3 files changed, 27 insertions, 10 deletions
diff --git a/lib/Transforms/Utils/InlineFunction.cpp b/lib/Transforms/Utils/InlineFunction.cpp
index a2ceded106b4..a40079ca8e76 100644
--- a/lib/Transforms/Utils/InlineFunction.cpp
+++ b/lib/Transforms/Utils/InlineFunction.cpp
@@ -760,7 +760,7 @@ static void PropagateParallelLoopAccessMetadata(CallSite CS,
 
 /// When inlining a function that contains noalias scope metadata,
 /// this metadata needs to be cloned so that the inlined blocks
-/// have different "unqiue scopes" at every call site. Were this not done, then
+/// have different "unique scopes" at every call site. Were this not done, then
 /// aliasing scopes from a function inlined into a caller multiple times could
 /// not be differentiated (and this would lead to miscompiles because the
 /// non-aliasing property communicated by the metadata could have
diff --git a/lib/Transforms/Utils/LoopUnrollPeel.cpp b/lib/Transforms/Utils/LoopUnrollPeel.cpp
index dc526a20c903..842cf31f2e3d 100644
--- a/lib/Transforms/Utils/LoopUnrollPeel.cpp
+++ b/lib/Transforms/Utils/LoopUnrollPeel.cpp
@@ -335,10 +335,12 @@ bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
   unsigned HeaderIdx = (LatchBR->getSuccessor(0) == Header ? 0 : 1);
 
   uint64_t TrueWeight, FalseWeight;
-  uint64_t ExitWeight = 0, BackEdgeWeight = 0;
+  uint64_t ExitWeight = 0, CurHeaderWeight = 0;
   if (LatchBR->extractProfMetadata(TrueWeight, FalseWeight)) {
     ExitWeight = HeaderIdx ? TrueWeight : FalseWeight;
-    BackEdgeWeight = HeaderIdx ? FalseWeight : TrueWeight;
+    // The # of times the loop body executes is the sum of the exit block
+    // weight and the # of times the backedges are taken.
+    CurHeaderWeight = TrueWeight + FalseWeight;
   }
 
   // For each peeled-off iteration, make a copy of the loop.
@@ -346,15 +348,14 @@ bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
     SmallVector<BasicBlock *, 8> NewBlocks;
     ValueToValueMapTy VMap;
 
-    // The exit weight of the previous iteration is the header entry weight
-    // of the current iteration. So this is exactly how many dynamic iterations
-    // the current peeled-off static iteration uses up.
+    // Subtract the exit weight from the current header weight -- the exit
+    // weight is exactly the weight of the previous iteration's header.
     // FIXME: due to the way the distribution is constructed, we need a
     // guard here to make sure we don't end up with non-positive weights.
-    if (ExitWeight < BackEdgeWeight)
-      BackEdgeWeight -= ExitWeight;
+    if (ExitWeight < CurHeaderWeight)
+      CurHeaderWeight -= ExitWeight;
     else
-      BackEdgeWeight = 1;
+      CurHeaderWeight = 1;
 
     cloneLoopBlocks(L, Iter, InsertTop, InsertBot, Exit,
                     NewBlocks, LoopBlocks, VMap, LVMap, LI);
@@ -388,6 +389,14 @@ bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
 
   // Adjust the branch weights on the loop exit.
   if (ExitWeight) {
+    // The backedge count is the difference of current header weight and
+    // current loop exit weight. If the current header weight is smaller than
+    // the current loop exit weight, we mark the loop backedge weight as 1.
+    uint64_t BackEdgeWeight = 0;
+    if (ExitWeight < CurHeaderWeight)
+      BackEdgeWeight = CurHeaderWeight - ExitWeight;
+    else
+      BackEdgeWeight = 1;
     MDBuilder MDB(LatchBR->getContext());
     MDNode *WeightNode =
         HeaderIdx ? MDB.createBranchWeights(ExitWeight, BackEdgeWeight)
diff --git a/lib/Transforms/Utils/SimplifyCFG.cpp b/lib/Transforms/Utils/SimplifyCFG.cpp
index 3846b21c502e..54390e77bb1f 100644
--- a/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -1574,12 +1574,20 @@ static bool sinkLastInstruction(ArrayRef<BasicBlock*> Blocks) {
     I0->getOperandUse(O).set(NewOperands[O]);
   I0->moveBefore(&*BBEnd->getFirstInsertionPt());
 
-  // Update metadata and IR flags.
+  // The debug location for the "common" instruction is the merged locations of
+  // all the commoned instructions.  We start with the original location of the
+  // "common" instruction and iteratively merge each location in the loop below.
+  DILocation *Loc = I0->getDebugLoc();
+
+  // Update metadata and IR flags, and merge debug locations.
   for (auto *I : Insts)
     if (I != I0) {
+      Loc = DILocation::getMergedLocation(Loc, I->getDebugLoc());
       combineMetadataForCSE(I0, I);
       I0->andIRFlags(I);
     }
+  if (!isa<CallInst>(I0))
+    I0->setDebugLoc(Loc);
 
   if (!isa<StoreInst>(I0)) {
     // canSinkLastInstruction checked that all instructions were used by