diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index b79783b048e..1912a936cec 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -3606,25 +3606,17 @@ def MOVDQUmr :   I<0x7F, MRMDestMem, (outs), (ins i128mem:$dst, VR128:$src),
                  XS, Requires<[UseSSE2]>;
 }
 
-// Intrinsic forms of MOVDQU load and store
-def VMOVDQUmr_Int : I<0x7F, MRMDestMem, (outs), (ins i128mem:$dst, VR128:$src),
-                       "vmovdqu\t{$src, $dst|$dst, $src}",
-                       [(int_x86_sse2_storeu_dq addr:$dst, VR128:$src)],
-                       IIC_SSE_MOVU_P_MR>,
-                     XS, VEX, Requires<[HasAVX]>;
-
-def MOVDQUmr_Int :   I<0x7F, MRMDestMem, (outs), (ins i128mem:$dst, VR128:$src),
-                       "movdqu\t{$src, $dst|$dst, $src}",
-                       [(int_x86_sse2_storeu_dq addr:$dst, VR128:$src)],
-                       IIC_SSE_MOVU_P_MR>,
-                     XS, Requires<[UseSSE2]>;
-
 } // ExeDomain = SSEPackedInt
 
 let Predicates = [HasAVX] in {
+  def : Pat<(int_x86_sse2_storeu_dq addr:$dst, VR128:$src),
+            (VMOVDQUmr addr:$dst, VR128:$src)>;
   def : Pat<(int_x86_avx_storeu_dq_256 addr:$dst, VR256:$src),
             (VMOVDQUYmr addr:$dst, VR256:$src)>;
 }
+let Predicates = [UseSSE2] in
+def : Pat<(int_x86_sse2_storeu_dq addr:$dst, VR128:$src),
+          (MOVDQUmr addr:$dst, VR128:$src)>;
 
 //===---------------------------------------------------------------------===//
 // SSE2 - Packed Integer Arithmetic Instructions
diff --git a/test/CodeGen/X86/avx-intrinsics-x86.ll b/test/CodeGen/X86/avx-intrinsics-x86.ll
index 88ecd5a5d34..fa90ae7ef1a 100644
--- a/test/CodeGen/X86/avx-intrinsics-x86.ll
+++ b/test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -671,7 +671,9 @@ define void @test_x86_sse2_storeu_dq(i8* %a0, <16 x i8> %a1) {
   ; CHECK: test_x86_sse2_storeu_dq
   ; CHECK: movl
   ; CHECK: vmovdqu
-  call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a1)
+  ; add operation forces the execution domain.
+  %a2 = add <16 x i8> %a1, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a2)
   ret void
 }
 declare void @llvm.x86.sse2.storeu.dq(i8*, <16 x i8>) nounwind
@@ -681,6 +683,7 @@ define void @test_x86_sse2_storeu_pd(i8* %a0, <2 x double> %a1) {
   ; CHECK: test_x86_sse2_storeu_pd
   ; CHECK: movl
   ; CHECK: vmovupd
+  ; fadd operation forces the execution domain.
   %a2 = fadd <2 x double> %a1, <double 0x0, double 0x4200000000000000>
   call void @llvm.x86.sse2.storeu.pd(i8* %a0, <2 x double> %a2)
   ret void