diff --git a/include/llvm/IR/DataLayout.h b/include/llvm/IR/DataLayout.h
index 25f7569e246..10630a26200 100644
--- a/include/llvm/IR/DataLayout.h
+++ b/include/llvm/IR/DataLayout.h
@@ -369,6 +369,17 @@ public:
   /// least as big as Width bits.
   Type *getSmallestLegalIntType(LLVMContext &C, unsigned Width = 0) const;
 
+  /// getLargestLegalIntType - Return the largest legal integer type, or null if
+  /// none are set.
+  Type *getLargestLegalIntType(LLVMContext &C) const {
+    unsigned LargestSize = getLargestLegalIntTypeSize();
+    return (LargestSize == 0) ? 0 : Type::getIntNTy(C, LargestSize);
+  }
+
+  /// getLargestLegalIntType - Return the size of largest legal integer type
+  /// size, or 0 if none are set.
+  unsigned getLargestLegalIntTypeSize() const;
+
   /// getIndexedOffset - return the offset from the beginning of the type for
   /// the specified indices.  This is used to implement getelementptr.
   uint64_t getIndexedOffset(Type *Ty, ArrayRef<Value *> Indices) const;
diff --git a/lib/IR/DataLayout.cpp b/lib/IR/DataLayout.cpp
index d786d33f9ca..6bdc09eaee4 100644
--- a/lib/IR/DataLayout.cpp
+++ b/lib/IR/DataLayout.cpp
@@ -629,6 +629,13 @@ Type *DataLayout::getSmallestLegalIntType(LLVMContext &C, unsigned Width) const
   return 0;
 }
 
+unsigned DataLayout::getLargestLegalIntTypeSize() const {
+  unsigned MaxWidth = 0;
+  for (unsigned i = 0, e = (unsigned)LegalIntWidths.size(); i != e; ++i)
+    MaxWidth = std::max<unsigned>(MaxWidth, LegalIntWidths[i]);
+  return MaxWidth;
+}
+
 uint64_t DataLayout::getIndexedOffset(Type *ptrTy,
                                       ArrayRef<Value *> Indices) const {
   Type *Ty = ptrTy;
diff --git a/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index 8f61ffd84bf..9912d3dafed 100644
--- a/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -170,14 +170,17 @@ bool MemsetRange::isProfitableToUseMemset(const DataLayout &TD) const {
   // pessimize the llvm optimizer.
   //
   // Since we don't have perfect knowledge here, make some assumptions: assume
-  // the maximum GPR width is the same size as the pointer size and assume that
-  // this width can be stored.  If so, check to see whether we will end up
-  // actually reducing the number of stores used.
+  // the maximum GPR width is the same size as the largest legal integer
+  // size. If so, check to see whether we will end up actually reducing the
+  // number of stores used.
   unsigned Bytes = unsigned(End-Start);
-  unsigned NumPointerStores = Bytes/TD.getPointerSize();
+  unsigned MaxIntSize = TD.getLargestLegalIntTypeSize();
+  if (MaxIntSize == 0)
+    MaxIntSize = 1;
+  unsigned NumPointerStores = Bytes / MaxIntSize;
 
   // Assume the remaining bytes if any are done a byte at a time.
-  unsigned NumByteStores = Bytes - NumPointerStores*TD.getPointerSize();
+  unsigned NumByteStores = Bytes - NumPointerStores * MaxIntSize;
 
   // If we will reduce the # stores (according to this heuristic), do the
   // transformation.  This encourages merging 4 x i8 -> i32 and 2 x i16 -> i32