diff --git a/clang/lib/Headers/intrin.h b/clang/lib/Headers/intrin.h
--- a/clang/lib/Headers/intrin.h
+++ b/clang/lib/Headers/intrin.h
@@ -451,24 +451,47 @@
 static __inline__ void __DEFAULT_FN_ATTRS __movsb(unsigned char *__dst,
                                                   unsigned char const *__src,
                                                   size_t __n) {
-  __asm__ __volatile__("rep movsb" : "+D"(__dst), "+S"(__src), "+c"(__n)
-                       : : "memory");
+#if defined(__x86_64__)
+  __asm__ __volatile__("rep movsb"
+                       : "+D"(__dst), "+S"(__src), "+c"(__n)
+                       :
+                       : "memory");
+#else
+  __asm__ __volatile__("xchg %%esi, %1\nrep movsb\nxchg %%esi, %1"
+                       : "+D"(__dst), "+r"(__src), "+c"(__n)
+                       :
+                       : "memory");
+#endif
 }
 static __inline__ void __DEFAULT_FN_ATTRS __movsd(unsigned long *__dst,
                                                   unsigned long const *__src,
                                                   size_t __n) {
+#if defined(__x86_64__)
   __asm__ __volatile__("rep movsl"
                        : "+D"(__dst), "+S"(__src), "+c"(__n)
                        :
                        : "memory");
+#else
+  __asm__ __volatile__("xchg %%esi, %1\nrep movsl\nxchg %%esi, %1"
+                       : "+D"(__dst), "+r"(__src), "+c"(__n)
+                       :
+                       : "memory");
+#endif
 }
 static __inline__ void __DEFAULT_FN_ATTRS __movsw(unsigned short *__dst,
                                                   unsigned short const *__src,
                                                   size_t __n) {
+#if defined(__x86_64__)
   __asm__ __volatile__("rep movsw"
                        : "+D"(__dst), "+S"(__src), "+c"(__n)
                        :
                        : "memory");
+#else
+  __asm__ __volatile__("xchg %%esi, %1\nrep movsw\nxchg %%esi, %1"
+                       : "+D"(__dst), "+r"(__src), "+c"(__n)
+                       :
+                       : "memory");
+#endif
 }
 static __inline__ void __DEFAULT_FN_ATTRS __stosd(unsigned long *__dst,
                                                   unsigned long __x,
diff --git a/clang/test/CodeGen/ms-intrinsics.c b/clang/test/CodeGen/ms-intrinsics.c
--- a/clang/test/CodeGen/ms-intrinsics.c
+++ b/clang/test/CodeGen/ms-intrinsics.c
@@ -36,7 +36,7 @@
   return __movsb(Dest, Src, Count);
 }
 // CHECK-I386-LABEL: define{{.*}} void @test__movsb
-// CHECK-I386:   call { i8*, i8*, i32 } asm sideeffect "rep movsb", "={di},={si},={cx},0,1,2,~{memory},~{dirflag},~{fpsr},~{flags}"(i8* %Dest, i8* %Src, i32 %Count)
+// CHECK-I386:   tail call { i8*, i8*, i32 } asm sideeffect "xchg %esi, $1\0Arep movsb\0Axchg %esi, $1", "={di},=r,={cx},0,1,2,~{memory},~{dirflag},~{fpsr},~{flags}"(i8* %Dest, i8* %Src, i32 %Count)
 // CHECK-I386:   ret void
 // CHECK-I386: }
 
@@ -62,7 +62,7 @@
   return __movsw(Dest, Src, Count);
 }
 // CHECK-I386-LABEL: define{{.*}} void @test__movsw
-// CHECK-I386:   call { i16*, i16*, i32 } asm sideeffect "rep movsw", "={di},={si},={cx},0,1,2,~{memory},~{dirflag},~{fpsr},~{flags}"(i16* %Dest, i16* %Src, i32 %Count)
+// CHECK-I386:   tail call { i16*, i16*, i32 } asm sideeffect "xchg %esi, $1\0Arep movsw\0Axchg %esi, $1", "={di},=r,={cx},0,1,2,~{memory},~{dirflag},~{fpsr},~{flags}"(i16* %Dest, i16* %Src, i32 %Count)
 // CHECK-I386:   ret void
 // CHECK-I386: }
 
@@ -88,7 +88,7 @@
   return __movsd(Dest, Src, Count);
 }
 // CHECK-I386-LABEL: define{{.*}} void @test__movsd
-// CHECK-I386:   call { i32*, i32*, i32 } asm sideeffect "rep movsl", "={di},={si},={cx},0,1,2,~{memory},~{dirflag},~{fpsr},~{flags}"(i32* %Dest, i32* %Src, i32 %Count)
+// CHECK-I386:   tail call { i32*, i32*, i32 } asm sideeffect "xchg %esi, $1\0Arep movsl\0Axchg %esi, $1", "={di},=r,={cx},0,1,2,~{memory},~{dirflag},~{fpsr},~{flags}"(i32* %Dest, i32* %Src, i32 %Count)
 // CHECK-I386:   ret void
 // CHECK-I386: }