Speed up strcoll by inlining

This patch improves the performance of strcoll_l by inlining the two
helper functions get_next_seq and do_compare.

measurement     old             new             diff
glibc files     202,393,000     138,597,000     -31.52%
vi_VN.UTF-8     2,772,150       2,055,920       -25.84%
en_US.UTF-8     2,741,380       1,952,770       -28.77%
ar_SA.UTF-8     3,062,180       2,484,940       -18.85%
zh_CN.UTF-8     917,198         875,756         -4.52%
cs_CZ.UTF-8     3,455,670       2,465,530       -28.65%
en_GB.UTF-8     3,334,790       2,420,540       -27.42%
da_DK.UTF-8     2,805,660       2,023,430       -27.88%
pl_PL.UTF-8     2,640,710       2,014,960       -23.70%
fr_FR.UTF-8     3,504,700       2,642,280       -24.61%
pt_PT.UTF-8     3,542,390       2,599,250       -26.62%
el_GR.UTF-8     4,529,580       3,881,700       -14.30%
ru_RU.UTF-8     3,527,070       2,806,480       -20.43%
iw_IL.UTF-8     3,047,060       2,530,360       -16.96%
es_ES.UTF-8     3,089,990       2,376,410       -23.09%
hi_IN.UTF-8     222,487,000     223,397,000     0.41%
sv_SE.UTF-8     2,724,630       2,019,420       -25.88%
hu_HU.UTF-8     4,446,990       3,658,830       -17.72%
tr_TR.UTF-8     2,966,180       2,200,790       -25.80%
is_IS.UTF-8     2,559,480       2,012,190       -21.38%
it_IT.UTF-8     3,301,190       2,527,230       -23.44%
sr_RS.UTF-8     2,973,150       2,322,010       -21.90%
ja_JP.UTF-8     985,042         1,044,980       6.08%

diff --git a/ChangeLog b/ChangeLog
index bf7998b..058c5a4 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2014-11-24  Leonhard Holz  <leonhard.holz@web.de>
+
+       * string/strcoll_l.c (get_next_seq): __always_inline.
+       * string/strcoll_l.c (do_compare): __always_inline.
+
 2014-11-24  Siddhesh Poyarekar  <siddhesh@redhat.com>
 
        * include/bits/stdlib-float.h: Use IS_IN only if _ISOMAC is

diff --git a/string/strcoll_l.c b/string/strcoll_l.c
index 7a2d066..ddac7e5 100644 (file)
--- a/string/strcoll_l.c
+++ b/string/strcoll_l.c
@@ -63,7 +63,7 @@ typedef struct
 } coll_seq;
 
 /* Get next sequence.  Traverse the string as required.  */
-static void
+static __always_inline void
 get_next_seq (coll_seq *seq, int nrules, const unsigned char *rulesets,
              const USTRING_TYPE *weights, const int32_t *table,
              const USTRING_TYPE *extra, const int32_t *indirect,
@@ -194,7 +194,7 @@ get_next_seq (coll_seq *seq, int nrules, const unsigned char *rulesets,
 }
 
 /* Compare two sequences.  */
-static int
+static __always_inline int
 do_compare (coll_seq *seq1, coll_seq *seq2, int position,
            const USTRING_TYPE *weights)
 {