diff options
author | Wilco Dijkstra <wdijkstr@arm.com> | 2016-12-21 15:16:29 +0000 |
---|---|---|
committer | Wilco Dijkstra <wdijkstr@arm.com> | 2016-12-21 15:16:29 +0000 |
commit | 5625f666cead9f3c71e00696df2907120aef1f31 (patch) | |
tree | 38d3bbb125573116a83930aa30d6d89d93f9a14e /string | |
parent | d08ab9ced75e0d88827e0bb58183612afb7fe1fd (diff) | |
download | glibc-5625f666cead9f3c71e00696df2907120aef1f31.zip glibc-5625f666cead9f3c71e00696df2907120aef1f31.tar.gz glibc-5625f666cead9f3c71e00696df2907120aef1f31.tar.bz2 |
This patch cleans up the strsep implementation and improves performance.
Currently strsep calls strpbrk is is now a veneer to strcspn. Calling
strcspn directly is faster. Since it handles a delimiter string of size
1 as a special case, this is not needed in strsep itself. Although this
means there is a slightly higher overhead if the delimiter size is 1,
all other cases are slightly faster. The overall performance gain is 5-10%
on AArch64.
The string/bits/string2.h header contains optimizations for constant
delimiters of size 1-3. Benchmarking these showed similar performance for
size 1 (since in all cases strchr/strchrnul is used), while size 2 and 3
can give up to 2x speedup for small input strings. However if these cases
are common it seems much better to add this optimization to strcspn.
So move these header optimizations to string-inlines.c.
Improve the strsep benchmark so that it actually benchmarks something.
The current version contains a delimiter character at every position in the
input string, so there is very little work to do, and the extremely inefficent
simple_strsep implementation appears fastest in every case. The new version
has either no match in the input for the fail case and a match halfway in the
input for the success case. The input is then restored so that each iteration
does exactly the same amount of work. Reduce the number of testcases since
simple_strsep takes a lot of time now.
* benchtests/bench-strsep.c (oldstrsep): Add old implementation.
(do_one_test) Restore original string so iteration works.
* string/string-inlines.c (do_test): Create better input strings.
(test_main) Reduce number of testruns.
* string/string-inlines.c (__old_strsep_1c): New function.
(__old_strsep_2c): Likewise.
(__old_strsep_3c): Likewise.
* string/strsep.c (__strsep): Remove case of small delim string.
Call strcspn directly rather than strpbrk.
* string/bits/string2.h (__strsep): Remove define.
(__strsep_1c): Remove.
(__strsep_2c): Remove.
(__strsep_3c): Remove.
(strsep): Remove.
* sysdeps/unix/sysv/linux/internal_statvfs.c
(__statvfs_getflags): Rename to __strsep.
Diffstat (limited to 'string')
-rw-r--r-- | string/bits/string2.h | 90 | ||||
-rw-r--r-- | string/string-inlines.c | 64 | ||||
-rw-r--r-- | string/strsep.c | 26 |
3 files changed, 67 insertions, 113 deletions
diff --git a/string/bits/string2.h b/string/bits/string2.h index e39d4f1..c136617 100644 --- a/string/bits/string2.h +++ b/string/bits/string2.h @@ -180,96 +180,6 @@ extern void *__rawmemchr (const void *__s, int __c); #endif -#if !defined _HAVE_STRING_ARCH_strsep || defined _FORCE_INLINES -# ifndef _HAVE_STRING_ARCH_strsep - -extern char *__strsep_g (char **__stringp, const char *__delim); -# define __strsep(s, reject) \ - __extension__ \ - ({ char __r0, __r1, __r2; \ - (__builtin_constant_p (reject) && __string2_1bptr_p (reject) \ - && (__r0 = ((const char *) (reject))[0], \ - ((const char *) (reject))[0] != '\0') \ - ? ((__r1 = ((const char *) (reject))[1], \ - ((const char *) (reject))[1] == '\0') \ - ? __strsep_1c (s, __r0) \ - : ((__r2 = ((const char *) (reject))[2], __r2 == '\0') \ - ? __strsep_2c (s, __r0, __r1) \ - : (((const char *) (reject))[3] == '\0' \ - ? __strsep_3c (s, __r0, __r1, __r2) \ - : __strsep_g (s, reject)))) \ - : __strsep_g (s, reject)); }) -# endif - -__STRING_INLINE char *__strsep_1c (char **__s, char __reject); -__STRING_INLINE char * -__strsep_1c (char **__s, char __reject) -{ - char *__retval = *__s; - if (__retval != NULL && (*__s = strchr (__retval, __reject)) != NULL) - *(*__s)++ = '\0'; - return __retval; -} - -__STRING_INLINE char *__strsep_2c (char **__s, char __reject1, char __reject2); -__STRING_INLINE char * -__strsep_2c (char **__s, char __reject1, char __reject2) -{ - char *__retval = *__s; - if (__retval != NULL) - { - char *__cp = __retval; - while (1) - { - if (*__cp == '\0') - { - __cp = NULL; - break; - } - if (*__cp == __reject1 || *__cp == __reject2) - { - *__cp++ = '\0'; - break; - } - ++__cp; - } - *__s = __cp; - } - return __retval; -} - -__STRING_INLINE char *__strsep_3c (char **__s, char __reject1, char __reject2, - char __reject3); -__STRING_INLINE char * -__strsep_3c (char **__s, char __reject1, char __reject2, char __reject3) -{ - char *__retval = *__s; - if (__retval != NULL) - { - char *__cp = __retval; - while (1) - { - if (*__cp == '\0') - { - __cp = NULL; - break; - } - if (*__cp == __reject1 || *__cp == __reject2 || *__cp == __reject3) - { - *__cp++ = '\0'; - break; - } - ++__cp; - } - *__s = __cp; - } - return __retval; -} -# ifdef __USE_MISC -# define strsep(s, reject) __strsep (s, reject) -# endif -#endif - /* We need the memory allocation functions for inline strdup(). Referring to stdlib.h (even minimally) is not allowed in any of the tight standards compliant modes. */ diff --git a/string/string-inlines.c b/string/string-inlines.c index d43e589..7b1de71 100644 --- a/string/string-inlines.c +++ b/string/string-inlines.c @@ -63,6 +63,70 @@ __old_strtok_r_1c (char *__s, char __sep, char **__nextp) return __result; } compat_symbol (libc, __old_strtok_r_1c, __strtok_r_1c, GLIBC_2_1_1); + +char * +__old_strsep_1c (char **__s, char __reject) +{ + char *__retval = *__s; + if (__retval != NULL && (*__s = strchr (__retval, __reject)) != NULL) + *(*__s)++ = '\0'; + return __retval; +} +compat_symbol (libc, __old_strsep_1c, __strsep_1c, GLIBC_2_1_1); + +char * +__old_strsep_2c (char **__s, char __reject1, char __reject2) +{ + char *__retval = *__s; + if (__retval != NULL) + { + char *__cp = __retval; + while (1) + { + if (*__cp == '\0') + { + __cp = NULL; + break; + } + if (*__cp == __reject1 || *__cp == __reject2) + { + *__cp++ = '\0'; + break; + } + ++__cp; + } + *__s = __cp; + } + return __retval; +} +compat_symbol (libc, __old_strsep_2c, __strsep_2c, GLIBC_2_1_1); + +char * +__old_strsep_3c (char **__s, char __reject1, char __reject2, char __reject3) +{ + char *__retval = *__s; + if (__retval != NULL) + { + char *__cp = __retval; + while (1) + { + if (*__cp == '\0') + { + __cp = NULL; + break; + } + if (*__cp == __reject1 || *__cp == __reject2 || *__cp == __reject3) + { + *__cp++ = '\0'; + break; + } + ++__cp; + } + *__s = __cp; + } + return __retval; +} +compat_symbol (libc, __old_strsep_3c, __strsep_3c, GLIBC_2_1_1); #endif #if SHLIB_COMPAT (libc, GLIBC_2_1_1, GLIBC_2_24) diff --git a/string/strsep.c b/string/strsep.c index 1054774..68581c8 100644 --- a/string/strsep.c +++ b/string/strsep.c @@ -29,30 +29,10 @@ __strsep (char **stringp, const char *delim) if (begin == NULL) return NULL; - /* A frequent case is when the delimiter string contains only one - character. Here we don't need to call the expensive `strpbrk' - function and instead work using `strchr'. */ - if (delim[0] == '\0' || delim[1] == '\0') - { - char ch = delim[0]; - - if (ch == '\0') - end = NULL; - else - { - if (*begin == ch) - end = begin; - else if (*begin == '\0') - end = NULL; - else - end = strchr (begin + 1, ch); - } - } - else - /* Find the end of the token. */ - end = strpbrk (begin, delim); + /* Find the end of the token. */ + end = begin + strcspn (begin, delim); - if (end) + if (*end) { /* Terminate the token and set *STRINGP past NUL character. */ *end++ = '\0'; |