From d3496c9f4f27d3009b71be87f6108b4fed7314bd Mon Sep 17 00:00:00 2001 From: Wilco Dijkstra Date: Fri, 25 Mar 2016 16:44:26 -0300 Subject: Improve generic strcspn performance Improve strcspn performance using a much faster algorithm. It is kept simple so it works well on most targets. It is generally at least 10 times faster than the existing implementation on bench-strcspn on a few AArch64 implementations, and for some tests 100 times as fast (repeatedly calling strchr on a small string is extremely slow...). In fact the string/bits/string2.h inlines make no longer sense, as GCC already uses strlen if reject is an empty string, strchrnul is 5 times as fast as __strcspn_c1, while __strcspn_c2 and __strcspn_c3 are slower than the strcspn main loop for large strings (though reject length 2-4 could be special cased in the future to gain even more performance). Tested on x86_64, i686, and aarch64. * string/Version (libc): Add GLIBC_2.24. * string/strcspn.c (strcspn): Rewrite function. * string/bits/string2.h (strcspn): Use __builtin_strcspn. (__strcspn_c1): Remove inline function. (__strcspn_c2): Likewise. (__strcspn_c3): Likewise. * string/string-inline.c [SHLIB_COMPAT(libc, GLIBC_2_1_1, GLIBC_2_24)] (__strcspn_c1): Add compatibility symbol. [SHLIB_COMPAT(libc, GLIBC_2_1_1, GLIBC_2_24)] (__strcspn_c2): Likewise. [SHLIB_COMPAT(libc, GLIBC_2_1_1, GLIBC_2_24)] (__strcspn_c3): Likewise. * sysdeps/i386/string-inlines.c: Include generic string-inlines.c. --- sysdeps/i386/string-inlines.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'sysdeps/i386') diff --git a/sysdeps/i386/string-inlines.c b/sysdeps/i386/string-inlines.c index c7de270c0a..64d80e8eef 100644 --- a/sysdeps/i386/string-inlines.c +++ b/sysdeps/i386/string-inlines.c @@ -15,27 +15,10 @@ License along with the GNU C Library; if not, see . */ -/* and declare some extern inline - functions. These functions are declared additionally here if - inlining is not possible. */ - -#undef __USE_STRING_INLINES -#define __USE_STRING_INLINES -#define _FORCE_INLINES -#define __STRING_INLINE /* empty */ -#define __NO_INLINE__ - /* This is to avoid PLT entries for the x86 version. */ #define __memcpy_g __memcpy_g_internal #define __strchr_g __strchr_g_internal - -#include -#undef index -#undef rindex - -#undef __NO_INLINE__ -#include -#include +#include void * (__memcpy_c) (void *d, const void *s, size_t n) -- cgit 1.4.1