AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-22 04:50:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Speed up x86-64 strcasestr a bit moew.

Browse Source 
Using the new SSE4.2 instructions is cool but not really the fastest.
Some older SSE instructions can do the trick faster.
This commit is contained in:
Ulrich Drepper 2010-07-24 08:34:44 -07:00
parent dbc676d4ff
commit 8e96b93aa7
2 changed files with 16 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ChangeLog
View File

@ -1,3 +1,8 @@
2010-07-24 Ulrich Drepper <drepper@redhat.com>
* sysdeps/x86_64/multiarch/strstr.c (__m128i_strloadu_tolower): Use
lower-latency instructions.
2010-07-23 Ulrich Drepper <drepper@redhat.com>
* string/test-strcasestr.c: New file.

16
sysdeps/x86_64/multiarch/strstr.c
View File

@ -173,11 +173,17 @@ __m128i_strloadu_tolower (const unsigned char *p, __m128i rangeuc,
{
__m128i frag = __m128i_strloadu (p);
/* Convert frag to lower case for POSIX/C locale. */
__m128i mask1 = _mm_cmpistrm (rangeuc, frag, 0x44);
__m128i mask2 = _mm_blendv_epi8 (u2ldelta, frag, mask1);
mask2 = _mm_sub_epi8 (mask2, u2ldelta);
return _mm_blendv_epi8 (frag, mask2, mask1);
#define UCLOW 0x4040404040404040ULL
#define UCHIGH 0x5a5a5a5a5a5a5a5aULL
#define LCQWORD 0x2020202020202020ULL
/* Compare if 'Z' > bytes. Inverted way to get a mask for byte <= 'Z'. */
__m128i r2 = _mm_cmpgt_epi8 (_mm_set1_epi64x (UCHIGH), frag);
/* Compare if bytes are > 'A' - 1. */
__m128i r1 = _mm_cmpgt_epi8 (frag, _mm_set1_epi64x (UCLOW));
/* Mask byte == ff if byte(r2) <= 'Z' and byte(r1) > 'A' - 1. */
__m128i mask = _mm_and_si128 (r2, r1);
/* Apply lowercase bit 6 mask for above mask bytes == ff. */
return _mm_or_si128 (frag, _mm_and_si128 (mask, _mm_set1_epi64x (LCQWORD)));
}
#endif