Index: lib/Transforms/InstCombine/InstCombineVectorOps.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineVectorOps.cpp
+++ lib/Transforms/InstCombine/InstCombineVectorOps.cpp
@@ -1309,6 +1309,9 @@
   // one instruction, which we know is safe.  This is good for things like
   // turning: (splat(splat)) -> splat, or
   // merge(V[0..n], V[n+1..2n]) -> V[0..2n]
+  // As an exception to the above, we always allow the case v1==v2, which lets
+  // us combine to `x=shuffle(v1,undef,newMask)` since targets should generally
+  // be good enough at single-vector shuffles.
   ShuffleVectorInst* LHSShuffle = dyn_cast<ShuffleVectorInst>(LHS);
   ShuffleVectorInst* RHSShuffle = dyn_cast<ShuffleVectorInst>(RHS);
   if (LHSShuffle)
@@ -1434,7 +1437,8 @@
 
   // If the result mask is equal to one of the original shuffle masks,
   // or is a splat, do the replacement.
-  if (isSplat || newMask == LHSMask || newMask == RHSMask || newMask == Mask) {
+  if (isSplat || newMask == LHSMask || newMask == RHSMask || newMask == Mask ||
+      !newRHS) {
     SmallVector<Constant*, 16> Elts;
     for (unsigned i = 0, e = newMask.size(); i != e; ++i) {
       if (newMask[i] < 0) {
Index: test/Transforms/InstCombine/vec_shuffle.ll
===================================================================
--- test/Transforms/InstCombine/vec_shuffle.ll
+++ test/Transforms/InstCombine/vec_shuffle.ll
@@ -463,3 +463,18 @@
   %1 = shufflevector <4 x i32*> %A, <4 x i32*> undef, <2 x i32> <i32 0, i32 1>
   ret <2 x i32*> %1
 }
+
+define <8 x double> @shuffle_after_wide_load(double* %ptr) #0 {
+  %a = bitcast double* %ptr to <8 x double>*
+  %1 = load <8 x double>, <8 x double>* %a, align 16
+; CHECK-LABEL: @shuffle_after_wide_load
+; CHECK-NOT: shufflevector
+  %2 = shufflevector <8 x double> %1, <8 x double> undef, <2 x i32> <i32 0, i32 1>
+  %3 = shufflevector <8 x double> %1, <8 x double> undef, <2 x i32> <i32 2, i32 3>
+  %4 = shufflevector <8 x double> %1, <8 x double> undef, <2 x i32> <i32 4, i32 5>
+  %5 = shufflevector <8 x double> %1, <8 x double> undef, <2 x i32> <i32 6, i32 7>
+  %s1 = shufflevector <2 x double> %2, <2 x double> %3, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %s2 = shufflevector <2 x double> %4, <2 x double> %5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+  %s3 = shufflevector <4 x double> %s1, <4 x double> %s2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x double> %s3
+}