3 files changed, 46 insertions, 25 deletions

diff --git a/lib/Transforms/Scalar/JumpThreading.cpp b/lib/Transforms/Scalar/JumpThreading.cpp
index 4056cc5cb346..dc9143bebc45 100644
--- a/lib/Transforms/Scalar/JumpThreading.cpp
+++ b/lib/Transforms/Scalar/JumpThreading.cpp
@@ -64,6 +64,11 @@ ImplicationSearchThreshold(
            "condition to use to thread over a weaker condition"),
   cl::init(3), cl::Hidden);
 
+static cl::opt<bool> PrintLVIAfterJumpThreading(
+    "print-lvi-after-jump-threading",
+    cl::desc("Print the LazyValueInfo cache after JumpThreading"), cl::init(false),
+    cl::Hidden);
+
 namespace {
   /// This pass performs 'jump threading', which looks at blocks that have
   /// multiple predecessors and multiple successors.  If one or more of the
@@ -93,9 +98,10 @@ namespace {
     bool runOnFunction(Function &F) override;
 
     void getAnalysisUsage(AnalysisUsage &AU) const override {
+      if (PrintLVIAfterJumpThreading)
+        AU.addRequired<DominatorTreeWrapperPass>();
       AU.addRequired<AAResultsWrapperPass>();
       AU.addRequired<LazyValueInfoWrapperPass>();
-      AU.addPreserved<LazyValueInfoWrapperPass>();
       AU.addPreserved<GlobalsAAWrapperPass>();
       AU.addRequired<TargetLibraryInfoWrapperPass>();
     }
@@ -137,8 +143,14 @@ bool JumpThreading::runOnFunction(Function &F) {
     BFI.reset(new BlockFrequencyInfo(F, *BPI, LI));
   }
 
-  return Impl.runImpl(F, TLI, LVI, AA, HasProfileData, std::move(BFI),
-                      std::move(BPI));
+  bool Changed = Impl.runImpl(F, TLI, LVI, AA, HasProfileData, std::move(BFI),
+                              std::move(BPI));
+  if (PrintLVIAfterJumpThreading) {
+    dbgs() << "LVI for function '" << F.getName() << "':\n";
+    LVI->printLVI(F, getAnalysis<DominatorTreeWrapperPass>().getDomTree(),
+                  dbgs());
+  }
+  return Changed;
 }
 
 PreservedAnalyses JumpThreadingPass::run(Function &F,
@@ -231,13 +243,15 @@ bool JumpThreadingPass::runImpl(Function &F, TargetLibraryInfo *TLI_,
       // Can't thread an unconditional jump, but if the block is "almost
       // empty", we can replace uses of it with uses of the successor and make
       // this dead.
-      // We should not eliminate the loop header either, because eliminating
-      // a loop header might later prevent LoopSimplify from transforming nested
-      // loops into simplified form.
+      // We should not eliminate the loop header or latch either, because
+      // eliminating a loop header or latch might later prevent LoopSimplify
+      // from transforming nested loops into simplified form. We will rely on
+      // later passes in backend to clean up empty blocks.
       if (BI && BI->isUnconditional() &&
           BB != &BB->getParent()->getEntryBlock() &&
           // If the terminator is the only non-phi instruction, try to nuke it.
-          BB->getFirstNonPHIOrDbg()->isTerminator() && !LoopHeaders.count(BB)) {
+          BB->getFirstNonPHIOrDbg()->isTerminator() && !LoopHeaders.count(BB) &&
+          !LoopHeaders.count(BI->getSuccessor(0))) {
         // FIXME: It is always conservatively correct to drop the info
         // for a block even if it doesn't get erased.  This isn't totally
         // awesome, but it allows us to use AssertingVH to prevent nasty
diff --git a/lib/Transforms/Utils/LoopUtils.cpp b/lib/Transforms/Utils/LoopUtils.cpp
index 58b70be95d99..3c522786641a 100644
--- a/lib/Transforms/Utils/LoopUtils.cpp
+++ b/lib/Transforms/Utils/LoopUtils.cpp
@@ -1376,16 +1376,21 @@ Value *llvm::createTargetReduction(IRBuilder<> &Builder,
   }
 }
 
-void llvm::propagateIRFlags(Value *I, ArrayRef<Value *> VL) {
-  if (auto *VecOp = dyn_cast<Instruction>(I)) {
-    if (auto *I0 = dyn_cast<Instruction>(VL[0])) {
-      // VecOVp is initialized to the 0th scalar, so start counting from index
-      // '1'.
-      VecOp->copyIRFlags(I0);
-      for (int i = 1, e = VL.size(); i < e; ++i) {
-        if (auto *Scalar = dyn_cast<Instruction>(VL[i]))
-          VecOp->andIRFlags(Scalar);
-      }
-    }
+void llvm::propagateIRFlags(Value *I, ArrayRef<Value *> VL, Value *OpValue) {
+  auto *VecOp = dyn_cast<Instruction>(I);
+  if (!VecOp)
+    return;
+  auto *Intersection = (OpValue == nullptr) ? dyn_cast<Instruction>(VL[0])
+                                            : dyn_cast<Instruction>(OpValue);
+  if (!Intersection)
+    return;
+  const unsigned Opcode = Intersection->getOpcode();
+  VecOp->copyIRFlags(Intersection);
+  for (auto *V : VL) {
+    auto *Instr = dyn_cast<Instruction>(V);
+    if (!Instr)
+      continue;
+    if (OpValue == nullptr || Opcode == Instr->getOpcode())
+      VecOp->andIRFlags(V);
   }
 }
diff --git a/lib/Transforms/Utils/SimplifyCFG.cpp b/lib/Transforms/Utils/SimplifyCFG.cpp
index dee658f98393..8784b9702141 100644
--- a/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -5656,20 +5656,22 @@ static bool TryToMergeLandingPad(LandingPadInst *LPad, BranchInst *BI,
 bool SimplifyCFGOpt::SimplifyUncondBranch(BranchInst *BI,
                                           IRBuilder<> &Builder) {
   BasicBlock *BB = BI->getParent();
+  BasicBlock *Succ = BI->getSuccessor(0);
 
   if (SinkCommon && SinkThenElseCodeToEnd(BI))
     return true;
 
   // If the Terminator is the only non-phi instruction, simplify the block.
-  // if LoopHeader is provided, check if the block is a loop header
-  // (This is for early invocations before loop simplify and vectorization
-  // to keep canonical loop forms for nested loops.
-  // These blocks can be eliminated when the pass is invoked later
-  // in the back-end.)
+  // if LoopHeader is provided, check if the block or its successor is a loop
+  // header (This is for early invocations before loop simplify and
+  // vectorization to keep canonical loop forms for nested loops. These blocks
+  // can be eliminated when the pass is invoked later in the back-end.)
+  bool NeedCanonicalLoop =
+      !LateSimplifyCFG &&
+      (LoopHeaders && (LoopHeaders->count(BB) || LoopHeaders->count(Succ)));
   BasicBlock::iterator I = BB->getFirstNonPHIOrDbg()->getIterator();
   if (I->isTerminator() && BB != &BB->getParent()->getEntryBlock() &&
-      (!LoopHeaders || !LoopHeaders->count(BB)) &&
-      TryToSimplifyUncondBranchFromEmptyBlock(BB))
+      !NeedCanonicalLoop && TryToSimplifyUncondBranchFromEmptyBlock(BB))
     return true;
 
   // If the only instruction in the block is a seteq/setne comparison