//===----------------------------------------------------------------------===//
#include "InstCombineInternal.h"
+#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/Loads.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/MDBuilder.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;
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))
continue;
+ unsigned DataOpNo = CS.getDataOperandNo(&U);
+ bool IsArgOperand = CS.isArgOperand(&U);
+
// Inalloca arguments are clobbered by the call.
- unsigned ArgNo = CS.getArgumentNo(&U);
- if (CS.isInAllocaArgument(ArgNo))
+ if (IsArgOperand && CS.isInAllocaArgument(DataOpNo))
return false;
// If this is a readonly/readnone call site, then we know it is just a
// load (but one that potentially returns the value itself), so we can
// ignore it if we know that the value isn't captured.
if (CS.onlyReadsMemory() &&
- (CS.getInstruction()->use_empty() || CS.doesNotCapture(ArgNo)))
+ (CS.getInstruction()->use_empty() || CS.doesNotCapture(DataOpNo)))
continue;
// If this is being passed as a byval argument, the caller is making a
// copy, so it is only a read of the alloca.
- if (CS.isByValArgument(ArgNo))
+ if (IsArgOperand && CS.isByValArgument(DataOpNo))
continue;
}
return nullptr;
}
-Instruction *InstCombiner::visitAllocaInst(AllocaInst &AI) {
- // Ensure that the alloca array size argument has type intptr_t, so that
- // any casting is exposed early.
- if (DL) {
- Type *IntPtrTy = DL->getIntPtrType(AI.getType());
- if (AI.getArraySize()->getType() != IntPtrTy) {
- Value *V = Builder->CreateIntCast(AI.getArraySize(),
- IntPtrTy, false);
- AI.setOperand(0, V);
- return &AI;
- }
+static Instruction *simplifyAllocaArraySize(InstCombiner &IC, AllocaInst &AI) {
+ // Check for array size of 1 (scalar allocation).
+ 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 (AI.isArrayAllocation()) { // Check C != 1
- if (const ConstantInt *C = dyn_cast<ConstantInt>(AI.getArraySize())) {
- Type *NewTy =
- ArrayType::get(AI.getAllocatedType(), C->getZExtValue());
- AllocaInst *New = Builder->CreateAlloca(NewTy, nullptr, AI.getName());
- New->setAlignment(AI.getAlignment());
-
- // Scan to the end of the allocation instructions, to skip over a block of
- // allocas if possible...also skip interleaved debug info
- //
- BasicBlock::iterator It = New;
- while (isa<AllocaInst>(*It) || isa<DbgInfoIntrinsic>(*It)) ++It;
-
- // Now that I is pointing to the first non-allocation-inst in the block,
- // insert our getelementptr instruction...
- //
- Type *IdxTy = DL
- ? DL->getIntPtrType(AI.getType())
- : Type::getInt64Ty(AI.getContext());
- Value *NullIdx = Constant::getNullValue(IdxTy);
- Value *Idx[2] = { NullIdx, NullIdx };
- Instruction *GEP =
+ if (const ConstantInt *C = dyn_cast<ConstantInt>(AI.getArraySize())) {
+ Type *NewTy = ArrayType::get(AI.getAllocatedType(), C->getZExtValue());
+ AllocaInst *New = IC.Builder->CreateAlloca(NewTy, nullptr, AI.getName());
+ New->setAlignment(AI.getAlignment());
+
+ // Scan to the end of the allocation instructions, to skip over a block of
+ // allocas if possible...also skip interleaved debug info
+ //
+ BasicBlock::iterator It(New);
+ while (isa<AllocaInst>(*It) || isa<DbgInfoIntrinsic>(*It))
+ ++It;
+
+ // Now that I is pointing to the first non-allocation-inst in the block,
+ // insert our getelementptr instruction...
+ //
+ Type *IdxTy = IC.getDataLayout().getIntPtrType(AI.getType());
+ Value *NullIdx = Constant::getNullValue(IdxTy);
+ Value *Idx[2] = {NullIdx, NullIdx};
+ Instruction *GEP =
GetElementPtrInst::CreateInBounds(New, Idx, New->getName() + ".sub");
- InsertNewInstBefore(GEP, *It);
+ IC.InsertNewInstBefore(GEP, *It);
- // Now make everything use the getelementptr instead of the original
- // allocation.
- return ReplaceInstUsesWith(AI, GEP);
- } else if (isa<UndefValue>(AI.getArraySize())) {
- return ReplaceInstUsesWith(AI, Constant::getNullValue(AI.getType()));
- }
+ // Now make everything use the getelementptr instead of the original
+ // allocation.
+ return IC.ReplaceInstUsesWith(AI, GEP);
}
- if (DL && AI.getAllocatedType()->isSized()) {
+ if (isa<UndefValue>(AI.getArraySize()))
+ return IC.ReplaceInstUsesWith(AI, Constant::getNullValue(AI.getType()));
+
+ // Ensure that the alloca array size argument has type intptr_t, so that
+ // any casting is exposed early.
+ Type *IntPtrTy = IC.getDataLayout().getIntPtrType(AI.getType());
+ if (AI.getArraySize()->getType() != IntPtrTy) {
+ Value *V = IC.Builder->CreateIntCast(AI.getArraySize(), IntPtrTy, false);
+ AI.setOperand(0, V);
+ return &AI;
+ }
+
+ return nullptr;
+}
+
+Instruction *InstCombiner::visitAllocaInst(AllocaInst &AI) {
+ if (auto *I = simplifyAllocaArraySize(*this, AI))
+ return I;
+
+ if (AI.getAllocatedType()->isSized()) {
// If the alignment is 0 (unspecified), assign it the preferred alignment.
if (AI.getAlignment() == 0)
- AI.setAlignment(DL->getPrefTypeAlignment(AI.getAllocatedType()));
+ AI.setAlignment(DL.getPrefTypeAlignment(AI.getAllocatedType()));
// Move all alloca's of zero byte objects to the entry block and merge them
// together. Note that we only do this for alloca's, because malloc should
// allocate and return a unique pointer, even for a zero byte allocation.
- if (DL->getTypeAllocSize(AI.getAllocatedType()) == 0) {
+ if (DL.getTypeAllocSize(AI.getAllocatedType()) == 0) {
// For a zero sized alloca there is no point in doing an array allocation.
// This is helpful if the array size is a complicated expression not used
// elsewhere.
// dominance as the array size was forced to a constant earlier already.
AllocaInst *EntryAI = dyn_cast<AllocaInst>(FirstInst);
if (!EntryAI || !EntryAI->getAllocatedType()->isSized() ||
- DL->getTypeAllocSize(EntryAI->getAllocatedType()) != 0) {
+ DL.getTypeAllocSize(EntryAI->getAllocatedType()) != 0) {
AI.moveBefore(FirstInst);
return &AI;
}
// assign it the preferred alignment.
if (EntryAI->getAlignment() == 0)
EntryAI->setAlignment(
- DL->getPrefTypeAlignment(EntryAI->getAllocatedType()));
+ DL.getPrefTypeAlignment(EntryAI->getAllocatedType()));
// Replace this zero-sized alloca with the one at the start of the entry
// block after ensuring that the address will be aligned enough for both
// types.
SmallVector<Instruction *, 4> ToDelete;
if (MemTransferInst *Copy = isOnlyCopiedFromConstantGlobal(&AI, ToDelete)) {
unsigned SourceAlign = getOrEnforceKnownAlignment(
- Copy->getSource(), AI.getAlignment(), DL, AC, &AI, DT);
+ Copy->getSource(), AI.getAlignment(), DL, &AI, AC, DT);
if (AI.getAlignment() <= SourceAlign) {
DEBUG(dbgs() << "Found alloca equal to global: " << AI << '\n');
DEBUG(dbgs() << " memcpy = " << *Copy << '\n');
///
/// 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;
MDNode *N = MDPair.second;
break;
case LLVMContext::MD_nonnull:
- // FIXME: We should translate this into range metadata for integer types
- // and vice versa.
+ // This only directly applies if the new type is also a pointer.
+ if (NewTy->isPointerTy()) {
+ NewLoad->setMetadata(ID, N);
+ break;
+ }
+ // If it's integral now, translate it to !range metadata.
+ if (NewTy->isIntegerTy()) {
+ auto *ITy = cast<IntegerType>(NewTy);
+ auto *NullInt = ConstantExpr::getPtrToInt(
+ ConstantPointerNull::get(cast<PointerType>(Ptr->getType())), ITy);
+ auto *NonNullInt =
+ ConstantExpr::getAdd(NullInt, ConstantInt::get(ITy, 1));
+ NewLoad->setMetadata(LLVMContext::MD_range,
+ MDB.createRange(NonNullInt, NullInt));
+ }
+ break;
+ case LLVMContext::MD_align:
+ case LLVMContext::MD_dereferenceable:
+ case LLVMContext::MD_dereferenceable_or_null:
+ // These only directly apply if the new type is also a pointer.
if (NewTy->isPointerTy())
NewLoad->setMetadata(ID, N);
break;
-
case LLVMContext::MD_range:
// FIXME: It would be nice to propagate this in some way, but the type
- // conversions make it hard.
+ // conversions make it hard. If the new type is a pointer, we could
+ // translate it to !nonnull metadata.
break;
}
}
case LLVMContext::MD_invariant_load:
case LLVMContext::MD_nonnull:
case LLVMContext::MD_range:
+ case LLVMContext::MD_align:
+ case LLVMContext::MD_dereferenceable:
+ case LLVMContext::MD_dereferenceable_or_null:
// These don't apply for stores.
break;
}
return nullptr;
Type *Ty = LI.getType();
+ const DataLayout &DL = IC.getDataLayout();
// Try to canonicalize loads which are only ever stored to operate over
// integers instead of any other type. We only do this when the loaded type
// is sized and has a size exactly the same as its store size and the store
// size is a legal integer type.
- const DataLayout *DL = IC.getDataLayout();
- if (!Ty->isIntegerTy() && Ty->isSized() && DL &&
- DL->isLegalInteger(DL->getTypeStoreSizeInBits(Ty)) &&
- DL->getTypeStoreSizeInBits(Ty) == DL->getTypeSizeInBits(Ty)) {
+ if (!Ty->isIntegerTy() && Ty->isSized() &&
+ DL.isLegalInteger(DL.getTypeStoreSizeInBits(Ty)) &&
+ DL.getTypeStoreSizeInBits(Ty) == DL.getTypeSizeInBits(Ty)) {
if (std::all_of(LI.user_begin(), LI.user_end(), [&LI](User *U) {
auto *SI = dyn_cast<StoreInst>(U);
return SI && SI->getPointerOperand() != &LI;
})) {
LoadInst *NewLoad = combineLoadToNewType(
IC, LI,
- Type::getIntNTy(LI.getContext(), DL->getTypeStoreSizeInBits(Ty)));
+ Type::getIntNTy(LI.getContext(), DL.getTypeStoreSizeInBits(Ty)));
// Replace all the stores with stores of the newly loaded value.
for (auto UI = LI.user_begin(), UE = LI.user_end(); UI != UE;) {
auto *SI = cast<StoreInst>(*UI++);
}
// 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.
+ unsigned Count = ST->getNumElements();
+ if (Count == 1) {
+ LoadInst *NewLoad = combineLoadToNewType(IC, LI, ST->getTypeAtIndex(0U),
+ ".unpack");
+ return IC.ReplaceInstUsesWith(LI, IC.Builder->CreateInsertValue(
+ UndefValue::get(T), NewLoad, 0, LI.getName()));
+ }
+
+ // We don't want to break loads with padding here as we'd loose
+ // the knowledge that padding exists for the rest of the pipeline.
+ const DataLayout &DL = IC.getDataLayout();
+ auto *SL = DL.getStructLayout(ST);
+ if (SL->hasPadding())
+ return nullptr;
+
+ auto Name = LI.getName();
+ SmallString<16> LoadName = Name;
+ LoadName += ".unpack";
+ SmallString<16> EltName = Name;
+ EltName += ".elt";
+ auto *Addr = LI.getPointerOperand();
+ Value *V = UndefValue::get(T);
+ auto *IdxType = Type::getInt32Ty(ST->getContext());
+ auto *Zero = ConstantInt::get(IdxType, 0);
+ for (unsigned i = 0; i < Count; i++) {
+ Value *Indices[2] = {
+ Zero,
+ ConstantInt::get(IdxType, i),
+ };
+ auto *Ptr = IC.Builder->CreateInBoundsGEP(ST, Addr, makeArrayRef(Indices), EltName);
+ auto *L = IC.Builder->CreateAlignedLoad(Ptr, LI.getAlignment(),
+ LoadName);
+ V = IC.Builder->CreateInsertValue(V, L, i);
+ }
+
+ V->setName(Name);
+ return IC.ReplaceInstUsesWith(LI, V);
+ }
+
+ 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
//
// FIXME: This should probably live in ValueTracking (or similar).
static bool isObjectSizeLessThanOrEq(Value *V, uint64_t MaxSize,
- const DataLayout *DL) {
+ const DataLayout &DL) {
SmallPtrSet<Value *, 4> Visited;
SmallVector<Value *, 4> Worklist(1, V);
}
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;
}
if (!CS)
return false;
- uint64_t TypeSize = DL->getTypeAllocSize(AI->getAllocatedType());
+ uint64_t TypeSize = DL.getTypeAllocSize(AI->getAllocatedType());
// Make sure that, even if the multiplication below would wrap as an
// uint64_t, we still do the right thing.
if ((CS->getValue().zextOrSelf(128)*APInt(128, TypeSize)).ugt(MaxSize))
if (!GV->hasDefinitiveInitializer() || !GV->isConstant())
return false;
- uint64_t InitSize = DL->getTypeAllocSize(GV->getType()->getElementType());
+ uint64_t InitSize = DL.getTypeAllocSize(GV->getType()->getElementType());
if (InitSize > MaxSize)
return false;
continue;
// offsets those indices implied.
static bool canReplaceGEPIdxWithZero(InstCombiner &IC, GetElementPtrInst *GEPI,
Instruction *MemI, unsigned &Idx) {
- const DataLayout *DL = IC.getDataLayout();
- if (GEPI->getNumOperands() < 2 || !DL)
+ if (GEPI->getNumOperands() < 2)
return false;
// Find the first non-zero index of a GEP. If all indices are zero, return
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;
- uint64_t TyAllocSize = DL->getTypeAllocSize(AllocTy);
+ const DataLayout &DL = IC.getDataLayout();
+ uint64_t TyAllocSize = DL.getTypeAllocSize(AllocTy);
// If there are more indices after the one we might replace with a zero, make
// sure they're all non-negative. If any of them are negative, the overall
// 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;
return Res;
// Attempt to improve the alignment.
- if (DL) {
- unsigned KnownAlign = getOrEnforceKnownAlignment(
- Op, DL->getPrefTypeAlignment(LI.getType()), DL, AC, &LI, DT);
- unsigned LoadAlign = LI.getAlignment();
- unsigned EffectiveLoadAlign = LoadAlign != 0 ? LoadAlign :
- DL->getABITypeAlignment(LI.getType());
-
- if (KnownAlign > EffectiveLoadAlign)
- LI.setAlignment(KnownAlign);
- else if (LoadAlign == 0)
- LI.setAlignment(EffectiveLoadAlign);
- }
+ unsigned KnownAlign = getOrEnforceKnownAlignment(
+ Op, DL.getPrefTypeAlignment(LI.getType()), DL, &LI, AC, DT);
+ unsigned LoadAlign = LI.getAlignment();
+ unsigned EffectiveLoadAlign =
+ LoadAlign != 0 ? LoadAlign : DL.getABITypeAlignment(LI.getType());
+
+ if (KnownAlign > EffectiveLoadAlign)
+ LI.setAlignment(KnownAlign);
+ else if (LoadAlign == 0)
+ LI.setAlignment(EffectiveLoadAlign);
// Replace GEP indices if possible.
if (Instruction *NewGEPI = replaceGEPIdxWithZero(*this, Op, LI)) {
// 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))
+ BasicBlock::iterator BBI(LI);
+ AAMDNodes AATags;
+ if (Value *AvailableVal =
+ FindAvailableLoadedValue(Op, LI.getParent(), BBI,
+ DefMaxInstsToScan, 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,
+ LLVMContext::MD_invariant_group, LLVMContext::MD_align,
+ LLVMContext::MD_dereferenceable,
+ LLVMContext::MD_dereferenceable_or_null};
+ 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)) {
if (SelectInst *SI = dyn_cast<SelectInst>(Op)) {
// load (select (Cond, &V1, &V2)) --> select(Cond, load &V1, load &V2).
unsigned Align = LI.getAlignment();
- if (isSafeToLoadUnconditionally(SI->getOperand(1), SI, Align, DL) &&
- isSafeToLoadUnconditionally(SI->getOperand(2), SI, Align, DL)) {
+ if (isSafeToLoadUnconditionally(SI->getOperand(1), SI, Align) &&
+ isSafeToLoadUnconditionally(SI->getOperand(2), SI, Align)) {
LoadInst *V1 = Builder->CreateLoad(SI->getOperand(1),
SI->getOperand(1)->getName()+".val");
LoadInst *V2 = Builder->CreateLoad(SI->getOperand(2),
}
// load (select (cond, null, P)) -> load P
- if (isa<ConstantPointerNull>(SI->getOperand(1)) &&
+ if (isa<ConstantPointerNull>(SI->getOperand(1)) &&
LI.getPointerAddressSpace() == 0) {
LI.setOperand(0, SI->getOperand(2));
return &LI;
///
/// \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.
+ unsigned Count = ST->getNumElements();
+ if (Count == 1) {
+ V = IC.Builder->CreateExtractValue(V, 0);
+ combineStoreToNewValue(IC, SI, V);
+ return true;
+ }
+
+ // We don't want to break loads with padding here as we'd loose
+ // the knowledge that padding exists for the rest of the pipeline.
+ const DataLayout &DL = IC.getDataLayout();
+ auto *SL = DL.getStructLayout(ST);
+ if (SL->hasPadding())
+ return false;
+
+ SmallString<16> EltName = V->getName();
+ EltName += ".elt";
+ auto *Addr = SI.getPointerOperand();
+ SmallString<16> AddrName = Addr->getName();
+ AddrName += ".repack";
+ auto *IdxType = Type::getInt32Ty(ST->getContext());
+ auto *Zero = ConstantInt::get(IdxType, 0);
+ for (unsigned i = 0; i < Count; i++) {
+ Value *Indices[2] = {
+ Zero,
+ ConstantInt::get(IdxType, i),
+ };
+ auto *Ptr = IC.Builder->CreateInBoundsGEP(ST, Addr, makeArrayRef(Indices), AddrName);
+ auto *Val = IC.Builder->CreateExtractValue(V, i, EltName);
+ IC.Builder->CreateStore(Val, Ptr);
+ }
+
+ 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:
return EraseInstFromFunction(SI);
// Attempt to improve the alignment.
- if (DL) {
- unsigned KnownAlign = getOrEnforceKnownAlignment(
- Ptr, DL->getPrefTypeAlignment(Val->getType()), DL, AC, &SI, DT);
- unsigned StoreAlign = SI.getAlignment();
- unsigned EffectiveStoreAlign = StoreAlign != 0 ? StoreAlign :
- DL->getABITypeAlignment(Val->getType());
-
- if (KnownAlign > EffectiveStoreAlign)
- SI.setAlignment(KnownAlign);
- else if (StoreAlign == 0)
- SI.setAlignment(EffectiveStoreAlign);
- }
+ unsigned KnownAlign = getOrEnforceKnownAlignment(
+ Ptr, DL.getPrefTypeAlignment(Val->getType()), DL, &SI, AC, DT);
+ unsigned StoreAlign = SI.getAlignment();
+ unsigned EffectiveStoreAlign =
+ StoreAlign != 0 ? StoreAlign : DL.getABITypeAlignment(Val->getType());
+
+ if (KnownAlign > EffectiveStoreAlign)
+ SI.setAlignment(KnownAlign);
+ 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)) {
return &SI;
}
- // Don't hack volatile/atomic stores.
- // FIXME: Some bits are legal for atomic stores; needs refactoring.
- if (!SI.isSimple()) return nullptr;
+ // Don't hack volatile/ordered stores.
+ // FIXME: Some bits are legal for ordered atomic stores; needs refactoring.
+ if (!SI.isUnordered()) return nullptr;
// If the RHS is an alloca with a single use, zapify the store, making the
// alloca dead.
// Do really simple DSE, to catch cases where there are several consecutive
// stores to the same location, separated by a few arithmetic operations. This
// situation often occurs with bitfield accesses.
- BasicBlock::iterator BBI = &SI;
+ BasicBlock::iterator BBI(SI);
for (unsigned ScanInsts = 6; BBI != SI.getParent()->begin() && ScanInsts;
--ScanInsts) {
--BBI;
if (StoreInst *PrevSI = dyn_cast<StoreInst>(BBI)) {
// Prev store isn't volatile, and stores to the same location?
- if (PrevSI->isSimple() && equivalentAddressValues(PrevSI->getOperand(1),
+ if (PrevSI->isUnordered() && equivalentAddressValues(PrevSI->getOperand(1),
SI.getOperand(1))) {
++NumDeadStore;
++BBI;
// the pointer we're loading and is producing the pointer we're storing,
// then *this* store is dead (X = load P; store X -> P).
if (LoadInst *LI = dyn_cast<LoadInst>(BBI)) {
- if (LI == Val && equivalentAddressValues(LI->getOperand(0), Ptr) &&
- LI->isSimple())
+ if (LI == Val && equivalentAddressValues(LI->getOperand(0), Ptr)) {
+ assert(SI.isUnordered() && "can't eliminate ordering operation");
return EraseInstFromFunction(SI);
+ }
// Otherwise, this is a load from some other location. Stores before it
// may not be dead.
if (isa<UndefValue>(Val))
return EraseInstFromFunction(SI);
+ // The code below needs to be audited and adjusted for unordered atomics
+ if (!SI.isSimple())
+ return nullptr;
+
// If this store is the last instruction in the basic block (possibly
// excepting debug info instructions), and if the block ends with an
// unconditional branch, try to move it to the successor block.
- BBI = &SI;
+ BBI = SI.getIterator();
do {
++BBI;
} while (isa<DbgInfoIntrinsic>(BBI) ||
return false;
// Verify that the other block ends in a branch and is not otherwise empty.
- BasicBlock::iterator BBI = OtherBB->getTerminator();
+ BasicBlock::iterator BBI(OtherBB->getTerminator());
BranchInst *OtherBr = dyn_cast<BranchInst>(BBI);
if (!OtherBr || BBI == OtherBB->begin())
return false;