bool
CostModelAnalysis::runOnFunction(Function &F) {
this->F = &F;
// Target information.
TargetTransformInfo *TTI;
TTI = getAnalysisIfAvailable<TargetTransformInfo>();
if (TTI)
VTTI = TTI->getVectorTargetTransformInfo();
return false;
}
static bool canSplitCallSite(CallSite CS, TargetTransformInfo &TTI) {
// FIXME: As of now we handle only CallInst. InvokeInst could be handled
// without too much effort.
Instruction *Instr = CS.getInstruction();
if (!isa<CallInst>(Instr))
return false;
BasicBlock *CallSiteBB = Instr->getParent();
// Allow splitting a call-site only when the CodeSize cost of the
// instructions before the call is less then DuplicationThreshold. The
// instructions before the call will be duplicated in the split blocks and
// corresponding uses will be updated.
unsigned Cost = 0;
for (auto &InstBeforeCall :
llvm::make_range(CallSiteBB->begin(), Instr->getIterator())) {
Cost += TTI.getInstructionCost(&InstBeforeCall,
TargetTransformInfo::TCK_CodeSize);
if (Cost >= DuplicationThreshold)
return false;
}
// Need 2 predecessors and cannot split an edge from an IndirectBrInst.
SmallVector<BasicBlock *, 2> Preds(predecessors(CallSiteBB));
if (Preds.size() != 2 || isa<IndirectBrInst>(Preds[0]->getTerminator()) ||
isa<IndirectBrInst>(Preds[1]->getTerminator()))
return false;
return CallSiteBB->canSplitPredecessors();
}
static unsigned ComputeSpeculationCost(const Instruction *I,
const TargetTransformInfo &TTI) {
switch (Operator::getOpcode(I)) {
case Instruction::GetElementPtr:
case Instruction::Add:
case Instruction::Mul:
case Instruction::And:
case Instruction::Or:
case Instruction::Select:
case Instruction::Shl:
case Instruction::Sub:
case Instruction::LShr:
case Instruction::AShr:
case Instruction::Xor:
case Instruction::ZExt:
case Instruction::SExt:
case Instruction::Call:
case Instruction::BitCast:
case Instruction::PtrToInt:
case Instruction::IntToPtr:
case Instruction::AddrSpaceCast:
case Instruction::FPToUI:
case Instruction::FPToSI:
case Instruction::UIToFP:
case Instruction::SIToFP:
case Instruction::FPExt:
case Instruction::FPTrunc:
case Instruction::FAdd:
case Instruction::FSub:
case Instruction::FMul:
case Instruction::FDiv:
case Instruction::FRem:
case Instruction::ICmp:
case Instruction::FCmp:
return TTI.getUserCost(I);
default:
return UINT_MAX; // Disallow anything not whitelisted.
}
}
static unsigned ComputeSpeculationCost(const Instruction *I,
const TargetTransformInfo &TTI) {
switch (Operator::getOpcode(I)) {
case Instruction::GetElementPtr:
case Instruction::Add:
case Instruction::Mul:
case Instruction::And:
case Instruction::Or:
case Instruction::Select:
case Instruction::Shl:
case Instruction::Sub:
case Instruction::LShr:
case Instruction::AShr:
case Instruction::Xor:
case Instruction::ZExt:
case Instruction::SExt:
return TTI.getUserCost(I);
default:
return UINT_MAX; // Disallow anything not whitelisted.
}
}
/// \brief Figure out if the loop is worth full unrolling.
///
/// 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 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.
Optional<EstimatedUnrollCost>
analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, ScalarEvolution &SE,
const TargetTransformInfo &TTI,
unsigned 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.
assert(UnrollMaxIterationsCountToAnalyze < (INT_MAX / 2) &&
"The unroll iterations max is too large!");
// Don't simulate loops with a big or unknown tripcount
if (!UnrollMaxIterationsCountToAnalyze || !TripCount ||
TripCount > UnrollMaxIterationsCountToAnalyze)
return None;
SmallSetVector<BasicBlock *, 16> BBWorklist;
DenseMap<Value *, Constant *> SimplifiedValues;
// 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;
// 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;
// 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) {
SimplifiedValues.clear();
UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, L, SE);
BBWorklist.clear();
BBWorklist.insert(L->getHeader());
// Note that we *must not* cache the size, this loop grows the worklist.
for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
BasicBlock *BB = BBWorklist[Idx];
// Visit all instructions in the given basic block and try to simplify
// it. We don't change the actual IR, just count optimization
// opportunities.
for (Instruction &I : *BB) {
unsigned 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;
// 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)
return None;
}
// Add BB's successors to the worklist.
for (BasicBlock *Succ : successors(BB))
if (L->contains(Succ))
BBWorklist.insert(Succ);
}
// If we found no optimization opportunities on the first iteration, we
// won't find them on later ones too.
if (UnrolledCost == RolledDynamicCost)
return None;
}
return {{UnrolledCost, RolledDynamicCost}};
}
/// \brief Figure out if the loop is worth full unrolling.
///
/// 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 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.
assert(UnrollMaxIterationsCountToAnalyze < (INT_MAX / 2) &&
"The unroll iterations max is too large!");
// Only analyze inner loops. We can't properly estimate cost of nested loops
// and we won't visit inner loops again anyway.
if (!L->empty())
return None;
// Don't simulate loops with a big or unknown tripcount
if (!UnrollMaxIterationsCountToAnalyze || !TripCount ||
TripCount > UnrollMaxIterationsCountToAnalyze)
return None;
SmallSetVector<BasicBlock *, 16> BBWorklist;
SmallSetVector<std::pair<BasicBlock *, BasicBlock *>, 4> ExitWorklist;
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.
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.
int RolledDynamicCost = 0;
// We track the simplification of each instruction in each iteration. We use
// this to recursively merge costs into the unrolled cost on-demand so that
// we don't count the cost of any dead code. This is essentially a map from
// <instruction, int> to <bool, bool>, but stored as a densely packed struct.
DenseSet<UnrolledInstState, UnrolledInstStateKeyInfo> InstCostMap;
// A small worklist used to accumulate cost of instructions from each
// observable and reached root in the loop.
SmallVector<Instruction *, 16> CostWorklist;
// PHI-used worklist used between iterations while accumulating cost.
SmallVector<Instruction *, 4> PHIUsedList;
// Helper function to accumulate cost for instructions in the loop.
auto AddCostRecursively = [&](Instruction &RootI, int Iteration) {
assert(Iteration >= 0 && "Cannot have a negative iteration!");
assert(CostWorklist.empty() && "Must start with an empty cost list");
assert(PHIUsedList.empty() && "Must start with an empty phi used list");
CostWorklist.push_back(&RootI);
for (;; --Iteration) {
do {
Instruction *I = CostWorklist.pop_back_val();
// InstCostMap only uses I and Iteration as a key, the other two values
// don't matter here.
auto CostIter = InstCostMap.find({I, Iteration, 0, 0});
if (CostIter == InstCostMap.end())
// If an input to a PHI node comes from a dead path through the loop
// we may have no cost data for it here. What that actually means is
// that it is free.
continue;
auto &Cost = *CostIter;
if (Cost.IsCounted)
// Already counted this instruction.
continue;
// Mark that we are counting the cost of this instruction now.
Cost.IsCounted = true;
// If this is a PHI node in the loop header, just add it to the PHI set.
if (auto *PhiI = dyn_cast<PHINode>(I))
if (PhiI->getParent() == L->getHeader()) {
assert(Cost.IsFree && "Loop PHIs shouldn't be evaluated as they "
"inherently simplify during unrolling.");
if (Iteration == 0)
continue;
// Push the incoming value from the backedge into the PHI used list
// if it is an in-loop instruction. We'll use this to populate the
// cost worklist for the next iteration (as we count backwards).
if (auto *OpI = dyn_cast<Instruction>(
PhiI->getIncomingValueForBlock(L->getLoopLatch())))
if (L->contains(OpI))
PHIUsedList.push_back(OpI);
continue;
}
// First accumulate the cost of this instruction.
if (!Cost.IsFree) {
UnrolledCost += TTI.getUserCost(I);
DEBUG(dbgs() << "Adding cost of instruction (iteration " << Iteration
<< "): ");
DEBUG(I->dump());
}
// We must count the cost of every operand which is not free,
// recursively. If we reach a loop PHI node, simply add it to the set
// to be considered on the next iteration (backwards!).
for (Value *Op : I->operands()) {
// Check whether this operand is free due to being a constant or
// outside the loop.
auto *OpI = dyn_cast<Instruction>(Op);
if (!OpI || !L->contains(OpI))
continue;
// Otherwise accumulate its cost.
CostWorklist.push_back(OpI);
}
} while (!CostWorklist.empty());
if (PHIUsedList.empty())
// We've exhausted the search.
break;
assert(Iteration > 0 &&
"Cannot track PHI-used values past the first iteration!");
CostWorklist.append(PHIUsedList.begin(), PHIUsedList.end());
PHIUsedList.clear();
}
};
// 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, SE, L);
BBWorklist.clear();
BBWorklist.insert(L->getHeader());
// Note that we *must not* cache the size, this loop grows the worklist.
for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
BasicBlock *BB = BBWorklist[Idx];
// Visit all instructions in the given basic block and try to simplify
// it. We don't change the actual IR, just count optimization
// opportunities.
for (Instruction &I : *BB) {
// Track this instruction's expected baseline cost when executing the
// rolled loop form.
RolledDynamicCost += TTI.getUserCost(&I);
// Visit the instruction to analyze its loop cost after unrolling,
// and if the visitor returns true, mark the instruction as free after
// unrolling and continue.
bool IsFree = Analyzer.visit(I);
bool Inserted = InstCostMap.insert({&I, (int)Iteration,
(unsigned)IsFree,
/*IsCounted*/ false}).second;
(void)Inserted;
assert(Inserted && "Cannot have a state for an unvisited instruction!");
if (IsFree)
continue;
// If the instruction might have a side-effect recursively account for
// the cost of it and all the instructions leading up to it.
if (I.mayHaveSideEffects())
AddCostRecursively(I, Iteration);
// Can't properly model a cost of a call.
// FIXME: With a proper cost model we should be able to do it.
if(isa<CallInst>(&I))
return None;
// If unrolled body turns out to be too big, bail out.
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.
BasicBlock *KnownSucc = nullptr;
if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
if (BI->isConditional()) {
if (Constant *SimpleCond =
SimplifiedValues.lookup(BI->getCondition())) {
// Just take the first successor if condition is undef
if (isa<UndefValue>(SimpleCond))
KnownSucc = BI->getSuccessor(0);
else if (ConstantInt *SimpleCondVal =
dyn_cast<ConstantInt>(SimpleCond))
KnownSucc = BI->getSuccessor(SimpleCondVal->isZero() ? 1 : 0);
}
}
} else if (SwitchInst *SI = dyn_cast<SwitchInst>(TI)) {
if (Constant *SimpleCond =
SimplifiedValues.lookup(SI->getCondition())) {
// Just take the first successor if condition is undef
if (isa<UndefValue>(SimpleCond))
KnownSucc = SI->getSuccessor(0);
else if (ConstantInt *SimpleCondVal =
dyn_cast<ConstantInt>(SimpleCond))
KnownSucc = SI->findCaseValue(SimpleCondVal).getCaseSuccessor();
}
}
if (KnownSucc) {
if (L->contains(KnownSucc))
BBWorklist.insert(KnownSucc);
else
ExitWorklist.insert({BB, KnownSucc});
continue;
}
// Add BB's successors to the worklist.
for (BasicBlock *Succ : successors(BB))
if (L->contains(Succ))
BBWorklist.insert(Succ);
else
ExitWorklist.insert({BB, Succ});
AddCostRecursively(*TI, Iteration);
}
// If we found no optimization opportunities on the first iteration, we
// won't find them on later ones too.
if (UnrolledCost == RolledDynamicCost) {
DEBUG(dbgs() << " No opportunities found.. exiting.\n"
<< " UnrolledCost: " << UnrolledCost << "\n");
return None;
}
}
while (!ExitWorklist.empty()) {
BasicBlock *ExitingBB, *ExitBB;
std::tie(ExitingBB, ExitBB) = ExitWorklist.pop_back_val();
for (Instruction &I : *ExitBB) {
auto *PN = dyn_cast<PHINode>(&I);
if (!PN)
break;
Value *Op = PN->getIncomingValueForBlock(ExitingBB);
if (auto *OpI = dyn_cast<Instruction>(Op))
if (L->contains(OpI))
AddCostRecursively(*OpI, TripCount - 1);
}
}
DEBUG(dbgs() << "Analysis finished:\n"
<< "UnrolledCost: " << UnrolledCost << ", "
<< "RolledDynamicCost: " << RolledDynamicCost << "\n");
return {{UnrolledCost, RolledDynamicCost}};
}
/// Gather the various unrolling parameters based on the defaults, compiler
/// flags, TTI overrides and user specified parameters.
static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
Loop *L, const TargetTransformInfo &TTI, Optional<unsigned> UserThreshold,
Optional<unsigned> UserCount, Optional<bool> UserAllowPartial,
Optional<bool> UserRuntime) {
TargetTransformInfo::UnrollingPreferences UP;
// Set up the defaults
UP.Threshold = 150;
UP.PercentDynamicCostSavedThreshold = 50;
UP.DynamicCostSavingsDiscount = 100;
UP.OptSizeThreshold = 0;
UP.PartialThreshold = UP.Threshold;
UP.PartialOptSizeThreshold = 0;
UP.Count = 0;
UP.MaxCount = UINT_MAX;
UP.FullUnrollMaxCount = UINT_MAX;
UP.Partial = false;
UP.Runtime = false;
UP.AllowRemainder = true;
UP.AllowExpensiveTripCount = false;
UP.Force = false;
// Override with any target specific settings
TTI.getUnrollingPreferences(L, UP);
// Apply size attributes
if (L->getHeader()->getParent()->optForSize()) {
UP.Threshold = UP.OptSizeThreshold;
UP.PartialThreshold = UP.PartialOptSizeThreshold;
}
// Apply any user values specified by cl::opt
if (UnrollThreshold.getNumOccurrences() > 0) {
UP.Threshold = UnrollThreshold;
UP.PartialThreshold = UnrollThreshold;
}
if (UnrollPercentDynamicCostSavedThreshold.getNumOccurrences() > 0)
UP.PercentDynamicCostSavedThreshold =
UnrollPercentDynamicCostSavedThreshold;
if (UnrollDynamicCostSavingsDiscount.getNumOccurrences() > 0)
UP.DynamicCostSavingsDiscount = UnrollDynamicCostSavingsDiscount;
if (UnrollMaxCount.getNumOccurrences() > 0)
UP.MaxCount = UnrollMaxCount;
if (UnrollFullMaxCount.getNumOccurrences() > 0)
UP.FullUnrollMaxCount = UnrollFullMaxCount;
if (UnrollAllowPartial.getNumOccurrences() > 0)
UP.Partial = UnrollAllowPartial;
if (UnrollAllowRemainder.getNumOccurrences() > 0)
UP.AllowRemainder = UnrollAllowRemainder;
if (UnrollRuntime.getNumOccurrences() > 0)
UP.Runtime = UnrollRuntime;
// Apply user values provided by argument
if (UserThreshold.hasValue()) {
UP.Threshold = *UserThreshold;
UP.PartialThreshold = *UserThreshold;
}
if (UserCount.hasValue())
UP.Count = *UserCount;
if (UserAllowPartial.hasValue())
UP.Partial = *UserAllowPartial;
if (UserRuntime.hasValue())
UP.Runtime = *UserRuntime;
return UP;
}
/// analyzeBasicBlock - Fill in the current structure with information gleaned
/// from the specified block.
void CodeMetrics::analyzeBasicBlock(const BasicBlock *BB,
const TargetTransformInfo &TTI) {
++NumBlocks;
unsigned NumInstsBeforeThisBB = NumInsts;
for (BasicBlock::const_iterator II = BB->begin(), E = BB->end();
II != E; ++II) {
// Special handling for calls.
if (isa<CallInst>(II) || isa<InvokeInst>(II)) {
ImmutableCallSite CS(cast<Instruction>(II));
if (const Function *F = CS.getCalledFunction()) {
// If a function is both internal and has a single use, then it is
// extremely likely to get inlined in the future (it was probably
// exposed by an interleaved devirtualization pass).
if (!CS.isNoInline() && F->hasInternalLinkage() && F->hasOneUse())
++NumInlineCandidates;
// If this call is to function itself, then the function is recursive.
// Inlining it into other functions is a bad idea, because this is
// basically just a form of loop peeling, and our metrics aren't useful
// for that case.
if (F == BB->getParent())
isRecursive = true;
if (TTI.isLoweredToCall(F))
++NumCalls;
} else {
// We don't want inline asm to count as a call - that would prevent loop
// unrolling. The argument setup cost is still real, though.
if (!isa<InlineAsm>(CS.getCalledValue()))
++NumCalls;
}
}
if (const AllocaInst *AI = dyn_cast<AllocaInst>(II)) {
if (!AI->isStaticAlloca())
this->usesDynamicAlloca = true;
}
if (isa<ExtractElementInst>(II) || II->getType()->isVectorTy())
++NumVectorInsts;
if (const CallInst *CI = dyn_cast<CallInst>(II))
if (CI->hasFnAttr(Attribute::NoDuplicate))
notDuplicatable = true;
if (const InvokeInst *InvI = dyn_cast<InvokeInst>(II))
if (InvI->hasFnAttr(Attribute::NoDuplicate))
notDuplicatable = true;
if (const IntrinsicInst *CI = dyn_cast<const IntrinsicInst>(II))
if (CI->getIntrinsicID() == Intrinsic::loopbound)
notDuplicatable = true;
NumInsts += TTI.getUserCost(&*II);
}
if (isa<ReturnInst>(BB->getTerminator()))
++NumRets;
// We never want to inline functions that contain an indirectbr. This is
// incorrect because all the blockaddress's (in static global initializers
// for example) would be referring to the original function, and this indirect
// jump would jump from the inlined copy of the function into the original
// function which is extremely undefined behavior.
// FIXME: This logic isn't really right; we can safely inline functions
// with indirectbr's as long as no other function or global references the
// blockaddress of a block within the current function. And as a QOI issue,
// if someone is using a blockaddress without an indirectbr, and that
// reference somehow ends up in another function or global, we probably
// don't want to inline this function.
notDuplicatable |= isa<IndirectBrInst>(BB->getTerminator());
// Remember NumInsts for this BB.
NumBBInsts[BB] = NumInsts - NumInstsBeforeThisBB;
}
/// Gather the various unrolling parameters based on the defaults, compiler
/// flags, TTI overrides, pragmas, and user specified parameters.
static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
Loop *L, const TargetTransformInfo &TTI, Optional<unsigned> UserThreshold,
Optional<unsigned> UserCount, Optional<bool> UserAllowPartial,
Optional<bool> UserRuntime, unsigned PragmaCount, bool PragmaFullUnroll,
bool PragmaEnableUnroll, unsigned TripCount) {
TargetTransformInfo::UnrollingPreferences UP;
// Set up the defaults
UP.Threshold = 150;
UP.PercentDynamicCostSavedThreshold = 20;
UP.DynamicCostSavingsDiscount = 2000;
UP.OptSizeThreshold = 0;
UP.PartialThreshold = UP.Threshold;
UP.PartialOptSizeThreshold = 0;
UP.Count = 0;
UP.MaxCount = UINT_MAX;
UP.FullUnrollMaxCount = UINT_MAX;
UP.Partial = false;
UP.Runtime = false;
UP.AllowExpensiveTripCount = false;
// Override with any target specific settings
TTI.getUnrollingPreferences(L, UP);
// Apply size attributes
if (L->getHeader()->getParent()->optForSize()) {
UP.Threshold = UP.OptSizeThreshold;
UP.PartialThreshold = UP.PartialOptSizeThreshold;
}
// Apply unroll count pragmas
if (PragmaCount)
UP.Count = PragmaCount;
else if (PragmaFullUnroll)
UP.Count = TripCount;
// Apply any user values specified by cl::opt
if (UnrollThreshold.getNumOccurrences() > 0) {
UP.Threshold = UnrollThreshold;
UP.PartialThreshold = UnrollThreshold;
}
if (UnrollPercentDynamicCostSavedThreshold.getNumOccurrences() > 0)
UP.PercentDynamicCostSavedThreshold =
UnrollPercentDynamicCostSavedThreshold;
if (UnrollDynamicCostSavingsDiscount.getNumOccurrences() > 0)
UP.DynamicCostSavingsDiscount = UnrollDynamicCostSavingsDiscount;
if (UnrollCount.getNumOccurrences() > 0)
UP.Count = UnrollCount;
if (UnrollMaxCount.getNumOccurrences() > 0)
UP.MaxCount = UnrollMaxCount;
if (UnrollFullMaxCount.getNumOccurrences() > 0)
UP.FullUnrollMaxCount = UnrollFullMaxCount;
if (UnrollAllowPartial.getNumOccurrences() > 0)
UP.Partial = UnrollAllowPartial;
if (UnrollRuntime.getNumOccurrences() > 0)
UP.Runtime = UnrollRuntime;
// Apply user values provided by argument
if (UserThreshold.hasValue()) {
UP.Threshold = *UserThreshold;
UP.PartialThreshold = *UserThreshold;
}
if (UserCount.hasValue())
UP.Count = *UserCount;
if (UserAllowPartial.hasValue())
UP.Partial = *UserAllowPartial;
if (UserRuntime.hasValue())
UP.Runtime = *UserRuntime;
if (PragmaCount > 0 ||
((PragmaFullUnroll || PragmaEnableUnroll) && TripCount != 0)) {
// 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 default limits.
if (UP.Threshold != NoThreshold)
UP.Threshold = std::max<unsigned>(UP.Threshold, PragmaUnrollThreshold);
if (UP.PartialThreshold != NoThreshold)
UP.PartialThreshold =
std::max<unsigned>(UP.PartialThreshold, PragmaUnrollThreshold);
}
return UP;
}
/// \brief Figure out if the loop is worth full unrolling.
///
/// 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 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.
assert(UnrollMaxIterationsCountToAnalyze < (INT_MAX / 2) &&
"The unroll iterations max is too large!");
// Don't simulate loops with a big or unknown tripcount
if (!UnrollMaxIterationsCountToAnalyze || !TripCount ||
TripCount > UnrollMaxIterationsCountToAnalyze)
return None;
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.
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.
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, SE);
BBWorklist.clear();
BBWorklist.insert(L->getHeader());
// Note that we *must not* cache the size, this loop grows the worklist.
for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
BasicBlock *BB = BBWorklist[Idx];
// Visit all instructions in the given basic block and try to simplify
// it. We don't change the actual IR, just count optimization
// opportunities.
for (Instruction &I : *BB) {
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) {
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.
for (BasicBlock *Succ : successors(BB))
if (L->contains(Succ))
BBWorklist.insert(Succ);
}
// If we found no optimization opportunities on the first iteration, we
// won't find them on later ones too.
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}};
}
