using namespace llvm;
/// Enable analysis of recursive PHI nodes.
-static cl::opt<bool> EnableRecPhiAnalysis("basicaa-recphi",
- cl::Hidden, cl::init(false));
+static cl::opt<bool> EnableRecPhiAnalysis("basicaa-recphi", cl::Hidden,
+ cl::init(false));
/// SearchLimitReached / SearchTimes shows how often the limit of
/// to decompose GEPs is reached. It will affect the precision
// Useful predicates
//===----------------------------------------------------------------------===//
-/// isNonEscapingLocalObject - Return true if the pointer is to a function-local
-/// object that never escapes from the function.
+/// Returns true if the pointer is to a function-local object that never
+/// escapes from the function.
static bool isNonEscapingLocalObject(const Value *V) {
// If this is a local allocation, check to see if it escapes.
if (isa<AllocaInst>(V) || isNoAliasCall(V))
return false;
}
-/// isEscapeSource - Return true if the pointer is one which would have
-/// been considered an escape by isNonEscapingLocalObject.
+/// Returns true if the pointer is one which would have been considered an
+/// escape by isNonEscapingLocalObject.
static bool isEscapeSource(const Value *V) {
if (isa<CallInst>(V) || isa<InvokeInst>(V) || isa<Argument>(V))
return true;
return false;
}
-/// getObjectSize - Return the size of the object specified by V, or
-/// UnknownSize if unknown.
+/// Returns the size of the object specified by V, or UnknownSize if unknown.
static uint64_t getObjectSize(const Value *V, const DataLayout &DL,
const TargetLibraryInfo &TLI,
bool RoundToAlign = false) {
return MemoryLocation::UnknownSize;
}
-/// isObjectSmallerThan - Return true if we can prove that the object specified
-/// by V is smaller than Size.
+/// Returns true if we can prove that the object specified by V is smaller than
+/// Size.
static bool isObjectSmallerThan(const Value *V, uint64_t Size,
const DataLayout &DL,
const TargetLibraryInfo &TLI) {
// This function needs to use the aligned object size because we allow
// reads a bit past the end given sufficient alignment.
- uint64_t ObjectSize = getObjectSize(V, DL, TLI, /*RoundToAlign*/true);
+ uint64_t ObjectSize = getObjectSize(V, DL, TLI, /*RoundToAlign*/ true);
return ObjectSize != MemoryLocation::UnknownSize && ObjectSize < Size;
}
-/// isObjectSize - Return true if we can prove that the object specified
-/// by V has size Size.
-static bool isObjectSize(const Value *V, uint64_t Size,
- const DataLayout &DL, const TargetLibraryInfo &TLI) {
+/// Returns true if we can prove that the object specified by V has size Size.
+static bool isObjectSize(const Value *V, uint64_t Size, const DataLayout &DL,
+ const TargetLibraryInfo &TLI) {
uint64_t ObjectSize = getObjectSize(V, DL, TLI);
return ObjectSize != MemoryLocation::UnknownSize && ObjectSize == Size;
}
// GetElementPtr Instruction Decomposition and Analysis
//===----------------------------------------------------------------------===//
-/// GetLinearExpression - Analyze the specified value as a linear expression:
-/// "A*V + B", where A and B are constant integers. Return the scale and offset
-/// values as APInts and return V as a Value*, and return whether we looked
-/// through any sign or zero extends. The incoming Value is known to have
-/// IntegerType and it may already be sign or zero extended.
+/// Analyzes the specified value as a linear expression: "A*V + B", where A and
+/// B are constant integers.
+///
+/// Returns the scale and offset values as APInts and return V as a Value*, and
+/// return whether we looked through any sign or zero extends. The incoming
+/// Value is known to have IntegerType and it may already be sign or zero
+/// extended.
///
/// Note that this looks through extends, so the high bits may not be
/// represented in the result.
-/*static*/ Value *BasicAliasAnalysis::GetLinearExpression(
- Value *V, APInt &Scale, APInt &Offset, ExtensionKind &Extension,
- const DataLayout &DL, unsigned Depth, AssumptionCache *AC,
- DominatorTree *DT) {
+/*static*/ const Value *BasicAliasAnalysis::GetLinearExpression(
+ const Value *V, APInt &Scale, APInt &Offset, unsigned &ZExtBits,
+ unsigned &SExtBits, const DataLayout &DL, unsigned Depth,
+ AssumptionCache *AC, DominatorTree *DT, bool &NSW, bool &NUW) {
assert(V->getType()->isIntegerTy() && "Not an integer value");
// Limit our recursion depth.
return V;
}
- if (ConstantInt *Const = dyn_cast<ConstantInt>(V)) {
- // if it's a constant, just convert it to an offset
- // and remove the variable.
- Offset += Const->getValue();
+ if (const ConstantInt *Const = dyn_cast<ConstantInt>(V)) {
+ // if it's a constant, just convert it to an offset and remove the variable.
+ // If we've been called recursively the Offset bit width will be greater
+ // than the constant's (the Offset's always as wide as the outermost call),
+ // so we'll zext here and process any extension in the isa<SExtInst> &
+ // isa<ZExtInst> cases below.
+ Offset += Const->getValue().zextOrSelf(Offset.getBitWidth());
assert(Scale == 0 && "Constant values don't have a scale");
return V;
}
- if (BinaryOperator *BOp = dyn_cast<BinaryOperator>(V)) {
+ if (const BinaryOperator *BOp = dyn_cast<BinaryOperator>(V)) {
if (ConstantInt *RHSC = dyn_cast<ConstantInt>(BOp->getOperand(1))) {
+
+ // If we've been called recursively then Offset and Scale will be wider
+ // that the BOp operands. We'll always zext it here as we'll process sign
+ // extensions below (see the isa<SExtInst> / isa<ZExtInst> cases).
+ APInt RHS = RHSC->getValue().zextOrSelf(Offset.getBitWidth());
+
switch (BOp->getOpcode()) {
- default: break;
+ default:
+ // We don't understand this instruction, so we can't decompose it any
+ // further.
+ Scale = 1;
+ Offset = 0;
+ return V;
case Instruction::Or:
// X|C == X+C if all the bits in C are unset in X. Otherwise we can't
// analyze it.
if (!MaskedValueIsZero(BOp->getOperand(0), RHSC->getValue(), DL, 0, AC,
- BOp, DT))
- break;
- // FALL THROUGH.
+ BOp, DT)) {
+ Scale = 1;
+ Offset = 0;
+ return V;
+ }
+ // FALL THROUGH.
case Instruction::Add:
- V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, Extension,
- DL, Depth + 1, AC, DT);
- Offset += RHSC->getValue();
- return V;
+ V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, ZExtBits,
+ SExtBits, DL, Depth + 1, AC, DT, NSW, NUW);
+ Offset += RHS;
+ break;
+ case Instruction::Sub:
+ V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, ZExtBits,
+ SExtBits, DL, Depth + 1, AC, DT, NSW, NUW);
+ Offset -= RHS;
+ break;
case Instruction::Mul:
- V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, Extension,
- DL, Depth + 1, AC, DT);
- Offset *= RHSC->getValue();
- Scale *= RHSC->getValue();
- return V;
+ V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, ZExtBits,
+ SExtBits, DL, Depth + 1, AC, DT, NSW, NUW);
+ Offset *= RHS;
+ Scale *= RHS;
+ break;
case Instruction::Shl:
- V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, Extension,
- DL, Depth + 1, AC, DT);
- Offset <<= RHSC->getValue().getLimitedValue();
- Scale <<= RHSC->getValue().getLimitedValue();
+ V = GetLinearExpression(BOp->getOperand(0), Scale, Offset, ZExtBits,
+ SExtBits, DL, Depth + 1, AC, DT, NSW, NUW);
+ Offset <<= RHS.getLimitedValue();
+ Scale <<= RHS.getLimitedValue();
+ // the semantics of nsw and nuw for left shifts don't match those of
+ // multiplications, so we won't propagate them.
+ NSW = NUW = false;
return V;
}
+
+ if (isa<OverflowingBinaryOperator>(BOp)) {
+ NUW &= BOp->hasNoUnsignedWrap();
+ NSW &= BOp->hasNoSignedWrap();
+ }
+ return V;
}
}
// Since GEP indices are sign extended anyway, we don't care about the high
// bits of a sign or zero extended value - just scales and offsets. The
// extensions have to be consistent though.
- if ((isa<SExtInst>(V) && Extension != EK_ZeroExt) ||
- (isa<ZExtInst>(V) && Extension != EK_SignExt)) {
+ if (isa<SExtInst>(V) || isa<ZExtInst>(V)) {
Value *CastOp = cast<CastInst>(V)->getOperand(0);
- unsigned OldWidth = Scale.getBitWidth();
+ unsigned NewWidth = V->getType()->getPrimitiveSizeInBits();
unsigned SmallWidth = CastOp->getType()->getPrimitiveSizeInBits();
- Scale = Scale.trunc(SmallWidth);
- Offset = Offset.trunc(SmallWidth);
- Extension = isa<SExtInst>(V) ? EK_SignExt : EK_ZeroExt;
-
- Value *Result = GetLinearExpression(CastOp, Scale, Offset, Extension, DL,
- Depth + 1, AC, DT);
- Scale = Scale.zext(OldWidth);
-
- // We have to sign-extend even if Extension == EK_ZeroExt as we can't
- // decompose a sign extension (i.e. zext(x - 1) != zext(x) - zext(-1)).
- Offset = Offset.sext(OldWidth);
+ unsigned OldZExtBits = ZExtBits, OldSExtBits = SExtBits;
+ const Value *Result =
+ GetLinearExpression(CastOp, Scale, Offset, ZExtBits, SExtBits, DL,
+ Depth + 1, AC, DT, NSW, NUW);
+
+ // zext(zext(%x)) == zext(%x), and similiarly for sext; we'll handle this
+ // by just incrementing the number of bits we've extended by.
+ unsigned ExtendedBy = NewWidth - SmallWidth;
+
+ if (isa<SExtInst>(V) && ZExtBits == 0) {
+ // sext(sext(%x, a), b) == sext(%x, a + b)
+
+ if (NSW) {
+ // We haven't sign-wrapped, so it's valid to decompose sext(%x + c)
+ // into sext(%x) + sext(c). We'll sext the Offset ourselves:
+ unsigned OldWidth = Offset.getBitWidth();
+ Offset = Offset.trunc(SmallWidth).sext(NewWidth).zextOrSelf(OldWidth);
+ } else {
+ // We may have signed-wrapped, so don't decompose sext(%x + c) into
+ // sext(%x) + sext(c)
+ Scale = 1;
+ Offset = 0;
+ Result = CastOp;
+ ZExtBits = OldZExtBits;
+ SExtBits = OldSExtBits;
+ }
+ SExtBits += ExtendedBy;
+ } else {
+ // sext(zext(%x, a), b) = zext(zext(%x, a), b) = zext(%x, a + b)
+
+ if (!NUW) {
+ // We may have unsigned-wrapped, so don't decompose zext(%x + c) into
+ // zext(%x) + zext(c)
+ Scale = 1;
+ Offset = 0;
+ Result = CastOp;
+ ZExtBits = OldZExtBits;
+ SExtBits = OldSExtBits;
+ }
+ ZExtBits += ExtendedBy;
+ }
return Result;
}
return V;
}
-/// DecomposeGEPExpression - If V is a symbolic pointer expression, decompose it
-/// into a base pointer with a constant offset and a number of scaled symbolic
-/// offsets.
+/// If V is a symbolic pointer expression, decompose it into a base pointer
+/// with a constant offset and a number of scaled symbolic offsets.
///
-/// The scaled symbolic offsets (represented by pairs of a Value* and a scale in
-/// the VarIndices vector) are Value*'s that are known to be scaled by the
-/// specified amount, but which may have other unrepresented high bits. As such,
-/// the gep cannot necessarily be reconstructed from its decomposed form.
+/// The scaled symbolic offsets (represented by pairs of a Value* and a scale
+/// in the VarIndices vector) are Value*'s that are known to be scaled by the
+/// specified amount, but which may have other unrepresented high bits. As
+/// such, the gep cannot necessarily be reconstructed from its decomposed form.
///
/// When DataLayout is around, this function is capable of analyzing everything
/// that GetUnderlyingObject can look through. To be able to do that
/// GetUnderlyingObject and DecomposeGEPExpression must use the same search
-/// depth (MaxLookupSearchDepth).
-/// When DataLayout not is around, it just looks through pointer casts.
-///
+/// depth (MaxLookupSearchDepth). When DataLayout not is around, it just looks
+/// through pointer casts.
/*static*/ const Value *BasicAliasAnalysis::DecomposeGEPExpression(
const Value *V, int64_t &BaseOffs,
SmallVectorImpl<VariableGEPIndex> &VarIndices, bool &MaxLookupReached,
// updated when GetUnderlyingObject is updated). TLI should be
// provided also.
if (const Value *Simplified =
- SimplifyInstruction(const_cast<Instruction *>(I), DL)) {
+ SimplifyInstruction(const_cast<Instruction *>(I), DL)) {
V = Simplified;
continue;
}
unsigned AS = GEPOp->getPointerAddressSpace();
// Walk the indices of the GEP, accumulating them into BaseOff/VarIndices.
gep_type_iterator GTI = gep_type_begin(GEPOp);
- for (User::const_op_iterator I = GEPOp->op_begin()+1,
- E = GEPOp->op_end(); I != E; ++I) {
- Value *Index = *I;
+ for (User::const_op_iterator I = GEPOp->op_begin() + 1, E = GEPOp->op_end();
+ I != E; ++I) {
+ const Value *Index = *I;
// Compute the (potentially symbolic) offset in bytes for this index.
if (StructType *STy = dyn_cast<StructType>(*GTI++)) {
// For a struct, add the member offset.
unsigned FieldNo = cast<ConstantInt>(Index)->getZExtValue();
- if (FieldNo == 0) continue;
+ if (FieldNo == 0)
+ continue;
BaseOffs += DL.getStructLayout(STy)->getElementOffset(FieldNo);
continue;
}
// For an array/pointer, add the element offset, explicitly scaled.
- if (ConstantInt *CIdx = dyn_cast<ConstantInt>(Index)) {
- if (CIdx->isZero()) continue;
+ if (const ConstantInt *CIdx = dyn_cast<ConstantInt>(Index)) {
+ if (CIdx->isZero())
+ continue;
BaseOffs += DL.getTypeAllocSize(*GTI) * CIdx->getSExtValue();
continue;
}
uint64_t Scale = DL.getTypeAllocSize(*GTI);
- ExtensionKind Extension = EK_NotExtended;
+ unsigned ZExtBits = 0, SExtBits = 0;
// If the integer type is smaller than the pointer size, it is implicitly
// sign extended to pointer size.
unsigned Width = Index->getType()->getIntegerBitWidth();
- if (DL.getPointerSizeInBits(AS) > Width)
- Extension = EK_SignExt;
+ unsigned PointerSize = DL.getPointerSizeInBits(AS);
+ if (PointerSize > Width)
+ SExtBits += PointerSize - Width;
// Use GetLinearExpression to decompose the index into a C1*V+C2 form.
APInt IndexScale(Width, 0), IndexOffset(Width, 0);
- Index = GetLinearExpression(Index, IndexScale, IndexOffset, Extension, DL,
- 0, AC, DT);
+ bool NSW = true, NUW = true;
+ Index = GetLinearExpression(Index, IndexScale, IndexOffset, ZExtBits,
+ SExtBits, DL, 0, AC, DT, NSW, NUW);
// The GEP index scale ("Scale") scales C1*V+C2, yielding (C1*V+C2)*Scale.
// This gives us an aggregate computation of (C1*Scale)*V + C2*Scale.
- BaseOffs += IndexOffset.getSExtValue()*Scale;
+ BaseOffs += IndexOffset.getSExtValue() * Scale;
Scale *= IndexScale.getSExtValue();
// If we already had an occurrence of this index variable, merge this
// A[x][x] -> x*16 + x*4 -> x*20
// This also ensures that 'x' only appears in the index list once.
for (unsigned i = 0, e = VarIndices.size(); i != e; ++i) {
- if (VarIndices[i].V == Index &&
- VarIndices[i].Extension == Extension) {
+ if (VarIndices[i].V == Index && VarIndices[i].ZExtBits == ZExtBits &&
+ VarIndices[i].SExtBits == SExtBits) {
Scale += VarIndices[i].Scale;
- VarIndices.erase(VarIndices.begin()+i);
+ VarIndices.erase(VarIndices.begin() + i);
break;
}
}
// Make sure that we have a scale that makes sense for this target's
// pointer size.
- if (unsigned ShiftBits = 64 - DL.getPointerSizeInBits(AS)) {
+ if (unsigned ShiftBits = 64 - PointerSize) {
Scale <<= ShiftBits;
Scale = (int64_t)Scale >> ShiftBits;
}
if (Scale) {
- VariableGEPIndex Entry = {Index, Extension,
+ VariableGEPIndex Entry = {Index, ZExtBits, SExtBits,
static_cast<int64_t>(Scale)};
VarIndices.push_back(Entry);
}
// Register the pass...
char BasicAliasAnalysis::ID = 0;
INITIALIZE_AG_PASS_BEGIN(BasicAliasAnalysis, AliasAnalysis, "basicaa",
- "Basic Alias Analysis (stateless AA impl)",
- false, true, false)
+ "Basic Alias Analysis (stateless AA impl)", false,
+ true, false)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_AG_PASS_END(BasicAliasAnalysis, AliasAnalysis, "basicaa",
- "Basic Alias Analysis (stateless AA impl)",
- false, true, false)
+ "Basic Alias Analysis (stateless AA impl)", false, true,
+ false)
ImmutablePass *llvm::createBasicAliasAnalysisPass() {
return new BasicAliasAnalysis();
}
-/// pointsToConstantMemory - Returns whether the given pointer value
-/// points to memory that is local to the function, with global constants being
-/// considered local to all functions.
+/// Returns whether the given pointer value points to memory that is local to
+/// the function, with global constants being considered local to all
+/// functions.
bool BasicAliasAnalysis::pointsToConstantMemory(const MemoryLocation &Loc,
bool OrLocal) {
assert(Visited.empty() && "Visited must be cleared after use!");
return false;
}
-/// getModRefBehavior - Return the behavior when calling the given call site.
+/// Returns the behavior when calling the given call site.
FunctionModRefBehavior
BasicAliasAnalysis::getModRefBehavior(ImmutableCallSite CS) {
if (CS.doesNotAccessMemory())
return FunctionModRefBehavior(AliasAnalysis::getModRefBehavior(CS) & Min);
}
-/// getModRefBehavior - Return the behavior when calling the given function.
-/// For use when the call site is not known.
+/// Returns the behavior when calling the given function. For use when the call
+/// site is not known.
FunctionModRefBehavior
BasicAliasAnalysis::getModRefBehavior(const Function *F) {
// If the function declares it doesn't access memory, we can't do better.
if (F->doesNotAccessMemory())
return FMRB_DoesNotAccessMemory;
- // For intrinsics, we can check the table.
- if (Intrinsic::ID iid = F->getIntrinsicID()) {
-#define GET_INTRINSIC_MODREF_BEHAVIOR
-#include "llvm/IR/Intrinsics.gen"
-#undef GET_INTRINSIC_MODREF_BEHAVIOR
- }
-
FunctionModRefBehavior Min = FMRB_UnknownModRefBehavior;
// If the function declares it only reads memory, go with that.
return true;
}
-/// getModRefInfo - Check to see if the specified callsite can clobber the
-/// specified memory object. Since we only look at local properties of this
-/// function, we really can't say much about this query. We do, however, use
-/// simple "address taken" analysis on local objects.
+/// Checks to see if the specified callsite can clobber the specified memory
+/// object.
+///
+/// Since we only look at local properties of this function, we really can't
+/// say much about this query. We do, however, use simple "address taken"
+/// analysis on local objects.
ModRefInfo BasicAliasAnalysis::getModRefInfo(ImmutableCallSite CS,
const MemoryLocation &Loc) {
assert(notDifferentParent(CS.getInstruction(), Loc.Ptr) &&
return AliasAnalysis::getModRefInfo(CS1, CS2);
}
-/// \brief Provide ad-hoc rules to disambiguate accesses through two GEP
-/// operators, both having the exact same pointer operand.
+/// Provide ad-hoc rules to disambiguate accesses through two GEP operators,
+/// both having the exact same pointer operand.
static AliasResult aliasSameBasePointerGEPs(const GEPOperator *GEP1,
uint64_t V1Size,
const GEPOperator *GEP2,
return MayAlias;
}
-/// aliasGEP - Provide a bunch of ad-hoc rules to disambiguate a GEP instruction
-/// against another pointer. We know that V1 is a GEP, but we don't know
-/// anything about V2. UnderlyingV1 is GetUnderlyingObject(GEP1, DL),
-/// UnderlyingV2 is the same for V2.
+/// Provides a bunch of ad-hoc rules to disambiguate a GEP instruction against
+/// another pointer.
///
+/// We know that V1 is a GEP, but we don't know anything about V2.
+/// UnderlyingV1 is GetUnderlyingObject(GEP1, DL), UnderlyingV2 is the same for
+/// V2.
AliasResult BasicAliasAnalysis::aliasGEP(
const GEPOperator *GEP1, uint64_t V1Size, const AAMDNodes &V1AAInfo,
const Value *V2, uint64_t V2Size, const AAMDNodes &V2AAInfo,
// identical.
if ((BaseAlias == MayAlias) && V1Size == V2Size) {
// Do the base pointers alias assuming type and size.
- AliasResult PreciseBaseAlias = aliasCheck(UnderlyingV1, V1Size,
- V1AAInfo, UnderlyingV2,
- V2Size, V2AAInfo);
+ AliasResult PreciseBaseAlias = aliasCheck(UnderlyingV1, V1Size, V1AAInfo,
+ UnderlyingV2, V2Size, V2AAInfo);
if (PreciseBaseAlias == NoAlias) {
// See if the computed offset from the common pointer tells us about the
// relation of the resulting pointer.
// If we get a No or May, then return it immediately, no amount of analysis
// will improve this situation.
- if (BaseAlias != MustAlias) return BaseAlias;
+ if (BaseAlias != MustAlias)
+ return BaseAlias;
// Otherwise, we have a MustAlias. Since the base pointers alias each other
// exactly, see if the computed offset from the common pointer tells us
// DecomposeGEPExpression and GetUnderlyingObject should return the
// same result except when DecomposeGEPExpression has no DataLayout.
if (GEP1BasePtr != UnderlyingV1 || GEP2BasePtr != UnderlyingV2) {
- assert(!DL &&
- "DecomposeGEPExpression and GetUnderlyingObject disagree!");
+ assert(!DL && "DecomposeGEPExpression and GetUnderlyingObject disagree!");
return MayAlias;
}
// DecomposeGEPExpression and GetUnderlyingObject should return the
// same result except when DecomposeGEPExpression has no DataLayout.
if (GEP1BasePtr != UnderlyingV1) {
- assert(!DL &&
- "DecomposeGEPExpression and GetUnderlyingObject disagree!");
+ assert(!DL && "DecomposeGEPExpression and GetUnderlyingObject disagree!");
return MayAlias;
}
// If the max search depth is reached the result is undefined
// Grab the least significant bit set in any of the scales. We
// don't need std::abs here (even if the scale's negative) as we'll
// be ^'ing Modulo with itself later.
- Modulo |= (uint64_t) GEP1VariableIndices[i].Scale;
+ Modulo |= (uint64_t)GEP1VariableIndices[i].Scale;
if (AllPositive) {
// If the Value could change between cycles, then any reasoning about
// Zero-extension widens the variable, and so forces the sign
// bit to zero.
- bool IsZExt = GEP1VariableIndices[i].Extension == EK_ZeroExt;
+ bool IsZExt = GEP1VariableIndices[i].ZExtBits > 0 || isa<ZExtInst>(V);
SignKnownZero |= IsZExt;
SignKnownOne &= !IsZExt;
// unsigned.
int64_t Scale = GEP1VariableIndices[i].Scale;
AllPositive =
- (SignKnownZero && Scale >= 0) ||
- (SignKnownOne && Scale < 0);
+ (SignKnownZero && Scale >= 0) || (SignKnownOne && Scale < 0);
}
}
// If we know all the variables are positive, then GEP1 >= GEP1BasePtr.
// If GEP1BasePtr > V2 (GEP1BaseOffset > 0) then we know the pointers
// don't alias if V2Size can fit in the gap between V2 and GEP1BasePtr.
- if (AllPositive && GEP1BaseOffset > 0 && V2Size <= (uint64_t) GEP1BaseOffset)
+ if (AllPositive && GEP1BaseOffset > 0 && V2Size <= (uint64_t)GEP1BaseOffset)
+ return NoAlias;
+
+ if (constantOffsetHeuristic(GEP1VariableIndices, V1Size, V2Size,
+ GEP1BaseOffset, DL, AC1, DT))
return NoAlias;
}
return MayAlias;
}
-/// aliasSelect - Provide a bunch of ad-hoc rules to disambiguate a Select
-/// instruction against another.
+/// Provides a bunch of ad-hoc rules to disambiguate a Select instruction
+/// against another.
AliasResult BasicAliasAnalysis::aliasSelect(const SelectInst *SI,
uint64_t SISize,
const AAMDNodes &SIAAInfo,
// check: just check for aliases between the values on corresponding arms.
if (const SelectInst *SI2 = dyn_cast<SelectInst>(V2))
if (SI->getCondition() == SI2->getCondition()) {
- AliasResult Alias =
- aliasCheck(SI->getTrueValue(), SISize, SIAAInfo,
- SI2->getTrueValue(), V2Size, V2AAInfo);
+ AliasResult Alias = aliasCheck(SI->getTrueValue(), SISize, SIAAInfo,
+ SI2->getTrueValue(), V2Size, V2AAInfo);
if (Alias == MayAlias)
return MayAlias;
AliasResult ThisAlias =
- aliasCheck(SI->getFalseValue(), SISize, SIAAInfo,
- SI2->getFalseValue(), V2Size, V2AAInfo);
+ aliasCheck(SI->getFalseValue(), SISize, SIAAInfo,
+ SI2->getFalseValue(), V2Size, V2AAInfo);
return MergeAliasResults(ThisAlias, Alias);
}
// If both arms of the Select node NoAlias or MustAlias V2, then returns
// NoAlias / MustAlias. Otherwise, returns MayAlias.
AliasResult Alias =
- aliasCheck(V2, V2Size, V2AAInfo, SI->getTrueValue(), SISize, SIAAInfo);
+ aliasCheck(V2, V2Size, V2AAInfo, SI->getTrueValue(), SISize, SIAAInfo);
if (Alias == MayAlias)
return MayAlias;
AliasResult ThisAlias =
- aliasCheck(V2, V2Size, V2AAInfo, SI->getFalseValue(), SISize, SIAAInfo);
+ aliasCheck(V2, V2Size, V2AAInfo, SI->getFalseValue(), SISize, SIAAInfo);
return MergeAliasResults(ThisAlias, Alias);
}
-// aliasPHI - Provide a bunch of ad-hoc rules to disambiguate a PHI instruction
-// against another.
+/// Provide a bunch of ad-hoc rules to disambiguate a PHI instruction against
+/// another.
AliasResult BasicAliasAnalysis::aliasPHI(const PHINode *PN, uint64_t PNSize,
const AAMDNodes &PNAAInfo,
const Value *V2, uint64_t V2Size,
for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
AliasResult ThisAlias =
- aliasCheck(PN->getIncomingValue(i), PNSize, PNAAInfo,
- PN2->getIncomingValueForBlock(PN->getIncomingBlock(i)),
- V2Size, V2AAInfo);
+ aliasCheck(PN->getIncomingValue(i), PNSize, PNAAInfo,
+ PN2->getIncomingValueForBlock(PN->getIncomingBlock(i)),
+ V2Size, V2AAInfo);
Alias = MergeAliasResults(ThisAlias, Alias);
if (Alias == MayAlias)
break;
return Alias;
}
- SmallPtrSet<Value*, 4> UniqueSrc;
- SmallVector<Value*, 4> V1Srcs;
+ SmallPtrSet<Value *, 4> UniqueSrc;
+ SmallVector<Value *, 4> V1Srcs;
bool isRecursive = false;
for (Value *PV1 : PN->incoming_values()) {
if (isa<PHINode>(PV1))
if (isRecursive)
PNSize = MemoryLocation::UnknownSize;
- AliasResult Alias = aliasCheck(V2, V2Size, V2AAInfo,
- V1Srcs[0], PNSize, PNAAInfo);
+ AliasResult Alias =
+ aliasCheck(V2, V2Size, V2AAInfo, V1Srcs[0], PNSize, PNAAInfo);
// Early exit if the check of the first PHI source against V2 is MayAlias.
// Other results are not possible.
for (unsigned i = 1, e = V1Srcs.size(); i != e; ++i) {
Value *V = V1Srcs[i];
- AliasResult ThisAlias = aliasCheck(V2, V2Size, V2AAInfo,
- V, PNSize, PNAAInfo);
+ AliasResult ThisAlias =
+ aliasCheck(V2, V2Size, V2AAInfo, V, PNSize, PNAAInfo);
Alias = MergeAliasResults(ThisAlias, Alias);
if (Alias == MayAlias)
break;
return Alias;
}
-// aliasCheck - Provide a bunch of ad-hoc rules to disambiguate in common cases,
-// such as array references.
-//
+/// Provideis a bunch of ad-hoc rules to disambiguate in common cases, such as
+/// array references.
AliasResult BasicAliasAnalysis::aliasCheck(const Value *V1, uint64_t V1Size,
AAMDNodes V1AAInfo, const Value *V2,
uint64_t V2Size,
return MustAlias;
if (!V1->getType()->isPointerTy() || !V2->getType()->isPointerTy())
- return NoAlias; // Scalars cannot alias each other
+ return NoAlias; // Scalars cannot alias each other
// Figure out what objects these things are pointing to if we can.
const Value *O1 = GetUnderlyingObject(V1, *DL, MaxLookupSearchDepth);
if (V1 > V2)
std::swap(Locs.first, Locs.second);
std::pair<AliasCacheTy::iterator, bool> Pair =
- AliasCache.insert(std::make_pair(Locs, MayAlias));
+ AliasCache.insert(std::make_pair(Locs, MayAlias));
if (!Pair.second)
return Pair.first->second;
std::swap(V1AAInfo, V2AAInfo);
}
if (const GEPOperator *GV1 = dyn_cast<GEPOperator>(V1)) {
- AliasResult Result = aliasGEP(GV1, V1Size, V1AAInfo, V2, V2Size, V2AAInfo, O1, O2);
- if (Result != MayAlias) return AliasCache[Locs] = Result;
+ AliasResult Result =
+ aliasGEP(GV1, V1Size, V1AAInfo, V2, V2Size, V2AAInfo, O1, O2);
+ if (Result != MayAlias)
+ return AliasCache[Locs] = Result;
}
if (isa<PHINode>(V2) && !isa<PHINode>(V1)) {
std::swap(V1AAInfo, V2AAInfo);
}
if (const PHINode *PN = dyn_cast<PHINode>(V1)) {
- AliasResult Result = aliasPHI(PN, V1Size, V1AAInfo,
- V2, V2Size, V2AAInfo);
- if (Result != MayAlias) return AliasCache[Locs] = Result;
+ AliasResult Result = aliasPHI(PN, V1Size, V1AAInfo, V2, V2Size, V2AAInfo);
+ if (Result != MayAlias)
+ return AliasCache[Locs] = Result;
}
if (isa<SelectInst>(V2) && !isa<SelectInst>(V1)) {
std::swap(V1AAInfo, V2AAInfo);
}
if (const SelectInst *S1 = dyn_cast<SelectInst>(V1)) {
- AliasResult Result = aliasSelect(S1, V1Size, V1AAInfo,
- V2, V2Size, V2AAInfo);
- if (Result != MayAlias) return AliasCache[Locs] = Result;
+ AliasResult Result =
+ aliasSelect(S1, V1Size, V1AAInfo, V2, V2Size, V2AAInfo);
+ if (Result != MayAlias)
+ return AliasCache[Locs] = Result;
}
// If both pointers are pointing into the same object and one of them
return AliasCache[Locs] = Result;
}
+/// Check whether two Values can be considered equivalent.
+///
+/// In addition to pointer equivalence of \p V1 and \p V2 this checks whether
+/// they can not be part of a cycle in the value graph by looking at all
+/// visited phi nodes an making sure that the phis cannot reach the value. We
+/// have to do this because we are looking through phi nodes (That is we say
+/// noalias(V, phi(VA, VB)) if noalias(V, VA) and noalias(V, VB).
bool BasicAliasAnalysis::isValueEqualInPotentialCycles(const Value *V,
const Value *V2) {
if (V != V2)
return true;
}
-/// GetIndexDifference - Dest and Src are the variable indices from two
-/// decomposed GetElementPtr instructions GEP1 and GEP2 which have common base
-/// pointers. Subtract the GEP2 indices from GEP1 to find the symbolic
-/// difference between the two pointers.
+/// Computes the symbolic difference between two de-composed GEPs.
+///
+/// Dest and Src are the variable indices from two decomposed GetElementPtr
+/// instructions GEP1 and GEP2 which have common base pointers.
void BasicAliasAnalysis::GetIndexDifference(
SmallVectorImpl<VariableGEPIndex> &Dest,
const SmallVectorImpl<VariableGEPIndex> &Src) {
for (unsigned i = 0, e = Src.size(); i != e; ++i) {
const Value *V = Src[i].V;
- ExtensionKind Extension = Src[i].Extension;
+ unsigned ZExtBits = Src[i].ZExtBits, SExtBits = Src[i].SExtBits;
int64_t Scale = Src[i].Scale;
// Find V in Dest. This is N^2, but pointer indices almost never have more
// than a few variable indexes.
for (unsigned j = 0, e = Dest.size(); j != e; ++j) {
if (!isValueEqualInPotentialCycles(Dest[j].V, V) ||
- Dest[j].Extension != Extension)
+ Dest[j].ZExtBits != ZExtBits || Dest[j].SExtBits != SExtBits)
continue;
// If we found it, subtract off Scale V's from the entry in Dest. If it
// If we didn't consume this entry, add it to the end of the Dest list.
if (Scale) {
- VariableGEPIndex Entry = { V, Extension, -Scale };
+ VariableGEPIndex Entry = {V, ZExtBits, SExtBits, -Scale};
Dest.push_back(Entry);
}
}
}
+
+bool BasicAliasAnalysis::constantOffsetHeuristic(
+ const SmallVectorImpl<VariableGEPIndex> &VarIndices, uint64_t V1Size,
+ uint64_t V2Size, int64_t BaseOffset, const DataLayout *DL,
+ AssumptionCache *AC, DominatorTree *DT) {
+ if (VarIndices.size() != 2 || V1Size == MemoryLocation::UnknownSize ||
+ V2Size == MemoryLocation::UnknownSize || !DL)
+ return false;
+
+ const VariableGEPIndex &Var0 = VarIndices[0], &Var1 = VarIndices[1];
+
+ if (Var0.ZExtBits != Var1.ZExtBits || Var0.SExtBits != Var1.SExtBits ||
+ Var0.Scale != -Var1.Scale)
+ return false;
+
+ unsigned Width = Var1.V->getType()->getIntegerBitWidth();
+
+ // We'll strip off the Extensions of Var0 and Var1 and do another round
+ // of GetLinearExpression decomposition. In the example above, if Var0
+ // is zext(%x + 1) we should get V1 == %x and V1Offset == 1.
+
+ APInt V0Scale(Width, 0), V0Offset(Width, 0), V1Scale(Width, 0),
+ V1Offset(Width, 0);
+ bool NSW = true, NUW = true;
+ unsigned V0ZExtBits = 0, V0SExtBits = 0, V1ZExtBits = 0, V1SExtBits = 0;
+ const Value *V0 = GetLinearExpression(Var0.V, V0Scale, V0Offset, V0ZExtBits,
+ V0SExtBits, *DL, 0, AC, DT, NSW, NUW);
+ NSW = true, NUW = true;
+ const Value *V1 = GetLinearExpression(Var1.V, V1Scale, V1Offset, V1ZExtBits,
+ V1SExtBits, *DL, 0, AC, DT, NSW, NUW);
+
+ if (V0Scale != V1Scale || V0ZExtBits != V1ZExtBits ||
+ V0SExtBits != V1SExtBits || !isValueEqualInPotentialCycles(V0, V1))
+ return false;
+
+ // We have a hit - Var0 and Var1 only differ by a constant offset!
+
+ // If we've been sext'ed then zext'd the maximum difference between Var0 and
+ // Var1 is possible to calculate, but we're just interested in the absolute
+ // minumum difference between the two. The minimum distance may occur due to
+ // wrapping; consider "add i3 %i, 5": if %i == 7 then 7 + 5 mod 8 == 4, and so
+ // the minimum distance between %i and %i + 5 is 3.
+ APInt MinDiff = V0Offset - V1Offset,
+ Wrapped = APInt::getMaxValue(Width) - MinDiff + APInt(Width, 1);
+ MinDiff = APIntOps::umin(MinDiff, Wrapped);
+ uint64_t MinDiffBytes = MinDiff.getZExtValue() * std::abs(Var0.Scale);
+
+ // We can't definitely say whether GEP1 is before or after V2 due to wrapping
+ // arithmetic (i.e. for some values of GEP1 and V2 GEP1 < V2, and for other
+ // values GEP1 > V2). We'll therefore only declare NoAlias if both V1Size and
+ // V2Size can fit in the MinDiffBytes gap.
+ return V1Size + std::abs(BaseOffset) <= MinDiffBytes &&
+ V2Size + std::abs(BaseOffset) <= MinDiffBytes;
+}
projects / oota-llvm.git / blobdiff