PointerType *PTy = cast<PointerType>(CI.getType());
BuilderTy AllocaBuilder(*Builder);
- AllocaBuilder.SetInsertPoint(AI.getParent(), &AI);
+ AllocaBuilder.SetInsertPoint(&AI);
// Get the type really allocated and the type casted to.
Type *AllocElTy = AI.getAllocatedType();
return false;
}
+/// Given a vector that is bitcast to an integer, optionally logically
+/// right-shifted, and truncated, convert it to an extractelement.
+/// Example (big endian):
+/// trunc (lshr (bitcast <4 x i32> %X to i128), 32) to i32
+/// --->
+/// extractelement <4 x i32> %X, 1
+static Instruction *foldVecTruncToExtElt(TruncInst &Trunc, InstCombiner &IC,
+ const DataLayout &DL) {
+ Value *TruncOp = Trunc.getOperand(0);
+ Type *DestType = Trunc.getType();
+ if (!TruncOp->hasOneUse() || !isa<IntegerType>(DestType))
+ return nullptr;
+
+ Value *VecInput = nullptr;
+ ConstantInt *ShiftVal = nullptr;
+ if (!match(TruncOp, m_CombineOr(m_BitCast(m_Value(VecInput)),
+ m_LShr(m_BitCast(m_Value(VecInput)),
+ m_ConstantInt(ShiftVal)))) ||
+ !isa<VectorType>(VecInput->getType()))
+ return nullptr;
+
+ VectorType *VecType = cast<VectorType>(VecInput->getType());
+ unsigned VecWidth = VecType->getPrimitiveSizeInBits();
+ unsigned DestWidth = DestType->getPrimitiveSizeInBits();
+ unsigned ShiftAmount = ShiftVal ? ShiftVal->getZExtValue() : 0;
+
+ if ((VecWidth % DestWidth != 0) || (ShiftAmount % DestWidth != 0))
+ return nullptr;
+
+ // If the element type of the vector doesn't match the result type,
+ // bitcast it to a vector type that we can extract from.
+ unsigned NumVecElts = VecWidth / DestWidth;
+ if (VecType->getElementType() != DestType) {
+ VecType = VectorType::get(DestType, NumVecElts);
+ VecInput = IC.Builder->CreateBitCast(VecInput, VecType, "bc");
+ }
+
+ unsigned Elt = ShiftAmount / DestWidth;
+ if (DL.isBigEndian())
+ Elt = NumVecElts - 1 - Elt;
+
+ return ExtractElementInst::Create(VecInput, IC.Builder->getInt32(Elt));
+}
+
Instruction *InstCombiner::visitTrunc(TruncInst &CI) {
if (Instruction *Result = commonCastTransforms(CI))
return Result;
// Canonicalize trunc x to i1 -> (icmp ne (and x, 1), 0), likewise for vector.
if (DestTy->getScalarSizeInBits() == 1) {
- Constant *One = ConstantInt::get(Src->getType(), 1);
+ Constant *One = ConstantInt::get(SrcTy, 1);
Src = Builder->CreateAnd(Src, One);
Value *Zero = Constant::getNullValue(Src->getType());
return new ICmpInst(ICmpInst::ICMP_NE, Src, Zero);
// If the shift amount is larger than the size of A, then the result is
// known to be zero because all the input bits got shifted out.
if (Cst->getZExtValue() >= ASize)
- return ReplaceInstUsesWith(CI, Constant::getNullValue(CI.getType()));
+ return ReplaceInstUsesWith(CI, Constant::getNullValue(DestTy));
// Since we're doing an lshr and a zero extend, and know that the shift
// amount is smaller than ASize, it is always safe to do the shift in A's
// type, then zero extend or truncate to the result.
Value *Shift = Builder->CreateLShr(A, Cst->getZExtValue());
Shift->takeName(Src);
- return CastInst::CreateIntegerCast(Shift, CI.getType(), false);
+ return CastInst::CreateIntegerCast(Shift, DestTy, false);
+ }
+
+ // Transform trunc(lshr (sext A), Cst) to ashr A, Cst to eliminate type
+ // conversion.
+ // It works because bits coming from sign extension have the same value as
+ // the sign bit of the original value; performing ashr instead of lshr
+ // generates bits of the same value as the sign bit.
+ if (Src->hasOneUse() &&
+ match(Src, m_LShr(m_SExt(m_Value(A)), m_ConstantInt(Cst))) &&
+ cast<Instruction>(Src)->getOperand(0)->hasOneUse()) {
+ const unsigned ASize = A->getType()->getPrimitiveSizeInBits();
+ // This optimization can be only performed when zero bits generated by
+ // the original lshr aren't pulled into the value after truncation, so we
+ // can only shift by values smaller than the size of destination type (in
+ // bits).
+ if (Cst->getValue().ult(ASize)) {
+ Value *Shift = Builder->CreateAShr(A, Cst->getZExtValue());
+ Shift->takeName(Src);
+ return CastInst::CreateIntegerCast(Shift, CI.getType(), true);
+ }
}
// Transform "trunc (and X, cst)" -> "and (trunc X), cst" so long as the dest
// type isn't non-native.
- if (Src->hasOneUse() && isa<IntegerType>(Src->getType()) &&
- ShouldChangeType(Src->getType(), CI.getType()) &&
+ if (Src->hasOneUse() && isa<IntegerType>(SrcTy) &&
+ ShouldChangeType(SrcTy, DestTy) &&
match(Src, m_And(m_Value(A), m_ConstantInt(Cst)))) {
- Value *NewTrunc = Builder->CreateTrunc(A, CI.getType(), A->getName()+".tr");
+ Value *NewTrunc = Builder->CreateTrunc(A, DestTy, A->getName() + ".tr");
return BinaryOperator::CreateAnd(NewTrunc,
- ConstantExpr::getTrunc(Cst, CI.getType()));
+ ConstantExpr::getTrunc(Cst, DestTy));
}
+ if (Instruction *I = foldVecTruncToExtElt(CI, *this, DL))
+ return I;
+
return nullptr;
}
// Okay, we can transform this! Insert the new expression now.
DEBUG(dbgs() << "ICE: EvaluateInDifferentType converting expression type"
- " to avoid zero extend: " << CI);
+ " to avoid zero extend: " << CI << '\n');
Value *Res = EvaluateInDifferentType(Src, DestTy, false);
assert(Res->getType() == DestTy);
canEvaluateSExtd(Src, DestTy)) {
// Okay, we can transform this! Insert the new expression now.
DEBUG(dbgs() << "ICE: EvaluateInDifferentType converting expression type"
- " to avoid sign extend: " << CI);
+ " to avoid sign extend: " << CI << '\n');
Value *Res = EvaluateInDifferentType(Src, DestTy, true);
assert(Res->getType() == DestTy);
if (Instruction *I = commonCastTransforms(CI))
return I;
// If we have fptrunc(OpI (fpextend x), (fpextend y)), we would like to
- // simpilify this expression to avoid one or more of the trunc/extend
+ // simplify this expression to avoid one or more of the trunc/extend
// operations if we can do so without changing the numerical results.
//
// The exact manner in which the widths of the operands interact to limit
Value *InnerTrunc = Builder->CreateFPTrunc(II->getArgOperand(0),
CI.getType());
Type *IntrinsicType[] = { CI.getType() };
- Function *Overload =
- Intrinsic::getDeclaration(CI.getParent()->getParent()->getParent(),
- II->getIntrinsicID(), IntrinsicType);
+ Function *Overload = Intrinsic::getDeclaration(
+ CI.getModule(), II->getIntrinsicID(), IntrinsicType);
Value *Args[] = { InnerTrunc };
return CallInst::Create(Overload, Args, II->getName());
return Result;
}
-
-/// See if we can optimize an integer->float/double bitcast.
-/// The various long double bitcasts can't get in here.
-static Instruction *optimizeIntToFloatBitCast(BitCastInst &CI, InstCombiner &IC,
+/// Canonicalize scalar bitcasts of extracted elements into a bitcast of the
+/// vector followed by extract element. The backend tends to handle bitcasts of
+/// vectors better than bitcasts of scalars because vector registers are
+/// usually not type-specific like scalar integer or scalar floating-point.
+static Instruction *canonicalizeBitCastExtElt(BitCastInst &BitCast,
+ InstCombiner &IC,
const DataLayout &DL) {
- Value *Src = CI.getOperand(0);
- Type *DestTy = CI.getType();
-
- // If this is a bitcast from int to float, check to see if the int is an
- // extraction from a vector.
- Value *VecInput = nullptr;
- // bitcast(trunc(bitcast(somevector)))
- if (match(Src, m_Trunc(m_BitCast(m_Value(VecInput)))) &&
- isa<VectorType>(VecInput->getType())) {
- VectorType *VecTy = cast<VectorType>(VecInput->getType());
- unsigned DestWidth = DestTy->getPrimitiveSizeInBits();
-
- if (VecTy->getPrimitiveSizeInBits() % DestWidth == 0) {
- // If the element type of the vector doesn't match the result type,
- // bitcast it to be a vector type we can extract from.
- if (VecTy->getElementType() != DestTy) {
- VecTy = VectorType::get(DestTy,
- VecTy->getPrimitiveSizeInBits() / DestWidth);
- VecInput = IC.Builder->CreateBitCast(VecInput, VecTy);
- }
-
- unsigned Elt = 0;
- if (DL.isBigEndian())
- Elt = VecTy->getPrimitiveSizeInBits() / DestWidth - 1;
- return ExtractElementInst::Create(VecInput, IC.Builder->getInt32(Elt));
- }
- }
+ // TODO: Create and use a pattern matcher for ExtractElementInst.
+ auto *ExtElt = dyn_cast<ExtractElementInst>(BitCast.getOperand(0));
+ if (!ExtElt || !ExtElt->hasOneUse())
+ return nullptr;
- // bitcast(trunc(lshr(bitcast(somevector), cst))
- ConstantInt *ShAmt = nullptr;
- if (match(Src, m_Trunc(m_LShr(m_BitCast(m_Value(VecInput)),
- m_ConstantInt(ShAmt)))) &&
- isa<VectorType>(VecInput->getType())) {
- VectorType *VecTy = cast<VectorType>(VecInput->getType());
- unsigned DestWidth = DestTy->getPrimitiveSizeInBits();
- if (VecTy->getPrimitiveSizeInBits() % DestWidth == 0 &&
- ShAmt->getZExtValue() % DestWidth == 0) {
- // If the element type of the vector doesn't match the result type,
- // bitcast it to be a vector type we can extract from.
- if (VecTy->getElementType() != DestTy) {
- VecTy = VectorType::get(DestTy,
- VecTy->getPrimitiveSizeInBits() / DestWidth);
- VecInput = IC.Builder->CreateBitCast(VecInput, VecTy);
- }
+ // The bitcast must be to a vectorizable type, otherwise we can't make a new
+ // type to extract from.
+ Type *DestType = BitCast.getType();
+ if (!VectorType::isValidElementType(DestType))
+ return nullptr;
- unsigned Elt = ShAmt->getZExtValue() / DestWidth;
- if (DL.isBigEndian())
- Elt = VecTy->getPrimitiveSizeInBits() / DestWidth - 1 - Elt;
- return ExtractElementInst::Create(VecInput, IC.Builder->getInt32(Elt));
- }
- }
- return nullptr;
+ unsigned NumElts = ExtElt->getVectorOperandType()->getNumElements();
+ auto *NewVecType = VectorType::get(DestType, NumElts);
+ auto *NewBC = IC.Builder->CreateBitCast(ExtElt->getVectorOperand(),
+ NewVecType, "bc");
+ return ExtractElementInst::Create(NewBC, ExtElt->getIndexOperand());
}
Instruction *InstCombiner::visitBitCast(BitCastInst &CI) {
}
}
- // Try to optimize int -> float bitcasts.
- if ((DestTy->isFloatTy() || DestTy->isDoubleTy()) && isa<IntegerType>(SrcTy))
- if (Instruction *I = optimizeIntToFloatBitCast(CI, *this, DL))
- return I;
-
if (VectorType *DestVTy = dyn_cast<VectorType>(DestTy)) {
if (DestVTy->getNumElements() == 1 && !SrcTy->isVectorTy()) {
Value *Elem = Builder->CreateBitCast(Src, DestVTy->getElementType());
}
}
+ if (Instruction *I = canonicalizeBitCastExtElt(CI, *this, DL))
+ return I;
+
if (SrcTy->isPointerTy())
return commonPointerCastTransforms(CI);
return commonCastTransforms(CI);
projects / oota-llvm.git / blobdiff