//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Scalar.h"
+#include "llvm/ADT/SetVector.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/CodeMetrics.h"
+#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/ScalarEvolution.h"
+#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/Dominators.h"
+#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Metadata.h"
#include "llvm/Support/CommandLine.h"
UnrollThreshold("unroll-threshold", cl::init(150), cl::Hidden,
cl::desc("The cut-off point for automatic loop unrolling"));
+static cl::opt<unsigned> UnrollMaxIterationsCountToAnalyze(
+ "unroll-max-iteration-count-to-analyze", cl::init(0), cl::Hidden,
+ cl::desc("Don't allow loop unrolling to simulate more than this number of"
+ "iterations when checking full unroll profitability"));
+
+static cl::opt<unsigned> UnrollMinPercentOfOptimized(
+ "unroll-percent-of-optimized-for-complete-unroll", cl::init(20), cl::Hidden,
+ cl::desc("If complete unrolling could trigger further optimizations, and, "
+ "by that, remove the given percent of instructions, perform the "
+ "complete unroll even if it's beyond the threshold"));
+
+static cl::opt<unsigned> UnrollAbsoluteThreshold(
+ "unroll-absolute-threshold", cl::init(2000), cl::Hidden,
+ cl::desc("Don't unroll if the unrolled size is bigger than this threshold,"
+ " even if we can remove big portion of instructions later."));
+
static cl::opt<unsigned>
UnrollCount("unroll-count", cl::init(0), cl::Hidden,
cl::desc("Use this unroll count for all loops including those with "
static char ID; // Pass ID, replacement for typeid
LoopUnroll(int T = -1, int C = -1, int P = -1, int R = -1) : LoopPass(ID) {
CurrentThreshold = (T == -1) ? UnrollThreshold : unsigned(T);
+ CurrentAbsoluteThreshold = UnrollAbsoluteThreshold;
+ CurrentMinPercentOfOptimized = UnrollMinPercentOfOptimized;
CurrentCount = (C == -1) ? UnrollCount : unsigned(C);
CurrentAllowPartial = (P == -1) ? UnrollAllowPartial : (bool)P;
CurrentRuntime = (R == -1) ? UnrollRuntime : (bool)R;
UserThreshold = (T != -1) || (UnrollThreshold.getNumOccurrences() > 0);
+ UserAbsoluteThreshold = (UnrollAbsoluteThreshold.getNumOccurrences() > 0);
+ UserPercentOfOptimized =
+ (UnrollMinPercentOfOptimized.getNumOccurrences() > 0);
UserAllowPartial = (P != -1) ||
(UnrollAllowPartial.getNumOccurrences() > 0);
UserRuntime = (R != -1) || (UnrollRuntime.getNumOccurrences() > 0);
unsigned CurrentCount;
unsigned CurrentThreshold;
+ unsigned CurrentAbsoluteThreshold;
+ unsigned CurrentMinPercentOfOptimized;
bool CurrentAllowPartial;
bool CurrentRuntime;
bool UserCount; // CurrentCount is user-specified.
bool UserThreshold; // CurrentThreshold is user-specified.
+ bool UserAbsoluteThreshold; // CurrentAbsoluteThreshold is
+ // user-specified.
+ bool UserPercentOfOptimized; // CurrentMinPercentOfOptimized is
+ // user-specified.
bool UserAllowPartial; // CurrentAllowPartial is user-specified.
bool UserRuntime; // CurrentRuntime is user-specified.
void getUnrollingPreferences(Loop *L, const TargetTransformInfo &TTI,
TargetTransformInfo::UnrollingPreferences &UP) {
UP.Threshold = CurrentThreshold;
+ UP.AbsoluteThreshold = CurrentAbsoluteThreshold;
+ UP.MinPercentOfOptimized = CurrentMinPercentOfOptimized;
UP.OptSizeThreshold = OptSizeUnrollThreshold;
UP.PartialThreshold = CurrentThreshold;
UP.PartialOptSizeThreshold = OptSizeUnrollThreshold;
// unrolled loops respectively.
void selectThresholds(const Loop *L, bool HasPragma,
const TargetTransformInfo::UnrollingPreferences &UP,
- unsigned &Threshold, unsigned &PartialThreshold) {
+ unsigned &Threshold, unsigned &PartialThreshold,
+ unsigned NumberOfOptimizedInstructions) {
// Determine the current unrolling threshold. While this is
// normally set from UnrollThreshold, it is overridden to a
// smaller value if the current function is marked as
// optimize-for-size, and the unroll threshold was not user
// specified.
Threshold = UserThreshold ? CurrentThreshold : UP.Threshold;
+
+ // If we are allowed to completely unroll if we can remove M% of
+ // instructions, and we know that with complete unrolling we'll be able
+ // to kill N instructions, then we can afford to completely unroll loops
+ // with unrolled size up to N*100/M.
+ // Adjust the threshold according to that:
+ unsigned PercentOfOptimizedForCompleteUnroll =
+ UserPercentOfOptimized ? CurrentMinPercentOfOptimized
+ : UP.MinPercentOfOptimized;
+ unsigned AbsoluteThreshold = UserAbsoluteThreshold
+ ? CurrentAbsoluteThreshold
+ : UP.AbsoluteThreshold;
+ if (PercentOfOptimizedForCompleteUnroll)
+ Threshold = std::max<unsigned>(Threshold,
+ NumberOfOptimizedInstructions * 100 /
+ PercentOfOptimizedForCompleteUnroll);
+ // But don't allow unrolling loops bigger than absolute threshold.
+ Threshold = std::min<unsigned>(Threshold, AbsoluteThreshold);
+
PartialThreshold = UserThreshold ? CurrentThreshold : UP.PartialThreshold;
if (!UserThreshold &&
- L->getHeader()->getParent()->getAttributes().
- hasAttribute(AttributeSet::FunctionIndex,
- Attribute::OptimizeForSize)) {
+ L->getHeader()->getParent()->hasFnAttribute(
+ Attribute::OptimizeForSize)) {
Threshold = UP.OptSizeThreshold;
PartialThreshold = UP.PartialOptSizeThreshold;
}
return llvm::createLoopUnrollPass(-1, -1, 0, 0);
}
+static bool isLoadFromConstantInitializer(Value *V) {
+ if (GlobalVariable *GV = dyn_cast<GlobalVariable>(V))
+ if (GV->isConstant() && GV->hasDefinitiveInitializer())
+ return GV->getInitializer();
+ return false;
+}
+
+namespace {
+struct FindConstantPointers {
+ bool LoadCanBeConstantFolded;
+ bool IndexIsConstant;
+ APInt Step;
+ APInt StartValue;
+ Value *BaseAddress;
+ const Loop *L;
+ ScalarEvolution &SE;
+ FindConstantPointers(const Loop *loop, ScalarEvolution &SE)
+ : LoadCanBeConstantFolded(true), IndexIsConstant(true), L(loop), SE(SE) {}
+
+ 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. Now it's time to see if it corresponds to a global constant
+ // global (in which case we can eliminate the load), or not.
+ BaseAddress = SC->getValue();
+ LoadCanBeConstantFolded =
+ IndexIsConstant && isLoadFromConstantInitializer(BaseAddress);
+ return false;
+ }
+ if (isa<SCEVConstant>(S))
+ return true;
+ 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)
+ return IndexIsConstant = false;
+ // If the step isn't constant, we won't get constant addresses in unrolled
+ // version. Bail out.
+ if (const SCEVConstant *StepSE =
+ dyn_cast<SCEVConstant>(AR->getStepRecurrence(SE)))
+ Step = StepSE->getValue()->getValue();
+ else
+ return IndexIsConstant = false;
+
+ return IndexIsConstant;
+ }
+ // If Result is true, continue traversal.
+ // Otherwise, we have found something that prevents us from (possible) load
+ // elimination.
+ return IndexIsConstant;
+ }
+ bool isDone() const { return !IndexIsConstant; }
+};
+
+// 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
+// loads might be replaced with concrete constant values and that could trigger
+// a chain of instruction simplifications.
+//
+// E.g. we might have:
+// int a[] = {0, 1, 0};
+// v = 0;
+// for (i = 0; i < 3; i ++)
+// v += b[i]*a[i];
+// If we completely unroll the loop, we would get:
+// v = b[0]*a[0] + b[1]*a[1] + b[2]*a[2]
+// Which then will be simplified to:
+// v = b[0]* 0 + b[1]* 1 + b[2]* 0
+// And finally:
+// v = b[1]
+class UnrollAnalyzer : public InstVisitor<UnrollAnalyzer, bool> {
+ typedef InstVisitor<UnrollAnalyzer, bool> Base;
+ friend class InstVisitor<UnrollAnalyzer, bool>;
+
+ const Loop *L;
+ unsigned TripCount;
+ ScalarEvolution &SE;
+ const TargetTransformInfo &TTI;
+
+ DenseMap<Value *, Constant *> SimplifiedValues;
+ DenseMap<LoadInst *, Value *> LoadBaseAddresses;
+ SmallPtrSet<Instruction *, 32> CountedInstructions;
+
+ /// \brief Count the number of optimized instructions.
+ unsigned NumberOfOptimizedInstructions;
+
+ // Provide base case for our instruction visit.
+ bool visitInstruction(Instruction &I) { return false; };
+ // TODO: We should also visit ICmp, FCmp, GetElementPtr, Trunc, ZExt, SExt,
+ // FPTrunc, FPExt, FPToUI, FPToSI, UIToFP, SIToFP, BitCast, Select,
+ // ExtractElement, InsertElement, ShuffleVector, ExtractValue, InsertValue.
+ //
+ // Probaly 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) {
+ Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
+ if (!isa<Constant>(LHS))
+ if (Constant *SimpleLHS = SimplifiedValues.lookup(LHS))
+ LHS = SimpleLHS;
+ 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))
+ SimpleV =
+ SimplifyFPBinOp(I.getOpcode(), LHS, RHS, FI->getFastMathFlags(), DL);
+ else
+ SimpleV = SimplifyBinOp(I.getOpcode(), LHS, RHS, DL);
+
+ if (SimpleV && CountedInstructions.insert(&I).second)
+ NumberOfOptimizedInstructions += TTI.getUserCost(&I);
+
+ if (Constant *C = dyn_cast_or_null<Constant>(SimpleV)) {
+ SimplifiedValues[&I] = C;
+ return true;
+ }
+ return false;
+ }
+
+ Constant *computeLoadValue(LoadInst *LI, unsigned Iteration) {
+ if (!LI)
+ return nullptr;
+ Value *BaseAddr = LoadBaseAddresses[LI];
+ if (!BaseAddr)
+ return nullptr;
+
+ auto GV = dyn_cast<GlobalVariable>(BaseAddr);
+ if (!GV)
+ return nullptr;
+
+ ConstantDataSequential *CDS =
+ dyn_cast<ConstantDataSequential>(GV->getInitializer());
+ if (!CDS)
+ return nullptr;
+
+ const SCEV *BaseAddrSE = SE.getSCEV(BaseAddr);
+ const SCEV *S = SE.getSCEV(LI->getPointerOperand());
+ const SCEV *OffSE = SE.getMinusSCEV(S, BaseAddrSE);
+
+ APInt StepC, StartC;
+ const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(OffSE);
+ if (!AR)
+ return nullptr;
+
+ if (const SCEVConstant *StepSE =
+ dyn_cast<SCEVConstant>(AR->getStepRecurrence(SE)))
+ StepC = StepSE->getValue()->getValue();
+ else
+ return nullptr;
+
+ if (const SCEVConstant *StartSE = dyn_cast<SCEVConstant>(AR->getStart()))
+ StartC = StartSE->getValue()->getValue();
+ else
+ return nullptr;
+
+ unsigned ElemSize = CDS->getElementType()->getPrimitiveSizeInBits() / 8U;
+ unsigned Start = StartC.getLimitedValue();
+ unsigned Step = StepC.getLimitedValue();
+
+ unsigned Index = (Start + Step * Iteration) / ElemSize;
+ if (Index >= CDS->getNumElements())
+ return nullptr;
+
+ Constant *CV = CDS->getElementAsConstant(Index);
+
+ return CV;
+ }
+
+public:
+ UnrollAnalyzer(const Loop *L, unsigned TripCount, ScalarEvolution &SE,
+ const TargetTransformInfo &TTI)
+ : L(L), TripCount(TripCount), SE(SE), TTI(TTI),
+ NumberOfOptimizedInstructions(0) {}
+
+ // Visit all loads the loop L, and for those that, after complete loop
+ // unrolling, would have a constant address and it will point to a known
+ // constant initializer, record its base address for future use. It is used
+ // when we estimate number of potentially simplified instructions.
+ void findConstFoldableLoads() {
+ for (auto BB : L->getBlocks()) {
+ for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
+ if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
+ if (!LI->isSimple())
+ continue;
+ Value *AddrOp = LI->getPointerOperand();
+ const SCEV *S = SE.getSCEV(AddrOp);
+ FindConstantPointers Visitor(L, SE);
+ SCEVTraversal<FindConstantPointers> T(Visitor);
+ T.visitAll(S);
+ if (Visitor.IndexIsConstant && Visitor.LoadCanBeConstantFolded) {
+ LoadBaseAddresses[LI] = Visitor.BaseAddress;
+ }
+ }
+ }
+ }
+ }
+
+ // Given a list of loads that could be constant-folded (LoadBaseAddresses),
+ // estimate number of optimized instructions after substituting the concrete
+ // values for the given Iteration. Also track how many instructions become
+ // dead through this process.
+ unsigned estimateNumberOfOptimizedInstructions(unsigned Iteration) {
+ // We keep a set vector for the worklist so that we don't wast space in the
+ // worklist queuing up the same instruction repeatedly. This can happen due
+ // to multiple operands being the same instruction or due to the same
+ // instruction being an operand of lots of things that end up dead or
+ // simplified.
+ SmallSetVector<Instruction *, 8> Worklist;
+
+ // Clear the simplified values and counts for this iteration.
+ SimplifiedValues.clear();
+ CountedInstructions.clear();
+ NumberOfOptimizedInstructions = 0;
+
+ // We start by adding all loads to the worklist.
+ for (auto &LoadDescr : LoadBaseAddresses) {
+ LoadInst *LI = LoadDescr.first;
+ SimplifiedValues[LI] = computeLoadValue(LI, Iteration);
+ if (CountedInstructions.insert(LI).second)
+ NumberOfOptimizedInstructions += TTI.getUserCost(LI);
+
+ for (User *U : LI->users())
+ Worklist.insert(cast<Instruction>(U));
+ }
+
+ // And then we try to simplify every user of every instruction from the
+ // worklist. If we do simplify a user, add it to the worklist to process
+ // its users as well.
+ while (!Worklist.empty()) {
+ Instruction *I = Worklist.pop_back_val();
+ if (!L->contains(I))
+ continue;
+ if (!visit(I))
+ continue;
+ for (User *U : I->users())
+ Worklist.insert(cast<Instruction>(U));
+ }
+
+ // Now that we know the potentially simplifed instructions, estimate number
+ // of instructions that would become dead if we do perform the
+ // simplification.
+
+ // The dead instructions are held in a separate set. This is used to
+ // prevent us from re-examining instructions and make sure we only count
+ // the benifit once. The worklist's internal set handles insertion
+ // deduplication.
+ SmallPtrSet<Instruction *, 16> DeadInstructions;
+
+ // Lambda to enque operands onto the worklist.
+ auto EnqueueOperands = [&](Instruction &I) {
+ for (auto *Op : I.operand_values())
+ if (auto *OpI = dyn_cast<Instruction>(Op))
+ if (!OpI->use_empty())
+ Worklist.insert(OpI);
+ };
+
+ // Start by initializing worklist with simplified instructions.
+ for (auto &FoldedKeyValue : SimplifiedValues)
+ if (auto *FoldedInst = dyn_cast<Instruction>(FoldedKeyValue.first)) {
+ DeadInstructions.insert(FoldedInst);
+
+ // Add each instruction operand of this dead instruction to the
+ // worklist.
+ EnqueueOperands(*FoldedInst);
+ }
+
+ // If a definition of an insn is only used by simplified or dead
+ // instructions, it's also dead. Check defs of all instructions from the
+ // worklist.
+ while (!Worklist.empty()) {
+ Instruction *I = Worklist.pop_back_val();
+ if (!L->contains(I))
+ continue;
+ if (DeadInstructions.count(I))
+ continue;
+
+ if (std::all_of(I->user_begin(), I->user_end(), [&](User *U) {
+ return DeadInstructions.count(cast<Instruction>(U));
+ })) {
+ NumberOfOptimizedInstructions += TTI.getUserCost(I);
+ DeadInstructions.insert(I);
+ EnqueueOperands(*I);
+ }
+ }
+ return NumberOfOptimizedInstructions;
+ }
+};
+} // namespace
+
+// 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 effect and returns the number of
+// instructions, that potentially might be optimized away.
+static unsigned
+approximateNumberOfOptimizedInstructions(const Loop *L, ScalarEvolution &SE,
+ unsigned TripCount,
+ const TargetTransformInfo &TTI) {
+ if (!TripCount || !UnrollMaxIterationsCountToAnalyze)
+ return 0;
+
+ UnrollAnalyzer UA(L, TripCount, SE, TTI);
+ UA.findConstFoldableLoads();
+
+ // Estimate number of instructions, that could be simplified if we replace a
+ // load with the corresponding constant. Since the same load will take
+ // different values on different iterations, we have to go through all loop's
+ // iterations here. To limit ourselves here, we check only first N
+ // iterations, and then scale the found number, if necessary.
+ unsigned IterationsNumberForEstimate =
+ std::min<unsigned>(UnrollMaxIterationsCountToAnalyze, TripCount);
+ unsigned NumberOfOptimizedInstructions = 0;
+ for (unsigned i = 0; i < IterationsNumberForEstimate; ++i)
+ NumberOfOptimizedInstructions +=
+ UA.estimateNumberOfOptimizedInstructions(i);
+
+ NumberOfOptimizedInstructions *= TripCount / IterationsNumberForEstimate;
+
+ return NumberOfOptimizedInstructions;
+}
+
/// ApproximateLoopSize - Approximate the size of the loop.
static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
bool &NotDuplicatable,
// Returns the loop hint metadata node with the given name (for example,
// "llvm.loop.unroll.count"). If no such metadata node exists, then nullptr is
// returned.
-static const MDNode *GetUnrollMetadataForLoop(const Loop *L, StringRef Name) {
- MDNode *LoopID = L->getLoopID();
- if (!LoopID)
- return nullptr;
- return GetUnrollMetadata(LoopID, Name);
+static MDNode *GetUnrollMetadataForLoop(const Loop *L, StringRef Name) {
+ if (MDNode *LoopID = L->getLoopID())
+ return GetUnrollMetadata(LoopID, Name);
+ return nullptr;
}
// Returns true if the loop has an unroll(full) pragma.
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.disable");
}
+// Returns true if the loop has an runtime unroll(disable) pragma.
+static bool HasRuntimeUnrollDisablePragma(const Loop *L) {
+ return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.runtime.disable");
+}
+
// If loop has an unroll_count pragma return the (necessarily
// positive) value from the pragma. Otherwise return 0.
static unsigned UnrollCountPragmaValue(const Loop *L) {
- const MDNode *MD = GetUnrollMetadataForLoop(L, "llvm.loop.unroll.count");
+ MDNode *MD = GetUnrollMetadataForLoop(L, "llvm.loop.unroll.count");
if (MD) {
assert(MD->getNumOperands() == 2 &&
"Unroll count hint metadata should have two operands.");
return false;
}
+ unsigned NumberOfOptimizedInstructions =
+ approximateNumberOfOptimizedInstructions(L, *SE, TripCount, TTI);
+ DEBUG(dbgs() << " Complete unrolling could save: "
+ << NumberOfOptimizedInstructions << "\n");
+
unsigned Threshold, PartialThreshold;
- selectThresholds(L, HasPragma, UP, Threshold, PartialThreshold);
+ selectThresholds(L, HasPragma, UP, Threshold, PartialThreshold,
+ NumberOfOptimizedInstructions);
// Given Count, TripCount and thresholds determine the type of
// unrolling which is to be performed.
// Reduce count based on the type of unrolling and the threshold values.
unsigned OriginalCount = Count;
bool AllowRuntime = UserRuntime ? CurrentRuntime : UP.Runtime;
+ if (HasRuntimeUnrollDisablePragma(L)) {
+ AllowRuntime = false;
+ }
if (Unrolling == Partial) {
bool AllowPartial = UserAllowPartial ? CurrentAllowPartial : UP.Partial;
if (!AllowPartial && !CountSetExplicitly) {