#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/SetVector.h"
+#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/InstructionSimplify.h"
///
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<AssumptionCacheTracker>();
+ AU.addRequired<DominatorTreeWrapperPass>();
AU.addRequired<LoopInfoWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addRequiredID(LoopSimplifyID);
AU.addPreservedID(LoopSimplifyID);
AU.addRequiredID(LCSSAID);
AU.addPreservedID(LCSSAID);
- AU.addRequired<ScalarEvolution>();
- AU.addPreserved<ScalarEvolution>();
+ AU.addRequired<ScalarEvolutionWrapperPass>();
+ AU.addPreserved<ScalarEvolutionWrapperPass>();
AU.addRequired<TargetTransformInfoWrapperPass>();
// FIXME: Loop unroll requires LCSSA. And LCSSA requires dom info.
// If loop unroll does not preserve dom info then LCSSA pass on next
// loop will receive invalid dom info.
// For now, recreate dom info, if loop is unrolled.
AU.addPreserved<DominatorTreeWrapperPass>();
+ AU.addPreserved<GlobalsAAWrapperPass>();
}
// Fill in the UnrollingPreferences parameter with values from the
// total unrolled size. Parameters Threshold and PartialThreshold
// are set to the maximum unrolled size for fully and partially
// unrolled loops respectively.
- void selectThresholds(const Loop *L, bool HasPragma,
+ void selectThresholds(const Loop *L, bool UsePragmaThreshold,
const TargetTransformInfo::UnrollingPreferences &UP,
unsigned &Threshold, unsigned &PartialThreshold,
unsigned &PercentDynamicCostSavedThreshold,
: UP.DynamicCostSavingsDiscount;
if (!UserThreshold &&
+ // FIXME: Use Function::optForSize().
L->getHeader()->getParent()->hasFnAttribute(
Attribute::OptimizeForSize)) {
Threshold = UP.OptSizeThreshold;
PartialThreshold = UP.PartialOptSizeThreshold;
}
- if (HasPragma) {
+ if (UsePragmaThreshold) {
// If the loop has an unrolling pragma, we want to be more
// aggressive with unrolling limits. Set thresholds to at
// least the PragmaTheshold value which is larger than the
bool canUnrollCompletely(Loop *L, unsigned Threshold,
unsigned PercentDynamicCostSavedThreshold,
unsigned DynamicCostSavingsDiscount,
- unsigned UnrolledCost, unsigned RolledDynamicCost);
+ uint64_t UnrolledCost, uint64_t RolledDynamicCost);
};
}
INITIALIZE_PASS_BEGIN(LoopUnroll, "loop-unroll", "Unroll loops", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_DEPENDENCY(LCSSA)
-INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
+INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_END(LoopUnroll, "loop-unroll", "Unroll loops", false, false)
Pass *llvm::createLoopUnrollPass(int Threshold, int Count, int AllowPartial,
return llvm::createLoopUnrollPass(-1, -1, 0, 0);
}
-namespace {
-/// \brief SCEV expressions visitor used for finding expressions that would
-/// become constants if the loop L is unrolled.
-struct FindConstantPointers {
- /// \brief Shows whether the expression is ConstAddress+Constant or not.
- bool IndexIsConstant;
-
- /// \brief Used for filtering out SCEV expressions with two or more AddRec
- /// subexpressions.
- ///
- /// Used to filter out complicated SCEV expressions, having several AddRec
- /// sub-expressions. We don't handle them, because unrolling one loop
- /// would help to replace only one of these inductions with a constant, and
- /// consequently, the expression would remain non-constant.
- bool HaveSeenAR;
-
- /// \brief If the SCEV expression becomes ConstAddress+Constant, this value
- /// holds ConstAddress. Otherwise, it's nullptr.
- Value *BaseAddress;
-
- /// \brief The loop, which we try to completely unroll.
- const Loop *L;
-
- ScalarEvolution &SE;
-
- FindConstantPointers(const Loop *L, ScalarEvolution &SE)
- : IndexIsConstant(true), HaveSeenAR(false), BaseAddress(nullptr),
- L(L), SE(SE) {}
-
- /// Examine the given expression S and figure out, if it can be a part of an
- /// expression, that could become a constant after the loop is unrolled.
- /// The routine sets IndexIsConstant and HaveSeenAR according to the analysis
- /// results.
- /// \returns true if we need to examine subexpressions, and false otherwise.
- bool follow(const SCEV *S) {
- if (const SCEVUnknown *SC = dyn_cast<SCEVUnknown>(S)) {
- // We've reached the leaf node of SCEV, it's most probably just a
- // variable.
- // If it's the only one SCEV-subexpression, then it might be a base
- // address of an index expression.
- // If we've already recorded base address, then just give up on this SCEV
- // - it's too complicated.
- if (BaseAddress) {
- IndexIsConstant = false;
- return false;
- }
- BaseAddress = SC->getValue();
- return false;
- }
- if (isa<SCEVConstant>(S))
- return false;
- if (const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(S)) {
- // If the current SCEV expression is AddRec, and its loop isn't the loop
- // we are about to unroll, then we won't get a constant address after
- // unrolling, and thus, won't be able to eliminate the load.
- if (AR->getLoop() != L) {
- IndexIsConstant = false;
- return false;
- }
- // We don't handle multiple AddRecs here, so give up in this case.
- if (HaveSeenAR) {
- IndexIsConstant = false;
- return false;
- }
- HaveSeenAR = true;
- }
-
- // Continue traversal.
- return true;
- }
- bool isDone() const { return !IndexIsConstant; }
-};
-} // End anonymous namespace.
-
-namespace {
-/// \brief A cache of SCEV results used to optimize repeated queries to SCEV on
-/// the same set of instructions.
-///
-/// The primary cost this saves is the cost of checking the validity of a SCEV
-/// every time it is looked up. However, in some cases we can provide a reduced
-/// and especially useful model for an instruction based upon SCEV that is
-/// non-trivial to compute but more useful to clients.
-class SCEVCache {
-public:
- /// \brief Struct to represent a GEP whose start and step are known fixed
- /// offsets from a base address due to SCEV's analysis.
- struct GEPDescriptor {
- Value *BaseAddr = nullptr;
- unsigned Start = 0;
- unsigned Step = 0;
- };
-
- Optional<GEPDescriptor> getGEPDescriptor(GetElementPtrInst *GEP);
-
- SCEVCache(const Loop &L, ScalarEvolution &SE) : L(L), SE(SE) {}
-
-private:
- const Loop &L;
- ScalarEvolution &SE;
-
- SmallDenseMap<GetElementPtrInst *, GEPDescriptor> GEPDescriptors;
-};
-} // End anonymous namespace.
-
-/// \brief Get a simplified descriptor for a GEP instruction.
-///
-/// Where possible, this produces a simplified descriptor for a GEP instruction
-/// using SCEV analysis of the containing loop. If this isn't possible, it
-/// returns an empty optional.
-///
-/// The model is a base address, an initial offset, and a per-iteration step.
-/// This fits very common patterns of GEPs inside loops and is something we can
-/// use to simulate the behavior of a particular iteration of a loop.
-///
-/// This is a cached interface. The first call may do non-trivial work to
-/// compute the result, but all subsequent calls will return a fast answer
-/// based on a cached result. This includes caching negative results.
-Optional<SCEVCache::GEPDescriptor>
-SCEVCache::getGEPDescriptor(GetElementPtrInst *GEP) {
- decltype(GEPDescriptors)::iterator It;
- bool Inserted;
-
- std::tie(It, Inserted) = GEPDescriptors.insert({GEP, {}});
-
- if (!Inserted) {
- if (!It->second.BaseAddr)
- return None;
-
- return It->second;
- }
-
- // We've inserted a new record into the cache, so compute the GEP descriptor
- // if possible.
- Value *V = cast<Value>(GEP);
- if (!SE.isSCEVable(V->getType()))
- return None;
- const SCEV *S = SE.getSCEV(V);
-
- // FIXME: It'd be nice if the worklist and set used by the
- // SCEVTraversal could be re-used between loop iterations, but the
- // interface doesn't support that. There is no way to clear the visited
- // sets between uses.
- FindConstantPointers Visitor(&L, SE);
- SCEVTraversal<FindConstantPointers> T(Visitor);
-
- // Try to find (BaseAddress+Step+Offset) tuple.
- // If succeeded, save it to the cache - it might help in folding
- // loads.
- T.visitAll(S);
- if (!Visitor.IndexIsConstant || !Visitor.BaseAddress)
- return None;
-
- const SCEV *BaseAddrSE = SE.getSCEV(Visitor.BaseAddress);
- if (BaseAddrSE->getType() != S->getType())
- return None;
- const SCEV *OffSE = SE.getMinusSCEV(S, BaseAddrSE);
- const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(OffSE);
-
- if (!AR)
- return None;
-
- const SCEVConstant *StepSE =
- dyn_cast<SCEVConstant>(AR->getStepRecurrence(SE));
- const SCEVConstant *StartSE = dyn_cast<SCEVConstant>(AR->getStart());
- if (!StepSE || !StartSE)
- return None;
-
- // Check and skip caching if doing so would require lots of bits to
- // avoid overflow.
- APInt Start = StartSE->getValue()->getValue();
- APInt Step = StepSE->getValue()->getValue();
- if (Start.getActiveBits() > 32 || Step.getActiveBits() > 32)
- return None;
-
- // We found a cacheable SCEV model for the GEP.
- It->second.BaseAddr = Visitor.BaseAddress;
- It->second.Start = Start.getLimitedValue();
- It->second.Step = Step.getLimitedValue();
- return It->second;
-}
-
namespace {
// This class is used to get an estimate of the optimization effects that we
// could get from complete loop unrolling. It comes from the fact that some
class UnrolledInstAnalyzer : private InstVisitor<UnrolledInstAnalyzer, bool> {
typedef InstVisitor<UnrolledInstAnalyzer, bool> Base;
friend class InstVisitor<UnrolledInstAnalyzer, bool>;
+ struct SimplifiedAddress {
+ Value *Base = nullptr;
+ ConstantInt *Offset = nullptr;
+ };
public:
UnrolledInstAnalyzer(unsigned Iteration,
DenseMap<Value *, Constant *> &SimplifiedValues,
- SCEVCache &SC)
- : Iteration(Iteration), SimplifiedValues(SimplifiedValues), SC(SC) {}
+ const Loop *L, ScalarEvolution &SE)
+ : Iteration(Iteration), SimplifiedValues(SimplifiedValues), L(L), SE(SE) {
+ IterationNumber = SE.getConstant(APInt(64, Iteration));
+ }
// Allow access to the initial visit method.
using Base::visit;
private:
+ /// \brief A cache of pointer bases and constant-folded offsets corresponding
+ /// to GEP (or derived from GEP) instructions.
+ ///
+ /// In order to find the base pointer one needs to perform non-trivial
+ /// traversal of the corresponding SCEV expression, so it's good to have the
+ /// results saved.
+ DenseMap<Value *, SimplifiedAddress> SimplifiedAddresses;
+
/// \brief Number of currently simulated iteration.
///
/// If an expression is ConstAddress+Constant, then the Constant is
/// SCEVGEPCache.
unsigned Iteration;
- // While we walk the loop instructions, we we build up and maintain a mapping
- // of simplified values specific to this iteration. The idea is to propagate
- // any special information we have about loads that can be replaced with
- // constants after complete unrolling, and account for likely simplifications
- // post-unrolling.
+ /// \brief SCEV expression corresponding to number of currently simulated
+ /// iteration.
+ const SCEV *IterationNumber;
+
+ /// \brief A Value->Constant map for keeping values that we managed to
+ /// constant-fold on the given iteration.
+ ///
+ /// While we walk the loop instructions, we build up and maintain a mapping
+ /// of simplified values specific to this iteration. The idea is to propagate
+ /// any special information we have about loads that can be replaced with
+ /// constants after complete unrolling, and account for likely simplifications
+ /// post-unrolling.
DenseMap<Value *, Constant *> &SimplifiedValues;
- // We use a cache to wrap all our SCEV queries.
- SCEVCache &SC;
+ const Loop *L;
+ ScalarEvolution &SE;
- /// Base case for the instruction visitor.
- bool visitInstruction(Instruction &I) { return false; };
+ /// \brief Try to simplify instruction \param I using its SCEV expression.
+ ///
+ /// The idea is that some AddRec expressions become constants, which then
+ /// could trigger folding of other instructions. However, that only happens
+ /// for expressions whose start value is also constant, which isn't always the
+ /// case. In another common and important case the start value is just some
+ /// address (i.e. SCEVUnknown) - in this case we compute the offset and save
+ /// it along with the base address instead.
+ bool simplifyInstWithSCEV(Instruction *I) {
+ if (!SE.isSCEVable(I->getType()))
+ return false;
+
+ const SCEV *S = SE.getSCEV(I);
+ if (auto *SC = dyn_cast<SCEVConstant>(S)) {
+ SimplifiedValues[I] = SC->getValue();
+ return true;
+ }
+
+ auto *AR = dyn_cast<SCEVAddRecExpr>(S);
+ if (!AR)
+ return false;
+
+ const SCEV *ValueAtIteration = AR->evaluateAtIteration(IterationNumber, SE);
+ // Check if the AddRec expression becomes a constant.
+ if (auto *SC = dyn_cast<SCEVConstant>(ValueAtIteration)) {
+ SimplifiedValues[I] = SC->getValue();
+ return true;
+ }
+
+ // Check if the offset from the base address becomes a constant.
+ auto *Base = dyn_cast<SCEVUnknown>(SE.getPointerBase(S));
+ if (!Base)
+ return false;
+ auto *Offset =
+ dyn_cast<SCEVConstant>(SE.getMinusSCEV(ValueAtIteration, Base));
+ if (!Offset)
+ return false;
+ SimplifiedAddress Address;
+ Address.Base = Base->getValue();
+ Address.Offset = Offset->getValue();
+ SimplifiedAddresses[I] = Address;
+ return true;
+ }
- /// TODO: Add visitors for other instruction types, e.g. ZExt, SExt.
+ /// Base case for the instruction visitor.
+ bool visitInstruction(Instruction &I) {
+ return simplifyInstWithSCEV(&I);
+ }
/// Try to simplify binary operator I.
///
- /// TODO: Probaly it's worth to hoist the code for estimating the
+ /// TODO: Probably it's worth to hoist the code for estimating the
/// simplifications effects to a separate class, since we have a very similar
/// code in InlineCost already.
bool visitBinaryOperator(BinaryOperator &I) {
if (!isa<Constant>(RHS))
if (Constant *SimpleRHS = SimplifiedValues.lookup(RHS))
RHS = SimpleRHS;
+
Value *SimpleV = nullptr;
const DataLayout &DL = I.getModule()->getDataLayout();
if (auto FI = dyn_cast<FPMathOperator>(&I))
if (Constant *C = dyn_cast_or_null<Constant>(SimpleV))
SimplifiedValues[&I] = C;
- return SimpleV;
+ if (SimpleV)
+ return true;
+ return Base::visitBinaryOperator(I);
}
/// Try to fold load I.
bool visitLoad(LoadInst &I) {
Value *AddrOp = I.getPointerOperand();
- if (!isa<Constant>(AddrOp))
- if (Constant *SimplifiedAddrOp = SimplifiedValues.lookup(AddrOp))
- AddrOp = SimplifiedAddrOp;
- auto *GEP = dyn_cast<GetElementPtrInst>(AddrOp);
- if (!GEP)
- return false;
- auto OptionalGEPDesc = SC.getGEPDescriptor(GEP);
- if (!OptionalGEPDesc)
+ auto AddressIt = SimplifiedAddresses.find(AddrOp);
+ if (AddressIt == SimplifiedAddresses.end())
return false;
+ ConstantInt *SimplifiedAddrOp = AddressIt->second.Offset;
- auto GV = dyn_cast<GlobalVariable>(OptionalGEPDesc->BaseAddr);
+ auto *GV = dyn_cast<GlobalVariable>(AddressIt->second.Base);
// We're only interested in loads that can be completely folded to a
// constant.
- if (!GV || !GV->hasInitializer())
+ if (!GV || !GV->hasDefinitiveInitializer() || !GV->isConstant())
return false;
ConstantDataSequential *CDS =
if (!CDS)
return false;
- // This calculation should never overflow because we bound Iteration quite
- // low and both the start and step are 32-bit integers. We use signed
- // integers so that UBSan will catch if a bug sneaks into the code.
int ElemSize = CDS->getElementType()->getPrimitiveSizeInBits() / 8U;
- int64_t Index = ((int64_t)OptionalGEPDesc->Start +
- (int64_t)OptionalGEPDesc->Step * (int64_t)Iteration) /
- ElemSize;
+ assert(SimplifiedAddrOp->getValue().getActiveBits() < 64 &&
+ "Unexpectedly large index value.");
+ int64_t Index = SimplifiedAddrOp->getSExtValue() / ElemSize;
if (Index >= CDS->getNumElements()) {
// FIXME: For now we conservatively ignore out of bound accesses, but
// we're allowed to perform the optimization in this case.
return true;
}
+
+ bool visitCastInst(CastInst &I) {
+ // Propagate constants through casts.
+ Constant *COp = dyn_cast<Constant>(I.getOperand(0));
+ if (!COp)
+ COp = SimplifiedValues.lookup(I.getOperand(0));
+ if (COp)
+ if (Constant *C =
+ ConstantExpr::getCast(I.getOpcode(), COp, I.getType())) {
+ SimplifiedValues[&I] = C;
+ return true;
+ }
+
+ return Base::visitCastInst(I);
+ }
+
+ bool visitCmpInst(CmpInst &I) {
+ Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
+
+ // First try to handle simplified comparisons.
+ if (!isa<Constant>(LHS))
+ if (Constant *SimpleLHS = SimplifiedValues.lookup(LHS))
+ LHS = SimpleLHS;
+ if (!isa<Constant>(RHS))
+ if (Constant *SimpleRHS = SimplifiedValues.lookup(RHS))
+ RHS = SimpleRHS;
+
+ if (!isa<Constant>(LHS) && !isa<Constant>(RHS)) {
+ auto SimplifiedLHS = SimplifiedAddresses.find(LHS);
+ if (SimplifiedLHS != SimplifiedAddresses.end()) {
+ auto SimplifiedRHS = SimplifiedAddresses.find(RHS);
+ if (SimplifiedRHS != SimplifiedAddresses.end()) {
+ SimplifiedAddress &LHSAddr = SimplifiedLHS->second;
+ SimplifiedAddress &RHSAddr = SimplifiedRHS->second;
+ if (LHSAddr.Base == RHSAddr.Base) {
+ LHS = LHSAddr.Offset;
+ RHS = RHSAddr.Offset;
+ }
+ }
+ }
+ }
+
+ if (Constant *CLHS = dyn_cast<Constant>(LHS)) {
+ if (Constant *CRHS = dyn_cast<Constant>(RHS)) {
+ if (Constant *C = ConstantExpr::getCompare(I.getPredicate(), CLHS, CRHS)) {
+ SimplifiedValues[&I] = C;
+ return true;
+ }
+ }
+ }
+
+ return Base::visitCmpInst(I);
+ }
};
} // namespace
namespace {
struct EstimatedUnrollCost {
/// \brief The estimated cost after unrolling.
- unsigned UnrolledCost;
+ int UnrolledCost;
/// \brief The estimated dynamic cost of executing the instructions in the
/// rolled form.
- unsigned RolledDynamicCost;
+ int RolledDynamicCost;
};
}
///
/// Complete loop unrolling can make some loads constant, and we need to know
/// if that would expose any further optimization opportunities. This routine
-/// estimates this optimization. It assigns computed number of instructions,
-/// that potentially might be optimized away, to
-/// NumberOfOptimizedInstructions, and total number of instructions to
-/// UnrolledLoopSize (not counting blocks that won't be reached, if we were
-/// able to compute the condition).
-/// \returns false if we can't analyze the loop, or if we discovered that
-/// unrolling won't give anything. Otherwise, returns true.
-Optional<EstimatedUnrollCost>
-analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, ScalarEvolution &SE,
- const TargetTransformInfo &TTI,
- unsigned MaxUnrolledLoopSize) {
+/// estimates this optimization. It computes cost of unrolled loop
+/// (UnrolledCost) and dynamic cost of the original loop (RolledDynamicCost). By
+/// dynamic cost we mean that we won't count costs of blocks that are known not
+/// to be executed (i.e. if we have a branch in the loop and we know that at the
+/// given iteration its condition would be resolved to true, we won't add up the
+/// cost of the 'false'-block).
+/// \returns Optional value, holding the RolledDynamicCost and UnrolledCost. If
+/// the analysis failed (no benefits expected from the unrolling, or the loop is
+/// too big to analyze), the returned value is None.
+static Optional<EstimatedUnrollCost>
+analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, DominatorTree &DT,
+ ScalarEvolution &SE, const TargetTransformInfo &TTI,
+ int MaxUnrolledLoopSize) {
// We want to be able to scale offsets by the trip count and add more offsets
// to them without checking for overflows, and we already don't want to
// analyze *massive* trip counts, so we force the max to be reasonably small.
SmallSetVector<BasicBlock *, 16> BBWorklist;
DenseMap<Value *, Constant *> SimplifiedValues;
-
- // Use a cache to access SCEV expressions so that we don't pay the cost on
- // each iteration. This cache is lazily self-populating.
- SCEVCache SC(*L, SE);
+ SmallVector<std::pair<Value *, Constant *>, 4> SimplifiedInputValues;
// The estimated cost of the unrolled form of the loop. We try to estimate
// this by simplifying as much as we can while computing the estimate.
- unsigned UnrolledCost = 0;
+ int UnrolledCost = 0;
// We also track the estimated dynamic (that is, actually executed) cost in
// the rolled form. This helps identify cases when the savings from unrolling
// aren't just exposing dead control flows, but actual reduced dynamic
// instructions due to the simplifications which we expect to occur after
// unrolling.
- unsigned RolledDynamicCost = 0;
+ int RolledDynamicCost = 0;
+
+ // Ensure that we don't violate the loop structure invariants relied on by
+ // this analysis.
+ assert(L->isLoopSimplifyForm() && "Must put loop into normal form first.");
+ assert(L->isLCSSAForm(DT) &&
+ "Must have loops in LCSSA form to track live-out values.");
+
+ DEBUG(dbgs() << "Starting LoopUnroll profitability analysis...\n");
// Simulate execution of each iteration of the loop counting instructions,
// which would be simplified.
// Since the same load will take different values on different iterations,
// we literally have to go through all loop's iterations.
for (unsigned Iteration = 0; Iteration < TripCount; ++Iteration) {
+ DEBUG(dbgs() << " Analyzing iteration " << Iteration << "\n");
+
+ // Prepare for the iteration by collecting any simplified entry or backedge
+ // inputs.
+ for (Instruction &I : *L->getHeader()) {
+ auto *PHI = dyn_cast<PHINode>(&I);
+ if (!PHI)
+ break;
+
+ // The loop header PHI nodes must have exactly two input: one from the
+ // loop preheader and one from the loop latch.
+ assert(
+ PHI->getNumIncomingValues() == 2 &&
+ "Must have an incoming value only for the preheader and the latch.");
+
+ Value *V = PHI->getIncomingValueForBlock(
+ Iteration == 0 ? L->getLoopPreheader() : L->getLoopLatch());
+ Constant *C = dyn_cast<Constant>(V);
+ if (Iteration != 0 && !C)
+ C = SimplifiedValues.lookup(V);
+ if (C)
+ SimplifiedInputValues.push_back({PHI, C});
+ }
+
+ // Now clear and re-populate the map for the next iteration.
SimplifiedValues.clear();
- UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, SC);
+ while (!SimplifiedInputValues.empty())
+ SimplifiedValues.insert(SimplifiedInputValues.pop_back_val());
+
+ UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, L, SE);
BBWorklist.clear();
BBWorklist.insert(L->getHeader());
// it. We don't change the actual IR, just count optimization
// opportunities.
for (Instruction &I : *BB) {
- unsigned InstCost = TTI.getUserCost(&I);
+ int InstCost = TTI.getUserCost(&I);
// Visit the instruction to analyze its loop cost after unrolling,
// and if the visitor returns false, include this instruction in the
// unrolled cost.
if (!Analyzer.visit(I))
UnrolledCost += InstCost;
+ else {
+ DEBUG(dbgs() << " " << I
+ << " would be simplified if loop is unrolled.\n");
+ (void)0;
+ }
// Also track this instructions expected cost when executing the rolled
// loop form.
RolledDynamicCost += InstCost;
// If unrolled body turns out to be too big, bail out.
- if (UnrolledCost > MaxUnrolledLoopSize)
+ if (UnrolledCost > MaxUnrolledLoopSize) {
+ DEBUG(dbgs() << " Exceeded threshold.. exiting.\n"
+ << " UnrolledCost: " << UnrolledCost
+ << ", MaxUnrolledLoopSize: " << MaxUnrolledLoopSize
+ << "\n");
return None;
+ }
+ }
+
+ TerminatorInst *TI = BB->getTerminator();
+
+ // Add in the live successors by first checking whether we have terminator
+ // that may be simplified based on the values simplified by this call.
+ if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
+ if (BI->isConditional()) {
+ if (Constant *SimpleCond =
+ SimplifiedValues.lookup(BI->getCondition())) {
+ BasicBlock *Succ = nullptr;
+ // Just take the first successor if condition is undef
+ if (isa<UndefValue>(SimpleCond))
+ Succ = BI->getSuccessor(0);
+ else
+ Succ = BI->getSuccessor(
+ cast<ConstantInt>(SimpleCond)->isZero() ? 1 : 0);
+ if (L->contains(Succ))
+ BBWorklist.insert(Succ);
+ continue;
+ }
+ }
+ } else if (SwitchInst *SI = dyn_cast<SwitchInst>(TI)) {
+ if (Constant *SimpleCond =
+ SimplifiedValues.lookup(SI->getCondition())) {
+ BasicBlock *Succ = nullptr;
+ // Just take the first successor if condition is undef
+ if (isa<UndefValue>(SimpleCond))
+ Succ = SI->getSuccessor(0);
+ else
+ Succ = SI->findCaseValue(cast<ConstantInt>(SimpleCond))
+ .getCaseSuccessor();
+ if (L->contains(Succ))
+ BBWorklist.insert(Succ);
+ continue;
+ }
}
// Add BB's successors to the worklist.
// If we found no optimization opportunities on the first iteration, we
// won't find them on later ones too.
- if (UnrolledCost == RolledDynamicCost)
+ if (UnrolledCost == RolledDynamicCost) {
+ DEBUG(dbgs() << " No opportunities found.. exiting.\n"
+ << " UnrolledCost: " << UnrolledCost << "\n");
return None;
+ }
}
+ DEBUG(dbgs() << "Analysis finished:\n"
+ << "UnrolledCost: " << UnrolledCost << ", "
+ << "RolledDynamicCost: " << RolledDynamicCost << "\n");
return {{UnrolledCost, RolledDynamicCost}};
}
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.full");
}
+// Returns true if the loop has an unroll(enable) pragma. This metadata is used
+// for both "#pragma unroll" and "#pragma clang loop unroll(enable)" directives.
+static bool HasUnrollEnablePragma(const Loop *L) {
+ return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.enable");
+}
+
// Returns true if the loop has an unroll(disable) pragma.
static bool HasUnrollDisablePragma(const Loop *L) {
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.disable");
bool LoopUnroll::canUnrollCompletely(Loop *L, unsigned Threshold,
unsigned PercentDynamicCostSavedThreshold,
unsigned DynamicCostSavingsDiscount,
- unsigned UnrolledCost,
- unsigned RolledDynamicCost) {
+ uint64_t UnrolledCost,
+ uint64_t RolledDynamicCost) {
if (Threshold == NoThreshold) {
DEBUG(dbgs() << " Can fully unroll, because no threshold is set.\n");
unsigned Count = UserCount ? CurrentCount : 0;
// If there is no user-specified count, unroll pragmas have the next
- // highest precendence.
+ // highest precedence.
if (Count == 0) {
if (PragmaCount) {
Count = PragmaCount;
Function &F = *L->getHeader()->getParent();
+ auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
- ScalarEvolution *SE = &getAnalysis<ScalarEvolution>();
+ ScalarEvolution *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
const TargetTransformInfo &TTI =
getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
return false;
}
bool PragmaFullUnroll = HasUnrollFullPragma(L);
+ bool PragmaEnableUnroll = HasUnrollEnablePragma(L);
unsigned PragmaCount = UnrollCountPragmaValue(L);
- bool HasPragma = PragmaFullUnroll || PragmaCount > 0;
+ bool HasPragma = PragmaFullUnroll || PragmaEnableUnroll || PragmaCount > 0;
TargetTransformInfo::UnrollingPreferences UP;
getUnrollingPreferences(L, TTI, UP);
unsigned Threshold, PartialThreshold;
unsigned PercentDynamicCostSavedThreshold;
unsigned DynamicCostSavingsDiscount;
- selectThresholds(L, HasPragma, UP, Threshold, PartialThreshold,
+ // Only use the high pragma threshold when we have a target unroll factor such
+ // as with "#pragma unroll N" or a pragma indicating full unrolling and the
+ // trip count is known. Otherwise we rely on the standard threshold to
+ // heuristically select a reasonable unroll count.
+ bool UsePragmaThreshold =
+ PragmaCount > 0 ||
+ ((PragmaFullUnroll || PragmaEnableUnroll) && TripCount != 0);
+
+ selectThresholds(L, UsePragmaThreshold, UP, Threshold, PartialThreshold,
PercentDynamicCostSavedThreshold,
DynamicCostSavingsDiscount);
// The loop isn't that small, but we still can fully unroll it if that
// helps to remove a significant number of instructions.
// To check that, run additional analysis on the loop.
- if (Optional<EstimatedUnrollCost> Cost = analyzeLoopUnrollCost(
- L, TripCount, *SE, TTI, Threshold + DynamicCostSavingsDiscount))
+ if (Optional<EstimatedUnrollCost> Cost =
+ analyzeLoopUnrollCost(L, TripCount, DT, *SE, TTI,
+ Threshold + DynamicCostSavingsDiscount))
if (canUnrollCompletely(L, Threshold, PercentDynamicCostSavedThreshold,
DynamicCostSavingsDiscount, Cost->UnrolledCost,
Cost->RolledDynamicCost)) {
// Reduce count based on the type of unrolling and the threshold values.
unsigned OriginalCount = Count;
- bool AllowRuntime = UserRuntime ? CurrentRuntime : UP.Runtime;
- if (HasRuntimeUnrollDisablePragma(L)) {
+ bool AllowRuntime = PragmaEnableUnroll || (PragmaCount > 0) ||
+ (UserRuntime ? CurrentRuntime : UP.Runtime);
+ // Don't unroll a runtime trip count loop with unroll full pragma.
+ if (HasRuntimeUnrollDisablePragma(L) || PragmaFullUnroll) {
AllowRuntime = false;
}
if (Unrolling == Partial) {
- bool AllowPartial = UserAllowPartial ? CurrentAllowPartial : UP.Partial;
+ bool AllowPartial = PragmaEnableUnroll ||
+ (UserAllowPartial ? CurrentAllowPartial : UP.Partial);
if (!AllowPartial && !CountSetExplicitly) {
DEBUG(dbgs() << " will not try to unroll partially because "
<< "-unroll-allow-partial not given\n");
DebugLoc LoopLoc = L->getStartLoc();
Function *F = Header->getParent();
LLVMContext &Ctx = F->getContext();
- if (PragmaFullUnroll && PragmaCount == 0) {
- if (TripCount && Count != TripCount) {
- emitOptimizationRemarkMissed(
- Ctx, DEBUG_TYPE, *F, LoopLoc,
- "Unable to fully unroll loop as directed by unroll(full) pragma "
- "because unrolled size is too large.");
- } else if (!TripCount) {
- emitOptimizationRemarkMissed(
- Ctx, DEBUG_TYPE, *F, LoopLoc,
- "Unable to fully unroll loop as directed by unroll(full) pragma "
- "because loop has a runtime trip count.");
- }
- } else if (PragmaCount > 0 && Count != OriginalCount) {
+ if ((PragmaCount > 0) && Count != OriginalCount) {
emitOptimizationRemarkMissed(
Ctx, DEBUG_TYPE, *F, LoopLoc,
"Unable to unroll loop the number of times directed by "
"unroll_count pragma because unrolled size is too large.");
+ } else if (PragmaFullUnroll && !TripCount) {
+ emitOptimizationRemarkMissed(
+ Ctx, DEBUG_TYPE, *F, LoopLoc,
+ "Unable to fully unroll loop as directed by unroll(full) pragma "
+ "because loop has a runtime trip count.");
+ } else if (PragmaEnableUnroll && Count != TripCount && Count < 2) {
+ emitOptimizationRemarkMissed(
+ Ctx, DEBUG_TYPE, *F, LoopLoc,
+ "Unable to unroll loop as directed by unroll(enable) pragma because "
+ "unrolled size is too large.");
+ } else if ((PragmaFullUnroll || PragmaEnableUnroll) && TripCount &&
+ Count != TripCount) {
+ emitOptimizationRemarkMissed(
+ Ctx, DEBUG_TYPE, *F, LoopLoc,
+ "Unable to fully unroll loop as directed by unroll pragma because "
+ "unrolled size is too large.");
}
}