reenable word-at-at-time copying in memmove

before restrict was added, memove called memcpy for forward copies and
used a byte-at-a-time loop for reverse copies. this was changed to
avoid invoking UB now that memcpy has an undefined copying order,
making memmove considerably slower.

performance is still rather bad, so I'll be adding asm soon.

diff --git a/src/string/memmove.c b/src/string/memmove.c
index 9153a64..27f670e 100644 (file)
--- a/src/string/memmove.c
+++ b/src/string/memmove.c
@@ -1,13 +1,36 @@
 #include <string.h>
+#include <stdint.h>
+
+#define WT size_t
+#define WS (sizeof(WT))
 
 void *memmove(void *dest, const void *src, size_t n)
 {
        char *d = dest;
        const char *s = src;
+
        if (d==s) return d;
-       if ((size_t)(d-s) < n)
-               while (n--) d[n] = s[n];
-       else
-               while (n--) *d++ = *s++;
+       if (s+n <= d || d+n <= s) return memcpy(d, s, n);
+
+       if (d<s) {
+               if ((uintptr_t)s % WS == (uintptr_t)d % WS) {
+                       while ((uintptr_t)d % WS) {
+                               if (!n--) return dest;
+                               *d++ = *s++;
+                       }
+                       for (; n>=WS; n-=WS, d+=WS, s+=WS) *(WT *)d = *(WT *)s;
+               }
+               for (; n; n--) *d++ = *s++;
+       } else {
+               if ((uintptr_t)s % WS == (uintptr_t)d % WS) {
+                       while ((uintptr_t)(d+n) % WS) {
+                               if (!n--) return dest;
+                               d[n] = s[n];
+                       }
+                       while (n>=WS) n-=WS, *(WT *)(d+n) = *(WT *)(s+n);
+               }
+               while (n) n--, d[n] = s[n];
+       }
+
        return dest;
 }