Improve memccpy performance by using memchr/memcpy/mempcpy rather than

a byte loop. Overall performance on bench-memccpy is > 2x faster when
using the C implementation of memchr and an optimized memcpy.

ChangeLog

@@ -1,3 +1,8 @@
+2015-08-05  Wilco Dijkstra  <wdijkstr@arm.com>
+
+	* string/memccpy.c (memccpy):
+	Improve performance by using memchr/memcpy/__mempcpy.
+
 2015-08-05  Wilco Dijkstra  <wdijkstr@arm.com>
 
 	* string/strncpy.c (strncpy):

string/memccpy.c

@@ -26,15 +26,12 @@
 void *
 __memccpy (void *dest, const void *src, int c, size_t n)
 {
-  const char *s = src;
-  char *d = dest;
-  const char x = c;
-  size_t i = n;
+  void *p = memchr (src, c, n);
 
-  while (i-- > 0)
-    if ((*d++ = *s++) == x)
-      return d;
+  if (p != NULL)
+    return __mempcpy (dest, src, p - src + 1);
 
+  memcpy (dest, src, n);
   return NULL;
 }