Skip to content

[Loads] Support dereferenceable assumption with variable size. #128436

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion llvm/include/llvm/Analysis/AssumeBundleQueries.h
Original file line number Diff line number Diff line change
Expand Up @@ -102,10 +102,14 @@ LLVM_ABI void fillMapFromAssume(AssumeInst &Assume,
struct RetainedKnowledge {
Attribute::AttrKind AttrKind = Attribute::None;
uint64_t ArgValue = 0;
Value *IRArgValue = nullptr;
Value *WasOn = nullptr;
RetainedKnowledge(Attribute::AttrKind AttrKind = Attribute::None,
uint64_t ArgValue = 0, Value *WasOn = nullptr)
: AttrKind(AttrKind), ArgValue(ArgValue), WasOn(WasOn) {}
bool operator==(RetainedKnowledge Other) const {
return AttrKind == Other.AttrKind && WasOn == Other.WasOn &&
ArgValue == Other.ArgValue;
ArgValue == Other.ArgValue && IRArgValue == Other.IRArgValue;
}
bool operator!=(RetainedKnowledge Other) const { return !(*this == Other); }
/// This is only intended for use in std::min/std::max between attribute that
Expand Down
3 changes: 3 additions & 0 deletions llvm/lib/Analysis/AssumeBundleQueries.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,9 @@ llvm::getKnowledgeFromBundle(AssumeInst &Assume,
};
if (BOI.End - BOI.Begin > ABA_Argument)
Result.ArgValue = GetArgOr1(0);
Result.IRArgValue = bundleHasArgument(BOI, ABA_Argument)
? getValueFromBundleOpInfo(Assume, BOI, ABA_Argument)
: nullptr;
if (Result.AttrKind == Attribute::Alignment)
if (BOI.End - BOI.Begin > ABA_Argument + 1)
Result.ArgValue = MinAlign(Result.ArgValue, GetArgOr1(1));
Expand Down
88 changes: 53 additions & 35 deletions llvm/lib/Analysis/Loads.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,40 @@ static bool isAligned(const Value *Base, Align Alignment,
return Base->getPointerAlignment(DL) >= Alignment;
}

static bool isDereferenceableAndAlignedPointerViaAssumption(
const Value *Ptr, Align Alignment,
function_ref<bool(const RetainedKnowledge &RK)> CheckSize,
const DataLayout &DL, const Instruction *CtxI, AssumptionCache *AC,
const DominatorTree *DT) {
// Dereferenceable information from assumptions is only valid if the value
// cannot be freed between the assumption and use. For now just use the
// information for values that cannot be freed in the function.
// TODO: More precisely check if the pointer can be freed between assumption
// and use.
if (!CtxI || Ptr->canBeFreed())
return false;
/// Look through assumes to see if both dereferencability and alignment can
/// be proven by an assume if needed.
RetainedKnowledge AlignRK;
RetainedKnowledge DerefRK;
bool IsAligned = Ptr->getPointerAlignment(DL) >= Alignment;
return getKnowledgeForValue(
Ptr, {Attribute::Dereferenceable, Attribute::Alignment}, *AC,
[&](RetainedKnowledge RK, Instruction *Assume, auto) {
if (!isValidAssumeForContext(Assume, CtxI, DT))
return false;
if (RK.AttrKind == Attribute::Alignment)
AlignRK = std::max(AlignRK, RK);
if (RK.AttrKind == Attribute::Dereferenceable)
DerefRK = std::max(DerefRK, RK);
IsAligned |= AlignRK && AlignRK.ArgValue >= Alignment.value();
if (IsAligned && DerefRK && CheckSize(DerefRK))
return true; // We have found what we needed so we stop looking
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: You can just do

  return IsAligned && DerefRK && CheckSize(DerefRK);

return false; // Other assumes may have better information. so
// keep looking
});
}

/// Test if V is always a pointer to allocated and suitably aligned memory for
/// a simple load or store.
static bool isDereferenceableAndAlignedPointer(
Expand Down Expand Up @@ -169,38 +203,12 @@ static bool isDereferenceableAndAlignedPointer(
Size, DL, CtxI, AC, DT, TLI,
Visited, MaxDepth);

// Dereferenceable information from assumptions is only valid if the value
// cannot be freed between the assumption and use. For now just use the
// information for values that cannot be freed in the function.
// TODO: More precisely check if the pointer can be freed between assumption
// and use.
if (CtxI && AC && !V->canBeFreed()) {
/// Look through assumes to see if both dereferencability and alignment can
/// be proven by an assume if needed.
RetainedKnowledge AlignRK;
RetainedKnowledge DerefRK;
bool IsAligned = V->getPointerAlignment(DL) >= Alignment;
if (getKnowledgeForValue(
V, {Attribute::Dereferenceable, Attribute::Alignment}, *AC,
[&](RetainedKnowledge RK, Instruction *Assume, auto) {
if (!isValidAssumeForContext(Assume, CtxI, DT))
return false;
if (RK.AttrKind == Attribute::Alignment)
AlignRK = std::max(AlignRK, RK);
if (RK.AttrKind == Attribute::Dereferenceable)
DerefRK = std::max(DerefRK, RK);
IsAligned |= AlignRK && AlignRK.ArgValue >= Alignment.value();
if (IsAligned && DerefRK &&
DerefRK.ArgValue >= Size.getZExtValue())
return true; // We have found what we needed so we stop looking
return false; // Other assumes may have better information. so
// keep looking
}))
return true;
}

// If we don't know, assume the worst.
return false;
return AC && isDereferenceableAndAlignedPointerViaAssumption(
V, Alignment,
[Size](const RetainedKnowledge &RK) {
return RK.ArgValue >= Size.getZExtValue();
},
DL, CtxI, AC, DT);
}

bool llvm::isDereferenceableAndAlignedPointer(
Expand Down Expand Up @@ -317,8 +325,8 @@ bool llvm::isDereferenceableAndAlignedInLoop(
return false;

const SCEV *MaxBECount =
Predicates ? SE.getPredicatedConstantMaxBackedgeTakenCount(L, *Predicates)
: SE.getConstantMaxBackedgeTakenCount(L);
Predicates ? SE.getPredicatedSymbolicMaxBackedgeTakenCount(L, *Predicates)
: SE.getSymbolicMaxBackedgeTakenCount(L);
const SCEV *BECount = Predicates
? SE.getPredicatedBackedgeTakenCount(L, *Predicates)
: SE.getBackedgeTakenCount(L);
Expand All @@ -339,9 +347,11 @@ bool llvm::isDereferenceableAndAlignedInLoop(

Value *Base = nullptr;
APInt AccessSize;
const SCEV *AccessSizeSCEV = nullptr;
if (const SCEVUnknown *NewBase = dyn_cast<SCEVUnknown>(AccessStart)) {
Base = NewBase->getValue();
AccessSize = MaxPtrDiff;
AccessSizeSCEV = PtrDiff;
} else if (auto *MinAdd = dyn_cast<SCEVAddExpr>(AccessStart)) {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OT - We may be able to strengthen this code using SCEV's getPointerBase and removePointerBase.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is a good point as a follow-up (I'll try it out). With a pre-loop before the vectorizable loop, I found it bailing out on the (MinAdd->getNumOperands() != 2), but I'm not sure if getPointerBase will help.

if (MinAdd->getNumOperands() != 2)
return false;
Expand All @@ -365,12 +375,20 @@ bool llvm::isDereferenceableAndAlignedInLoop(
return false;

AccessSize = MaxPtrDiff + Offset->getAPInt();
AccessSizeSCEV = SE.getAddExpr(PtrDiff, Offset);
Base = NewBase->getValue();
} else
return false;

Instruction *HeaderFirstNonPHI = &*L->getHeader()->getFirstNonPHIIt();
return isDereferenceableAndAlignedPointer(Base, Alignment, AccessSize, DL,
return isDereferenceableAndAlignedPointerViaAssumption(
Base, Alignment,
[&SE, AccessSizeSCEV](const RetainedKnowledge &RK) {
return SE.isKnownPredicate(CmpInst::ICMP_ULE, AccessSizeSCEV,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There is a potential to use isKnownPredicateAt with Loop's predecessor as the Ctx instruction if it exists. I don't yet see a benefit for it, but just stating it.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yep, there's probably a number of improvements we can make as follow ups!

SE.getSCEV(RK.IRArgValue));
},
DL, HeaderFirstNonPHI, AC, &DT) ||
isDereferenceableAndAlignedPointer(Base, Alignment, AccessSize, DL,
HeaderFirstNonPHI, AC, &DT);
}

Expand Down
9 changes: 9 additions & 0 deletions llvm/lib/IR/Verifier.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -5604,6 +5604,15 @@ void Verifier::visitIntrinsicCall(Intrinsic::ID ID, CallBase &Call) {
"third argument should be an integer if present", Call);
continue;
}
if (Kind == Attribute::Dereferenceable) {
Check(ArgCount == 2,
"dereferenceable assumptions should have 2 arguments", Call);
Check(Call.getOperand(Elem.Begin)->getType()->isPointerTy(),
"first argument should be a pointer", Call);
Check(Call.getOperand(Elem.Begin + 1)->getType()->isIntegerTy(),
"second argument should be an integer", Call);
continue;
}
Check(ArgCount <= 2, "too many arguments", Call);
if (Kind == Attribute::None)
break;
Expand Down
Loading
Loading