Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -449,6 +449,11 @@
                           EVT LoadResultTy, EVT &ExtVT, EVT &LoadedVT,
                           bool &NarrowLoad);
 
+    //// Helper function for MergeConsecutiveStores which merges the
+    //// component store chains.
+    SDValue getMergeStoreChains(SmallVectorImpl<MemOpLink> &StoreNodes,
+                                unsigned NumStores);
+
     /// This is a helper function for MergeConsecutiveStores. When the source
     /// elements of the consecutive stores are all constants or all extracted
     /// vector elements, try to merge them into one larger store.
@@ -12071,6 +12076,26 @@
   return false;
 }
 
+SDValue DAGCombiner::getMergeStoreChains(SmallVectorImpl<MemOpLink> &StoreNodes,
+                                         unsigned NumStores) {
+  SmallVector<SDValue, 8> Chains;
+  SmallPtrSet<const SDNode *, 8> Visited;
+  SDLoc StoreDL(StoreNodes[0].MemNode);
+
+  for (unsigned i = 0; i < NumStores; ++i) {
+    Visited.insert(StoreNodes[i].MemNode);
+  }
+
+  // don't include nodes that are children
+  for (unsigned i = 0; i < NumStores; ++i) {
+    if (Visited.count(StoreNodes[i].MemNode->getChain().getNode()) == 0)
+      Chains.push_back(StoreNodes[i].MemNode->getChain());
+  }
+
+  assert(Chains.size() > 0 && "Chain should have generated a chain");
+  return DAG.getNode(ISD::TokenFactor, StoreDL, MVT::Other, Chains);
+}
+
 bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
                   SmallVectorImpl<MemOpLink> &StoreNodes, EVT MemVT,
                   unsigned NumStores, bool IsConstantSrc, bool UseVector) {
@@ -12153,17 +12178,8 @@
     StoredVal = DAG.getConstant(StoreInt, DL, StoreTy);
   }
 
-  SmallVector<SDValue, 8> Chains;
-
-  // Gather all Chains we're inheriting. As generally all chains are
-  // equal, do minor check to remove obvious redundancies.
-  Chains.push_back(StoreNodes[0].MemNode->getChain());
-  for (unsigned i = 1; i < NumStores; ++i)
-    if (StoreNodes[0].MemNode->getChain() != StoreNodes[i].MemNode->getChain())
-      Chains.push_back(StoreNodes[i].MemNode->getChain());
-
   LSBaseSDNode *FirstInChain = StoreNodes[0].MemNode;
-  SDValue NewChain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Chains);
+  SDValue NewChain = getMergeStoreChains(StoreNodes, NumStores);
   SDValue NewStore = DAG.getStore(NewChain, DL, StoredVal,
                                   FirstInChain->getBasePtr(),
                                   FirstInChain->getPointerInfo(),
@@ -12192,6 +12208,54 @@
   if (BasePtr.Base.isUndef())
     return;
 
+  bool IsLoadSrc = isa<LoadSDNode>(St->getValue());
+  bool IsConstantSrc = isa<ConstantSDNode>(St->getValue()) ||
+                       isa<ConstantFPSDNode>(St->getValue());
+  bool IsExtractVecSrc =
+      (St->getValue().getOpcode() == ISD::EXTRACT_VECTOR_ELT ||
+       St->getValue().getOpcode() == ISD::EXTRACT_SUBVECTOR);
+  auto CandidateMatch = [&](StoreSDNode *Other, BaseIndexOffset &Ptr) -> bool {
+    if (Other->isVolatile() || Other->isIndexed())
+      return false;
+    // We can merge constant floats to equivalent integers
+    if (Other->getMemoryVT() != MemVT)
+      if (!(MemVT.isInteger() && MemVT.bitsEq(Other->getMemoryVT()) &&
+            isa<ConstantFPSDNode>(Other->getValue())))
+        return false;
+    Ptr = BaseIndexOffset::match(Other->getBasePtr(), DAG);
+    if (!Ptr.equalBaseIndex(BasePtr))
+      return false;
+    if (IsLoadSrc)
+      return isa<LoadSDNode>(Other->getValue());
+    if (IsConstantSrc)
+      return (isa<ConstantSDNode>(Other->getValue()) ||
+              isa<ConstantFPSDNode>(Other->getValue()));
+    if (IsExtractVecSrc)
+      return (Other->getValue().getOpcode() == ISD::EXTRACT_VECTOR_ELT ||
+              Other->getValue().getOpcode() == ISD::EXTRACT_SUBVECTOR);
+    return false;
+  };
+
+  // In the case FindBetterChain gives up, we capture direct chains of Stores
+
+  StoreSDNode *STChain = St;
+
+  int64_t LastOffset = BasePtr.Offset;
+  while (true) {
+    BaseIndexOffset Ptr;
+    if (StoreSDNode *Chain = dyn_cast<StoreSDNode>(STChain->getChain())) {
+      if (CandidateMatch(Chain, Ptr) && Ptr.Offset <= LastOffset) {
+        StoreNodes.push_back(MemOpLink(STChain, LastOffset));
+        LastOffset = Ptr.Offset;
+        STChain = Chain;
+        continue;
+      }
+    }
+    break;
+  }
+
+  SDNode *RootNode = (STChain->getChain()).getNode();
+
   // We looking for a root node which is an ancestor to all mergable
   // stores. We search up through a load, to our root and then down
   // through all children. For instance we will find Store{1,2,3} if
@@ -12203,13 +12267,11 @@
   // |-------|-------|
   // Load    Load    Store3
   // |       |
-  // Store1   Store2
+  // Store1  Store2
   //
   // FIXME: We should be able to climb and
   // descend TokenFactors to find candidates as well.
 
-  SDNode *RootNode = (St->getChain()).getNode();
-
   // Set of Parents of Candidates
   std::set<SDNode *> CandidateParents;
 
@@ -12221,39 +12283,13 @@
   } else
     CandidateParents.insert(RootNode);
 
-  bool IsLoadSrc = isa<LoadSDNode>(St->getValue());
-  bool IsConstantSrc = isa<ConstantSDNode>(St->getValue()) ||
-                       isa<ConstantFPSDNode>(St->getValue());
-  bool IsExtractVecSrc =
-      (St->getValue().getOpcode() == ISD::EXTRACT_VECTOR_ELT ||
-       St->getValue().getOpcode() == ISD::EXTRACT_SUBVECTOR);
-  auto CorrectValueKind = [&](StoreSDNode *Other) -> bool {
-    if (IsLoadSrc)
-      return isa<LoadSDNode>(Other->getValue());
-    if (IsConstantSrc)
-      return (isa<ConstantSDNode>(Other->getValue()) ||
-              isa<ConstantFPSDNode>(Other->getValue()));
-    if (IsExtractVecSrc)
-      return (Other->getValue().getOpcode() == ISD::EXTRACT_VECTOR_ELT ||
-              Other->getValue().getOpcode() == ISD::EXTRACT_SUBVECTOR);
-    return false;
-  };
-
   // check all parents of mergable children
   for (auto P = CandidateParents.begin(); P != CandidateParents.end(); ++P)
     for (auto I = (*P)->use_begin(), E = (*P)->use_end(); I != E; ++I)
       if (I.getOperandNo() == 0)
         if (StoreSDNode *OtherST = dyn_cast<StoreSDNode>(*I)) {
-          if (OtherST->isVolatile() || OtherST->isIndexed())
-            continue;
-          // We can merge constant floats to equivalent integers
-          if (OtherST->getMemoryVT() != MemVT)
-            if (!(MemVT.isInteger() && MemVT.bitsEq(OtherST->getMemoryVT()) &&
-                  isa<ConstantFPSDNode>(OtherST->getValue())))
-              continue;
-          BaseIndexOffset Ptr =
-              BaseIndexOffset::match(OtherST->getBasePtr(), DAG);
-          if (Ptr.equalBaseIndex(BasePtr) && CorrectValueKind(OtherST))
+          BaseIndexOffset Ptr;
+          if (CandidateMatch(OtherST, Ptr))
             StoreNodes.push_back(MemOpLink(OtherST, Ptr.Offset));
         }
 }
@@ -12611,14 +12647,6 @@
   if (NumElem < 2)
     return false;
 
-  // Collect the chains from all merged stores. Because the common case
-  // all chains are the same, check if we match the first Chain.
-  SmallVector<SDValue, 8> MergeStoreChains;
-  MergeStoreChains.push_back(StoreNodes[0].MemNode->getChain());
-  for (unsigned i = 1; i < NumElem; ++i)
-    if (StoreNodes[0].MemNode->getChain() != StoreNodes[i].MemNode->getChain())
-      MergeStoreChains.push_back(StoreNodes[i].MemNode->getChain());
-
   // Find if it is better to use vectors or integers to load and store
   // to memory.
   EVT JointMemOpVT;
@@ -12638,8 +12666,7 @@
                                 FirstLoad->getBasePtr(),
                                 FirstLoad->getPointerInfo(), FirstLoadAlign);
 
-  SDValue NewStoreChain =
-    DAG.getNode(ISD::TokenFactor, StoreDL, MVT::Other, MergeStoreChains);
+  SDValue NewStoreChain = getMergeStoreChains(StoreNodes, NumElem);
 
   AddToWorklist(NewStoreChain.getNode());