Index: llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -4903,30 +4903,13 @@
       // The current type we are using is too large. Find a better size.
       NewVT = FindMemType(DAG, TLI, LdWidth, WidenVT, LdAlign, WidthDiff);
       NewVTWidth = NewVT.getSizeInBits();
-      L = DAG.getLoad(NewVT, dl, Chain, BasePtr,
-                      LD->getPointerInfo().getWithOffset(Offset),
-                      MinAlign(Align, Increment), MMOFlags, AAInfo);
-      LdChain.push_back(L.getValue(1));
-      if (L->getValueType(0).isVector() && NewVTWidth >= LdWidth) {
-        // Later code assumes the vector loads produced will be mergeable, so we
-        // must pad the final entry up to the previous width. Scalars are
-        // combined separately.
-        SmallVector<SDValue, 16> Loads;
-        Loads.push_back(L);
-        unsigned size = L->getValueSizeInBits(0);
-        while (size < LdOp->getValueSizeInBits(0)) {
-          Loads.push_back(DAG.getUNDEF(L->getValueType(0)));
-          size += L->getValueSizeInBits(0);
-        }
-        L = DAG.getNode(ISD::CONCAT_VECTORS, dl, LdOp->getValueType(0), Loads);
-      }
-    } else {
-      L = DAG.getLoad(NewVT, dl, Chain, BasePtr,
-                      LD->getPointerInfo().getWithOffset(Offset),
-                      MinAlign(Align, Increment), MMOFlags, AAInfo);
-      LdChain.push_back(L.getValue(1));
     }
 
+    L = DAG.getLoad(NewVT, dl, Chain, BasePtr,
+                    LD->getPointerInfo().getWithOffset(Offset),
+                    MinAlign(Align, Increment), MMOFlags, AAInfo);
+    LdChain.push_back(L.getValue(1));
+
     LdOps.push_back(L);
     LdOp = L;
 
@@ -4959,9 +4942,20 @@
   for (--i; i >= 0; --i) {
     EVT NewLdTy = LdOps[i].getValueType();
     if (NewLdTy != LdTy) {
+      // We may need to fill the rest with undefs to build the larger vector.
+      unsigned NumOps = NewLdTy.getSizeInBits() / LdTy.getSizeInBits();
+      SmallVector<SDValue, 16> WidenOps(NumOps);
+      SDValue UndefVal = DAG.getUNDEF(LdTy);
+      {
+        unsigned i = 0;
+        for (; i != End - Idx; ++i)
+          WidenOps[i] = ConcatOps[Idx + i];
+        for (; i != NumOps; ++i)
+          WidenOps[i] = UndefVal;
+      }
       // Create a larger vector.
-      ConcatOps[End-1] = DAG.getNode(ISD::CONCAT_VECTORS, dl, NewLdTy,
-                                     makeArrayRef(&ConcatOps[Idx], End - Idx));
+      ConcatOps[End - 1] =
+          DAG.getNode(ISD::CONCAT_VECTORS, dl, NewLdTy, WidenOps);
       Idx = End - 1;
       LdTy = NewLdTy;
     }