diff --git a/lib/Transforms/InstCombine/InstCombineCalls.cpp b/lib/Transforms/InstCombine/InstCombineCalls.cpp
index d4b583b3a7d..d4bdd75fa82 100644
--- a/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -800,6 +800,11 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
 
   case Intrinsic::ppc_altivec_vperm:
     // Turn vperm(V1,V2,mask) -> shuffle(V1,V2,mask) if mask is a constant.
+    // Note that ppc_altivec_vperm has a big-endian bias, so when creating
+    // a vectorshuffle for little endian, we must undo the transformation
+    // performed on vec_perm in altivec.h.  That is, we must complement
+    // the permutation mask with respect to 31 and reverse the order of
+    // V1 and V2.
     if (Constant *Mask = dyn_cast<Constant>(II->getArgOperand(2))) {
       assert(Mask->getType()->getVectorNumElements() == 16 &&
              "Bad type for intrinsic!");
@@ -832,10 +837,14 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
           unsigned Idx =
             cast<ConstantInt>(Mask->getAggregateElement(i))->getZExtValue();
           Idx &= 31;  // Match the hardware behavior.
+          if (DL && DL->isLittleEndian())
+            Idx = 31 - Idx;
 
           if (!ExtractedElts[Idx]) {
+            Value *Op0ToUse = (DL && DL->isLittleEndian()) ? Op1 : Op0;
+            Value *Op1ToUse = (DL && DL->isLittleEndian()) ? Op0 : Op1;
             ExtractedElts[Idx] =
-              Builder->CreateExtractElement(Idx < 16 ? Op0 : Op1,
+              Builder->CreateExtractElement(Idx < 16 ? Op0ToUse : Op1ToUse,
                                             Builder->getInt32(Idx&15));
           }