diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp --- a/clang/lib/CodeGen/CGExprScalar.cpp +++ b/clang/lib/CodeGen/CGExprScalar.cpp @@ -3264,10 +3264,10 @@ expr->getRHS())) return CGF.Builder.CreateIntToPtr(index, pointer->getType()); - if (width != DL.getTypeSizeInBits(PtrTy)) { + if (width != DL.getIndexTypeSizeInBits(PtrTy)) { // Zero-extend or sign-extend the pointer value according to // whether the index is signed or not. - index = CGF.Builder.CreateIntCast(index, DL.getIntPtrType(PtrTy), isSigned, + index = CGF.Builder.CreateIntCast(index, DL.getIndexType(PtrTy), isSigned, "idx.ext"); } diff --git a/llvm/include/llvm/Analysis/PtrUseVisitor.h b/llvm/include/llvm/Analysis/PtrUseVisitor.h --- a/llvm/include/llvm/Analysis/PtrUseVisitor.h +++ b/llvm/include/llvm/Analysis/PtrUseVisitor.h @@ -222,9 +222,9 @@ // offsets on this pointer. // FIXME: Support a vector of pointers. assert(I.getType()->isPointerTy()); - IntegerType *IntPtrTy = cast(DL.getIntPtrType(I.getType())); + IntegerType *IntIdxTy = cast(DL.getIndexType(I.getType())); IsOffsetKnown = true; - Offset = APInt(IntPtrTy->getBitWidth(), 0); + Offset = APInt(IntIdxTy->getBitWidth(), 0); PI.reset(); // Enqueue the uses of this pointer. diff --git a/llvm/include/llvm/Analysis/Utils/Local.h b/llvm/include/llvm/Analysis/Utils/Local.h --- a/llvm/include/llvm/Analysis/Utils/Local.h +++ b/llvm/include/llvm/Analysis/Utils/Local.h @@ -29,15 +29,15 @@ Value *EmitGEPOffset(IRBuilderTy *Builder, const DataLayout &DL, User *GEP, bool NoAssumptions = false) { GEPOperator *GEPOp = cast(GEP); - Type *IntPtrTy = DL.getIntPtrType(GEP->getType()); - Value *Result = Constant::getNullValue(IntPtrTy); + Type *IntIdxTy = DL.getIndexType(GEP->getType()); + Value *Result = Constant::getNullValue(IntIdxTy); // If the GEP is inbounds, we know that none of the addressing operations will // overflow in a signed sense. bool isInBounds = GEPOp->isInBounds() && !NoAssumptions; // Build a mask for high order bits. - unsigned IntPtrWidth = IntPtrTy->getScalarType()->getIntegerBitWidth(); + unsigned IntPtrWidth = IntIdxTy->getScalarType()->getIntegerBitWidth(); uint64_t PtrSizeMask = std::numeric_limits::max() >> (64 - IntPtrWidth); @@ -56,17 +56,17 @@ Size = DL.getStructLayout(STy)->getElementOffset(OpValue); if (Size) - Result = Builder->CreateAdd(Result, ConstantInt::get(IntPtrTy, Size), + Result = Builder->CreateAdd(Result, ConstantInt::get(IntIdxTy, Size), GEP->getName()+".offs"); continue; } // Splat the constant if needed. - if (IntPtrTy->isVectorTy() && !OpC->getType()->isVectorTy()) - OpC = ConstantVector::getSplat(IntPtrTy->getVectorNumElements(), OpC); + if (IntIdxTy->isVectorTy() && !OpC->getType()->isVectorTy()) + OpC = ConstantVector::getSplat(IntIdxTy->getVectorNumElements(), OpC); - Constant *Scale = ConstantInt::get(IntPtrTy, Size); - Constant *OC = ConstantExpr::getIntegerCast(OpC, IntPtrTy, true /*SExt*/); + Constant *Scale = ConstantInt::get(IntIdxTy, Size); + Constant *OC = ConstantExpr::getIntegerCast(OpC, IntIdxTy, true /*SExt*/); Scale = ConstantExpr::getMul(OC, Scale, false /*NUW*/, isInBounds /*NSW*/); // Emit an add instruction. @@ -75,15 +75,15 @@ } // Splat the index if needed. - if (IntPtrTy->isVectorTy() && !Op->getType()->isVectorTy()) - Op = Builder->CreateVectorSplat(IntPtrTy->getVectorNumElements(), Op); + if (IntIdxTy->isVectorTy() && !Op->getType()->isVectorTy()) + Op = Builder->CreateVectorSplat(IntIdxTy->getVectorNumElements(), Op); // Convert to correct type. - if (Op->getType() != IntPtrTy) - Op = Builder->CreateIntCast(Op, IntPtrTy, true, Op->getName()+".c"); + if (Op->getType() != IntIdxTy) + Op = Builder->CreateIntCast(Op, IntIdxTy, true, Op->getName()+".c"); if (Size != 1) { // We'll let instcombine(mul) convert this to a shl if possible. - Op = Builder->CreateMul(Op, ConstantInt::get(IntPtrTy, Size), + Op = Builder->CreateMul(Op, ConstantInt::get(IntIdxTy, Size), GEP->getName() + ".idx", false /*NUW*/, isInBounds /*NSW*/); } diff --git a/llvm/lib/Analysis/ConstantFolding.cpp b/llvm/lib/Analysis/ConstantFolding.cpp --- a/llvm/lib/Analysis/ConstantFolding.cpp +++ b/llvm/lib/Analysis/ConstantFolding.cpp @@ -766,8 +766,8 @@ Constant *CastGEPIndices(Type *SrcElemTy, ArrayRef Ops, Type *ResultTy, Optional InRangeIndex, const DataLayout &DL, const TargetLibraryInfo *TLI) { - Type *IntPtrTy = DL.getIntPtrType(ResultTy); - Type *IntPtrScalarTy = IntPtrTy->getScalarType(); + Type *IntIdxTy = DL.getIndexType(ResultTy); + Type *IntIdxScalarTy = IntIdxTy->getScalarType(); bool Any = false; SmallVector NewIdxs; @@ -775,11 +775,11 @@ if ((i == 1 || !isa(GetElementPtrInst::getIndexedType( SrcElemTy, Ops.slice(1, i - 1)))) && - Ops[i]->getType()->getScalarType() != IntPtrScalarTy) { + Ops[i]->getType()->getScalarType() != IntIdxScalarTy) { Any = true; Type *NewType = Ops[i]->getType()->isVectorTy() - ? IntPtrTy - : IntPtrTy->getScalarType(); + ? IntIdxTy + : IntIdxScalarTy; NewIdxs.push_back(ConstantExpr::getCast(CastInst::getCastOpcode(Ops[i], true, NewType, @@ -839,7 +839,7 @@ if (!Ptr->getType()->isPointerTy()) return nullptr; - Type *IntPtrTy = DL.getIntPtrType(Ptr->getType()); + Type *IntIdxTy = DL.getIndexType(Ptr->getType()); // If this is a constant expr gep that is effectively computing an // "offsetof", fold it into 'cast int Size to T*' instead of 'gep 0, 0, 12' @@ -850,7 +850,7 @@ // "inttoptr (sub (ptrtoint Ptr), V)" if (Ops.size() == 2 && ResElemTy->isIntegerTy(8)) { auto *CE = dyn_cast(Ops[1]); - assert((!CE || CE->getType() == IntPtrTy) && + assert((!CE || CE->getType() == IntIdxTy) && "CastGEPIndices didn't canonicalize index types!"); if (CE && CE->getOpcode() == Instruction::Sub && CE->getOperand(0)->isNullValue()) { @@ -865,7 +865,7 @@ return nullptr; } - unsigned BitWidth = DL.getTypeSizeInBits(IntPtrTy); + unsigned BitWidth = DL.getTypeSizeInBits(IntIdxTy); APInt Offset = APInt(BitWidth, DL.getIndexedOffsetInType( @@ -945,7 +945,7 @@ // The element size is 0. This may be [0 x Ty]*, so just use a zero // index for this level and proceed to the next level to see if it can // accommodate the offset. - NewIdxs.push_back(ConstantInt::get(IntPtrTy, 0)); + NewIdxs.push_back(ConstantInt::get(IntIdxTy, 0)); } else { // The element size is non-zero divide the offset by the element // size (rounding down), to compute the index at this level. @@ -954,7 +954,7 @@ if (Overflow) break; Offset -= NewIdx * ElemSize; - NewIdxs.push_back(ConstantInt::get(IntPtrTy, NewIdx)); + NewIdxs.push_back(ConstantInt::get(IntIdxTy, NewIdx)); } } else { auto *STy = cast(Ty); diff --git a/llvm/lib/Analysis/InlineCost.cpp b/llvm/lib/Analysis/InlineCost.cpp --- a/llvm/lib/Analysis/InlineCost.cpp +++ b/llvm/lib/Analysis/InlineCost.cpp @@ -1678,8 +1678,8 @@ assert(V->getType()->isPointerTy() && "Unexpected operand type!"); } while (Visited.insert(V).second); - Type *IntPtrTy = DL.getIntPtrType(V->getContext(), AS); - return cast(ConstantInt::get(IntPtrTy, Offset)); + Type *IdxPtrTy = DL.getIndexType(V->getType()); + return cast(ConstantInt::get(IdxPtrTy, Offset)); } /// Find dead blocks due to deleted CFG edges during inlining. diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp --- a/llvm/lib/Analysis/InstructionSimplify.cpp +++ b/llvm/lib/Analysis/InstructionSimplify.cpp @@ -662,16 +662,16 @@ bool AllowNonInbounds = false) { assert(V->getType()->isPtrOrPtrVectorTy()); - Type *IntPtrTy = DL.getIntPtrType(V->getType())->getScalarType(); - APInt Offset = APInt::getNullValue(IntPtrTy->getIntegerBitWidth()); + Type *IntIdxTy = DL.getIndexType(V->getType())->getScalarType(); + APInt Offset = APInt::getNullValue(IntIdxTy->getIntegerBitWidth()); V = V->stripAndAccumulateConstantOffsets(DL, Offset, AllowNonInbounds); // As that strip may trace through `addrspacecast`, need to sext or trunc // the offset calculated. - IntPtrTy = DL.getIntPtrType(V->getType())->getScalarType(); - Offset = Offset.sextOrTrunc(IntPtrTy->getIntegerBitWidth()); + IntIdxTy = DL.getIndexType(V->getType())->getScalarType(); + Offset = Offset.sextOrTrunc(IntIdxTy->getIntegerBitWidth()); - Constant *OffsetIntPtr = ConstantInt::get(IntPtrTy, Offset); + Constant *OffsetIntPtr = ConstantInt::get(IntIdxTy, Offset); if (V->getType()->isVectorTy()) return ConstantVector::getSplat(V->getType()->getVectorNumElements(), OffsetIntPtr); @@ -4032,7 +4032,7 @@ // The following transforms are only safe if the ptrtoint cast // doesn't truncate the pointers. if (Ops[1]->getType()->getScalarSizeInBits() == - Q.DL.getIndexSizeInBits(AS)) { + Q.DL.getPointerSizeInBits(AS)) { auto PtrToIntOrZero = [GEPTy](Value *P) -> Value * { if (match(P, m_Zero())) return Constant::getNullValue(GEPTy); diff --git a/llvm/lib/Analysis/Loads.cpp b/llvm/lib/Analysis/Loads.cpp --- a/llvm/lib/Analysis/Loads.cpp +++ b/llvm/lib/Analysis/Loads.cpp @@ -150,7 +150,7 @@ // Require ABI alignment for loads without alignment specification const Align Alignment = DL.getValueOrABITypeAlignment(MA, Ty); - APInt AccessSize(DL.getIndexTypeSizeInBits(V->getType()), + APInt AccessSize(DL.getPointerTypeSizeInBits(V->getType()), DL.getTypeStoreSize(Ty)); return isDereferenceableAndAlignedPointer(V, Alignment, AccessSize, DL, CtxI, DT); diff --git a/llvm/lib/Analysis/MemoryBuiltins.cpp b/llvm/lib/Analysis/MemoryBuiltins.cpp --- a/llvm/lib/Analysis/MemoryBuiltins.cpp +++ b/llvm/lib/Analysis/MemoryBuiltins.cpp @@ -544,6 +544,7 @@ Builder.CreateSub(SizeOffsetPair.first, SizeOffsetPair.second); Value *UseZero = Builder.CreateICmpULT(SizeOffsetPair.first, SizeOffsetPair.second); + ResultSize = Builder.CreateZExtOrTrunc(ResultSize, ResultType); return Builder.CreateSelect(UseZero, ConstantInt::get(ResultType, 0), ResultSize); } @@ -576,7 +577,7 @@ } SizeOffsetType ObjectSizeOffsetVisitor::compute(Value *V) { - IntTyBits = DL.getPointerTypeSizeInBits(V->getType()); + IntTyBits = DL.getIndexTypeSizeInBits(V->getType()); Zero = APInt::getNullValue(IntTyBits); V = V->stripPointerCasts(); @@ -746,7 +747,7 @@ SizeOffsetType ObjectSizeOffsetVisitor::visitGEPOperator(GEPOperator &GEP) { SizeOffsetType PtrData = compute(GEP.getPointerOperand()); - APInt Offset(IntTyBits, 0); + APInt Offset(DL.getIndexTypeSizeInBits(GEP.getPointerOperand()->getType()), 0); if (!bothKnown(PtrData) || !GEP.accumulateConstantOffset(DL, Offset)) return unknown(); @@ -834,7 +835,7 @@ SizeOffsetEvalType ObjectSizeOffsetEvaluator::compute(Value *V) { // XXX - Are vectors of pointers possible here? - IntTy = cast(DL.getIntPtrType(V->getType())); + IntTy = cast(DL.getIndexType(V->getType())); Zero = ConstantInt::get(IntTy, 0); SizeOffsetEvalType Result = compute_(V); @@ -938,12 +939,12 @@ } Value *FirstArg = CS.getArgument(FnData->FstParam); - FirstArg = Builder.CreateZExt(FirstArg, IntTy); + FirstArg = Builder.CreateZExtOrTrunc(FirstArg, IntTy); if (FnData->SndParam < 0) return std::make_pair(FirstArg, Zero); Value *SecondArg = CS.getArgument(FnData->SndParam); - SecondArg = Builder.CreateZExt(SecondArg, IntTy); + SecondArg = Builder.CreateZExtOrTrunc(SecondArg, IntTy); Value *Size = Builder.CreateMul(FirstArg, SecondArg); return std::make_pair(Size, Zero); diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp --- a/llvm/lib/Analysis/ScalarEvolution.cpp +++ b/llvm/lib/Analysis/ScalarEvolution.cpp @@ -3495,7 +3495,7 @@ const SCEV *BaseExpr = getSCEV(GEP->getPointerOperand()); // getSCEV(Base)->getType() has the same address space as Base->getType() // because SCEV::getType() preserves the address space. - Type *IntPtrTy = getEffectiveSCEVType(BaseExpr->getType()); + Type *IntIdxTy = getEffectiveSCEVType(BaseExpr->getType()); // FIXME(PR23527): Don't blindly transfer the inbounds flag from the GEP // instruction to its SCEV, because the Instruction may be guarded by control // flow and the no-overflow bits may not be valid for the expression in any @@ -3504,7 +3504,7 @@ SCEV::NoWrapFlags Wrap = GEP->isInBounds() ? SCEV::FlagNSW : SCEV::FlagAnyWrap; - const SCEV *TotalOffset = getZero(IntPtrTy); + const SCEV *TotalOffset = getZero(IntIdxTy); // The array size is unimportant. The first thing we do on CurTy is getting // its element type. Type *CurTy = ArrayType::get(GEP->getSourceElementType(), 0); @@ -3514,7 +3514,7 @@ // For a struct, add the member offset. ConstantInt *Index = cast(IndexExpr)->getValue(); unsigned FieldNo = Index->getZExtValue(); - const SCEV *FieldOffset = getOffsetOfExpr(IntPtrTy, STy, FieldNo); + const SCEV *FieldOffset = getOffsetOfExpr(IntIdxTy, STy, FieldNo); // Add the field offset to the running total offset. TotalOffset = getAddExpr(TotalOffset, FieldOffset); @@ -3525,9 +3525,9 @@ // Update CurTy to its element type. CurTy = cast(CurTy)->getElementType(); // For an array, add the element offset, explicitly scaled. - const SCEV *ElementSize = getSizeOfExpr(IntPtrTy, CurTy); + const SCEV *ElementSize = getSizeOfExpr(IntIdxTy, CurTy); // Getelementptr indices are signed. - IndexExpr = getTruncateOrSignExtend(IndexExpr, IntPtrTy); + IndexExpr = getTruncateOrSignExtend(IndexExpr, IntIdxTy); // Multiply the index by the element size to compute the element offset. const SCEV *LocalOffset = getMulExpr(IndexExpr, ElementSize, Wrap); @@ -3786,7 +3786,7 @@ /// Return a type with the same bitwidth as the given type and which represents /// how SCEV will treat the given type, for which isSCEVable must return -/// true. For pointer types, this is the pointer-sized integer type. +/// true. For pointer types, this is the pointer index sized integer type. Type *ScalarEvolution::getEffectiveSCEVType(Type *Ty) const { assert(isSCEVable(Ty) && "Type is not SCEVable!"); @@ -3795,7 +3795,7 @@ // The only other support type is pointer. assert(Ty->isPointerTy() && "Unexpected non-pointer non-integer type!"); - return getDataLayout().getIntPtrType(Ty); + return getDataLayout().getIndexType(Ty); } Type *ScalarEvolution::getWiderType(Type *T1, Type *T2) const { @@ -5726,6 +5726,15 @@ assert(SignHint == ScalarEvolution::HINT_RANGE_SIGNED && "generalize as needed!"); unsigned NS = ComputeNumSignBits(U->getValue(), DL, 0, &AC, nullptr, &DT); + // If the pointer size is larger than the index size type, this can cause + // NS to be larger than BitWidth. So compensate for this. + if (U->getType()->isPointerTy()) { + unsigned ptrSize = DL.getPointerTypeSizeInBits(U->getType()); + int ptrIdxDiff = ptrSize - BitWidth; + if (ptrIdxDiff > 0 && ptrSize > BitWidth && NS > (unsigned)ptrIdxDiff) + NS -= ptrIdxDiff; + } + if (NS > 1) ConservativeResult = ConservativeResult.intersectWith( ConstantRange(APInt::getSignedMinValue(BitWidth).ashr(NS - 1), diff --git a/llvm/lib/Analysis/ScalarEvolutionExpander.cpp b/llvm/lib/Analysis/ScalarEvolutionExpander.cpp --- a/llvm/lib/Analysis/ScalarEvolutionExpander.cpp +++ b/llvm/lib/Analysis/ScalarEvolutionExpander.cpp @@ -414,7 +414,7 @@ // without the other. SplitAddRecs(Ops, Ty, SE); - Type *IntPtrTy = DL.getIntPtrType(PTy); + Type *IntIdxTy = DL.getIndexType(PTy); // Descend down the pointer's type and attempt to convert the other // operands into GEP indices, at each level. The first index in a GEP @@ -426,7 +426,7 @@ // array indexing. SmallVector ScaledOps; if (ElTy->isSized()) { - const SCEV *ElSize = SE.getSizeOfExpr(IntPtrTy, ElTy); + const SCEV *ElSize = SE.getSizeOfExpr(IntIdxTy, ElTy); if (!ElSize->isZero()) { SmallVector NewOps; for (const SCEV *Op : Ops) { diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp --- a/llvm/lib/Analysis/ValueTracking.cpp +++ b/llvm/lib/Analysis/ValueTracking.cpp @@ -90,7 +90,7 @@ if (unsigned BitWidth = Ty->getScalarSizeInBits()) return BitWidth; - return DL.getIndexTypeSizeInBits(Ty); + return DL.getPointerTypeSizeInBits(Ty); } namespace { @@ -1137,7 +1137,7 @@ // which fall through here. Type *ScalarTy = SrcTy->getScalarType(); SrcBitWidth = ScalarTy->isPointerTy() ? - Q.DL.getIndexTypeSizeInBits(ScalarTy) : + Q.DL.getPointerTypeSizeInBits(ScalarTy) : Q.DL.getTypeSizeInBits(ScalarTy); assert(SrcBitWidth && "SrcBitWidth can't be zero"); @@ -1664,7 +1664,7 @@ Type *ScalarTy = V->getType()->getScalarType(); unsigned ExpectedWidth = ScalarTy->isPointerTy() ? - Q.DL.getIndexTypeSizeInBits(ScalarTy) : Q.DL.getTypeSizeInBits(ScalarTy); + Q.DL.getPointerTypeSizeInBits(ScalarTy) : Q.DL.getTypeSizeInBits(ScalarTy); assert(ExpectedWidth == BitWidth && "V and Known should have same BitWidth"); (void)BitWidth; (void)ExpectedWidth; @@ -2409,7 +2409,7 @@ Type *ScalarTy = V->getType()->getScalarType(); unsigned TyBits = ScalarTy->isPointerTy() ? - Q.DL.getIndexTypeSizeInBits(ScalarTy) : + Q.DL.getPointerTypeSizeInBits(ScalarTy) : Q.DL.getTypeSizeInBits(ScalarTy); unsigned Tmp, Tmp2; diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp @@ -9322,8 +9322,8 @@ const GlobalValue *GV = nullptr; int64_t GVOffset = 0; if (TLI->isGAPlusOffset(Ptr.getNode(), GV, GVOffset)) { - unsigned IdxWidth = getDataLayout().getIndexTypeSizeInBits(GV->getType()); - KnownBits Known(IdxWidth); + unsigned PtrWidth = getDataLayout().getPointerTypeSizeInBits(GV->getType()); + KnownBits Known(PtrWidth); llvm::computeKnownBits(GV, Known, getDataLayout()); unsigned AlignBits = Known.countMinTrailingZeros(); unsigned Align = AlignBits ? 1 << std::min(31U, AlignBits) : 0; diff --git a/llvm/lib/IR/DataLayout.cpp b/llvm/lib/IR/DataLayout.cpp --- a/llvm/lib/IR/DataLayout.cpp +++ b/llvm/lib/IR/DataLayout.cpp @@ -768,13 +768,13 @@ IntegerType *DataLayout::getIntPtrType(LLVMContext &C, unsigned AddressSpace) const { - return IntegerType::get(C, getIndexSizeInBits(AddressSpace)); + return IntegerType::get(C, getPointerSizeInBits(AddressSpace)); } Type *DataLayout::getIntPtrType(Type *Ty) const { assert(Ty->isPtrOrPtrVectorTy() && "Expected a pointer or pointer vector type."); - unsigned NumBits = getIndexTypeSizeInBits(Ty); + unsigned NumBits = getPointerTypeSizeInBits(Ty); IntegerType *IntTy = IntegerType::get(Ty->getContext(), NumBits); if (VectorType *VecTy = dyn_cast(Ty)) return VectorType::get(IntTy, VecTy->getNumElements()); diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp --- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp @@ -1832,7 +1832,7 @@ Type *Ty = CI.getType(); unsigned AS = CI.getPointerAddressSpace(); - if (Ty->getScalarSizeInBits() == DL.getIndexSizeInBits(AS)) + if (Ty->getScalarSizeInBits() == DL.getPointerSizeInBits(AS)) return commonPointerCastTransforms(CI); Type *PtrTy = DL.getIntPtrType(CI.getContext(), AS); diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp --- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp @@ -4930,7 +4930,7 @@ // Get scalar or pointer size. unsigned BitWidth = Ty->isIntOrIntVectorTy() ? Ty->getScalarSizeInBits() - : DL.getIndexTypeSizeInBits(Ty->getScalarType()); + : DL.getPointerTypeSizeInBits(Ty->getScalarType()); if (!BitWidth) return nullptr; diff --git a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp --- a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp +++ b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp @@ -901,12 +901,12 @@ SCEVExpander Expander(*SE, *DL, "loop-idiom"); Type *DestInt8PtrTy = Builder.getInt8PtrTy(DestAS); - Type *IntPtr = Builder.getIntPtrTy(*DL, DestAS); + Type *IntIdxTy = DL->getIndexType(DestPtr->getType()); const SCEV *Start = Ev->getStart(); // Handle negative strided loops. if (NegStride) - Start = getStartForNegStride(Start, BECount, IntPtr, StoreSize, SE); + Start = getStartForNegStride(Start, BECount, IntIdxTy, StoreSize, SE); // TODO: ideally we should still be able to generate memset if SCEV expander // is taught to generate the dependencies at the latest point. @@ -934,7 +934,7 @@ // Okay, everything looks good, insert the memset. const SCEV *NumBytesS = - getNumBytes(BECount, IntPtr, StoreSize, CurLoop, DL, SE); + getNumBytes(BECount, IntIdxTy, StoreSize, CurLoop, DL, SE); // TODO: ideally we should still be able to generate memset if SCEV expander // is taught to generate the dependencies at the latest point. @@ -942,7 +942,7 @@ return false; Value *NumBytes = - Expander.expandCodeFor(NumBytesS, IntPtr, Preheader->getTerminator()); + Expander.expandCodeFor(NumBytesS, IntIdxTy, Preheader->getTerminator()); CallInst *NewCall; if (SplatValue) { @@ -955,7 +955,7 @@ Module *M = TheStore->getModule(); StringRef FuncName = "memset_pattern16"; FunctionCallee MSP = M->getOrInsertFunction(FuncName, Builder.getVoidTy(), - Int8PtrTy, Int8PtrTy, IntPtr); + Int8PtrTy, Int8PtrTy, IntIdxTy); inferLibFuncAttributes(M, FuncName, *TLI); // Otherwise we should form a memset_pattern16. PatternValue is known to be @@ -1022,11 +1022,11 @@ const SCEV *StrStart = StoreEv->getStart(); unsigned StrAS = SI->getPointerAddressSpace(); - Type *IntPtrTy = Builder.getIntPtrTy(*DL, StrAS); + Type *IntIdxTy = Builder.getIntNTy(DL->getIndexSizeInBits(StrAS)); // Handle negative strided loops. if (NegStride) - StrStart = getStartForNegStride(StrStart, BECount, IntPtrTy, StoreSize, SE); + StrStart = getStartForNegStride(StrStart, BECount, IntIdxTy, StoreSize, SE); // Okay, we have a strided store "p[i]" of a loaded value. We can turn // this into a memcpy in the loop preheader now if we want. However, this @@ -1052,7 +1052,7 @@ // Handle negative strided loops. if (NegStride) - LdStart = getStartForNegStride(LdStart, BECount, IntPtrTy, StoreSize, SE); + LdStart = getStartForNegStride(LdStart, BECount, IntIdxTy, StoreSize, SE); // For a memcpy, we have to make sure that the input array is not being // mutated by the loop. @@ -1074,10 +1074,10 @@ // Okay, everything is safe, we can transform this! const SCEV *NumBytesS = - getNumBytes(BECount, IntPtrTy, StoreSize, CurLoop, DL, SE); + getNumBytes(BECount, IntIdxTy, StoreSize, CurLoop, DL, SE); Value *NumBytes = - Expander.expandCodeFor(NumBytesS, IntPtrTy, Preheader->getTerminator()); + Expander.expandCodeFor(NumBytesS, IntIdxTy, Preheader->getTerminator()); CallInst *NewCall = nullptr; // Check whether to generate an unordered atomic memcpy: diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp --- a/llvm/lib/Transforms/Utils/Local.cpp +++ b/llvm/lib/Transforms/Utils/Local.cpp @@ -2579,7 +2579,7 @@ if (!NewTy->isPointerTy()) return; - unsigned BitWidth = DL.getIndexTypeSizeInBits(NewTy); + unsigned BitWidth = DL.getPointerTypeSizeInBits(NewTy); if (!getConstantRangeFromMetadata(*N).contains(APInt(BitWidth, 0))) { MDNode *NN = MDNode::get(OldLI.getContext(), None); NewLI.setMetadata(LLVMContext::MD_nonnull, NN); diff --git a/llvm/test/Transforms/InstCombine/builtin-object-size-custom-dl.ll b/llvm/test/Transforms/InstCombine/builtin-object-size-custom-dl.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/InstCombine/builtin-object-size-custom-dl.ll @@ -0,0 +1,32 @@ +; RUN: opt -instcombine -S < %s | FileCheck %s +target datalayout = "e-m:o-p:40:64:64:32-i64:64-f80:128-n8:16:32:64-S128" + +; check that memory builtins can be handled. +define i64 @objsize1_custom_idx(i64 %sz) { +entry: + %ptr = call i8* @malloc(i64 %sz) + %ptr2 = getelementptr inbounds i8, i8* %ptr, i32 2 + %calc_size = call i64 @llvm.objectsize.i64.p0i8(i8* %ptr2, i1 false, i1 true, i1 true) + ret i64 %calc_size +} + +%struct.V = type { [10 x i8], i32, [10 x i8] } + +define i32 @objsize2_custom_idx() #0 { +entry: + %var = alloca %struct.V, align 4 + %0 = bitcast %struct.V* %var to i8* + call void @llvm.lifetime.start.p0i8(i64 28, i8* %0) #3 + %buf1 = getelementptr inbounds %struct.V, %struct.V* %var, i32 0, i32 0 + %arrayidx = getelementptr inbounds [10 x i8], [10 x i8]* %buf1, i64 0, i64 1 + %1 = call i64 @llvm.objectsize.i64.p0i8(i8* %arrayidx, i1 false, i1 false, i1 false) + %conv = trunc i64 %1 to i32 + call void @llvm.lifetime.end.p0i8(i64 28, i8* %0) #3 + ret i32 %conv +; CHECK: ret i32 27 +} + +declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1 +declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1 +declare i8* @malloc(i64) +declare i64 @llvm.objectsize.i64.p0i8(i8*, i1, i1, i1) diff --git a/llvm/test/Transforms/InstCombine/gep-custom-dl.ll b/llvm/test/Transforms/InstCombine/gep-custom-dl.ll --- a/llvm/test/Transforms/InstCombine/gep-custom-dl.ll +++ b/llvm/test/Transforms/InstCombine/gep-custom-dl.ll @@ -164,3 +164,22 @@ %B = ptrtoint double* %A to i32 ret i32 %B } + +@X_as1 = addrspace(1) global [1000 x i8] zeroinitializer, align 16 + +define i16 @constant_fold_custom_dl() { +; CHECK-LABEL: @constant_fold_custom_dl( + ; CHECK: ret i16 ptrtoint + +entry: + %A = bitcast i8 addrspace(1)* getelementptr inbounds ([1000 x i8], [1000 x i8] addrspace(1)* @X_as1, i64 1, i64 0) to i8 addrspace(1)* + %B = bitcast i8 addrspace(1)* getelementptr inbounds ([1000 x i8], [1000 x i8] addrspace(1)* @X_as1, i64 0, i64 0) to i8 addrspace(1)* + + %B2 = ptrtoint i8 addrspace(1)* %B to i16 + %C = sub i16 0, %B2 + %D = getelementptr i8, i8 addrspace(1)* %A, i16 %C + %E = ptrtoint i8 addrspace(1)* %D to i16 + + ret i16 %E +} + diff --git a/llvm/test/Transforms/InstCombine/icmp-custom-dl.ll b/llvm/test/Transforms/InstCombine/icmp-custom-dl.ll --- a/llvm/test/Transforms/InstCombine/icmp-custom-dl.ll +++ b/llvm/test/Transforms/InstCombine/icmp-custom-dl.ll @@ -8,8 +8,8 @@ define i1 @test59(i8* %foo) { ; CHECK-LABEL: @test59( ; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, i8* [[FOO:%.*]], i32 8 -; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint i8* [[GEP1]] to i32 -; CHECK-NEXT: [[USE:%.*]] = zext i32 [[TMP1]] to i64 +; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint i8* [[GEP1]] to i40 +; CHECK-NEXT: [[USE:%.*]] = zext i40 [[TMP1]] to i64 ; CHECK-NEXT: [[CALL:%.*]] = call i32 @test58_d(i64 [[USE]]) ; CHECK-NEXT: ret i1 true ; diff --git a/llvm/test/Transforms/InstCombine/stdio-custom-dl.ll b/llvm/test/Transforms/InstCombine/stdio-custom-dl.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/InstCombine/stdio-custom-dl.ll @@ -0,0 +1,22 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -instcombine -S -mtriple=x86_64-unknown-linux-gnu | FileCheck %s + +target datalayout = "e-m:o-p:40:64:64:32-i64:64-f80:128-n8:16:32:64-S128" +%struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] } +%struct._IO_marker = type { %struct._IO_marker*, %struct._IO_FILE*, i32 } +@.str = private unnamed_addr constant [5 x i8] c"file\00", align 1 +@.str.1 = private unnamed_addr constant [2 x i8] c"w\00", align 1 +@.str.2 = private unnamed_addr constant [4 x i8] c"str\00", align 1 + +; Check fwrite is generated with arguments of ptr size, not index size +define internal void @fputs_test_custom_dl() { +; CHECK-LABEL: @fputs_test_custom_dl( +; CHECK-NEXT: [[TMP1:%.*]] = call %struct._IO_FILE* @fopen(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @.str, i32 0, i32 0), i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str.1, i32 0, i32 0)) +; + %call = call %struct._IO_FILE* @fopen(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @.str, i64 0, i64 0), i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str.1, i64 0, i64 0)) + %call1 = call i32 @fputs(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str.2, i64 0, i64 0), %struct._IO_FILE* %call) + ret void +} + +declare %struct._IO_FILE* @fopen(i8*, i8*) +declare i32 @fputs(i8* nocapture readonly, %struct._IO_FILE* nocapture) diff --git a/llvm/test/Transforms/PhaseOrdering/scev-custom-dl.ll b/llvm/test/Transforms/PhaseOrdering/scev-custom-dl.ll --- a/llvm/test/Transforms/PhaseOrdering/scev-custom-dl.ll +++ b/llvm/test/Transforms/PhaseOrdering/scev-custom-dl.ll @@ -65,3 +65,73 @@ for.end: ; preds = %for.cond ret void } + +@array = weak global [101 x i32] zeroinitializer, align 32 ; <[100 x i32]*> [#uses=1] + +; CHECK: Loop %bb: backedge-taken count is 100 + +define void @test_range_ref1a(i32 %x) { +entry: + br label %bb + +bb: ; preds = %bb, %entry + %i.01.0 = phi i32 [ 100, %entry ], [ %tmp4, %bb ] ; [#uses=2] + %tmp1 = getelementptr [101 x i32], [101 x i32]* @array, i32 0, i32 %i.01.0 ; [#uses=1] + store i32 %x, i32* %tmp1 + %tmp4 = add i32 %i.01.0, -1 ; [#uses=2] + %tmp7 = icmp sgt i32 %tmp4, -1 ; [#uses=1] + br i1 %tmp7, label %bb, label %return + +return: ; preds = %bb + ret void +} + +define i32 @test_loop_idiom_recogize(i32 %x, i32 %y, i32* %lam, i32* %alp) nounwind { +bb1.thread: + br label %bb1 + +bb1: ; preds = %bb1, %bb1.thread + %indvar = phi i32 [ 0, %bb1.thread ], [ %indvar.next, %bb1 ] ; [#uses=4] + %i.0.reg2mem.0 = sub i32 255, %indvar ; [#uses=2] + %0 = getelementptr i32, i32* %alp, i32 %i.0.reg2mem.0 ; [#uses=1] + %1 = load i32, i32* %0, align 4 ; [#uses=1] + %2 = getelementptr i32, i32* %lam, i32 %i.0.reg2mem.0 ; [#uses=1] + store i32 %1, i32* %2, align 4 + %3 = sub i32 254, %indvar ; [#uses=1] + %4 = icmp slt i32 %3, 0 ; [#uses=1] + %indvar.next = add i32 %indvar, 1 ; [#uses=1] + br i1 %4, label %bb2, label %bb1 + +bb2: ; preds = %bb1 + %tmp10 = mul i32 %indvar, %x ; [#uses=1] + %z.0.reg2mem.0 = add i32 %tmp10, %y ; [#uses=1] + %5 = add i32 %z.0.reg2mem.0, %x ; [#uses=1] + ret i32 %5 +} + +declare void @use(i1) + +declare void @llvm.experimental.guard(i1, ...) + +; This tests getRangeRef acts as intended with different idx size. +; CHECK: max backedge-taken count is 318 +define void @test_range_ref1(i8 %t) { + entry: + %t.ptr = inttoptr i8 %t to i8* + %p.42 = inttoptr i8 42 to i8* + %cmp1 = icmp slt i8* %t.ptr, %p.42 + call void(i1, ...) @llvm.experimental.guard(i1 %cmp1) [ "deopt"() ] + br label %loop + + loop: + %idx = phi i8* [ %t.ptr, %entry ], [ %snext, %loop ] + %snext = getelementptr inbounds i8, i8* %idx, i64 1 + %c = icmp slt i8* %idx, %p.42 + call void @use(i1 %c) + %be = icmp slt i8* %snext, %p.42 + br i1 %be, label %loop, label %exit + + exit: + ret void +} + diff --git a/llvm/test/Transforms/SimplifyCFG/switch_create-custom-dl.ll b/llvm/test/Transforms/SimplifyCFG/switch_create-custom-dl.ll --- a/llvm/test/Transforms/SimplifyCFG/switch_create-custom-dl.ll +++ b/llvm/test/Transforms/SimplifyCFG/switch_create-custom-dl.ll @@ -33,10 +33,10 @@ define void @test1_ptr(i32* %V) { ; CHECK-LABEL: @test1_ptr( -; CHECK-NEXT: [[MAGICPTR:%.*]] = ptrtoint i32* [[V:%.*]] to i32 -; CHECK-NEXT: switch i32 [[MAGICPTR]], label [[F:%.*]] [ -; CHECK-NEXT: i32 17, label [[T:%.*]] -; CHECK-NEXT: i32 4, label [[T]] +; CHECK-NEXT: [[MAGICPTR:%.*]] = ptrtoint i32* [[V:%.*]] to i40 +; CHECK-NEXT: switch i40 [[MAGICPTR]], label [[F:%.*]] [ +; CHECK-NEXT: i40 17, label [[T:%.*]] +; CHECK-NEXT: i40 4, label [[T]] ; CHECK-NEXT: ] ; CHECK: T: ; CHECK-NEXT: call void @foo1() @@ -59,10 +59,10 @@ define void @test1_ptr_as1(i32 addrspace(1)* %V) { ; CHECK-LABEL: @test1_ptr_as1( -; CHECK-NEXT: [[MAGICPTR:%.*]] = ptrtoint i32 addrspace(1)* [[V:%.*]] to i32 -; CHECK-NEXT: switch i32 [[MAGICPTR]], label [[F:%.*]] [ -; CHECK-NEXT: i32 17, label [[T:%.*]] -; CHECK-NEXT: i32 4, label [[T]] +; CHECK-NEXT: [[MAGICPTR:%.*]] = ptrtoint i32 addrspace(1)* [[V:%.*]] to i40 +; CHECK-NEXT: switch i40 [[MAGICPTR]], label [[F:%.*]] [ +; CHECK-NEXT: i40 17, label [[T:%.*]] +; CHECK-NEXT: i40 4, label [[T]] ; CHECK-NEXT: ] ; CHECK: T: ; CHECK-NEXT: call void @foo1()