Improve performance of mempcpy by inlining and using memcpy. Enable

this for all targets except sparc which has an optimized mempcpy
implementation.

ChangeLog

@@ -1,3 +1,9 @@
+2015-08-05  Wilco Dijkstra  <wdijkstr@arm.com>
+
+	* string/string.h: (mempcpy): Redirect to __mempcpy_inline.
+	(__mempcpy): Likewise.  (__mempcpy_inline): New inline function.
+	* sysdeps/sparc/bits/string.h: (_HAVE_STRING_ARCH_mempcpy): Define.
+
 2015-08-05  Wilco Dijkstra  <wdijkstr@arm.com>
 
 	* string/memccpy.c (memccpy):

string/string.h

@@ -636,6 +636,25 @@ extern char *basename (const char *__filename) __THROW __nonnull ((1));
 # endif
 #endif
 
+#if defined __USE_GNU && defined __OPTIMIZE__ \
+    && defined __extern_always_inline && __GNUC_PREREQ (3,2)
+# if !defined _FORCE_INLINES && !defined _HAVE_STRING_ARCH_mempcpy
+
+#undef mempcpy
+#undef __mempcpy
+#define mempcpy(dest, src, n) __mempcpy_inline (dest, src, n)
+#define __mempcpy(dest, src, n) __mempcpy_inline (dest, src, n)
+
+__extern_always_inline void *
+__mempcpy_inline (void *__restrict __dest,
+		  const void *__restrict __src, size_t __n)
+{
+  return (char *) memcpy (__dest, __src, __n) + __n;
+}
+
+# endif
+#endif
+
 __END_DECLS
 
 #endif /* string.h  */

sysdeps/sparc/bits/string.h

@@ -26,3 +26,6 @@
 /* sparc32 and sparc64 strchr(x, '\0') perform better than
    __rawmemchr(x, '\0').  */
 #define _HAVE_STRING_ARCH_strchr 1
+
+/* Don't inline mempcpy into memcpy as sparc has an optimized mempcpy.  */
+#define _HAVE_STRING_ARCH_mempcpy 1