diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index fb0d1adaada..23347c28547 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -4846,21 +4846,16 @@ X86TargetLowering::LowerAsSplatVectorLoad(SDValue SrcOp, EVT VT, DebugLoc dl,
     int EltNo = (Offset - StartOffset) >> 2;
     int NumElems = VT.getVectorNumElements();
 
-    EVT CanonVT = VT.getSizeInBits() == 128 ? MVT::v4i32 : MVT::v8i32;
     EVT NVT = EVT::getVectorVT(*DAG.getContext(), PVT, NumElems);
     SDValue V1 = DAG.getLoad(NVT, dl, Chain, Ptr,
                              LD->getPointerInfo().getWithOffset(StartOffset),
                              false, false, false, 0);
 
-    // Canonicalize it to a v4i32 or v8i32 shuffle.
     SmallVector<int, 8> Mask;
     for (int i = 0; i < NumElems; ++i)
       Mask.push_back(EltNo);
 
-    V1 = DAG.getNode(ISD::BITCAST, dl, CanonVT, V1);
-    return DAG.getNode(ISD::BITCAST, dl, NVT,
-                       DAG.getVectorShuffle(CanonVT, dl, V1,
-                                            DAG.getUNDEF(CanonVT),&Mask[0]));
+    return DAG.getVectorShuffle(NVT, dl, V1, DAG.getUNDEF(NVT), &Mask[0]);
   }
 
   return SDValue();
diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index 43790cf3ea8..01b4dd670fa 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -3998,8 +3998,7 @@ let Predicates = [HasAVX] in {
   def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv2i64 addr:$src1)),
                                    (i8 imm:$imm))),
             (VPSHUFDmi addr:$src1, imm:$imm)>;
-  def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv4f32 addr:$src1)),
-                                   (i8 imm:$imm))),
+  def : Pat<(v4f32 (X86PShufd (memopv4f32 addr:$src1), (i8 imm:$imm))),
             (VPSHUFDmi addr:$src1, imm:$imm)>;
   def : Pat<(v4f32 (X86PShufd VR128:$src1, (i8 imm:$imm))),
             (VPSHUFDri VR128:$src1, imm:$imm)>;
@@ -4051,8 +4050,7 @@ let Predicates = [HasSSE2] in {
   def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv2i64 addr:$src1)),
                                    (i8 imm:$imm))),
             (PSHUFDmi addr:$src1, imm:$imm)>;
-  def : Pat<(v4i32 (X86PShufd (bc_v4i32 (memopv4f32 addr:$src1)),
-                                   (i8 imm:$imm))),
+  def : Pat<(v4f32 (X86PShufd (memopv4f32 addr:$src1), (i8 imm:$imm))),
             (PSHUFDmi addr:$src1, imm:$imm)>;
   def : Pat<(v4f32 (X86PShufd VR128:$src1, (i8 imm:$imm))),
             (PSHUFDri VR128:$src1, imm:$imm)>;
diff --git a/test/CodeGen/X86/avx-shuffle.ll b/test/CodeGen/X86/avx-shuffle.ll
index ee038ce21ee..08b668c983b 100644
--- a/test/CodeGen/X86/avx-shuffle.ll
+++ b/test/CodeGen/X86/avx-shuffle.ll
@@ -96,3 +96,16 @@ define i32 @test10(<4 x i32> %a) nounwind {
   %r = extractelement <8 x i32> %b, i32 2
   ret i32 %r
 }
+
+define <4 x float> @test11(<4 x float> %a) nounwind  {
+; CHECK: pshufd $27
+  %tmp1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  ret <4 x float> %tmp1
+}
+
+define <4 x float> @test12(<4 x float>* %a) nounwind  {
+; CHECK: pshufd $27, (
+  %tmp0 = load <4 x float>* %a
+  %tmp1 = shufflevector <4 x float> %tmp0, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  ret <4 x float> %tmp1
+}