Index: lib/Headers/emmintrin.h
===================================================================
--- lib/Headers/emmintrin.h
+++ lib/Headers/emmintrin.h
@@ -582,19 +582,22 @@
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
+_mm_store_pd(double *__dp, __m128d __a)
+{
+  *(__m128d *)__dp = __a;
+}
+
+static __inline__ void __DEFAULT_FN_ATTRS
 _mm_store1_pd(double *__dp, __m128d __a)
 {
-  struct __mm_store1_pd_struct {
-    double __u[2];
-  } __attribute__((__packed__, __may_alias__));
-  ((struct __mm_store1_pd_struct*)__dp)->__u[0] = __a[0];
-  ((struct __mm_store1_pd_struct*)__dp)->__u[1] = __a[0];
+  __a = __builtin_shufflevector((__v2df)__a, (__v2df)__a, 0, 0);
+  _mm_store_pd(__dp, __a);
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_store_pd(double *__dp, __m128d __a)
+_mm_store_pd1(double *__dp, __m128d __a)
 {
-  *(__m128d *)__dp = __a;
+  return _mm_store1_pd(__dp, __a);
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
Index: lib/Headers/xmmintrin.h
===================================================================
--- lib/Headers/xmmintrin.h
+++ lib/Headers/xmmintrin.h
@@ -1590,22 +1590,22 @@
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_store1_ps(float *__p, __m128 __a)
+_mm_store_ps(float *__p, __m128 __a)
 {
-  __a = __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 0, 0, 0, 0);
-  _mm_storeu_ps(__p, __a);
+  *(__m128 *)__p = __a;
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_store_ps1(float *__p, __m128 __a)
+_mm_store1_ps(float *__p, __m128 __a)
 {
-    return _mm_store1_ps(__p, __a);
+  __a = __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 0, 0, 0, 0);
+  _mm_store_ps(__p, __a);
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_store_ps(float *__p, __m128 __a)
+_mm_store_ps1(float *__p, __m128 __a)
 {
-  *(__m128 *)__p = __a;
+  return _mm_store1_ps(__p, __a);
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
Index: test/CodeGen/sse-builtins.c
===================================================================
--- test/CodeGen/sse-builtins.c
+++ test/CodeGen/sse-builtins.c
@@ -651,7 +651,7 @@
 void test_mm_store_ps1(float* x, __m128 y) {
   // CHECK-LABEL: test_mm_store_ps1
   // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x i32> zeroinitializer
-  // CHECK: call void @llvm.x86.sse.storeu.ps(i8* %{{.*}}, <4 x float> %{{.*}})
+  // CHECK: store <4 x float> %{{.*}}, <4 x float>* {{.*}}, align 16
   _mm_store_ps1(x, y);
 }
 
@@ -665,7 +665,7 @@
 void test_mm_store1_ps(float* x, __m128 y) {
   // CHECK-LABEL: test_mm_store1_ps
   // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x i32> zeroinitializer
-  // CHECK: call void @llvm.x86.sse.storeu.ps(i8* %{{.*}}, <4 x float> %{{.*}})
+  // CHECK: store <4 x float> %{{.*}}, <4 x float>* {{.*}}, align 16
   _mm_store1_ps(x, y);
 }
 
Index: test/CodeGen/sse2-builtins.c
===================================================================
--- test/CodeGen/sse2-builtins.c
+++ test/CodeGen/sse2-builtins.c
@@ -1205,6 +1205,13 @@
   _mm_store_pd(A, B);
 }
 
+void test_mm_store_pd1(double* x, __m128d y) {
+  // CHECK-LABEL: test_mm_store_pd1
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x i32> zeroinitializer
+  // CHECK: store <2 x double> %{{.*}}, <2 x double>* {{.*}}, align 16
+  _mm_store_pd1(x, y);
+}
+
 void test_mm_store_sd(double* A, __m128d B) {
   // CHECK-LABEL: test_mm_store_sd
   // CHECK: extractelement <2 x double> %{{.*}}, i32 0
@@ -1220,9 +1227,8 @@
 
 void test_mm_store1_pd(double* x, __m128d y) {
   // CHECK-LABEL: test_mm_store1_pd
-  // CHECK: extractelement <2 x double> %{{.*}}, i32 0
-  // CHECK: store {{.*}} double* {{.*}}, align 1{{$}}
-  // CHECK: store {{.*}} double* {{.*}}, align 1{{$}}
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x i32> zeroinitializer
+  // CHECK: store <2 x double> %{{.*}}, <2 x double>* {{.*}}, align 16
   _mm_store1_pd(x, y);
 }