/// ApproximateLoopSize - Approximate the size of the loop.
static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
bool &NotDuplicatable,
const TargetTransformInfo &TTI,
AssumptionCache *AC) {
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AC, EphValues);
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I, TTI, EphValues);
NumCalls = Metrics.NumInlineCandidates;
NotDuplicatable = Metrics.notDuplicatable;
unsigned LoopSize = Metrics.NumInsts;
// Don't allow an estimate of size zero. This would allows unrolling of loops
// with huge iteration counts, which is a compile time problem even if it's
// not a problem for code quality. Also, the code using this size may assume
// that each loop has at least three instructions (likely a conditional
// branch, a comparison feeding that branch, and some kind of loop increment
// feeding that comparison instruction).
LoopSize = std::max(LoopSize, 3u);
return LoopSize;
}
// Analyze loop. Check its size, calculate is it possible to unswitch
// it. Returns true if we can unswitch this loop.
bool LUAnalysisCache::countLoop(const Loop *L, const TargetTransformInfo &TTI,
AssumptionCache *AC) {
LoopPropsMapIt PropsIt;
bool Inserted;
std::tie(PropsIt, Inserted) =
LoopsProperties.insert(std::make_pair(L, LoopProperties()));
LoopProperties &Props = PropsIt->second;
if (Inserted) {
// New loop.
// Limit the number of instructions to avoid causing significant code
// expansion, and the number of basic blocks, to avoid loops with
// large numbers of branches which cause loop unswitching to go crazy.
// This is a very ad-hoc heuristic.
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AC, EphValues);
// FIXME: This is overly conservative because it does not take into
// consideration code simplification opportunities and code that can
// be shared by the resultant unswitched loops.
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I, TTI, EphValues);
Props.SizeEstimation = std::min(Metrics.NumInsts, Metrics.NumBlocks * 5);
Props.CanBeUnswitchedCount = MaxSize / (Props.SizeEstimation);
MaxSize -= Props.SizeEstimation * Props.CanBeUnswitchedCount;
if (Metrics.notDuplicatable) {
DEBUG(dbgs() << "NOT unswitching loop %"
<< L->getHeader()->getName() << ", contents cannot be "
<< "duplicated!\n");
return false;
}
}
if (!Props.CanBeUnswitchedCount) {
DEBUG(dbgs() << "NOT unswitching loop %"
<< L->getHeader()->getName() << ", cost too high: "
<< L->getBlocks().size() << "\n");
return false;
}
// Be careful. This links are good only before new loop addition.
CurrentLoopProperties = &Props;
CurLoopInstructions = &Props.UnswitchedVals;
return true;
}
/// UnswitchIfProfitable - We have found that we can unswitch currentLoop when
/// LoopCond == Val to simplify the loop. If we decide that this is profitable,
/// unswitch the loop, reprocess the pieces, then return true.
bool LoopUnswitch::UnswitchIfProfitable(Value *LoopCond, Constant *Val) {
initLoopData();
// If LoopSimplify was unable to form a preheader, don't do any unswitching.
if (!loopPreheader)
return false;
Function *F = loopHeader->getParent();
Constant *CondVal = 0;
BasicBlock *ExitBlock = 0;
if (IsTrivialUnswitchCondition(LoopCond, &CondVal, &ExitBlock)) {
// If the condition is trivial, always unswitch. There is no code growth
// for this case.
UnswitchTrivialCondition(currentLoop, LoopCond, CondVal, ExitBlock);
return true;
}
// Check to see if it would be profitable to unswitch current loop.
// Do not do non-trivial unswitch while optimizing for size.
if (OptimizeForSize || F->hasFnAttr(Attribute::OptimizeForSize))
return false;
// FIXME: This is overly conservative because it does not take into
// consideration code simplification opportunities and code that can
// be shared by the resultant unswitched loops.
CodeMetrics Metrics;
for (Loop::block_iterator I = currentLoop->block_begin(),
E = currentLoop->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I);
// Limit the number of instructions to avoid causing significant code
// expansion, and the number of basic blocks, to avoid loops with
// large numbers of branches which cause loop unswitching to go crazy.
// This is a very ad-hoc heuristic.
if (Metrics.NumInsts > Threshold ||
Metrics.NumBlocks * 5 > Threshold ||
Metrics.containsIndirectBr || Metrics.isRecursive) {
DEBUG(dbgs() << "NOT unswitching loop %"
<< currentLoop->getHeader()->getName() << ", cost too high: "
<< currentLoop->getBlocks().size() << "\n");
return false;
}
UnswitchNontrivialCondition(LoopCond, Val, currentLoop);
return true;
}
/// Rotate loop LP. Return true if the loop is rotated.
///
/// \param SimplifiedLatch is true if the latch was just folded into the final
/// loop exit. In this case we may want to rotate even though the new latch is
/// now an exiting branch. This rotation would have happened had the latch not
/// been simplified. However, if SimplifiedLatch is false, then we avoid
/// rotating loops in which the latch exits to avoid excessive or endless
/// rotation. LoopRotate should be repeatable and converge to a canonical
/// form. This property is satisfied because simplifying the loop latch can only
/// happen once across multiple invocations of the LoopRotate pass.
bool LoopRotate::rotateLoop(Loop *L, bool SimplifiedLatch) {
// If the loop has only one block then there is not much to rotate.
if (L->getBlocks().size() == 1)
return false;
BasicBlock *OrigHeader = L->getHeader();
BasicBlock *OrigLatch = L->getLoopLatch();
BranchInst *BI = dyn_cast<BranchInst>(OrigHeader->getTerminator());
if (!BI || BI->isUnconditional())
return false;
// If the loop header is not one of the loop exiting blocks then
// either this loop is already rotated or it is not
// suitable for loop rotation transformations.
if (!L->isLoopExiting(OrigHeader))
return false;
// If the loop latch already contains a branch that leaves the loop then the
// loop is already rotated.
if (!OrigLatch)
return false;
// Rotate if either the loop latch does *not* exit the loop, or if the loop
// latch was just simplified. Or if we think it will be profitable.
if (L->isLoopExiting(OrigLatch) && !SimplifiedLatch && IsUtilMode == false &&
!shouldRotateLoopExitingLatch(L))
return false;
// Check size of original header and reject loop if it is very big or we can't
// duplicate blocks inside it.
{
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AC, EphValues);
CodeMetrics Metrics;
Metrics.analyzeBasicBlock(OrigHeader, *TTI, EphValues);
if (Metrics.notDuplicatable) {
LLVM_DEBUG(
dbgs() << "LoopRotation: NOT rotating - contains non-duplicatable"
<< " instructions: ";
L->dump());
return false;
}
if (Metrics.convergent) {
LLVM_DEBUG(dbgs() << "LoopRotation: NOT rotating - contains convergent "
"instructions: ";
L->dump());
return false;
}
/// ApproximateLoopSize - Approximate the size of the loop.
static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls) {
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I);
NumCalls = Metrics.NumInlineCandidates;
unsigned LoopSize = Metrics.NumInsts;
// Don't allow an estimate of size zero. This would allows unrolling of loops
// with huge iteration counts, which is a compile time problem even if it's
// not a problem for code quality.
if (LoopSize == 0) LoopSize = 1;
return LoopSize;
}
// Analyze loop. Check its size, calculate is it possible to unswitch
// it. Returns true if we can unswitch this loop.
bool LUAnalysisCache::countLoop(const Loop* L) {
std::pair<LoopPropsMapIt, bool> InsertRes =
LoopsProperties.insert(std::make_pair(L, LoopProperties()));
LoopProperties& Props = InsertRes.first->second;
if (InsertRes.second) {
// New loop.
// Limit the number of instructions to avoid causing significant code
// expansion, and the number of basic blocks, to avoid loops with
// large numbers of branches which cause loop unswitching to go crazy.
// This is a very ad-hoc heuristic.
// FIXME: This is overly conservative because it does not take into
// consideration code simplification opportunities and code that can
// be shared by the resultant unswitched loops.
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(),
E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I);
Props.SizeEstimation = std::min(Metrics.NumInsts, Metrics.NumBlocks * 5);
Props.CanBeUnswitchedCount = MaxSize / (Props.SizeEstimation);
MaxSize -= Props.SizeEstimation * Props.CanBeUnswitchedCount;
}
if (!Props.CanBeUnswitchedCount) {
DEBUG(dbgs() << "NOT unswitching loop %"
<< L->getHeader()->getName() << ", cost too high: "
<< L->getBlocks().size() << "\n");
return false;
}
// Be careful. This links are good only before new loop addition.
CurrentLoopProperties = &Props;
CurLoopInstructions = &Props.UnswitchedVals;
return true;
}
/// Rotate loop LP. Return true if the loop is rotated.
///
/// \param SimplifiedLatch is true if the latch was just folded into the final
/// loop exit. In this case we may want to rotate even though the new latch is
/// now an exiting branch. This rotation would have happened had the latch not
/// been simplified. However, if SimplifiedLatch is false, then we avoid
/// rotating loops in which the latch exits to avoid excessive or endless
/// rotation. LoopRotate should be repeatable and converge to a canonical
/// form. This property is satisfied because simplifying the loop latch can only
/// happen once across multiple invocations of the LoopRotate pass.
bool LoopRotate::rotateLoop(Loop *L, bool SimplifiedLatch) {
// If the loop has only one block then there is not much to rotate.
if (L->getBlocks().size() == 1)
return false;
BasicBlock *OrigHeader = L->getHeader();
BasicBlock *OrigLatch = L->getLoopLatch();
BranchInst *BI = dyn_cast<BranchInst>(OrigHeader->getTerminator());
if (BI == 0 || BI->isUnconditional())
return false;
// If the loop header is not one of the loop exiting blocks then
// either this loop is already rotated or it is not
// suitable for loop rotation transformations.
if (!L->isLoopExiting(OrigHeader))
return false;
// If the loop latch already contains a branch that leaves the loop then the
// loop is already rotated.
if (OrigLatch == 0)
return false;
// Rotate if either the loop latch does *not* exit the loop, or if the loop
// latch was just simplified.
if (L->isLoopExiting(OrigLatch) && !SimplifiedLatch)
return false;
// Check size of original header and reject loop if it is very big or we can't
// duplicate blocks inside it.
{
CodeMetrics Metrics;
Metrics.analyzeBasicBlock(OrigHeader, *TTI);
if (Metrics.notDuplicatable) {
DEBUG(dbgs() << "LoopRotation: NOT rotating - contains non duplicatable"
<< " instructions: "; L->dump());
return false;
}
if (Metrics.NumInsts > MAX_HEADER_SIZE)
return false;
}
/// ApproximateLoopSize - Approximate the size of the loop.
static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
bool &NotDuplicatable,
const TargetTransformInfo &TTI,
AssumptionTracker *AT) {
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AT, EphValues);
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I, TTI, EphValues);
NumCalls = Metrics.NumInlineCandidates;
NotDuplicatable = Metrics.notDuplicatable;
unsigned LoopSize = Metrics.NumInsts;
// Don't allow an estimate of size zero. This would allows unrolling of loops
// with huge iteration counts, which is a compile time problem even if it's
// not a problem for code quality.
if (LoopSize == 0) LoopSize = 1;
return LoopSize;
}
bool PPCLoopDataPrefetch::runOnLoop(Loop *L) {
bool MadeChange = false;
// Only prefetch in the inner-most loop
if (!L->empty())
return MadeChange;
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AC, EphValues);
// Calculate the number of iterations ahead to prefetch
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), IE = L->block_end();
I != IE; ++I) {
// If the loop already has prefetches, then assume that the user knows
// what he or she is doing and don't add any more.
for (BasicBlock::iterator J = (*I)->begin(), JE = (*I)->end();
J != JE; ++J)
if (CallInst *CI = dyn_cast<CallInst>(J))
if (Function *F = CI->getCalledFunction())
if (F->getIntrinsicID() == Intrinsic::prefetch)
return MadeChange;
Metrics.analyzeBasicBlock(*I, *TTI, EphValues);
}
unsigned LoopSize = Metrics.NumInsts;
if (!LoopSize)
LoopSize = 1;
unsigned ItersAhead = PrefDist/LoopSize;
if (!ItersAhead)
ItersAhead = 1;
SmallVector<std::pair<Instruction *, const SCEVAddRecExpr *>, 16> PrefLoads;
for (Loop::block_iterator I = L->block_begin(), IE = L->block_end();
I != IE; ++I) {
for (BasicBlock::iterator J = (*I)->begin(), JE = (*I)->end();
J != JE; ++J) {
Value *PtrValue;
Instruction *MemI;
if (LoadInst *LMemI = dyn_cast<LoadInst>(J)) {
MemI = LMemI;
PtrValue = LMemI->getPointerOperand();
} else if (StoreInst *SMemI = dyn_cast<StoreInst>(J)) {
if (!PrefetchWrites) continue;
MemI = SMemI;
PtrValue = SMemI->getPointerOperand();
} else continue;
unsigned PtrAddrSpace = PtrValue->getType()->getPointerAddressSpace();
if (PtrAddrSpace)
continue;
if (L->isLoopInvariant(PtrValue))
continue;
const SCEV *LSCEV = SE->getSCEV(PtrValue);
const SCEVAddRecExpr *LSCEVAddRec = dyn_cast<SCEVAddRecExpr>(LSCEV);
if (!LSCEVAddRec)
continue;
// We don't want to double prefetch individual cache lines. If this load
// is known to be within one cache line of some other load that has
// already been prefetched, then don't prefetch this one as well.
bool DupPref = false;
for (SmallVector<std::pair<Instruction *, const SCEVAddRecExpr *>,
16>::iterator K = PrefLoads.begin(), KE = PrefLoads.end();
K != KE; ++K) {
const SCEV *PtrDiff = SE->getMinusSCEV(LSCEVAddRec, K->second);
if (const SCEVConstant *ConstPtrDiff =
dyn_cast<SCEVConstant>(PtrDiff)) {
int64_t PD = std::abs(ConstPtrDiff->getValue()->getSExtValue());
if (PD < (int64_t) CacheLineSize) {
DupPref = true;
break;
}
}
}
if (DupPref)
continue;
const SCEV *NextLSCEV = SE->getAddExpr(LSCEVAddRec, SE->getMulExpr(
SE->getConstant(LSCEVAddRec->getType(), ItersAhead),
LSCEVAddRec->getStepRecurrence(*SE)));
if (!isSafeToExpand(NextLSCEV, *SE))
continue;
PrefLoads.push_back(std::make_pair(MemI, LSCEVAddRec));
Type *I8Ptr = Type::getInt8PtrTy((*I)->getContext(), PtrAddrSpace);
SCEVExpander SCEVE(*SE, J->getModule()->getDataLayout(), "prefaddr");
Value *PrefPtrValue = SCEVE.expandCodeFor(NextLSCEV, I8Ptr, MemI);
IRBuilder<> Builder(MemI);
Module *M = (*I)->getParent()->getParent();
Type *I32 = Type::getInt32Ty((*I)->getContext());
Value *PrefetchFunc = Intrinsic::getDeclaration(M, Intrinsic::prefetch);
Builder.CreateCall4(PrefetchFunc, PrefPtrValue,
ConstantInt::get(I32, MemI->mayReadFromMemory() ? 0 : 1),
ConstantInt::get(I32, 3), ConstantInt::get(I32, 1));
MadeChange = true;
}
}
return MadeChange;
}
/// Rotate loop LP. Return true if the loop is rotated.
bool LoopRotate::rotateLoop(Loop *L) {
// If the loop has only one block then there is not much to rotate.
if (L->getBlocks().size() == 1)
return false;
BasicBlock *OrigHeader = L->getHeader();
BranchInst *BI = dyn_cast<BranchInst>(OrigHeader->getTerminator());
if (BI == 0 || BI->isUnconditional())
return false;
// If the loop header is not one of the loop exiting blocks then
// either this loop is already rotated or it is not
// suitable for loop rotation transformations.
if (!L->isLoopExiting(OrigHeader))
return false;
// Updating PHInodes in loops with multiple exits adds complexity.
// Keep it simple, and restrict loop rotation to loops with one exit only.
// In future, lift this restriction and support for multiple exits if
// required.
SmallVector<BasicBlock*, 8> ExitBlocks;
L->getExitBlocks(ExitBlocks);
if (ExitBlocks.size() > 1)
return false;
// Check size of original header and reject loop if it is very big.
{
CodeMetrics Metrics;
Metrics.analyzeBasicBlock(OrigHeader);
if (Metrics.NumInsts > MAX_HEADER_SIZE)
return false;
}
// Now, this loop is suitable for rotation.
BasicBlock *OrigPreheader = L->getLoopPreheader();
BasicBlock *OrigLatch = L->getLoopLatch();
// If the loop could not be converted to canonical form, it must have an
// indirectbr in it, just give up.
if (OrigPreheader == 0 || OrigLatch == 0)
return false;
// Anything ScalarEvolution may know about this loop or the PHI nodes
// in its header will soon be invalidated.
if (ScalarEvolution *SE = getAnalysisIfAvailable<ScalarEvolution>())
SE->forgetLoop(L);
// Find new Loop header. NewHeader is a Header's one and only successor
// that is inside loop. Header's other successor is outside the
// loop. Otherwise loop is not suitable for rotation.
BasicBlock *Exit = BI->getSuccessor(0);
BasicBlock *NewHeader = BI->getSuccessor(1);
if (L->contains(Exit))
std::swap(Exit, NewHeader);
assert(NewHeader && "Unable to determine new loop header");
assert(L->contains(NewHeader) && !L->contains(Exit) &&
"Unable to determine loop header and exit blocks");
// This code assumes that the new header has exactly one predecessor.
// Remove any single-entry PHI nodes in it.
assert(NewHeader->getSinglePredecessor() &&
"New header doesn't have one pred!");
FoldSingleEntryPHINodes(NewHeader);
// Begin by walking OrigHeader and populating ValueMap with an entry for
// each Instruction.
BasicBlock::iterator I = OrigHeader->begin(), E = OrigHeader->end();
ValueToValueMapTy ValueMap;
// For PHI nodes, the value available in OldPreHeader is just the
// incoming value from OldPreHeader.
for (; PHINode *PN = dyn_cast<PHINode>(I); ++I)
ValueMap[PN] = PN->getIncomingValue(PN->getBasicBlockIndex(OrigPreheader));
// For the rest of the instructions, either hoist to the OrigPreheader if
// possible or create a clone in the OldPreHeader if not.
TerminatorInst *LoopEntryBranch = OrigPreheader->getTerminator();
while (I != E) {
Instruction *Inst = I++;
// If the instruction's operands are invariant and it doesn't read or write
// memory, then it is safe to hoist. Doing this doesn't change the order of
// execution in the preheader, but does prevent the instruction from
// executing in each iteration of the loop. This means it is safe to hoist
// something that might trap, but isn't safe to hoist something that reads
// memory (without proving that the loop doesn't write).
if (L->hasLoopInvariantOperands(Inst) &&
!Inst->mayReadFromMemory() && !Inst->mayWriteToMemory() &&
!isa<TerminatorInst>(Inst) && !isa<DbgInfoIntrinsic>(Inst)) {
Inst->moveBefore(LoopEntryBranch);
continue;
}
// Otherwise, create a duplicate of the instruction.
Instruction *C = Inst->clone();
// Eagerly remap the operands of the instruction.
RemapInstruction(C, ValueMap,
RF_NoModuleLevelChanges|RF_IgnoreMissingEntries);
// With the operands remapped, see if the instruction constant folds or is
// otherwise simplifyable. This commonly occurs because the entry from PHI
// nodes allows icmps and other instructions to fold.
Value *V = SimplifyInstruction(C);
if (V && LI->replacementPreservesLCSSAForm(C, V)) {
// If so, then delete the temporary instruction and stick the folded value
// in the map.
delete C;
ValueMap[Inst] = V;
} else {
// Otherwise, stick the new instruction into the new block!
C->setName(Inst->getName());
C->insertBefore(LoopEntryBranch);
ValueMap[Inst] = C;
}
}
// Along with all the other instructions, we just cloned OrigHeader's
// terminator into OrigPreHeader. Fix up the PHI nodes in each of OrigHeader's
// successors by duplicating their incoming values for OrigHeader.
TerminatorInst *TI = OrigHeader->getTerminator();
for (unsigned i = 0, e = TI->getNumSuccessors(); i != e; ++i)
for (BasicBlock::iterator BI = TI->getSuccessor(i)->begin();
PHINode *PN = dyn_cast<PHINode>(BI); ++BI)
PN->addIncoming(PN->getIncomingValueForBlock(OrigHeader), OrigPreheader);
// Now that OrigPreHeader has a clone of OrigHeader's terminator, remove
// OrigPreHeader's old terminator (the original branch into the loop), and
// remove the corresponding incoming values from the PHI nodes in OrigHeader.
LoopEntryBranch->eraseFromParent();
// If there were any uses of instructions in the duplicated block outside the
// loop, update them, inserting PHI nodes as required
RewriteUsesOfClonedInstructions(OrigHeader, OrigPreheader, ValueMap);
// NewHeader is now the header of the loop.
L->moveToHeader(NewHeader);
assert(L->getHeader() == NewHeader && "Latch block is our new header");
// At this point, we've finished our major CFG changes. As part of cloning
// the loop into the preheader we've simplified instructions and the
// duplicated conditional branch may now be branching on a constant. If it is
// branching on a constant and if that constant means that we enter the loop,
// then we fold away the cond branch to an uncond branch. This simplifies the
// loop in cases important for nested loops, and it also means we don't have
// to split as many edges.
BranchInst *PHBI = cast<BranchInst>(OrigPreheader->getTerminator());
assert(PHBI->isConditional() && "Should be clone of BI condbr!");
if (!isa<ConstantInt>(PHBI->getCondition()) ||
PHBI->getSuccessor(cast<ConstantInt>(PHBI->getCondition())->isZero())
!= NewHeader) {
// The conditional branch can't be folded, handle the general case.
// Update DominatorTree to reflect the CFG change we just made. Then split
// edges as necessary to preserve LoopSimplify form.
if (DominatorTree *DT = getAnalysisIfAvailable<DominatorTree>()) {
// Since OrigPreheader now has the conditional branch to Exit block, it is
// the dominator of Exit.
DT->changeImmediateDominator(Exit, OrigPreheader);
DT->changeImmediateDominator(NewHeader, OrigPreheader);
// Update OrigHeader to be dominated by the new header block.
DT->changeImmediateDominator(OrigHeader, OrigLatch);
}
// Right now OrigPreHeader has two successors, NewHeader and ExitBlock, and
// thus is not a preheader anymore. Split the edge to form a real preheader.
BasicBlock *NewPH = SplitCriticalEdge(OrigPreheader, NewHeader, this);
NewPH->setName(NewHeader->getName() + ".lr.ph");
// Preserve canonical loop form, which means that 'Exit' should have only one
// predecessor.
BasicBlock *ExitSplit = SplitCriticalEdge(L->getLoopLatch(), Exit, this);
ExitSplit->moveBefore(Exit);
} else {
// We can fold the conditional branch in the preheader, this makes things
// simpler. The first step is to remove the extra edge to the Exit block.
Exit->removePredecessor(OrigPreheader, true /*preserve LCSSA*/);
BranchInst::Create(NewHeader, PHBI);
PHBI->eraseFromParent();
// With our CFG finalized, update DomTree if it is available.
if (DominatorTree *DT = getAnalysisIfAvailable<DominatorTree>()) {
// Update OrigHeader to be dominated by the new header block.
DT->changeImmediateDominator(NewHeader, OrigPreheader);
DT->changeImmediateDominator(OrigHeader, OrigLatch);
}
}
assert(L->getLoopPreheader() && "Invalid loop preheader after loop rotation");
assert(L->getLoopLatch() && "Invalid loop latch after loop rotation");
// Now that the CFG and DomTree are in a consistent state again, try to merge
// the OrigHeader block into OrigLatch. This will succeed if they are
// connected by an unconditional branch. This is just a cleanup so the
// emitted code isn't too gross in this common case.
MergeBlockIntoPredecessor(OrigHeader, this);
++NumRotated;
return true;
}
bool PPCCTRLoops::convertToCTRLoop(Loop *L) {
bool MadeChange = false;
// Do not convert small short loops to CTR loop.
unsigned ConstTripCount = SE->getSmallConstantTripCount(L);
if (ConstTripCount && ConstTripCount < SmallCTRLoopThreshold) {
SmallPtrSet<const Value *, 32> EphValues;
auto AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(
*L->getHeader()->getParent());
CodeMetrics::collectEphemeralValues(L, &AC, EphValues);
CodeMetrics Metrics;
for (BasicBlock *BB : L->blocks())
Metrics.analyzeBasicBlock(BB, *TTI, EphValues);
// 6 is an approximate latency for the mtctr instruction.
if (Metrics.NumInsts <= (6 * SchedModel.getIssueWidth()))
return false;
}
// Process nested loops first.
for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I) {
MadeChange |= convertToCTRLoop(*I);
LLVM_DEBUG(dbgs() << "Nested loop converted\n");
}
// If a nested loop has been converted, then we can't convert this loop.
if (MadeChange)
return MadeChange;
// Bail out if the loop has irreducible control flow.
LoopBlocksRPO RPOT(L);
RPOT.perform(LI);
if (containsIrreducibleCFG<const BasicBlock *>(RPOT, *LI))
return false;
#ifndef NDEBUG
// Stop trying after reaching the limit (if any).
int Limit = CTRLoopLimit;
if (Limit >= 0) {
if (Counter >= CTRLoopLimit)
return false;
Counter++;
}
#endif
// We don't want to spill/restore the counter register, and so we don't
// want to use the counter register if the loop contains calls.
for (Loop::block_iterator I = L->block_begin(), IE = L->block_end();
I != IE; ++I)
if (mightUseCTR(*I))
return MadeChange;
SmallVector<BasicBlock*, 4> ExitingBlocks;
L->getExitingBlocks(ExitingBlocks);
// If there is an exit edge known to be frequently taken,
// we should not transform this loop.
for (auto &BB : ExitingBlocks) {
Instruction *TI = BB->getTerminator();
if (!TI) continue;
if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
uint64_t TrueWeight = 0, FalseWeight = 0;
if (!BI->isConditional() ||
!BI->extractProfMetadata(TrueWeight, FalseWeight))
continue;
// If the exit path is more frequent than the loop path,
// we return here without further analysis for this loop.
bool TrueIsExit = !L->contains(BI->getSuccessor(0));
if (( TrueIsExit && FalseWeight < TrueWeight) ||
(!TrueIsExit && FalseWeight > TrueWeight))
return MadeChange;
}
}
BasicBlock *CountedExitBlock = nullptr;
const SCEV *ExitCount = nullptr;
BranchInst *CountedExitBranch = nullptr;
for (SmallVectorImpl<BasicBlock *>::iterator I = ExitingBlocks.begin(),
IE = ExitingBlocks.end(); I != IE; ++I) {
const SCEV *EC = SE->getExitCount(L, *I);
LLVM_DEBUG(dbgs() << "Exit Count for " << *L << " from block "
<< (*I)->getName() << ": " << *EC << "\n");
if (isa<SCEVCouldNotCompute>(EC))
continue;
if (const SCEVConstant *ConstEC = dyn_cast<SCEVConstant>(EC)) {
if (ConstEC->getValue()->isZero())
continue;
} else if (!SE->isLoopInvariant(EC, L))
continue;
if (SE->getTypeSizeInBits(EC->getType()) > (TM->isPPC64() ? 64 : 32))
continue;
// If this exiting block is contained in a nested loop, it is not eligible
// for insertion of the branch-and-decrement since the inner loop would
// end up messing up the value in the CTR.
if (LI->getLoopFor(*I) != L)
continue;
// We now have a loop-invariant count of loop iterations (which is not the
// constant zero) for which we know that this loop will not exit via this
// existing block.
// We need to make sure that this block will run on every loop iteration.
// For this to be true, we must dominate all blocks with backedges. Such
// blocks are in-loop predecessors to the header block.
bool NotAlways = false;
for (pred_iterator PI = pred_begin(L->getHeader()),
PIE = pred_end(L->getHeader()); PI != PIE; ++PI) {
if (!L->contains(*PI))
continue;
if (!DT->dominates(*I, *PI)) {
NotAlways = true;
break;
}
}
if (NotAlways)
continue;
// Make sure this blocks ends with a conditional branch.
Instruction *TI = (*I)->getTerminator();
if (!TI)
continue;
if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
if (!BI->isConditional())
continue;
CountedExitBranch = BI;
} else
continue;
// Note that this block may not be the loop latch block, even if the loop
// has a latch block.
CountedExitBlock = *I;
ExitCount = EC;
break;
}
if (!CountedExitBlock)
return MadeChange;
BasicBlock *Preheader = L->getLoopPreheader();
// If we don't have a preheader, then insert one. If we already have a
// preheader, then we can use it (except if the preheader contains a use of
// the CTR register because some such uses might be reordered by the
// selection DAG after the mtctr instruction).
if (!Preheader || mightUseCTR(Preheader))
Preheader = InsertPreheaderForLoop(L, DT, LI, PreserveLCSSA);
if (!Preheader)
return MadeChange;
LLVM_DEBUG(dbgs() << "Preheader for exit count: " << Preheader->getName()
<< "\n");
// Insert the count into the preheader and replace the condition used by the
// selected branch.
MadeChange = true;
SCEVExpander SCEVE(*SE, *DL, "loopcnt");
LLVMContext &C = SE->getContext();
Type *CountType = TM->isPPC64() ? Type::getInt64Ty(C) : Type::getInt32Ty(C);
if (!ExitCount->getType()->isPointerTy() &&
ExitCount->getType() != CountType)
ExitCount = SE->getZeroExtendExpr(ExitCount, CountType);
ExitCount = SE->getAddExpr(ExitCount, SE->getOne(CountType));
Value *ECValue =
SCEVE.expandCodeFor(ExitCount, CountType, Preheader->getTerminator());
IRBuilder<> CountBuilder(Preheader->getTerminator());
Module *M = Preheader->getParent()->getParent();
Function *MTCTRFunc =
Intrinsic::getDeclaration(M, Intrinsic::ppc_mtctr, CountType);
CountBuilder.CreateCall(MTCTRFunc, ECValue);
IRBuilder<> CondBuilder(CountedExitBranch);
Function *DecFunc =
Intrinsic::getDeclaration(M, Intrinsic::ppc_is_decremented_ctr_nonzero);
Value *NewCond = CondBuilder.CreateCall(DecFunc, {});
Value *OldCond = CountedExitBranch->getCondition();
CountedExitBranch->setCondition(NewCond);
// The false branch must exit the loop.
if (!L->contains(CountedExitBranch->getSuccessor(0)))
CountedExitBranch->swapSuccessors();
// The old condition may be dead now, and may have even created a dead PHI
// (the original induction variable).
RecursivelyDeleteTriviallyDeadInstructions(OldCond);
// Run through the basic blocks of the loop and see if any of them have dead
// PHIs that can be removed.
for (auto I : L->blocks())
DeleteDeadPHIs(I);
++NumCTRLoops;
return MadeChange;
}
