+/// RewriteUsesOfClonedInstructions - We just cloned the instructions from the
+/// old header into the preheader. If there were uses of the values produced by
+/// these instruction that were outside of the loop, we have to insert PHI nodes
+/// to merge the two values. Do this now.
+static void RewriteUsesOfClonedInstructions(BasicBlock *OrigHeader,
+ BasicBlock *OrigPreheader,
+ ValueToValueMapTy &ValueMap) {
+ // Remove PHI node entries that are no longer live.
+ BasicBlock::iterator I, E = OrigHeader->end();
+ for (I = OrigHeader->begin(); PHINode *PN = dyn_cast<PHINode>(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
+ // and the loop "next" value in the original header.
+ 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;
+
+ // 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<Instruction>(U.getUser());
+ if (!isa<PHINode>(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) {
+ U = OrigPreHeaderVal;
+ 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<DbgInfoIntrinsic>(I))
+ continue;
+
+ switch (I->getOpcode()) {
+ default:
+ return false;
+ case Instruction::GetElementPtr:
+ // GEPs are cheap if all indices are constant.
+ if (!cast<GEPOperator>(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<Constant>(I->getOperand(0))
+ ? I->getOperand(0)
+ : !isa<Constant>(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<Instruction>(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<BranchInst>(Latch->getTerminator());
+ if (!Jmp || !Jmp->isUnconditional())
+ return false;
+
+ BasicBlock *LastExit = Latch->getSinglePredecessor();
+ if (!LastExit || !L->isLoopExiting(LastExit))
+ return false;
+
+ BranchInst *BI = dyn_cast<BranchInst>(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");