SrcVT)
return false;
unsigned DstNumElems = DstVT->getNumElements();
unsigned SrcNumElems = SrcVT->getNumElements();
IRBuilder<> Builder(BCI.getParent(), &BCI);
Scatterer Op0 = scatter(&BCI, BCI.getOperand(0));
ValueVector Res;
Res.resize(DstNumElems);
if (DstNumElems == SrcNumElems) {
for (unsigned I = 0; I < DstNumElems; ++I)
Res[I] = Builder.CreateBitCast(Op0[I], DstVT->getElementType(),
BCI.getName() + ".i" + Twine(I));
} else if (DstNumElems > SrcNumElems) {
// <M x t1> -> <N*M x t2>. Convert each t1 to <N x t2> and copy the
// individual elements to the destination.
unsigned FanOut = DstNumElems / SrcNumElems;
Type *MidTy = VectorType::get(DstVT->getElementType(), FanOut);
unsigned ResI = 0;
for (unsigned Op0I = 0; Op0I < SrcNumElems; ++Op0I) {
Value *V = Op0[Op0I];
Instruction *VI;
// Look through any existing bitcasts before converting to <N x t2>.
// In the best case, the resulting conversion might be a no-op.
while ((VI = dyn_cast<Instruction>(V)) &&
VI->getOpcode() == Instruction::BitCast)
V = VI->getOperand(0);
V = Builder.CreateBitCast(V, MidTy, V->getName() + ".cast");
Scatterer Mid = scatter(&BCI, V);
for (unsigned MidI = 0; MidI < FanOut; ++MidI)
Res[ResI++] = Mid[MidI];
}
} else {
// <N*M x t1> -> <M x t2>. Convert each group of <N x t1> into a t2.
unsigned FanIn = SrcNumElems / DstNumElems;
Type *MidTy = VectorType::get(SrcVT->getElementType(), FanIn);
unsigned Op0I = 0;
for (unsigned ResI = 0; ResI < DstNumElems; ++ResI) {
Value *V = UndefValue::get(MidTy);
for (unsigned MidI = 0; MidI < FanIn; ++MidI)
V = Builder.CreateInsertElement(V, Op0[Op0I++], Builder.getInt32(MidI),
BCI.getName() + ".i" + Twine(ResI)
+ ".upto" + Twine(MidI));
Res[ResI] = Builder.CreateBitCast(V, DstVT->getElementType(),
BCI.getName() + ".i" + Twine(ResI));
}
}
gather(&BCI, Res);
return true;
}
bool Scalarizer::visitCastInst(CastInst &CI) {
VectorType *VT = dyn_cast<VectorType>(CI.getDestTy());
if (!VT)
return false;
unsigned NumElems = VT->getNumElements();
IRBuilder<> Builder(CI.getParent(), &CI);
Scatterer Op0 = scatter(&CI, CI.getOperand(0));
assert(Op0.size() == NumElems && "Mismatched cast");
ValueVector Res;
Res.resize(NumElems);
for (unsigned I = 0; I < NumElems; ++I)
Res[I] = Builder.CreateCast(CI.getOpcode(), Op0[I], VT->getElementType(),
CI.getName() + ".i" + Twine(I));
gather(&CI, Res);
return true;
}
bool Scalarizer::splitBinary(Instruction &I, const Splitter &Split) {
VectorType *VT = dyn_cast<VectorType>(I.getType());
if (!VT)
return false;
unsigned NumElems = VT->getNumElements();
IRBuilder<> Builder(I.getParent(), &I);
Scatterer Op0 = scatter(&I, I.getOperand(0));
Scatterer Op1 = scatter(&I, I.getOperand(1));
assert(Op0.size() == NumElems && "Mismatched binary operation");
assert(Op1.size() == NumElems && "Mismatched binary operation");
ValueVector Res;
Res.resize(NumElems);
for (unsigned Elem = 0; Elem < NumElems; ++Elem)
Res[Elem] = Split(Builder, Op0[Elem], Op1[Elem],
I.getName() + ".i" + Twine(Elem));
gather(&I, Res);
return true;
}
bool Scalarizer::visitLoadInst(LoadInst &LI) {
if (!ScalarizeLoadStore)
return false;
if (!LI.isSimple())
return false;
VectorLayout Layout;
if (!getVectorLayout(LI.getType(), LI.getAlignment(), Layout))
return false;
unsigned NumElems = Layout.VecTy->getNumElements();
IRBuilder<> Builder(LI.getParent(), &LI);
Scatterer Ptr = scatter(&LI, LI.getPointerOperand());
ValueVector Res;
Res.resize(NumElems);
for (unsigned I = 0; I < NumElems; ++I)
Res[I] = Builder.CreateAlignedLoad(Ptr[I], Layout.getElemAlign(I),
LI.getName() + ".i" + Twine(I));
gather(&LI, Res);
return true;
}
bool Scalarizer::visitShuffleVectorInst(ShuffleVectorInst &SVI) {
VectorType *VT = dyn_cast<VectorType>(SVI.getType());
if (!VT)
return false;
unsigned NumElems = VT->getNumElements();
Scatterer Op0 = scatter(&SVI, SVI.getOperand(0));
Scatterer Op1 = scatter(&SVI, SVI.getOperand(1));
ValueVector Res;
Res.resize(NumElems);
for (unsigned I = 0; I < NumElems; ++I) {
int Selector = SVI.getMaskValue(I);
if (Selector < 0)
Res[I] = UndefValue::get(VT->getElementType());
else if (unsigned(Selector) < Op0.size())
Res[I] = Op0[Selector];
else
Res[I] = Op1[Selector - Op0.size()];
}
gather(&SVI, Res);
return true;
}
bool Scalarizer::visitPHINode(PHINode &PHI) {
VectorType *VT = dyn_cast<VectorType>(PHI.getType());
if (!VT)
return false;
unsigned NumElems = VT->getNumElements();
IRBuilder<> Builder(PHI.getParent(), &PHI);
ValueVector Res;
Res.resize(NumElems);
unsigned NumOps = PHI.getNumOperands();
for (unsigned I = 0; I < NumElems; ++I)
Res[I] = Builder.CreatePHI(VT->getElementType(), NumOps,
PHI.getName() + ".i" + Twine(I));
for (unsigned I = 0; I < NumOps; ++I) {
Scatterer Op = scatter(&PHI, PHI.getIncomingValue(I));
BasicBlock *IncomingBlock = PHI.getIncomingBlock(I);
for (unsigned J = 0; J < NumElems; ++J)
cast<PHINode>(Res[J])->addIncoming(Op[J], IncomingBlock);
}
gather(&PHI, Res);
return true;
}