Index: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -10055,19 +10055,19 @@
 
   int64_t ElementSizeBytes = MemVT.getSizeInBits() / 8;
   LSBaseSDNode *FirstInChain = StoreNodes[0].MemNode;
-  unsigned EarliestNodeUsed = 0;
+  unsigned LatestNodeUsed = 0;
 
   for (unsigned i=0; i < NumElem; ++i) {
     // Find a chain for the new wide-store operand. Notice that some
     // of the store nodes that we found may not be selected for inclusion
     // in the wide store. The chain we use needs to be the chain of the
-    // earliest store node which is *used* and replaced by the wide store.
-    if (StoreNodes[i].SequenceNum > StoreNodes[EarliestNodeUsed].SequenceNum)
-      EarliestNodeUsed = i;
+    // latest store node which is *used* and replaced by the wide store.
+    if (StoreNodes[i].SequenceNum < StoreNodes[LatestNodeUsed].SequenceNum)
+      LatestNodeUsed = i;
   }
 
-  // The earliest Node in the DAG.
-  LSBaseSDNode *EarliestOp = StoreNodes[EarliestNodeUsed].MemNode;
+  // The latest Node in the DAG.
+  LSBaseSDNode *LatestOp = StoreNodes[LatestNodeUsed].MemNode;
   SDLoc DL(StoreNodes[0].MemNode);
 
   SDValue StoredVal;
@@ -10126,17 +10126,17 @@
     StoredVal = DAG.getConstant(StoreInt, StoreTy);
   }
 
-  SDValue NewStore = DAG.getStore(EarliestOp->getChain(), DL, StoredVal,
+  SDValue NewStore = DAG.getStore(LatestOp->getChain(), DL, StoredVal,
                                   FirstInChain->getBasePtr(),
                                   FirstInChain->getPointerInfo(),
                                   false, false,
                                   FirstInChain->getAlignment());
 
-  // Replace the first store with the new store
-  CombineTo(EarliestOp, NewStore);
+  // Replace the last store with the new store
+  CombineTo(LatestOp, NewStore);
   // Erase all other stores.
   for (unsigned i = 0; i < NumElem ; ++i) {
-    if (StoreNodes[i].MemNode == EarliestOp)
+    if (StoreNodes[i].MemNode == LatestOp)
       continue;
     StoreSDNode *St = cast<StoreSDNode>(StoreNodes[i].MemNode);
     // ReplaceAllUsesWith will replace all uses that existed when it was
@@ -10513,18 +10513,19 @@
   if (NumElem < 2)
     return false;
 
-  // The earliest Node in the DAG.
-  unsigned EarliestNodeUsed = 0;
-  LSBaseSDNode *EarliestOp = StoreNodes[EarliestNodeUsed].MemNode;
+  // The latest Node in the DAG.
+  unsigned LatestNodeUsed = 0;
   for (unsigned i=1; i<NumElem; ++i) {
     // Find a chain for the new wide-store operand. Notice that some
     // of the store nodes that we found may not be selected for inclusion
     // in the wide store. The chain we use needs to be the chain of the
-    // earliest store node which is *used* and replaced by the wide store.
-    if (StoreNodes[i].SequenceNum > StoreNodes[EarliestNodeUsed].SequenceNum)
-      EarliestNodeUsed = i;
+    // latest store node which is *used* and replaced by the wide store.
+    if (StoreNodes[i].SequenceNum < StoreNodes[LatestNodeUsed].SequenceNum)
+      LatestNodeUsed = i;
   }
 
+  LSBaseSDNode *LatestOp = StoreNodes[LatestNodeUsed].MemNode;
+
   // Find if it is better to use vectors or integers to load and store
   // to memory.
   EVT JointMemOpVT;
@@ -10546,7 +10547,7 @@
                                 false, false, false,
                                 FirstLoad->getAlignment());
 
-  SDValue NewStore = DAG.getStore(EarliestOp->getChain(), StoreDL, NewLoad,
+  SDValue NewStore = DAG.getStore(LatestOp->getChain(), StoreDL, NewLoad,
                                   FirstInChain->getBasePtr(),
                                   FirstInChain->getPointerInfo(), false, false,
                                   FirstInChain->getAlignment());
@@ -10564,12 +10565,12 @@
     DAG.ReplaceAllUsesOfValueWith(SDValue(Ld, 1), Ld->getChain());
   }
 
-  // Replace the first store with the new store.
-  CombineTo(EarliestOp, NewStore);
+  // Replace the last store with the new store.
+  CombineTo(LatestOp, NewStore);
   // Erase all other stores.
   for (unsigned i = 0; i < NumElem ; ++i) {
     // Remove all Store nodes.
-    if (StoreNodes[i].MemNode == EarliestOp)
+    if (StoreNodes[i].MemNode == LatestOp)
       continue;
     StoreSDNode *St = cast<StoreSDNode>(StoreNodes[i].MemNode);
     DAG.ReplaceAllUsesOfValueWith(SDValue(St, 0), St->getChain());
Index: llvm/trunk/test/CodeGen/AArch64/merge-store.ll
===================================================================
--- llvm/trunk/test/CodeGen/AArch64/merge-store.ll
+++ llvm/trunk/test/CodeGen/AArch64/merge-store.ll
@@ -0,0 +1,20 @@
+; RUN: llc -march=aarch64 %s -o - | FileCheck %s
+
+@g0 = external global <3 x float>, align 16
+@g1 = external global <3 x float>, align 4
+
+; CHECK: ldr s[[R0:[0-9]+]], {{\[}}[[R1:x[0-9]+]]{{\]}}, #4
+; CHECK: ld1.s { v[[R0]] }[1], {{\[}}[[R1]]{{\]}}
+; CHECK: str d[[R0]]
+
+define void @blam() {
+  %tmp4 = getelementptr inbounds <3 x float>, <3 x float>* @g1, i64 0, i64 0
+  %tmp5 = load <3 x float>, <3 x float>* @g0, align 16
+  %tmp6 = extractelement <3 x float> %tmp5, i64 0
+  store float %tmp6, float* %tmp4
+  %tmp7 = getelementptr inbounds float, float* %tmp4, i64 1
+  %tmp8 = load <3 x float>, <3 x float>* @g0, align 16
+  %tmp9 = extractelement <3 x float> %tmp8, i64 1
+  store float %tmp9, float* %tmp7
+  ret void;
+}
Index: llvm/trunk/test/CodeGen/X86/2012-11-28-merge-store-alias.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/2012-11-28-merge-store-alias.ll
+++ llvm/trunk/test/CodeGen/X86/2012-11-28-merge-store-alias.ll
@@ -2,7 +2,7 @@
 
 ; CHECK: merge_stores_can
 ; CHECK: callq foo
-; CHECK-NEXT: xorps %xmm0, %xmm0
+; CHECK: xorps %xmm0, %xmm0
 ; CHECK-NEXT: movups  %xmm0
 ; CHECK: callq foo
 ; CHECK: ret