continue;
}
- if (CallSite CS = I) {
+ if (auto CS = CallSite(I)) {
// If this is the function being called then we treat it like a load and
// ignore it.
if (CS.isCallee(&U))
static Instruction *simplifyAllocaArraySize(InstCombiner &IC, AllocaInst &AI) {
// Check for array size of 1 (scalar allocation).
- if (!AI.isArrayAllocation())
- return nullptr;
+ if (!AI.isArrayAllocation()) {
+ // i32 1 is the canonical array size for scalar allocations.
+ if (AI.getArraySize()->getType()->isIntegerTy(32))
+ return nullptr;
+
+ // Canonicalize it.
+ Value *V = IC.Builder->getInt32(1);
+ AI.setOperand(0, V);
+ return &AI;
+ }
// Convert: alloca Ty, C - where C is a constant != 1 into: alloca [C x Ty], 1
if (const ConstantInt *C = dyn_cast<ConstantInt>(AI.getArraySize())) {
///
/// Note that this will create all of the instructions with whatever insert
/// point the \c InstCombiner currently is using.
-static LoadInst *combineLoadToNewType(InstCombiner &IC, LoadInst &LI, Type *NewTy) {
+static LoadInst *combineLoadToNewType(InstCombiner &IC, LoadInst &LI, Type *NewTy,
+ const Twine &Suffix = "") {
Value *Ptr = LI.getPointerOperand();
unsigned AS = LI.getPointerAddressSpace();
SmallVector<std::pair<unsigned, MDNode *>, 8> MD;
LoadInst *NewLoad = IC.Builder->CreateAlignedLoad(
IC.Builder->CreateBitCast(Ptr, NewTy->getPointerTo(AS)),
- LI.getAlignment(), LI.getName());
+ LI.getAlignment(), LI.getName() + Suffix);
MDBuilder MDB(NewLoad->getContext());
for (const auto &MDPair : MD) {
unsigned ID = MDPair.first;
}
// Fold away bit casts of the loaded value by loading the desired type.
+ // We can do this for BitCastInsts as well as casts from and to pointer types,
+ // as long as those are noops (i.e., the source or dest type have the same
+ // bitwidth as the target's pointers).
if (LI.hasOneUse())
- if (auto *BC = dyn_cast<BitCastInst>(LI.user_back())) {
- LoadInst *NewLoad = combineLoadToNewType(IC, LI, BC->getDestTy());
- BC->replaceAllUsesWith(NewLoad);
- IC.EraseInstFromFunction(*BC);
- return &LI;
+ if (auto* CI = dyn_cast<CastInst>(LI.user_back())) {
+ if (CI->isNoopCast(DL)) {
+ LoadInst *NewLoad = combineLoadToNewType(IC, LI, CI->getDestTy());
+ CI->replaceAllUsesWith(NewLoad);
+ IC.EraseInstFromFunction(*CI);
+ return &LI;
+ }
}
// FIXME: We should also canonicalize loads of vectors when their elements are
return nullptr;
}
+static Instruction *unpackLoadToAggregate(InstCombiner &IC, LoadInst &LI) {
+ // FIXME: We could probably with some care handle both volatile and atomic
+ // stores here but it isn't clear that this is important.
+ if (!LI.isSimple())
+ return nullptr;
+
+ Type *T = LI.getType();
+ if (!T->isAggregateType())
+ return nullptr;
+
+ assert(LI.getAlignment() && "Alignment must be set at this point");
+
+ if (auto *ST = dyn_cast<StructType>(T)) {
+ // If the struct only have one element, we unpack.
+ if (ST->getNumElements() == 1) {
+ LoadInst *NewLoad = combineLoadToNewType(IC, LI, ST->getTypeAtIndex(0U),
+ ".unpack");
+ return IC.ReplaceInstUsesWith(LI, IC.Builder->CreateInsertValue(
+ UndefValue::get(T), NewLoad, 0, LI.getName()));
+ }
+ }
+
+ if (auto *AT = dyn_cast<ArrayType>(T)) {
+ // If the array only have one element, we unpack.
+ if (AT->getNumElements() == 1) {
+ LoadInst *NewLoad = combineLoadToNewType(IC, LI, AT->getElementType(),
+ ".unpack");
+ return IC.ReplaceInstUsesWith(LI, IC.Builder->CreateInsertValue(
+ UndefValue::get(T), NewLoad, 0, LI.getName()));
+ }
+ }
+
+ return nullptr;
+}
+
// If we can determine that all possible objects pointed to by the provided
// pointer value are, not only dereferenceable, but also definitively less than
// or equal to the provided maximum size, then return true. Otherwise, return
}
if (PHINode *PN = dyn_cast<PHINode>(P)) {
- for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
- Worklist.push_back(PN->getIncomingValue(i));
+ for (Value *IncValue : PN->incoming_values())
+ Worklist.push_back(IncValue);
continue;
}
return false;
SmallVector<Value *, 4> Ops(GEPI->idx_begin(), GEPI->idx_begin() + Idx);
- Type *AllocTy =
- GetElementPtrInst::getIndexedType(GEPI->getOperand(0)->getType(), Ops);
+ Type *AllocTy = GetElementPtrInst::getIndexedType(
+ cast<PointerType>(GEPI->getOperand(0)->getType()->getScalarType())
+ ->getElementType(),
+ Ops);
if (!AllocTy || !AllocTy->isSized())
return false;
const DataLayout &DL = IC.getDataLayout();
// FIXME: If the GEP is not inbounds, and there are extra indices after the
// one we'll replace, those could cause the address computation to wrap
// (rendering the IsAllNonNegative() check below insufficient). We can do
- // better, ignoring zero indicies (and other indicies we can prove small
+ // better, ignoring zero indices (and other indices we can prove small
// enough not to wrap).
if (Idx+1 != GEPI->getNumOperands() && !GEPI->isInBounds())
return false;
// FIXME: Some of it is okay for atomic loads; needs refactoring.
if (!LI.isSimple()) return nullptr;
+ if (Instruction *Res = unpackLoadToAggregate(*this, LI))
+ return Res;
+
// Do really simple store-to-load forwarding and load CSE, to catch cases
// where there are several consecutive memory accesses to the same location,
// separated by a few arithmetic operations.
BasicBlock::iterator BBI = &LI;
- if (Value *AvailableVal = FindAvailableLoadedValue(Op, LI.getParent(), BBI,6))
+ AAMDNodes AATags;
+ if (Value *AvailableVal = FindAvailableLoadedValue(Op, LI.getParent(), BBI,
+ 6, AA, &AATags)) {
+ if (LoadInst *NLI = dyn_cast<LoadInst>(AvailableVal)) {
+ unsigned KnownIDs[] = {
+ LLVMContext::MD_tbaa,
+ LLVMContext::MD_alias_scope,
+ LLVMContext::MD_noalias,
+ LLVMContext::MD_range,
+ LLVMContext::MD_invariant_load,
+ LLVMContext::MD_nonnull,
+ };
+ combineMetadata(NLI, &LI, KnownIDs);
+ };
+
return ReplaceInstUsesWith(
LI, Builder->CreateBitOrPointerCast(AvailableVal, LI.getType(),
LI.getName() + ".cast"));
+ }
// load(gep null, ...) -> unreachable
if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(Op)) {
///
/// \returns true if the store was successfully combined away. This indicates
/// the caller must erase the store instruction. We have to let the caller erase
-/// the store instruction sas otherwise there is no way to signal whether it was
+/// the store instruction as otherwise there is no way to signal whether it was
/// combined or not: IC.EraseInstFromFunction returns a null pointer.
static bool combineStoreToValueType(InstCombiner &IC, StoreInst &SI) {
// FIXME: We could probably with some care handle both volatile and atomic
return false;
}
+static bool unpackStoreToAggregate(InstCombiner &IC, StoreInst &SI) {
+ // FIXME: We could probably with some care handle both volatile and atomic
+ // stores here but it isn't clear that this is important.
+ if (!SI.isSimple())
+ return false;
+
+ Value *V = SI.getValueOperand();
+ Type *T = V->getType();
+
+ if (!T->isAggregateType())
+ return false;
+
+ if (auto *ST = dyn_cast<StructType>(T)) {
+ // If the struct only have one element, we unpack.
+ if (ST->getNumElements() == 1) {
+ V = IC.Builder->CreateExtractValue(V, 0);
+ combineStoreToNewValue(IC, SI, V);
+ return true;
+ }
+ }
+
+ if (auto *AT = dyn_cast<ArrayType>(T)) {
+ // If the array only have one element, we unpack.
+ if (AT->getNumElements() == 1) {
+ V = IC.Builder->CreateExtractValue(V, 0);
+ combineStoreToNewValue(IC, SI, V);
+ return true;
+ }
+ }
+
+ return false;
+}
+
/// equivalentAddressValues - Test if A and B will obviously have the same
/// value. This includes recognizing that %t0 and %t1 will have the same
/// value in code like this:
else if (StoreAlign == 0)
SI.setAlignment(EffectiveStoreAlign);
+ // Try to canonicalize the stored type.
+ if (unpackStoreToAggregate(*this, SI))
+ return EraseInstFromFunction(SI);
+
// Replace GEP indices if possible.
if (Instruction *NewGEPI = replaceGEPIdxWithZero(*this, Ptr, SI)) {
Worklist.Add(NewGEPI);