diff --git a/include/llvm/Target/TargetLowering.h b/include/llvm/Target/TargetLowering.h
index 46d860c3c2f..3a7053f2882 100644
--- a/include/llvm/Target/TargetLowering.h
+++ b/include/llvm/Target/TargetLowering.h
@@ -413,6 +413,15 @@ public:
        getOperationAction(Op, VT) == Custom);
   }
 
+  /// isOperationLegalOrPromote - Return true if the specified operation is
+  /// legal on this target or can be made legal using promotion. This
+  /// is used to help guide high-level lowering decisions.
+  bool isOperationLegalOrPromote(unsigned Op, EVT VT) const {
+    return (VT == MVT::Other || isTypeLegal(VT)) &&
+      (getOperationAction(Op, VT) == Legal ||
+       getOperationAction(Op, VT) == Promote);
+  }
+
   /// isOperationExpand - Return true if the specified operation is illegal on
   /// this target or unlikely to be made legal with custom lowering. This is
   /// used to help guide high-level lowering decisions.
diff --git a/lib/Target/TargetTransformImpl.cpp b/lib/Target/TargetTransformImpl.cpp
index 1f568506d9a..3d640dc0235 100644
--- a/lib/Target/TargetTransformImpl.cpp
+++ b/lib/Target/TargetTransformImpl.cpp
@@ -179,12 +179,22 @@ unsigned VectorTargetTransformImpl::getArithmeticInstrCost(unsigned Opcode,
 
   std::pair<unsigned, MVT> LT = getTypeLegalizationCost(Ty);
 
-  if (!TLI->isOperationExpand(ISD, LT.second)) {
-    // The operation is legal. Assume it costs 1. Multiply
-    // by the type-legalization overhead.
+  if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
+    // The operation is legal. Assume it costs 1.
+    // If the type is split to multiple registers, assume that thre is some
+    // overhead to this.
+    // TODO: Once we have extract/insert subvector cost we need to use them.
+    if (LT.first > 1)
+      return LT.first * 2;
     return LT.first * 1;
   }
 
+  if (!TLI->isOperationExpand(ISD, LT.second)) {
+    // If the operation is custom lowered then assume
+    // thare the code is twice as expensive.
+    return LT.first * 2;
+  }
+
   // Else, assume that we need to scalarize this op.
   if (Ty->isVectorTy()) {
     unsigned Num = Ty->getVectorNumElements();
diff --git a/test/Transforms/LoopVectorize/X86/gcc-examples.ll b/test/Transforms/LoopVectorize/X86/gcc-examples.ll
index 574c529834a..156e7454a4c 100644
--- a/test/Transforms/LoopVectorize/X86/gcc-examples.ll
+++ b/test/Transforms/LoopVectorize/X86/gcc-examples.ll
@@ -9,9 +9,9 @@ target triple = "x86_64-apple-macosx10.8.0"
 
 ; Select VF = 8;
 ;CHECK: @example1
-;CHECK: load <8 x i32>
-;CHECK: add nsw <8 x i32>
-;CHECK: store <8 x i32>
+;CHECK: load <4 x i32>
+;CHECK: add nsw <4 x i32>
+;CHECK: store <4 x i32>
 ;CHECK: ret void
 define void @example1() nounwind uwtable ssp {
   br label %1