X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTransforms%2FScalar%2FLoopRotation.cpp;h=aeb5b36b4b8cfb402119447cebd226b6aed59b3a;hb=9146833fa313fb0339355f9ca8b63122dd73ba88;hp=199c42009d29d8c076e1fe59ef0c6488863f172a;hpb=64c24db959815c6b7edbebd32e5a16936d75b2e1;p=oota-llvm.git diff --git a/lib/Transforms/Scalar/LoopRotation.cpp b/lib/Transforms/Scalar/LoopRotation.cpp index 199c42009d2..aeb5b36b4b8 100644 --- a/lib/Transforms/Scalar/LoopRotation.cpp +++ b/lib/Transforms/Scalar/LoopRotation.cpp @@ -11,22 +11,38 @@ // //===----------------------------------------------------------------------===// -#define DEBUG_TYPE "loop-rotate" #include "llvm/Transforms/Scalar.h" -#include "llvm/Function.h" +#include "llvm/ADT/Statistic.h" +#include "llvm/Analysis/AliasAnalysis.h" +#include "llvm/Analysis/BasicAliasAnalysis.h" +#include "llvm/Analysis/AssumptionCache.h" #include "llvm/Analysis/CodeMetrics.h" -#include "llvm/Analysis/LoopPass.h" #include "llvm/Analysis/InstructionSimplify.h" +#include "llvm/Analysis/GlobalsModRef.h" +#include "llvm/Analysis/LoopPass.h" #include "llvm/Analysis/ScalarEvolution.h" -#include "llvm/Transforms/Utils/Local.h" +#include "llvm/Analysis/ScalarEvolutionAliasAnalysis.h" +#include "llvm/Analysis/TargetTransformInfo.h" +#include "llvm/Analysis/ValueTracking.h" +#include "llvm/IR/CFG.h" +#include "llvm/IR/Dominators.h" +#include "llvm/IR/Function.h" +#include "llvm/IR/IntrinsicInst.h" +#include "llvm/IR/Module.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/raw_ostream.h" #include "llvm/Transforms/Utils/BasicBlockUtils.h" +#include "llvm/Transforms/Utils/Local.h" #include "llvm/Transforms/Utils/SSAUpdater.h" #include "llvm/Transforms/Utils/ValueMapper.h" -#include "llvm/Support/Debug.h" -#include "llvm/ADT/Statistic.h" using namespace llvm; -#define MAX_HEADER_SIZE 16 +#define DEBUG_TYPE "loop-rotate" + +static cl::opt +DefaultRotationThreshold("rotation-max-header-size", cl::init(16), cl::Hidden, + cl::desc("The default maximum header size for automatic loop rotation")); STATISTIC(NumRotated, "Number of loops rotated"); namespace { @@ -34,48 +50,94 @@ namespace { class LoopRotate : public LoopPass { public: static char ID; // Pass ID, replacement for typeid - LoopRotate() : LoopPass(ID) { + LoopRotate(int SpecifiedMaxHeaderSize = -1) : LoopPass(ID) { initializeLoopRotatePass(*PassRegistry::getPassRegistry()); + if (SpecifiedMaxHeaderSize == -1) + MaxHeaderSize = DefaultRotationThreshold; + else + MaxHeaderSize = unsigned(SpecifiedMaxHeaderSize); } // LCSSA form makes instruction renaming easier. - virtual void getAnalysisUsage(AnalysisUsage &AU) const { - AU.addPreserved(); - AU.addRequired(); - AU.addPreserved(); + void getAnalysisUsage(AnalysisUsage &AU) const override { + AU.addPreserved(); + AU.addRequired(); + AU.addPreserved(); + AU.addRequired(); + AU.addPreserved(); AU.addRequiredID(LoopSimplifyID); AU.addPreservedID(LoopSimplifyID); AU.addRequiredID(LCSSAID); AU.addPreservedID(LCSSAID); - AU.addPreserved(); + AU.addPreserved(); + AU.addPreserved(); + AU.addRequired(); + AU.addPreserved(); + AU.addPreserved(); } - bool runOnLoop(Loop *L, LPPassManager &LPM); - bool rotateLoop(Loop *L); - + bool runOnLoop(Loop *L, LPPassManager &LPM) override; + bool simplifyLoopLatch(Loop *L); + bool rotateLoop(Loop *L, bool SimplifiedLatch); + private: + unsigned MaxHeaderSize; LoopInfo *LI; + const TargetTransformInfo *TTI; + AssumptionCache *AC; + DominatorTree *DT; }; } - + char LoopRotate::ID = 0; INITIALIZE_PASS_BEGIN(LoopRotate, "loop-rotate", "Rotate Loops", false, false) -INITIALIZE_PASS_DEPENDENCY(LoopInfo) +INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass) +INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker) +INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass) INITIALIZE_PASS_DEPENDENCY(LoopSimplify) INITIALIZE_PASS_DEPENDENCY(LCSSA) +INITIALIZE_PASS_DEPENDENCY(SCEVAAWrapperPass) +INITIALIZE_PASS_DEPENDENCY(BasicAAWrapperPass) +INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass) INITIALIZE_PASS_END(LoopRotate, "loop-rotate", "Rotate Loops", false, false) -Pass *llvm::createLoopRotatePass() { return new LoopRotate(); } +Pass *llvm::createLoopRotatePass(int MaxHeaderSize) { + return new LoopRotate(MaxHeaderSize); +} /// Rotate Loop L as many times as possible. Return true if /// the loop is rotated at least once. bool LoopRotate::runOnLoop(Loop *L, LPPassManager &LPM) { - LI = &getAnalysis(); + if (skipOptnoneFunction(L)) + return false; + + // Save the loop metadata. + MDNode *LoopMD = L->getLoopID(); + + Function &F = *L->getHeader()->getParent(); + + LI = &getAnalysis().getLoopInfo(); + TTI = &getAnalysis().getTTI(F); + AC = &getAnalysis().getAssumptionCache(F); + auto *DTWP = getAnalysisIfAvailable(); + DT = DTWP ? &DTWP->getDomTree() : nullptr; + + // Simplify the loop latch before attempting to rotate the header + // upward. Rotation may not be needed if the loop tail can be folded into the + // loop exit. + bool SimplifiedLatch = simplifyLoopLatch(L); // One loop can be rotated multiple times. bool MadeChange = false; - while (rotateLoop(L)) + while (rotateLoop(L, SimplifiedLatch)) { MadeChange = true; + SimplifiedLatch = false; + } + + // Restore the loop metadata. + // NB! We presume LoopRotation DOESN'T ADD its own metadata. + if ((MadeChange || SimplifiedLatch) && LoopMD) + L->setLoopID(LoopMD); return MadeChange; } @@ -91,18 +153,18 @@ static void RewriteUsesOfClonedInstructions(BasicBlock *OrigHeader, BasicBlock::iterator I, E = OrigHeader->end(); for (I = OrigHeader->begin(); PHINode *PN = dyn_cast(I); ++I) PN->removeIncomingValue(PN->getBasicBlockIndex(OrigPreheader)); - + // Now fix up users of the instructions in OrigHeader, inserting PHI nodes // as necessary. SSAUpdater SSA; for (I = OrigHeader->begin(); I != E; ++I) { Value *OrigHeaderVal = I; - + // If there are no uses of the value (e.g. because it returns void), there // is nothing to rewrite. if (OrigHeaderVal->use_empty()) continue; - + Value *OrigPreHeaderVal = ValueMap[OrigHeaderVal]; // The value now exits in two versions: the initial value in the preheader @@ -110,27 +172,27 @@ static void RewriteUsesOfClonedInstructions(BasicBlock *OrigHeader, SSA.Initialize(OrigHeaderVal->getType(), OrigHeaderVal->getName()); SSA.AddAvailableValue(OrigHeader, OrigHeaderVal); SSA.AddAvailableValue(OrigPreheader, OrigPreHeaderVal); - + // Visit each use of the OrigHeader instruction. for (Value::use_iterator UI = OrigHeaderVal->use_begin(), UE = OrigHeaderVal->use_end(); UI != UE; ) { // Grab the use before incrementing the iterator. - Use &U = UI.getUse(); - + Use &U = *UI; + // Increment the iterator before removing the use from the list. ++UI; - + // SSAUpdater can't handle a non-PHI use in the same block as an // earlier def. We can easily handle those cases manually. Instruction *UserInst = cast(U.getUser()); if (!isa(UserInst)) { BasicBlock *UserBB = UserInst->getParent(); - + // The original users in the OrigHeader are already using the // original definitions. if (UserBB == OrigHeader) continue; - + // Users in the OrigPreHeader need to use the value to which the // original definitions are mapped. if (UserBB == OrigPreheader) { @@ -138,57 +200,203 @@ static void RewriteUsesOfClonedInstructions(BasicBlock *OrigHeader, continue; } } - + // Anything else can be handled by SSAUpdater. SSA.RewriteUse(U); } } -} +} + +/// Determine whether the instructions in this range may be safely and cheaply +/// speculated. This is not an important enough situation to develop complex +/// heuristics. We handle a single arithmetic instruction along with any type +/// conversions. +static bool shouldSpeculateInstrs(BasicBlock::iterator Begin, + BasicBlock::iterator End, Loop *L) { + bool seenIncrement = false; + bool MultiExitLoop = false; + + if (!L->getExitingBlock()) + MultiExitLoop = true; + + for (BasicBlock::iterator I = Begin; I != End; ++I) { + + if (!isSafeToSpeculativelyExecute(I)) + return false; + + if (isa(I)) + continue; + + switch (I->getOpcode()) { + default: + return false; + case Instruction::GetElementPtr: + // GEPs are cheap if all indices are constant. + if (!cast(I)->hasAllConstantIndices()) + return false; + // fall-thru to increment case + case Instruction::Add: + case Instruction::Sub: + case Instruction::And: + case Instruction::Or: + case Instruction::Xor: + case Instruction::Shl: + case Instruction::LShr: + case Instruction::AShr: { + Value *IVOpnd = !isa(I->getOperand(0)) + ? I->getOperand(0) + : !isa(I->getOperand(1)) + ? I->getOperand(1) + : nullptr; + if (!IVOpnd) + return false; + + // If increment operand is used outside of the loop, this speculation + // could cause extra live range interference. + if (MultiExitLoop) { + for (User *UseI : IVOpnd->users()) { + auto *UserInst = cast(UseI); + if (!L->contains(UserInst)) + return false; + } + } + + if (seenIncrement) + return false; + seenIncrement = true; + break; + } + case Instruction::Trunc: + case Instruction::ZExt: + case Instruction::SExt: + // ignore type conversions + break; + } + } + return true; +} + +/// Fold the loop tail into the loop exit by speculating the loop tail +/// instructions. Typically, this is a single post-increment. In the case of a +/// simple 2-block loop, hoisting the increment can be much better than +/// duplicating the entire loop header. In the case of loops with early exits, +/// rotation will not work anyway, but simplifyLoopLatch will put the loop in +/// canonical form so downstream passes can handle it. +/// +/// I don't believe this invalidates SCEV. +bool LoopRotate::simplifyLoopLatch(Loop *L) { + BasicBlock *Latch = L->getLoopLatch(); + if (!Latch || Latch->hasAddressTaken()) + return false; + + BranchInst *Jmp = dyn_cast(Latch->getTerminator()); + if (!Jmp || !Jmp->isUnconditional()) + return false; + + BasicBlock *LastExit = Latch->getSinglePredecessor(); + if (!LastExit || !L->isLoopExiting(LastExit)) + return false; + + BranchInst *BI = dyn_cast(LastExit->getTerminator()); + if (!BI) + return false; + + if (!shouldSpeculateInstrs(Latch->begin(), Jmp, L)) + return false; + + DEBUG(dbgs() << "Folding loop latch " << Latch->getName() << " into " + << LastExit->getName() << "\n"); + + // Hoist the instructions from Latch into LastExit. + LastExit->getInstList().splice(BI, Latch->getInstList(), Latch->begin(), Jmp); + + unsigned FallThruPath = BI->getSuccessor(0) == Latch ? 0 : 1; + BasicBlock *Header = Jmp->getSuccessor(0); + assert(Header == L->getHeader() && "expected a backward branch"); + + // Remove Latch from the CFG so that LastExit becomes the new Latch. + BI->setSuccessor(FallThruPath, Header); + Latch->replaceSuccessorsPhiUsesWith(LastExit); + Jmp->eraseFromParent(); + + // Nuke the Latch block. + assert(Latch->empty() && "unable to evacuate Latch"); + LI->removeBlock(Latch); + if (DT) + DT->eraseNode(Latch); + Latch->eraseFromParent(); + return true; +} /// Rotate loop LP. Return true if the loop is rotated. -bool LoopRotate::rotateLoop(Loop *L) { +/// +/// \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(OrigHeader->getTerminator()); - if (BI == 0 || BI->isUnconditional()) + 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; - // 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 ExitBlocks; - L->getExitBlocks(ExitBlocks); - if (ExitBlocks.size() > 1) + // 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. + if (L->isLoopExiting(OrigLatch) && !SimplifiedLatch) return false; - // Check size of original header and reject loop if it is very big. + // Check size of original header and reject loop if it is very big or we can't + // duplicate blocks inside it. { + SmallPtrSet EphValues; + CodeMetrics::collectEphemeralValues(L, AC, EphValues); + CodeMetrics Metrics; - Metrics.analyzeBasicBlock(OrigHeader); - if (Metrics.NumInsts > MAX_HEADER_SIZE) + Metrics.analyzeBasicBlock(OrigHeader, *TTI, EphValues); + if (Metrics.notDuplicatable) { + DEBUG(dbgs() << "LoopRotation: NOT rotating - contains non-duplicatable" + << " instructions: "; L->dump()); + return false; + } + if (Metrics.NumInsts > MaxHeaderSize) return false; } // Now, this loop is suitable for rotation. BasicBlock *OrigPreheader = L->getLoopPreheader(); - BasicBlock *OrigLatch = L->getLoopLatch(); - assert(OrigPreheader && OrigLatch && "Loop not in canonical form?"); + + // If the loop could not be converted to canonical form, it must have an + // indirectbr in it, just give up. + if (!OrigPreheader) + return false; // Anything ScalarEvolution may know about this loop or the PHI nodes // in its header will soon be invalidated. - if (ScalarEvolution *SE = getAnalysisIfAvailable()) - SE->forgetLoop(L); + if (auto *SEWP = getAnalysisIfAvailable()) + SEWP->getSE().forgetLoop(L); + + DEBUG(dbgs() << "LoopRotation: rotating "; L->dump()); // Find new Loop header. NewHeader is a Header's one and only successor // that is inside loop. Header's other successor is outside the @@ -198,9 +406,9 @@ bool LoopRotate::rotateLoop(Loop *L) { if (L->contains(Exit)) std::swap(Exit, NewHeader); assert(NewHeader && "Unable to determine new loop header"); - assert(L->contains(NewHeader) && !L->contains(Exit) && + 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() && @@ -215,14 +423,16 @@ bool LoopRotate::rotateLoop(Loop *L) { // For PHI nodes, the value available in OldPreHeader is just the // incoming value from OldPreHeader. for (; PHINode *PN = dyn_cast(I); ++I) - ValueMap[PN] = PN->getIncomingValue(PN->getBasicBlockIndex(OrigPreheader)); + ValueMap[PN] = PN->getIncomingValueForBlock(OrigPreheader); + + const DataLayout &DL = L->getHeader()->getModule()->getDataLayout(); // 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 @@ -231,22 +441,24 @@ bool LoopRotate::rotateLoop(Loop *L) { // memory (without proving that the loop doesn't write). if (L->hasLoopInvariantOperands(Inst) && !Inst->mayReadFromMemory() && !Inst->mayWriteToMemory() && - !isa(Inst)) { + !isa(Inst) && !isa(Inst) && + !isa(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); + // FIXME: Provide TLI, DT, AC to SimplifyInstruction. + Value *V = SimplifyInstruction(C, DL); if (V && LI->replacementPreservesLCSSAForm(C, V)) { // If so, then delete the temporary instruction and stick the folded value // in the map. @@ -264,8 +476,8 @@ bool LoopRotate::rotateLoop(Loop *L) { // 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(); + for (BasicBlock *SuccBB : TI->successors()) + for (BasicBlock::iterator BI = SuccBB->begin(); PHINode *PN = dyn_cast(BI); ++BI) PN->addIncoming(PN->getIncomingValueForBlock(OrigHeader), OrigPreheader); @@ -282,40 +494,127 @@ bool LoopRotate::rotateLoop(Loop *L) { L->moveToHeader(NewHeader); assert(L->getHeader() == NewHeader && "Latch block is our new header"); - // Update DominatorTree to reflect the CFG change we just made. Then split - // edges as necessary to preserve LoopSimplify form. - if (DominatorTree *DT = getAnalysisIfAvailable()) { - // 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); + + // 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(OrigPreheader->getTerminator()); + assert(PHBI->isConditional() && "Should be clone of BI condbr!"); + if (!isa(PHBI->getCondition()) || + PHBI->getSuccessor(cast(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 (DT) { + // Everything that was dominated by the old loop header is now dominated + // by the original loop preheader. Conceptually the header was merged + // into the preheader, even though we reuse the actual block as a new + // loop latch. + DomTreeNode *OrigHeaderNode = DT->getNode(OrigHeader); + SmallVector HeaderChildren(OrigHeaderNode->begin(), + OrigHeaderNode->end()); + DomTreeNode *OrigPreheaderNode = DT->getNode(OrigPreheader); + for (unsigned I = 0, E = HeaderChildren.size(); I != E; ++I) + DT->changeImmediateDominator(HeaderChildren[I], OrigPreheaderNode); + + assert(DT->getNode(Exit)->getIDom() == OrigPreheaderNode); + assert(DT->getNode(NewHeader)->getIDom() == OrigPreheaderNode); + + // 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, + CriticalEdgeSplittingOptions(DT, LI).setPreserveLCSSA()); + NewPH->setName(NewHeader->getName() + ".lr.ph"); + + // Preserve canonical loop form, which means that 'Exit' should have only + // one predecessor. Note that Exit could be an exit block for multiple + // nested loops, causing both of the edges to now be critical and need to + // be split. + SmallVector ExitPreds(pred_begin(Exit), pred_end(Exit)); + bool SplitLatchEdge = false; + for (SmallVectorImpl::iterator PI = ExitPreds.begin(), + PE = ExitPreds.end(); + PI != PE; ++PI) { + // We only need to split loop exit edges. + Loop *PredLoop = LI->getLoopFor(*PI); + if (!PredLoop || PredLoop->contains(Exit)) + continue; + if (isa((*PI)->getTerminator())) + continue; + SplitLatchEdge |= L->getLoopLatch() == *PI; + BasicBlock *ExitSplit = SplitCriticalEdge( + *PI, Exit, CriticalEdgeSplittingOptions(DT, LI).setPreserveLCSSA()); + ExitSplit->moveBefore(Exit); + } + assert(SplitLatchEdge && + "Despite splitting all preds, failed to split latch 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 *NewBI = BranchInst::Create(NewHeader, PHBI); + NewBI->setDebugLoc(PHBI->getDebugLoc()); + PHBI->eraseFromParent(); + + // With our CFG finalized, update DomTree if it is available. + if (DT) { + // Update OrigHeader to be dominated by the new header block. + DT->changeImmediateDominator(NewHeader, OrigPreheader); + DT->changeImmediateDominator(OrigHeader, OrigLatch); + + // Brute force incremental dominator tree update. Call + // findNearestCommonDominator on all CFG predecessors of each child of the + // original header. + DomTreeNode *OrigHeaderNode = DT->getNode(OrigHeader); + SmallVector HeaderChildren(OrigHeaderNode->begin(), + OrigHeaderNode->end()); + bool Changed; + do { + Changed = false; + for (unsigned I = 0, E = HeaderChildren.size(); I != E; ++I) { + DomTreeNode *Node = HeaderChildren[I]; + BasicBlock *BB = Node->getBlock(); + + pred_iterator PI = pred_begin(BB); + BasicBlock *NearestDom = *PI; + for (pred_iterator PE = pred_end(BB); PI != PE; ++PI) + NearestDom = DT->findNearestCommonDominator(NearestDom, *PI); + + // Remember if this changes the DomTree. + if (Node->getIDom()->getBlock() != NearestDom) { + DT->changeImmediateDominator(BB, NearestDom); + Changed = true; + } + } + + // If the dominator changed, this may have an effect on other + // predecessors, continue until we reach a fixpoint. + } while (Changed); + } } - - // 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); - - assert(L->getLoopPreheader() == NewPH && - "Invalid loop preheader after loop rotation"); + + 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, merge the - // OrigHeader block into OrigLatch. We know that they are joined by an - // unconditional branch. This is just a cleanup so the emitted code isn't - // too gross. - bool DidIt = MergeBlockIntoPredecessor(OrigHeader, this); - assert(DidIt && "Block merge failed??"); (void)DidIt; - + // 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, DT, LI); + + DEBUG(dbgs() << "LoopRotation: into "; L->dump()); + ++NumRotated; return true; } -