+
+ return BEBlock;
+}
+
+/// \brief Simplify one loop and queue further loops for simplification.
+///
+/// FIXME: Currently this accepts both lots of analyses that it uses and a raw
+/// Pass pointer. The Pass pointer is used by numerous utilities to update
+/// specific analyses. Rather than a pass it would be much cleaner and more
+/// explicit if they accepted the analysis directly and then updated it.
+static bool simplifyOneLoop(Loop *L, SmallVectorImpl<Loop *> &Worklist,
+ AliasAnalysis *AA, DominatorTree *DT, LoopInfo *LI,
+ ScalarEvolution *SE, Pass *PP) {
+ bool Changed = false;
+ReprocessLoop:
+
+ // Check to see that no blocks (other than the header) in this loop have
+ // predecessors that are not in the loop. This is not valid for natural
+ // loops, but can occur if the blocks are unreachable. Since they are
+ // unreachable we can just shamelessly delete those CFG edges!
+ for (Loop::block_iterator BB = L->block_begin(), E = L->block_end();
+ BB != E; ++BB) {
+ if (*BB == L->getHeader()) continue;
+
+ SmallPtrSet<BasicBlock*, 4> BadPreds;
+ for (pred_iterator PI = pred_begin(*BB),
+ PE = pred_end(*BB); PI != PE; ++PI) {
+ BasicBlock *P = *PI;
+ if (!L->contains(P))
+ BadPreds.insert(P);
+ }
+
+ // Delete each unique out-of-loop (and thus dead) predecessor.
+ for (SmallPtrSet<BasicBlock*, 4>::iterator I = BadPreds.begin(),
+ E = BadPreds.end(); I != E; ++I) {
+
+ DEBUG(dbgs() << "LoopSimplify: Deleting edge from dead predecessor "
+ << (*I)->getName() << "\n");
+
+ // Inform each successor of each dead pred.
+ for (succ_iterator SI = succ_begin(*I), SE = succ_end(*I); SI != SE; ++SI)
+ (*SI)->removePredecessor(*I);
+ // Zap the dead pred's terminator and replace it with unreachable.
+ TerminatorInst *TI = (*I)->getTerminator();
+ TI->replaceAllUsesWith(UndefValue::get(TI->getType()));
+ (*I)->getTerminator()->eraseFromParent();
+ new UnreachableInst((*I)->getContext(), *I);
+ Changed = true;
+ }
+ }
+
+ // If there are exiting blocks with branches on undef, resolve the undef in
+ // the direction which will exit the loop. This will help simplify loop
+ // trip count computations.
+ SmallVector<BasicBlock*, 8> ExitingBlocks;
+ L->getExitingBlocks(ExitingBlocks);
+ for (SmallVectorImpl<BasicBlock *>::iterator I = ExitingBlocks.begin(),
+ E = ExitingBlocks.end(); I != E; ++I)
+ if (BranchInst *BI = dyn_cast<BranchInst>((*I)->getTerminator()))
+ if (BI->isConditional()) {
+ if (UndefValue *Cond = dyn_cast<UndefValue>(BI->getCondition())) {
+
+ DEBUG(dbgs() << "LoopSimplify: Resolving \"br i1 undef\" to exit in "
+ << (*I)->getName() << "\n");
+
+ BI->setCondition(ConstantInt::get(Cond->getType(),
+ !L->contains(BI->getSuccessor(0))));
+
+ // This may make the loop analyzable, force SCEV recomputation.
+ if (SE)
+ SE->forgetLoop(L);
+
+ Changed = true;
+ }
+ }
+
+ // Does the loop already have a preheader? If so, don't insert one.
+ BasicBlock *Preheader = L->getLoopPreheader();
+ if (!Preheader) {
+ Preheader = InsertPreheaderForLoop(L, PP);
+ if (Preheader) {
+ ++NumInserted;
+ Changed = true;
+ }
+ }
+
+ // Next, check to make sure that all exit nodes of the loop only have
+ // predecessors that are inside of the loop. This check guarantees that the
+ // loop preheader/header will dominate the exit blocks. If the exit block has
+ // predecessors from outside of the loop, split the edge now.
+ SmallVector<BasicBlock*, 8> ExitBlocks;
+ L->getExitBlocks(ExitBlocks);
+
+ SmallSetVector<BasicBlock *, 8> ExitBlockSet(ExitBlocks.begin(),
+ ExitBlocks.end());
+ for (SmallSetVector<BasicBlock *, 8>::iterator I = ExitBlockSet.begin(),
+ E = ExitBlockSet.end(); I != E; ++I) {
+ BasicBlock *ExitBlock = *I;
+ for (pred_iterator PI = pred_begin(ExitBlock), PE = pred_end(ExitBlock);
+ PI != PE; ++PI)
+ // Must be exactly this loop: no subloops, parent loops, or non-loop preds
+ // allowed.
+ if (!L->contains(*PI)) {
+ if (rewriteLoopExitBlock(L, ExitBlock, PP)) {
+ ++NumInserted;
+ Changed = true;
+ }
+ break;
+ }
+ }
+
+ // If the header has more than two predecessors at this point (from the
+ // preheader and from multiple backedges), we must adjust the loop.
+ BasicBlock *LoopLatch = L->getLoopLatch();
+ if (!LoopLatch) {
+ // If this is really a nested loop, rip it out into a child loop. Don't do
+ // this for loops with a giant number of backedges, just factor them into a
+ // common backedge instead.
+ if (L->getNumBackEdges() < 8) {
+ if (Loop *OuterL = separateNestedLoop(L, Preheader, AA, DT, LI, SE, PP)) {
+ ++NumNested;
+ // Enqueue the outer loop as it should be processed next in our
+ // depth-first nest walk.
+ Worklist.push_back(OuterL);
+
+ // This is a big restructuring change, reprocess the whole loop.
+ Changed = true;
+ // GCC doesn't tail recursion eliminate this.
+ // FIXME: It isn't clear we can't rely on LLVM to TRE this.
+ goto ReprocessLoop;
+ }
+ }
+
+ // If we either couldn't, or didn't want to, identify nesting of the loops,
+ // insert a new block that all backedges target, then make it jump to the
+ // loop header.
+ LoopLatch = insertUniqueBackedgeBlock(L, Preheader, AA, DT, LI);
+ if (LoopLatch) {
+ ++NumInserted;
+ Changed = true;
+ }
+ }
+
+ // Scan over the PHI nodes in the loop header. Since they now have only two
+ // incoming values (the loop is canonicalized), we may have simplified the PHI
+ // down to 'X = phi [X, Y]', which should be replaced with 'Y'.
+ PHINode *PN;
+ for (BasicBlock::iterator I = L->getHeader()->begin();
+ (PN = dyn_cast<PHINode>(I++)); )
+ if (Value *V = SimplifyInstruction(PN, nullptr, nullptr, DT)) {
+ if (AA) AA->deleteValue(PN);
+ if (SE) SE->forgetValue(PN);
+ PN->replaceAllUsesWith(V);
+ PN->eraseFromParent();
+ }
+
+ // If this loop has multiple exits and the exits all go to the same
+ // block, attempt to merge the exits. This helps several passes, such
+ // as LoopRotation, which do not support loops with multiple exits.
+ // SimplifyCFG also does this (and this code uses the same utility
+ // function), however this code is loop-aware, where SimplifyCFG is
+ // not. That gives it the advantage of being able to hoist
+ // loop-invariant instructions out of the way to open up more
+ // opportunities, and the disadvantage of having the responsibility
+ // to preserve dominator information.
+ bool UniqueExit = true;
+ if (!ExitBlocks.empty())
+ for (unsigned i = 1, e = ExitBlocks.size(); i != e; ++i)
+ if (ExitBlocks[i] != ExitBlocks[0]) {
+ UniqueExit = false;
+ break;
+ }
+ if (UniqueExit) {
+ for (unsigned i = 0, e = ExitingBlocks.size(); i != e; ++i) {
+ BasicBlock *ExitingBlock = ExitingBlocks[i];
+ if (!ExitingBlock->getSinglePredecessor()) continue;
+ BranchInst *BI = dyn_cast<BranchInst>(ExitingBlock->getTerminator());
+ if (!BI || !BI->isConditional()) continue;
+ CmpInst *CI = dyn_cast<CmpInst>(BI->getCondition());
+ if (!CI || CI->getParent() != ExitingBlock) continue;
+
+ // Attempt to hoist out all instructions except for the
+ // comparison and the branch.
+ bool AllInvariant = true;
+ bool AnyInvariant = false;
+ for (BasicBlock::iterator I = ExitingBlock->begin(); &*I != BI; ) {
+ Instruction *Inst = I++;
+ // Skip debug info intrinsics.
+ if (isa<DbgInfoIntrinsic>(Inst))
+ continue;
+ if (Inst == CI)
+ continue;
+ if (!L->makeLoopInvariant(Inst, AnyInvariant,
+ Preheader ? Preheader->getTerminator()
+ : nullptr)) {
+ AllInvariant = false;
+ break;
+ }
+ }
+ if (AnyInvariant) {
+ Changed = true;
+ // The loop disposition of all SCEV expressions that depend on any
+ // hoisted values have also changed.
+ if (SE)
+ SE->forgetLoopDispositions(L);
+ }
+ if (!AllInvariant) continue;
+
+ // The block has now been cleared of all instructions except for
+ // a comparison and a conditional branch. SimplifyCFG may be able
+ // to fold it now.
+ if (!FoldBranchToCommonDest(BI)) continue;
+
+ // Success. The block is now dead, so remove it from the loop,
+ // update the dominator tree and delete it.
+ DEBUG(dbgs() << "LoopSimplify: Eliminating exiting block "
+ << ExitingBlock->getName() << "\n");
+
+ // Notify ScalarEvolution before deleting this block. Currently assume the
+ // parent loop doesn't change (spliting edges doesn't count). If blocks,
+ // CFG edges, or other values in the parent loop change, then we need call
+ // to forgetLoop() for the parent instead.
+ if (SE)
+ SE->forgetLoop(L);
+
+ assert(pred_begin(ExitingBlock) == pred_end(ExitingBlock));
+ Changed = true;
+ LI->removeBlock(ExitingBlock);
+
+ DomTreeNode *Node = DT->getNode(ExitingBlock);
+ const std::vector<DomTreeNodeBase<BasicBlock> *> &Children =
+ Node->getChildren();
+ while (!Children.empty()) {
+ DomTreeNode *Child = Children.front();
+ DT->changeImmediateDominator(Child, Node->getIDom());
+ }
+ DT->eraseNode(ExitingBlock);
+
+ BI->getSuccessor(0)->removePredecessor(ExitingBlock);
+ BI->getSuccessor(1)->removePredecessor(ExitingBlock);
+ ExitingBlock->eraseFromParent();
+ }
+ }
+
+ return Changed;
+}
+
+bool llvm::simplifyLoop(Loop *L, DominatorTree *DT, LoopInfo *LI, Pass *PP,
+ AliasAnalysis *AA, ScalarEvolution *SE) {
+ bool Changed = false;
+
+ // Worklist maintains our depth-first queue of loops in this nest to process.
+ SmallVector<Loop *, 4> Worklist;
+ Worklist.push_back(L);
+
+ // Walk the worklist from front to back, pushing newly found sub loops onto
+ // the back. This will let us process loops from back to front in depth-first
+ // order. We can use this simple process because loops form a tree.
+ for (unsigned Idx = 0; Idx != Worklist.size(); ++Idx) {
+ Loop *L2 = Worklist[Idx];
+ for (Loop::iterator I = L2->begin(), E = L2->end(); I != E; ++I)
+ Worklist.push_back(*I);
+ }
+
+ while (!Worklist.empty())
+ Changed |= simplifyOneLoop(Worklist.pop_back_val(), Worklist, AA, DT, LI, SE, PP);
+
+ return Changed;
+}
+
+namespace {
+ struct LoopSimplify : public FunctionPass {
+ static char ID; // Pass identification, replacement for typeid
+ LoopSimplify() : FunctionPass(ID) {
+ initializeLoopSimplifyPass(*PassRegistry::getPassRegistry());
+ }
+
+ // AA - If we have an alias analysis object to update, this is it, otherwise
+ // this is null.
+ AliasAnalysis *AA;
+ DominatorTree *DT;
+ LoopInfo *LI;
+ ScalarEvolution *SE;
+
+ bool runOnFunction(Function &F) override;
+
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
+ // We need loop information to identify the loops...
+ AU.addRequired<DominatorTreeWrapperPass>();
+ AU.addPreserved<DominatorTreeWrapperPass>();
+
+ AU.addRequired<LoopInfo>();
+ AU.addPreserved<LoopInfo>();
+
+ AU.addPreserved<AliasAnalysis>();
+ AU.addPreserved<ScalarEvolution>();
+ AU.addPreserved<DependenceAnalysis>();
+ AU.addPreservedID(BreakCriticalEdgesID); // No critical edges added.
+ }
+
+ /// verifyAnalysis() - Verify LoopSimplifyForm's guarantees.
+ void verifyAnalysis() const override;
+ };
+}
+
+char LoopSimplify::ID = 0;
+INITIALIZE_PASS_BEGIN(LoopSimplify, "loop-simplify",
+ "Canonicalize natural loops", true, false)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LoopInfo)
+INITIALIZE_PASS_END(LoopSimplify, "loop-simplify",
+ "Canonicalize natural loops", true, false)
+
+// Publicly exposed interface to pass...
+char &llvm::LoopSimplifyID = LoopSimplify::ID;
+Pass *llvm::createLoopSimplifyPass() { return new LoopSimplify(); }
+
+/// runOnFunction - Run down all loops in the CFG (recursively, but we could do
+/// it in any convenient order) inserting preheaders...
+///
+bool LoopSimplify::runOnFunction(Function &F) {
+ bool Changed = false;
+ AA = getAnalysisIfAvailable<AliasAnalysis>();
+ LI = &getAnalysis<LoopInfo>();
+ DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+ SE = getAnalysisIfAvailable<ScalarEvolution>();
+
+ // Simplify each loop nest in the function.
+ for (LoopInfo::iterator I = LI->begin(), E = LI->end(); I != E; ++I)
+ Changed |= simplifyLoop(*I, DT, LI, this, AA, SE);
+
+ return Changed;
+}
+
+// FIXME: Restore this code when we re-enable verification in verifyAnalysis
+// below.
+#if 0
+static void verifyLoop(Loop *L) {
+ // Verify subloops.
+ for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I)
+ verifyLoop(*I);
+
+ // It used to be possible to just assert L->isLoopSimplifyForm(), however
+ // with the introduction of indirectbr, there are now cases where it's
+ // not possible to transform a loop as necessary. We can at least check
+ // that there is an indirectbr near any time there's trouble.
+
+ // Indirectbr can interfere with preheader and unique backedge insertion.
+ if (!L->getLoopPreheader() || !L->getLoopLatch()) {
+ bool HasIndBrPred = false;
+ for (pred_iterator PI = pred_begin(L->getHeader()),
+ PE = pred_end(L->getHeader()); PI != PE; ++PI)
+ if (isa<IndirectBrInst>((*PI)->getTerminator())) {
+ HasIndBrPred = true;
+ break;
+ }
+ assert(HasIndBrPred &&
+ "LoopSimplify has no excuse for missing loop header info!");
+ (void)HasIndBrPred;
+ }
+
+ // Indirectbr can interfere with exit block canonicalization.
+ if (!L->hasDedicatedExits()) {
+ bool HasIndBrExiting = false;
+ SmallVector<BasicBlock*, 8> ExitingBlocks;
+ L->getExitingBlocks(ExitingBlocks);
+ for (unsigned i = 0, e = ExitingBlocks.size(); i != e; ++i) {
+ if (isa<IndirectBrInst>((ExitingBlocks[i])->getTerminator())) {
+ HasIndBrExiting = true;
+ break;
+ }
+ }
+
+ assert(HasIndBrExiting &&
+ "LoopSimplify has no excuse for missing exit block info!");
+ (void)HasIndBrExiting;
+ }
+}
+#endif
+
+void LoopSimplify::verifyAnalysis() const {
+ // FIXME: This routine is being called mid-way through the loop pass manager
+ // as loop passes destroy this analysis. That's actually fine, but we have no
+ // way of expressing that here. Once all of the passes that destroy this are
+ // hoisted out of the loop pass manager we can add back verification here.
+#if 0
+ for (LoopInfo::iterator I = LI->begin(), E = LI->end(); I != E; ++I)
+ verifyLoop(*I);
+#endif