///
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<AssumptionCacheTracker>();
+ AU.addRequired<DominatorTreeWrapperPass>();
AU.addRequired<LoopInfoWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addRequiredID(LoopSimplifyID);
: UP.DynamicCostSavingsDiscount;
if (!UserThreshold &&
+ // FIXME: Use Function::optForSize().
L->getHeader()->getParent()->hasFnAttribute(
Attribute::OptimizeForSize)) {
Threshold = UP.OptSizeThreshold;
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)
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;
};
}
/// the analysis failed (no benefits expected from the unrolling, or the loop is
/// too big to analyze), the returned value is None.
Optional<EstimatedUnrollCost>
-analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, ScalarEvolution &SE,
- const TargetTransformInfo &TTI,
- unsigned MaxUnrolledLoopSize) {
+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;
+ 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();
+ while (!SimplifiedInputValues.empty())
+ SimplifiedValues.insert(SimplifiedInputValues.pop_back_val());
+
UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, L, SE);
BBWorklist.clear();
// 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();
if (BI->isConditional()) {
if (Constant *SimpleCond =
SimplifiedValues.lookup(BI->getCondition())) {
- BasicBlock *Succ = BI->getSuccessor(
- cast<ConstantInt>(SimpleCond)->isZero() ? 1 : 0);
+ 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 =
- SI->getSuccessor(cast<ConstantInt>(SimpleCond)->getSExtValue());
+ 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;
// 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}};
}
Function &F = *L->getHeader()->getParent();
+ auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
ScalarEvolution *SE = &getAnalysis<ScalarEvolution>();
const TargetTransformInfo &TTI =
// 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)) {
projects / oota-llvm.git / blobdiff