OpenE2K
/
glibc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

This patch improves strncpy performance by using strnlen/memcpy rather than a byte loop. Performance 

on bench-strncpy is 1.9-2.1x faster on average. I tried several variations, and using a tailcall and
calling memset conditionally gave the best overall results.
This commit is contained in:
Wilco Dijkstra 2015-08-05 15:15:28 +01:00
parent 7b1c56e483
commit f6482cf29d
2 changed files with 10 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ChangeLog
View File

@ -1,3 +1,8 @@
2015-08-05 Wilco Dijkstra <wdijkstr@arm.com>
* string/strncpy.c (strncpy):
Improve performance by using __strnlen/memcpy.
2015-08-05 Wilco Dijkstra <wdijkstr@arm.com>
* sysdeps/aarch64/fpu/feenablxcpt.c (feenableexcept):

59
string/strncpy.c
View File

@ -16,68 +16,19 @@
<http://www.gnu.org/licenses/>. */
#include <string.h>
#include <memcopy.h>
#undef strncpy
#ifndef STRNCPY
#define STRNCPY strncpy
#define STRNCPY strncpy
#endif
char *
STRNCPY (char *s1, const char *s2, size_t n)
{
char c;
char *s = s1;
--s1;
if (n >= 4)
{
size_t n4 = n >> 2;
for (;;)
{
c = *s2++;
*++s1 = c;
if (c == '\0')
break;
c = *s2++;
*++s1 = c;
if (c == '\0')
break;
c = *s2++;
*++s1 = c;
if (c == '\0')
break;
c = *s2++;
*++s1 = c;
if (c == '\0')
break;
if (--n4 == 0)
goto last_chars;
}
s1++;
n = n - (s1 - s);
memset (s1, '\0', n);
return s;
}
last_chars:
n &= 3;
if (n == 0)
return s;
do
{
c = *s2++;
*++s1 = c;
if (--n == 0)
return s;
}
while (c != '\0');
memset (s1 + 1, '\0', n);
return s;
size_t size = __strnlen (s2, n);
if (size != n)
memset (s1 + size, '\0', n - size);
return memcpy (s1, s2, size);
}
libc_hidden_builtin_def (strncpy)