@matheusbsbs / matheus-bagliano / commits / b95c5ada99

Use kwset in pickaxe

Benchmarks in the hot cache case: before: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 47,092,744 cache-misses # 2.825 M/sec ( +- 1.607% ) 123,368,389 cache-references # 7.400 M/sec ( +- 0.812% ) 330,040,998 branch-misses # 3.134 % ( +- 0.257% ) 10,530,896,750 branches # 631.663 M/sec ( +- 0.121% ) 62,037,201,030 instructions # 1.399 IPC ( +- 0.142% ) 44,331,294,321 cycles # 2659.073 M/sec ( +- 0.326% ) 96,794 page-faults # 0.006 M/sec ( +- 11.952% ) 25 CPU-migrations # 0.000 M/sec ( +- 25.266% ) 1,424 context-switches # 0.000 M/sec ( +- 0.540% ) 16671.708650 task-clock-msecs # 0.997 CPUs ( +- 0.343% ) 16.728692052 seconds time elapsed ( +- 0.344% ) after: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 51,385,522 cache-misses # 4.619 M/sec ( +- 0.565% ) 129,177,880 cache-references # 11.611 M/sec ( +- 0.219% ) 319,222,775 branch-misses # 6.946 % ( +- 0.134% ) 4,595,913,233 branches # 413.086 M/sec ( +- 0.112% ) 31,395,042,533 instructions # 1.062 IPC ( +- 0.129% ) 29,558,348,598 cycles # 2656.740 M/sec ( +- 0.204% ) 93,224 page-faults # 0.008 M/sec ( +- 4.487% ) 19 CPU-migrations # 0.000 M/sec ( +- 10.425% ) 950 context-switches # 0.000 M/sec ( +- 0.360% ) 11125.796039 task-clock-msecs # 0.997 CPUs ( +- 0.239% ) 11.164216599 seconds time elapsed ( +- 0.240% ) So the kwset code is about 33% faster. Signed-off-by: Fredrik Kuivinen <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Fredrik Kuivinen committed Aug 21, 2011 at 00:41 UTC b95c5ada990ee2afb83af9be5b82d2804618a59d

2 files changed +25 -11

Makefile

@@ -533,6 +533,7 @@ LIB_H += graph.h

533 LIB_H += grep.h

534 LIB_H += hash.h

535 LIB_H += help.h

536 +LIB_H += kwset.h

537 LIB_H += levenshtein.h

538 LIB_H += list-objects.h

539 LIB_H += ll-merge.h

@@ -624,6 +625,7 @@ LIB_OBJS += hash.o

625 LIB_OBJS += help.o

626 LIB_OBJS += hex.o

627 LIB_OBJS += ident.o

628 +LIB_OBJS += kwset.o

629 LIB_OBJS += levenshtein.o

630 LIB_OBJS += list-objects.o

631 LIB_OBJS += ll-merge.o

diffcore-pickaxe.c

+23 -11

@@ -6,6 +6,7 @@

6 #include "diff.h"

7 #include "diffcore.h"

8 #include "xdiff-interface.h"

9 +#include "kwset.h"

11 struct diffgrep_cb {

12 regex_t *regexp;

@@ -146,7 +147,7 @@ static void diffcore_pickaxe_grep(struct diff_options *o)

147

148 static unsigned int contains(struct diff_filespec *one,

149 const char *needle, unsigned long len,

149 - regex_t *regexp)

150 + regex_t *regexp, kwset_t kws)

151 {

152 unsigned int cnt;

153 unsigned long sz;

@@ -175,9 +176,12 @@ static unsigned int contains(struct diff_filespec *one,

176

177 } else { /* Classic exact string match */

178 while (sz) {

178 - const char *found = memmem(data, sz, needle, len);

179 - if (!found)

179 + size_t offset = kwsexec(kws, data, sz, NULL);

180 + const char *found;

181 + if (offset == -1)

182 break;

183 + else

184 + found = data + offset;

185 sz -= found - data + len;

186 data = found + len;

187 cnt++;

@@ -195,6 +199,7 @@ static void diffcore_pickaxe_count(struct diff_options *o)

199 unsigned long len = strlen(needle);

200 int i, has_changes;

201 regex_t regex, *regexp = NULL;

202 + kwset_t kws = NULL;

203 struct diff_queue_struct outq;

204 DIFF_QUEUE_CLEAR(&outq);

205

@@ -209,6 +214,10 @@ static void diffcore_pickaxe_count(struct diff_options *o)

214 die("invalid pickaxe regex: %s", errbuf);

215 }

216 regexp = &regex;

217 + } else {

218 + kws = kwsalloc(NULL);

219 + kwsincr(kws, needle, len);

220 + kwsprep(kws);

221 }

222

223 if (opts & DIFF_PICKAXE_ALL) {

@@ -219,16 +228,16 @@ static void diffcore_pickaxe_count(struct diff_options *o)

228 if (!DIFF_FILE_VALID(p->two))

229 continue; /* ignore unmerged */

230 /* created */

222 - if (contains(p->two, needle, len, regexp))

231 + if (contains(p->two, needle, len, regexp, kws))

232 has_changes++;

233 }

234 else if (!DIFF_FILE_VALID(p->two)) {

226 - if (contains(p->one, needle, len, regexp))

235 + if (contains(p->one, needle, len, regexp, kws))

236 has_changes++;

237 }

238 else if (!diff_unmodified_pair(p) &&

230 - contains(p->one, needle, len, regexp) !=

231 - contains(p->two, needle, len, regexp))

239 + contains(p->one, needle, len, regexp, kws) !=

240 + contains(p->two, needle, len, regexp, kws))

241 has_changes++;

242 }

243 if (has_changes)

@@ -251,16 +260,17 @@ static void diffcore_pickaxe_count(struct diff_options *o)

260 if (!DIFF_FILE_VALID(p->two))

261 ; /* ignore unmerged */

262 /* created */

254 - else if (contains(p->two, needle, len, regexp))

263 + else if (contains(p->two, needle, len, regexp,

264 + kws))

265 has_changes = 1;

266 }

267 else if (!DIFF_FILE_VALID(p->two)) {

258 - if (contains(p->one, needle, len, regexp))

268 + if (contains(p->one, needle, len, regexp, kws))

269 has_changes = 1;

270 }

271 else if (!diff_unmodified_pair(p) &&

262 - contains(p->one, needle, len, regexp) !=

263 - contains(p->two, needle, len, regexp))

272 + contains(p->one, needle, len, regexp, kws) !=

273 + contains(p->two, needle, len, regexp, kws))

274 has_changes = 1;

275

276 if (has_changes)

@@ -271,6 +281,8 @@ static void diffcore_pickaxe_count(struct diff_options *o)

281

282 if (opts & DIFF_PICKAXE_REGEX)

283 regfree(&regex);

284 + else

285 + kwsfree(kws);

286

287 free(q->queue);

288 *q = outq;