Index: lib/Target/X86/X86InterleavedAccess.cpp
===================================================================
--- lib/Target/X86/X86InterleavedAccess.cpp
+++ lib/Target/X86/X86InterleavedAccess.cpp
@@ -98,17 +98,19 @@
 
 bool X86InterleavedAccessGroup::isSupported() const {
   VectorType *ShuffleVecTy = Shuffles[0]->getType();
-  uint64_t ShuffleVecSize = DL.getTypeSizeInBits(ShuffleVecTy);
   Type *ShuffleEltTy = ShuffleVecTy->getVectorElementType();
+  unsigned WideInstSize;
 
   // Currently, lowering is supported for 4-element vectors of 64 bits on AVX.
-  uint64_t ExpectedShuffleVecSize;
-  if (isa<LoadInst>(Inst))
-    ExpectedShuffleVecSize = 256;
-  else
-    ExpectedShuffleVecSize = 1024;
+  if (isa<LoadInst>(Inst)) {
+    if (DL.getTypeSizeInBits(ShuffleVecTy) != 256)
+      return false;
+
+    WideInstSize = DL.getTypeSizeInBits(Inst->getType());
+  } else
+    WideInstSize = DL.getTypeSizeInBits(Shuffles[0]->getType());
 
-  if (!Subtarget.hasAVX() || ShuffleVecSize != ExpectedShuffleVecSize ||
+  if (!Subtarget.hasAVX() || WideInstSize != 1024 ||
       DL.getTypeSizeInBits(ShuffleEltTy) != 64 || Factor != 4)
     return false;
 
Index: test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll
===================================================================
--- test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll
+++ test/Transforms/InterleavedAccess/X86/interleaved-accesses-64bits-avx.ll
@@ -217,3 +217,20 @@
   store <16 x double> %interleaved.vec, <16 x double>* %ptr, align 16
   ret void
 }
+
+; This verifies whether the test passes and does not hit any assertions.
+; Today, X86InterleavedAccess could have handled this case and
+; generate transposed sequence by extending the current implementation
+; which would be creating dummy vectors of undef. But it decided not to
+; optimize these cases where the load-size is less Factor * NumberOfElements.
+; Because a better sequence can easily be generated by CG.
+
+@a = local_unnamed_addr global <4 x double> zeroinitializer, align 32
+; Function Attrs: norecurse nounwind readonly uwtable
+define <4 x double> @test_unhandled(<4 x double> %b) {
+entry:
+  %0 = load <4 x double>, <4 x double>* @a, align 32
+  %1 = shufflevector <4 x double> %0, <4 x double> undef, <4 x i32> <i32 3, i32 undef, i32 undef, i32 undef>
+  %shuffle = shufflevector <4 x double> %1, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 0, i32 0>
+  ret <4 x double> %shuffle
+}