1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
|
// Copyright (C) 2013 Davis E. King (davis@dlib.net)
// License: Boost Software License See LICENSE.txt for the full license.
#undef DLIB_PARALLEL_FoR_ABSTRACT_Hh_
#ifdef DLIB_PARALLEL_FoR_ABSTRACT_Hh_
#include "thread_pool_extension_abstract.h"
#include "async_abstract.h"
namespace dlib
{
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked (
thread_pool& tp,
long begin,
long end,
T& obj,
void (T::*funct)(long, long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This is a convenience function for submitting a block of jobs to a thread_pool.
In particular, given the half open range [begin, end), this function will
split the range into approximately tp.num_threads_in_pool()*chunks_per_thread
blocks, which it will then submit to the thread_pool. The given thread_pool
will then call (obj.*funct)() on each of the subranges.
- To be precise, suppose we have broken the range [begin, end) into the
following subranges:
- [begin[0], end[0])
- [begin[1], end[1])
- [begin[2], end[2])
...
- [begin[n], end[n])
Then parallel_for_blocked() submits each of these subranges to tp for
processing such that (obj.*funct)(begin[i], end[i]) is invoked for all valid
values of i. Moreover, the subranges are non-overlapping and completely
cover the total range of [begin, end).
- This function will not perform any memory allocations or create any system
resources such as mutex objects.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked (
unsigned long num_threads,
long begin,
long end,
T& obj,
void (T::*funct)(long, long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following block of code:
thread_pool tp(num_threads);
parallel_for_blocked(tp, begin, end, obj, funct, chunks_per_thread);
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked (
thread_pool& tp,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- chunks_per_thread > 0
- begin <= end
ensures
- This is a convenience function for submitting a block of jobs to a
thread_pool. In particular, given the range [begin, end), this function will
split the range into approximately tp.num_threads_in_pool()*chunks_per_thread
blocks, which it will then submit to the thread_pool. The given thread_pool
will then call funct() on each of the subranges.
- To be precise, suppose we have broken the range [begin, end) into the
following subranges:
- [begin[0], end[0])
- [begin[1], end[1])
- [begin[2], end[2])
...
- [begin[n], end[n])
Then parallel_for_blocked() submits each of these subranges to tp for
processing such that funct(begin[i], end[i]) is invoked for all valid values
of i.
- This function will not perform any memory allocations or create any system
resources such as mutex objects.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked (
unsigned long num_threads,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following block of code:
thread_pool tp(num_threads);
parallel_for_blocked(tp, begin, end, funct, chunks_per_thread);
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked (
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following block of code:
parallel_for_blocked(default_thread_pool(), begin, end, funct, chunks_per_thread);
!*/
// ----------------------------------------------------------------------------------------
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for (
thread_pool& tp,
long begin,
long end,
T& obj,
void (T::*funct)(long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following function call:
parallel_for_blocked(tp, begin, end, [&](long begin_sub, long end_sub)
{
for (long i = begin_sub; i < end_sub; ++i)
(obj.*funct)(i);
}, chunks_per_thread);
- Therefore, this routine invokes (obj.*funct)(i) for all i in the range
[begin, end). However, it does so using tp.num_threads_in_pool() parallel
threads.
- This function will not perform any memory allocations or create any system
resources such as mutex objects.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for (
unsigned long num_threads,
long begin,
long end,
T& obj,
void (T::*funct)(long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following block of code:
thread_pool tp(num_threads);
parallel_for(tp, begin, end, obj, funct, chunks_per_thread);
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for (
thread_pool& tp,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following function call:
parallel_for_blocked(tp, begin, end, [&](long begin_sub, long end_sub)
{
for (long i = begin_sub; i < end_sub; ++i)
funct(i);
}, chunks_per_thread);
- Therefore, this routine invokes funct(i) for all i in the range [begin, end).
However, it does so using tp.num_threads_in_pool() parallel threads.
- This function will not perform any memory allocations or create any system
resources such as mutex objects.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for (
unsigned long num_threads,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following block of code:
thread_pool tp(num_threads);
parallel_for(tp, begin, end, funct, chunks_per_thread);
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for (
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is equivalent to the following block of code:
parallel_for(default_thread_pool(), begin, end, funct, chunks_per_thread);
!*/
// ----------------------------------------------------------------------------------------
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_verbose (
thread_pool& tp,
long begin,
long end,
T& obj,
void (T::*funct)(long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for() routine defined above except
that it will print messages to cout showing the progress in executing the
parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_verbose (
unsigned long num_threads,
long begin,
long end,
T& obj,
void (T::*funct)(long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for() routine defined above except
that it will print messages to cout showing the progress in executing the
parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_verbose (
thread_pool& tp,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for() routine defined above except
that it will print messages to cout showing the progress in executing the
parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_verbose (
unsigned long num_threads,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for() routine defined above except
that it will print messages to cout showing the progress in executing the
parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_verbose (
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for() routine defined above except
that it will print messages to cout showing the progress in executing the
parallel for loop.
- It will also use the default_thread_pool().
!*/
// ----------------------------------------------------------------------------------------
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked_verbose (
thread_pool& tp,
long begin,
long end,
T& obj,
void (T::*funct)(long,long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for_blocked() routine defined
above except that it will print messages to cout showing the progress in
executing the parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked_verbose (
unsigned long num_threads,
long begin,
long end,
T& obj,
void (T::*funct)(long,long),
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for_blocked() routine defined
above except that it will print messages to cout showing the progress in
executing the parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked_verbose (
thread_pool& tp,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for_blocked() routine defined
above except that it will print messages to cout showing the progress in
executing the parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked_verbose (
unsigned long num_threads,
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for_blocked() routine defined
above except that it will print messages to cout showing the progress in
executing the parallel for loop.
!*/
// ----------------------------------------------------------------------------------------
template <typename T>
void parallel_for_blocked_verbose (
long begin,
long end,
const T& funct,
long chunks_per_thread = 8
);
/*!
requires
- begin <= end
- chunks_per_thread > 0
ensures
- This function is identical to the parallel_for_blocked() routine defined
above except that it will print messages to cout showing the progress in
executing the parallel for loop.
- It will also use the default_thread_pool()
!*/
// ----------------------------------------------------------------------------------------
}
#endif // DLIB_PARALLEL_FoR_ABSTRACT_Hh_
|
