|
0
|
1 \input texinfo @c -*-texinfo-*-
|
|
|
2
|
|
|
3 @c %**start of header
|
|
|
4 @setfilename libgomp.info
|
|
|
5 @settitle GNU libgomp
|
|
|
6 @c %**end of header
|
|
|
7
|
|
|
8
|
|
|
9 @copying
|
|
|
10 Copyright @copyright{} 2006, 2007, 2008 Free Software Foundation, Inc.
|
|
|
11
|
|
|
12 Permission is granted to copy, distribute and/or modify this document
|
|
|
13 under the terms of the GNU Free Documentation License, Version 1.2 or
|
|
|
14 any later version published by the Free Software Foundation; with the
|
|
|
15 Invariant Sections being ``Funding Free Software'', the Front-Cover
|
|
|
16 texts being (a) (see below), and with the Back-Cover Texts being (b)
|
|
|
17 (see below). A copy of the license is included in the section entitled
|
|
|
18 ``GNU Free Documentation License''.
|
|
|
19
|
|
|
20 (a) The FSF's Front-Cover Text is:
|
|
|
21
|
|
|
22 A GNU Manual
|
|
|
23
|
|
|
24 (b) The FSF's Back-Cover Text is:
|
|
|
25
|
|
|
26 You have freedom to copy and modify this GNU Manual, like GNU
|
|
|
27 software. Copies published by the Free Software Foundation raise
|
|
|
28 funds for GNU development.
|
|
|
29 @end copying
|
|
|
30
|
|
|
31 @ifinfo
|
|
|
32 @dircategory GNU Libraries
|
|
|
33 @direntry
|
|
|
34 * libgomp: (libgomp). GNU OpenMP runtime library
|
|
|
35 @end direntry
|
|
|
36
|
|
|
37 This manual documents the GNU implementation of the OpenMP API for
|
|
|
38 multi-platform shared-memory parallel programming in C/C++ and Fortran.
|
|
|
39
|
|
|
40 Published by the Free Software Foundation
|
|
|
41 51 Franklin Street, Fifth Floor
|
|
|
42 Boston, MA 02110-1301 USA
|
|
|
43
|
|
|
44 @insertcopying
|
|
|
45 @end ifinfo
|
|
|
46
|
|
|
47
|
|
|
48 @setchapternewpage odd
|
|
|
49
|
|
|
50 @titlepage
|
|
|
51 @title The GNU OpenMP Implementation
|
|
|
52 @page
|
|
|
53 @vskip 0pt plus 1filll
|
|
|
54 @comment For the @value{version-GCC} Version*
|
|
|
55 @sp 1
|
|
|
56 Published by the Free Software Foundation @*
|
|
|
57 51 Franklin Street, Fifth Floor@*
|
|
|
58 Boston, MA 02110-1301, USA@*
|
|
|
59 @sp 1
|
|
|
60 @insertcopying
|
|
|
61 @end titlepage
|
|
|
62
|
|
|
63 @summarycontents
|
|
|
64 @contents
|
|
|
65 @page
|
|
|
66
|
|
|
67
|
|
|
68 @node Top
|
|
|
69 @top Introduction
|
|
|
70 @cindex Introduction
|
|
|
71
|
|
|
72 This manual documents the usage of libgomp, the GNU implementation of the
|
|
|
73 @uref{http://www.openmp.org, OpenMP} Application Programming Interface (API)
|
|
|
74 for multi-platform shared-memory parallel programming in C/C++ and Fortran.
|
|
|
75
|
|
|
76
|
|
|
77
|
|
|
78 @comment
|
|
|
79 @comment When you add a new menu item, please keep the right hand
|
|
|
80 @comment aligned to the same column. Do not use tabs. This provides
|
|
|
81 @comment better formatting.
|
|
|
82 @comment
|
|
|
83 @menu
|
|
|
84 * Enabling OpenMP:: How to enable OpenMP for your applications.
|
|
|
85 * Runtime Library Routines:: The OpenMP runtime application programming
|
|
|
86 interface.
|
|
|
87 * Environment Variables:: Influencing runtime behavior with environment
|
|
|
88 variables.
|
|
|
89 * The libgomp ABI:: Notes on the external ABI presented by libgomp.
|
|
|
90 * Reporting Bugs:: How to report bugs in GNU OpenMP.
|
|
|
91 * Copying:: GNU general public license says
|
|
|
92 how you can copy and share libgomp.
|
|
|
93 * GNU Free Documentation License::
|
|
|
94 How you can copy and share this manual.
|
|
|
95 * Funding:: How to help assure continued work for free
|
|
|
96 software.
|
|
|
97 * Index:: Index of this documentation.
|
|
|
98 @end menu
|
|
|
99
|
|
|
100
|
|
|
101 @c ---------------------------------------------------------------------
|
|
|
102 @c Enabling OpenMP
|
|
|
103 @c ---------------------------------------------------------------------
|
|
|
104
|
|
|
105 @node Enabling OpenMP
|
|
|
106 @chapter Enabling OpenMP
|
|
|
107
|
|
|
108 To activate the OpenMP extensions for C/C++ and Fortran, the compile-time
|
|
|
109 flag @command{-fopenmp} must be specified. This enables the OpenMP directive
|
|
|
110 @code{#pragma omp} in C/C++ and @code{!$omp} directives in free form,
|
|
|
111 @code{c$omp}, @code{*$omp} and @code{!$omp} directives in fixed form,
|
|
|
112 @code{!$} conditional compilation sentinels in free form and @code{c$},
|
|
|
113 @code{*$} and @code{!$} sentinels in fixed form, for Fortran. The flag also
|
|
|
114 arranges for automatic linking of the OpenMP runtime library
|
|
|
115 (@ref{Runtime Library Routines}).
|
|
|
116
|
|
|
117 A complete description of all OpenMP directives accepted may be found in
|
|
|
118 the @uref{http://www.openmp.org, OpenMP Application Program Interface} manual,
|
|
|
119 version 3.0.
|
|
|
120
|
|
|
121
|
|
|
122 @c ---------------------------------------------------------------------
|
|
|
123 @c Runtime Library Routines
|
|
|
124 @c ---------------------------------------------------------------------
|
|
|
125
|
|
|
126 @node Runtime Library Routines
|
|
|
127 @chapter Runtime Library Routines
|
|
|
128
|
|
|
129 The runtime routines described here are defined by section 3 of the OpenMP
|
|
|
130 specifications in version 3.0. The routines are structured in following
|
|
|
131 three parts:
|
|
|
132
|
|
|
133 Control threads, processors and the parallel environment.
|
|
|
134
|
|
|
135 @menu
|
|
|
136 * omp_get_active_level:: Number of active parallel regions
|
|
|
137 * omp_get_ancestor_thread_num:: Ancestor thread ID
|
|
|
138 * omp_get_dynamic:: Dynamic teams setting
|
|
|
139 * omp_get_level:: Number of parallel regions
|
|
|
140 * omp_get_max_active_levels:: Maximal number of active regions
|
|
|
141 * omp_get_max_threads:: Maximal number of threads of parallel region
|
|
|
142 * omp_get_nested:: Nested parallel regions
|
|
|
143 * omp_get_num_procs:: Number of processors online
|
|
|
144 * omp_get_num_threads:: Size of the active team
|
|
|
145 * omp_get_schedule:: Obtain the runtime scheduling method
|
|
|
146 * omp_get_team_size:: Number of threads in a team
|
|
|
147 * omp_get_thread_limit:: Maximal number of threads
|
|
|
148 * omp_get_thread_num:: Current thread ID
|
|
|
149 * omp_in_parallel:: Whether a parallel region is active
|
|
|
150 * omp_set_dynamic:: Enable/disable dynamic teams
|
|
|
151 * omp_set_max_active_levels:: Limits the number of active parallel regions
|
|
|
152 * omp_set_nested:: Enable/disable nested parallel regions
|
|
|
153 * omp_set_num_threads:: Set upper team size limit
|
|
|
154 * omp_set_schedule:: Set the runtime scheduling method
|
|
|
155 @end menu
|
|
|
156
|
|
|
157 Initialize, set, test, unset and destroy simple and nested locks.
|
|
|
158
|
|
|
159 @menu
|
|
|
160 * omp_init_lock:: Initialize simple lock
|
|
|
161 * omp_set_lock:: Wait for and set simple lock
|
|
|
162 * omp_test_lock:: Test and set simple lock if available
|
|
|
163 * omp_unset_lock:: Unset simple lock
|
|
|
164 * omp_destroy_lock:: Destroy simple lock
|
|
|
165 * omp_init_nest_lock:: Initialize nested lock
|
|
|
166 * omp_set_nest_lock:: Wait for and set simple lock
|
|
|
167 * omp_test_nest_lock:: Test and set nested lock if available
|
|
|
168 * omp_unset_nest_lock:: Unset nested lock
|
|
|
169 * omp_destroy_nest_lock:: Destroy nested lock
|
|
|
170 @end menu
|
|
|
171
|
|
|
172 Portable, thread-based, wall clock timer.
|
|
|
173
|
|
|
174 @menu
|
|
|
175 * omp_get_wtick:: Get timer precision.
|
|
|
176 * omp_get_wtime:: Elapsed wall clock time.
|
|
|
177 @end menu
|
|
|
178
|
|
|
179
|
|
|
180
|
|
|
181 @node omp_get_active_level
|
|
|
182 @section @code{omp_get_active_level} -- Number of parallel regions
|
|
|
183 @table @asis
|
|
|
184 @item @emph{Description}:
|
|
|
185 This function returns the nesting level for the active parallel blocks,
|
|
|
186 which enclose the calling call.
|
|
|
187
|
|
|
188 @item @emph{C/C++}
|
|
|
189 @multitable @columnfractions .20 .80
|
|
|
190 @item @emph{Prototype}: @tab @code{int omp_get_active_level();}
|
|
|
191 @end multitable
|
|
|
192
|
|
|
193 @item @emph{Fortran}:
|
|
|
194 @multitable @columnfractions .20 .80
|
|
|
195 @item @emph{Interface}: @tab @code{integer omp_get_active_level()}
|
|
|
196 @end multitable
|
|
|
197
|
|
|
198 @item @emph{See also}:
|
|
|
199 @ref{omp_get_level}, @ref{omp_get_max_active_levels}, @ref{omp_set_max_active_levels}
|
|
|
200
|
|
|
201 @item @emph{Reference}:
|
|
|
202 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.19.
|
|
|
203 @end table
|
|
|
204
|
|
|
205
|
|
|
206
|
|
|
207 @node omp_get_ancestor_thread_num
|
|
|
208 @section @code{omp_get_ancestor_thread_num} -- Ancestor thread ID
|
|
|
209 @table @asis
|
|
|
210 @item @emph{Description}:
|
|
|
211 This function returns the thread identification number for the given
|
|
|
212 nesting level of the current thread. For values of @var{level} outside
|
|
|
213 zero to @code{omp_get_level} -1 is returned; if @var{level} is
|
|
|
214 @code{omp_get_level} the result is identical to @code{omp_get_thread_num}.
|
|
|
215
|
|
|
216 @item @emph{C/C++}
|
|
|
217 @multitable @columnfractions .20 .80
|
|
|
218 @item @emph{Prototype}: @tab @code{int omp_get_ancestor_thread_num(int level);}
|
|
|
219 @end multitable
|
|
|
220
|
|
|
221 @item @emph{Fortran}:
|
|
|
222 @multitable @columnfractions .20 .80
|
|
|
223 @item @emph{Interface}: @tab @code{integer omp_ancestor_thread_num(level)}
|
|
|
224 @item @tab @code{integer level}
|
|
|
225 @end multitable
|
|
|
226
|
|
|
227 @item @emph{See also}:
|
|
|
228 @ref{omp_get_level}, @ref{omp_get_thread_num}, @ref{omp_get_team_size}
|
|
|
229
|
|
|
230 @item @emph{Reference}:
|
|
|
231 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.17.
|
|
|
232 @end table
|
|
|
233
|
|
|
234
|
|
|
235
|
|
|
236 @node omp_get_dynamic
|
|
|
237 @section @code{omp_get_dynamic} -- Dynamic teams setting
|
|
|
238 @table @asis
|
|
|
239 @item @emph{Description}:
|
|
|
240 This function returns @code{true} if enabled, @code{false} otherwise.
|
|
|
241 Here, @code{true} and @code{false} represent their language-specific
|
|
|
242 counterparts.
|
|
|
243
|
|
|
244 The dynamic team setting may be initialized at startup by the
|
|
|
245 @code{OMP_DYNAMIC} environment variable or at runtime using
|
|
|
246 @code{omp_set_dynamic}. If undefined, dynamic adjustment is
|
|
|
247 disabled by default.
|
|
|
248
|
|
|
249 @item @emph{C/C++}:
|
|
|
250 @multitable @columnfractions .20 .80
|
|
|
251 @item @emph{Prototype}: @tab @code{int omp_get_dynamic();}
|
|
|
252 @end multitable
|
|
|
253
|
|
|
254 @item @emph{Fortran}:
|
|
|
255 @multitable @columnfractions .20 .80
|
|
|
256 @item @emph{Interface}: @tab @code{logical function omp_get_dynamic()}
|
|
|
257 @end multitable
|
|
|
258
|
|
|
259 @item @emph{See also}:
|
|
|
260 @ref{omp_set_dynamic}, @ref{OMP_DYNAMIC}
|
|
|
261
|
|
|
262 @item @emph{Reference}:
|
|
|
263 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.8.
|
|
|
264 @end table
|
|
|
265
|
|
|
266
|
|
|
267
|
|
|
268 @node omp_get_level
|
|
|
269 @section @code{omp_get_level} -- Obtain the current nesting level
|
|
|
270 @table @asis
|
|
|
271 @item @emph{Description}:
|
|
|
272 This function returns the nesting level for the parallel blocks,
|
|
|
273 which enclose the calling call.
|
|
|
274
|
|
|
275 @item @emph{C/C++}
|
|
|
276 @multitable @columnfractions .20 .80
|
|
|
277 @item @emph{Prototype}: @tab @code{int omp_get level();}
|
|
|
278 @end multitable
|
|
|
279
|
|
|
280 @item @emph{Fortran}:
|
|
|
281 @multitable @columnfractions .20 .80
|
|
|
282 @item @emph{Interface}: @tab @code{integer omp_level()}
|
|
|
283 @end multitable
|
|
|
284
|
|
|
285 @item @emph{See also}:
|
|
|
286 @ref{omp_get_active_level}
|
|
|
287
|
|
|
288 @item @emph{Reference}:
|
|
|
289 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.16.
|
|
|
290 @end table
|
|
|
291
|
|
|
292
|
|
|
293
|
|
|
294 @node omp_get_max_active_levels
|
|
|
295 @section @code{omp_set_max_active_levels} -- Maximal number of active regions
|
|
|
296 @table @asis
|
|
|
297 @item @emph{Description}:
|
|
|
298 This function obtains the maximally allowed number of nested, active parallel regions.
|
|
|
299
|
|
|
300 @item @emph{C/C++}
|
|
|
301 @multitable @columnfractions .20 .80
|
|
|
302 @item @emph{Prototype}: @tab @code{int omp_get_max_active_levels();}
|
|
|
303 @end multitable
|
|
|
304
|
|
|
305 @item @emph{Fortran}:
|
|
|
306 @multitable @columnfractions .20 .80
|
|
|
307 @item @emph{Interface}: @tab @code{int omp_get_max_active_levels()}
|
|
|
308 @end multitable
|
|
|
309
|
|
|
310 @item @emph{See also}:
|
|
|
311 @ref{omp_set_max_active_levels}, @ref{omp_get_active_level}
|
|
|
312
|
|
|
313 @item @emph{Reference}:
|
|
|
314 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.14.
|
|
|
315 @end table
|
|
|
316
|
|
|
317
|
|
|
318
|
|
|
319 @node omp_get_max_threads
|
|
|
320 @section @code{omp_get_max_threads} -- Maximal number of threads of parallel region
|
|
|
321 @table @asis
|
|
|
322 @item @emph{Description}:
|
|
|
323 Return the maximal number of threads used for the current parallel region
|
|
|
324 that does not use the clause @code{num_threads}.
|
|
|
325
|
|
|
326 @item @emph{C/C++}:
|
|
|
327 @multitable @columnfractions .20 .80
|
|
|
328 @item @emph{Prototype}: @tab @code{int omp_get_max_threads();}
|
|
|
329 @end multitable
|
|
|
330
|
|
|
331 @item @emph{Fortran}:
|
|
|
332 @multitable @columnfractions .20 .80
|
|
|
333 @item @emph{Interface}: @tab @code{integer function omp_get_max_threads()}
|
|
|
334 @end multitable
|
|
|
335
|
|
|
336 @item @emph{See also}:
|
|
|
337 @ref{omp_set_num_threads}, @ref{omp_set_dynamic}, @ref{omp_get_thread_limit}
|
|
|
338
|
|
|
339 @item @emph{Reference}:
|
|
|
340 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.3.
|
|
|
341 @end table
|
|
|
342
|
|
|
343
|
|
|
344
|
|
|
345 @node omp_get_nested
|
|
|
346 @section @code{omp_get_nested} -- Nested parallel regions
|
|
|
347 @table @asis
|
|
|
348 @item @emph{Description}:
|
|
|
349 This function returns @code{true} if nested parallel regions are
|
|
|
350 enabled, @code{false} otherwise. Here, @code{true} and @code{false}
|
|
|
351 represent their language-specific counterparts.
|
|
|
352
|
|
|
353 Nested parallel regions may be initialized at startup by the
|
|
|
354 @code{OMP_NESTED} environment variable or at runtime using
|
|
|
355 @code{omp_set_nested}. If undefined, nested parallel regions are
|
|
|
356 disabled by default.
|
|
|
357
|
|
|
358 @item @emph{C/C++}:
|
|
|
359 @multitable @columnfractions .20 .80
|
|
|
360 @item @emph{Prototype}: @tab @code{int omp_get_nested();}
|
|
|
361 @end multitable
|
|
|
362
|
|
|
363 @item @emph{Fortran}:
|
|
|
364 @multitable @columnfractions .20 .80
|
|
|
365 @item @emph{Interface}: @tab @code{integer function omp_get_nested()}
|
|
|
366 @end multitable
|
|
|
367
|
|
|
368 @item @emph{See also}:
|
|
|
369 @ref{omp_set_nested}, @ref{OMP_NESTED}
|
|
|
370
|
|
|
371 @item @emph{Reference}:
|
|
|
372 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.10.
|
|
|
373 @end table
|
|
|
374
|
|
|
375
|
|
|
376
|
|
|
377 @node omp_get_num_procs
|
|
|
378 @section @code{omp_get_num_procs} -- Number of processors online
|
|
|
379 @table @asis
|
|
|
380 @item @emph{Description}:
|
|
|
381 Returns the number of processors online.
|
|
|
382
|
|
|
383 @item @emph{C/C++}:
|
|
|
384 @multitable @columnfractions .20 .80
|
|
|
385 @item @emph{Prototype}: @tab @code{int omp_get_num_procs();}
|
|
|
386 @end multitable
|
|
|
387
|
|
|
388 @item @emph{Fortran}:
|
|
|
389 @multitable @columnfractions .20 .80
|
|
|
390 @item @emph{Interface}: @tab @code{integer function omp_get_num_procs()}
|
|
|
391 @end multitable
|
|
|
392
|
|
|
393 @item @emph{Reference}:
|
|
|
394 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.5.
|
|
|
395 @end table
|
|
|
396
|
|
|
397
|
|
|
398
|
|
|
399 @node omp_get_num_threads
|
|
|
400 @section @code{omp_get_num_threads} -- Size of the active team
|
|
|
401 @table @asis
|
|
|
402 @item @emph{Description}:
|
|
|
403 The number of threads in the current team. In a sequential section of
|
|
|
404 the program @code{omp_get_num_threads} returns 1.
|
|
|
405
|
|
|
406 The default team size may be initialized at startup by the
|
|
|
407 @code{OMP_NUM_THREADS} environment variable. At runtime, the size
|
|
|
408 of the current team may be set either by the @code{NUM_THREADS}
|
|
|
409 clause or by @code{omp_set_num_threads}. If none of the above were
|
|
|
410 used to define a specific value and @code{OMP_DYNAMIC} is disabled,
|
|
|
411 one thread per CPU online is used.
|
|
|
412
|
|
|
413 @item @emph{C/C++}:
|
|
|
414 @multitable @columnfractions .20 .80
|
|
|
415 @item @emph{Prototype}: @tab @code{int omp_get_num_threads();}
|
|
|
416 @end multitable
|
|
|
417
|
|
|
418 @item @emph{Fortran}:
|
|
|
419 @multitable @columnfractions .20 .80
|
|
|
420 @item @emph{Interface}: @tab @code{integer function omp_get_num_threads()}
|
|
|
421 @end multitable
|
|
|
422
|
|
|
423 @item @emph{See also}:
|
|
|
424 @ref{omp_get_max_threads}, @ref{omp_set_num_threads}, @ref{OMP_NUM_THREADS}
|
|
|
425
|
|
|
426 @item @emph{Reference}:
|
|
|
427 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.2.
|
|
|
428 @end table
|
|
|
429
|
|
|
430
|
|
|
431
|
|
|
432 @node omp_get_schedule
|
|
|
433 @section @code{omp_get_schedule} -- Obtain the runtime scheduling method
|
|
|
434 @table @asis
|
|
|
435 @item @emph{Description}:
|
|
|
436 Obtain runtime the scheduling method. The @var{kind} argument will be
|
|
|
437 set to the value @code{omp_sched_static}, @code{omp_sched_dynamic},
|
|
|
438 @code{opm_sched_guided} or @code{auto}. The second argument, @var{modifier},
|
|
|
439 is set to the chunk size.
|
|
|
440
|
|
|
441 @item @emph{C/C++}
|
|
|
442 @multitable @columnfractions .20 .80
|
|
|
443 @item @emph{Prototype}: @tab @code{omp_schedule(omp_sched_t * kind, int *modifier);}
|
|
|
444 @end multitable
|
|
|
445
|
|
|
446 @item @emph{Fortran}:
|
|
|
447 @multitable @columnfractions .20 .80
|
|
|
448 @item @emph{Interface}: @tab @code{subroutine omp_schedule(kind, modifier)}
|
|
|
449 @item @tab @code{integer(kind=omp_sched_kind) kind}
|
|
|
450 @item @tab @code{integer modifier}
|
|
|
451 @end multitable
|
|
|
452
|
|
|
453 @item @emph{See also}:
|
|
|
454 @ref{omp_set_schedule}, @ref{OMP_SCHEDULE}
|
|
|
455
|
|
|
456 @item @emph{Reference}:
|
|
|
457 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.12.
|
|
|
458 @end table
|
|
|
459
|
|
|
460
|
|
|
461
|
|
|
462 @node omp_get_team_size
|
|
|
463 @section @code{omp_get_team_size} -- Number of threads in a team
|
|
|
464 @table @asis
|
|
|
465 @item @emph{Description}:
|
|
|
466 This function returns the number of threads in a thread team to which
|
|
|
467 either the current thread or its ancestor belongs. For values of @var{level}
|
|
|
468 outside zero to @code{omp_get_level} -1 is returned; if @var{level} is zero
|
|
|
469 1 is returned and for @code{omp_get_level} the result is identical
|
|
|
470 to @code{omp_get_num_threads}.
|
|
|
471
|
|
|
472 @item @emph{C/C++}:
|
|
|
473 @multitable @columnfractions .20 .80
|
|
|
474 @item @emph{Prototype}: @tab @code{int omp_get_time_size(int level);}
|
|
|
475 @end multitable
|
|
|
476
|
|
|
477 @item @emph{Fortran}:
|
|
|
478 @multitable @columnfractions .20 .80
|
|
|
479 @item @emph{Interface}: @tab @code{integer function omp_get_team_size(level)}
|
|
|
480 @item @tab @code{integer level}
|
|
|
481 @end multitable
|
|
|
482
|
|
|
483 @item @emph{See also}:
|
|
|
484 @ref{omp_get_num_threads}, @ref{omp_get_level}, @ref{omp_get_ancestor_thread_num}
|
|
|
485
|
|
|
486 @item @emph{Reference}:
|
|
|
487 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.18.
|
|
|
488 @end table
|
|
|
489
|
|
|
490
|
|
|
491
|
|
|
492 @node omp_get_thread_limit
|
|
|
493 @section @code{omp_get_thread_limit} -- Maximal number of threads
|
|
|
494 @table @asis
|
|
|
495 @item @emph{Description}:
|
|
|
496 Return the maximal number of threads of the program.
|
|
|
497
|
|
|
498 @item @emph{C/C++}:
|
|
|
499 @multitable @columnfractions .20 .80
|
|
|
500 @item @emph{Prototype}: @tab @code{int omp_get_thread_limit();}
|
|
|
501 @end multitable
|
|
|
502
|
|
|
503 @item @emph{Fortran}:
|
|
|
504 @multitable @columnfractions .20 .80
|
|
|
505 @item @emph{Interface}: @tab @code{integer function omp_get_thread_limit()}
|
|
|
506 @end multitable
|
|
|
507
|
|
|
508 @item @emph{See also}:
|
|
|
509 @ref{omp_get_max_threads}, @ref{OMP_THREAD_LIMIT}
|
|
|
510
|
|
|
511 @item @emph{Reference}:
|
|
|
512 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.13.
|
|
|
513 @end table
|
|
|
514
|
|
|
515
|
|
|
516
|
|
|
517 @node omp_get_thread_num
|
|
|
518 @section @code{omp_get_thread_num} -- Current thread ID
|
|
|
519 @table @asis
|
|
|
520 @item @emph{Description}:
|
|
|
521 Unique thread identification number within the current team.
|
|
|
522 In a sequential parts of the program, @code{omp_get_thread_num}
|
|
|
523 always returns 0. In parallel regions the return value varies
|
|
|
524 from 0 to @code{omp_get_num_threads}-1 inclusive. The return
|
|
|
525 value of the master thread of a team is always 0.
|
|
|
526
|
|
|
527 @item @emph{C/C++}:
|
|
|
528 @multitable @columnfractions .20 .80
|
|
|
529 @item @emph{Prototype}: @tab @code{int omp_get_thread_num();}
|
|
|
530 @end multitable
|
|
|
531
|
|
|
532 @item @emph{Fortran}:
|
|
|
533 @multitable @columnfractions .20 .80
|
|
|
534 @item @emph{Interface}: @tab @code{integer function omp_get_thread_num()}
|
|
|
535 @end multitable
|
|
|
536
|
|
|
537 @item @emph{See also}:
|
|
|
538 @ref{omp_get_num_threads}, @ref{omp_get_ancestor_thread_num}
|
|
|
539
|
|
|
540 @item @emph{Reference}:
|
|
|
541 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.4.
|
|
|
542 @end table
|
|
|
543
|
|
|
544
|
|
|
545
|
|
|
546 @node omp_in_parallel
|
|
|
547 @section @code{omp_in_parallel} -- Whether a parallel region is active
|
|
|
548 @table @asis
|
|
|
549 @item @emph{Description}:
|
|
|
550 This function returns @code{true} if currently running in parallel,
|
|
|
551 @code{false} otherwise. Here, @code{true} and @code{false} represent
|
|
|
552 their language-specific counterparts.
|
|
|
553
|
|
|
554 @item @emph{C/C++}:
|
|
|
555 @multitable @columnfractions .20 .80
|
|
|
556 @item @emph{Prototype}: @tab @code{int omp_in_parallel();}
|
|
|
557 @end multitable
|
|
|
558
|
|
|
559 @item @emph{Fortran}:
|
|
|
560 @multitable @columnfractions .20 .80
|
|
|
561 @item @emph{Interface}: @tab @code{logical function omp_in_parallel()}
|
|
|
562 @end multitable
|
|
|
563
|
|
|
564 @item @emph{Reference}:
|
|
|
565 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.6.
|
|
|
566 @end table
|
|
|
567
|
|
|
568
|
|
|
569 @node omp_set_dynamic
|
|
|
570 @section @code{omp_set_dynamic} -- Enable/disable dynamic teams
|
|
|
571 @table @asis
|
|
|
572 @item @emph{Description}:
|
|
|
573 Enable or disable the dynamic adjustment of the number of threads
|
|
|
574 within a team. The function takes the language-specific equivalent
|
|
|
575 of @code{true} and @code{false}, where @code{true} enables dynamic
|
|
|
576 adjustment of team sizes and @code{false} disables it.
|
|
|
577
|
|
|
578 @item @emph{C/C++}:
|
|
|
579 @multitable @columnfractions .20 .80
|
|
|
580 @item @emph{Prototype}: @tab @code{void omp_set_dynamic(int);}
|
|
|
581 @end multitable
|
|
|
582
|
|
|
583 @item @emph{Fortran}:
|
|
|
584 @multitable @columnfractions .20 .80
|
|
|
585 @item @emph{Interface}: @tab @code{subroutine omp_set_dynamic(set)}
|
|
|
586 @item @tab @code{integer, intent(in) :: set}
|
|
|
587 @end multitable
|
|
|
588
|
|
|
589 @item @emph{See also}:
|
|
|
590 @ref{OMP_DYNAMIC}, @ref{omp_get_dynamic}
|
|
|
591
|
|
|
592 @item @emph{Reference}:
|
|
|
593 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.7.
|
|
|
594 @end table
|
|
|
595
|
|
|
596
|
|
|
597
|
|
|
598 @node omp_set_max_active_levels
|
|
|
599 @section @code{omp_set_max_active_levels} -- Limits the number of active parallel regions
|
|
|
600 @table @asis
|
|
|
601 @item @emph{Description}:
|
|
|
602 This function limits the maximally allowed number of nested, active parallel regions.
|
|
|
603
|
|
|
604 @item @emph{C/C++}
|
|
|
605 @multitable @columnfractions .20 .80
|
|
|
606 @item @emph{Prototype}: @tab @code{omp_set_max_active_levels(int max_levels);}
|
|
|
607 @end multitable
|
|
|
608
|
|
|
609 @item @emph{Fortran}:
|
|
|
610 @multitable @columnfractions .20 .80
|
|
|
611 @item @emph{Interface}: @tab @code{omp_max_active_levels(max_levels)}
|
|
|
612 @item @tab @code{integer max_levels}
|
|
|
613 @end multitable
|
|
|
614
|
|
|
615 @item @emph{See also}:
|
|
|
616 @ref{omp_get_max_active_levels}, @ref{omp_get_active_level}
|
|
|
617
|
|
|
618 @item @emph{Reference}:
|
|
|
619 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.14.
|
|
|
620 @end table
|
|
|
621
|
|
|
622
|
|
|
623
|
|
|
624 @node omp_set_nested
|
|
|
625 @section @code{omp_set_nested} -- Enable/disable nested parallel regions
|
|
|
626 @table @asis
|
|
|
627 @item @emph{Description}:
|
|
|
628 Enable or disable nested parallel regions, i.e., whether team members
|
|
|
629 are allowed to create new teams. The function takes the language-specific
|
|
|
630 equivalent of @code{true} and @code{false}, where @code{true} enables
|
|
|
631 dynamic adjustment of team sizes and @code{false} disables it.
|
|
|
632
|
|
|
633 @item @emph{C/C++}:
|
|
|
634 @multitable @columnfractions .20 .80
|
|
|
635 @item @emph{Prototype}: @tab @code{void omp_set_dynamic(int);}
|
|
|
636 @end multitable
|
|
|
637
|
|
|
638 @item @emph{Fortran}:
|
|
|
639 @multitable @columnfractions .20 .80
|
|
|
640 @item @emph{Interface}: @tab @code{subroutine omp_set_dynamic(set)}
|
|
|
641 @item @tab @code{integer, intent(in) :: set}
|
|
|
642 @end multitable
|
|
|
643
|
|
|
644 @item @emph{See also}:
|
|
|
645 @ref{OMP_NESTED}, @ref{omp_get_nested}
|
|
|
646
|
|
|
647 @item @emph{Reference}:
|
|
|
648 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.9.
|
|
|
649 @end table
|
|
|
650
|
|
|
651
|
|
|
652
|
|
|
653 @node omp_set_num_threads
|
|
|
654 @section @code{omp_set_num_threads} -- Set upper team size limit
|
|
|
655 @table @asis
|
|
|
656 @item @emph{Description}:
|
|
|
657 Specifies the number of threads used by default in subsequent parallel
|
|
|
658 sections, if those do not specify a @code{num_threads} clause. The
|
|
|
659 argument of @code{omp_set_num_threads} shall be a positive integer.
|
|
|
660
|
|
|
661 @item @emph{C/C++}:
|
|
|
662 @multitable @columnfractions .20 .80
|
|
|
663 @item @emph{Prototype}: @tab @code{void omp_set_num_threads(int);}
|
|
|
664 @end multitable
|
|
|
665
|
|
|
666 @item @emph{Fortran}:
|
|
|
667 @multitable @columnfractions .20 .80
|
|
|
668 @item @emph{Interface}: @tab @code{subroutine omp_set_num_threads(set)}
|
|
|
669 @item @tab @code{integer, intent(in) :: set}
|
|
|
670 @end multitable
|
|
|
671
|
|
|
672 @item @emph{See also}:
|
|
|
673 @ref{OMP_NUM_THREADS}, @ref{omp_get_num_threads}, @ref{omp_get_max_threads}
|
|
|
674
|
|
|
675 @item @emph{Reference}:
|
|
|
676 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.1.
|
|
|
677 @end table
|
|
|
678
|
|
|
679
|
|
|
680
|
|
|
681 @node omp_set_schedule
|
|
|
682 @section @code{omp_set_schedule} -- Set the runtime scheduling method
|
|
|
683 @table @asis
|
|
|
684 @item @emph{Description}:
|
|
|
685 Sets the runtime scheduling method. The @var{kind} argument can have the
|
|
|
686 value @code{omp_sched_static}, @code{omp_sched_dynamic},
|
|
|
687 @code{opm_sched_guided} or @code{omp_sched_auto}. Except for
|
|
|
688 @code{omp_sched_auto}, the chunk size is set to the value of
|
|
|
689 @var{modifier} if positive or to the default value if zero or negative.
|
|
|
690 For @code{omp_sched_auto} the @var{modifier} argument is ignored.
|
|
|
691
|
|
|
692 @item @emph{C/C++}
|
|
|
693 @multitable @columnfractions .20 .80
|
|
|
694 @item @emph{Prototype}: @tab @code{int omp_schedule(omp_sched_t * kind, int *modifier);}
|
|
|
695 @end multitable
|
|
|
696
|
|
|
697 @item @emph{Fortran}:
|
|
|
698 @multitable @columnfractions .20 .80
|
|
|
699 @item @emph{Interface}: @tab @code{subroutine omp_schedule(kind, modifier)}
|
|
|
700 @item @tab @code{integer(kind=omp_sched_kind) kind}
|
|
|
701 @item @tab @code{integer modifier}
|
|
|
702 @end multitable
|
|
|
703
|
|
|
704 @item @emph{See also}:
|
|
|
705 @ref{omp_get_schedule}
|
|
|
706 @ref{OMP_SCHEDULE}
|
|
|
707
|
|
|
708 @item @emph{Reference}:
|
|
|
709 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.2.11.
|
|
|
710 @end table
|
|
|
711
|
|
|
712
|
|
|
713
|
|
|
714 @node omp_init_lock
|
|
|
715 @section @code{omp_init_lock} -- Initialize simple lock
|
|
|
716 @table @asis
|
|
|
717 @item @emph{Description}:
|
|
|
718 Initialize a simple lock. After initialization, the lock is in
|
|
|
719 an unlocked state.
|
|
|
720
|
|
|
721 @item @emph{C/C++}:
|
|
|
722 @multitable @columnfractions .20 .80
|
|
|
723 @item @emph{Prototype}: @tab @code{void omp_init_lock(omp_lock_t *lock);}
|
|
|
724 @end multitable
|
|
|
725
|
|
|
726 @item @emph{Fortran}:
|
|
|
727 @multitable @columnfractions .20 .80
|
|
|
728 @item @emph{Interface}: @tab @code{subroutine omp_init_lock(lock)}
|
|
|
729 @item @tab @code{integer(omp_lock_kind), intent(out) :: lock}
|
|
|
730 @end multitable
|
|
|
731
|
|
|
732 @item @emph{See also}:
|
|
|
733 @ref{omp_destroy_lock}
|
|
|
734
|
|
|
735 @item @emph{Reference}:
|
|
|
736 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.1.
|
|
|
737 @end table
|
|
|
738
|
|
|
739
|
|
|
740
|
|
|
741 @node omp_set_lock
|
|
|
742 @section @code{omp_set_lock} -- Wait for and set simple lock
|
|
|
743 @table @asis
|
|
|
744 @item @emph{Description}:
|
|
|
745 Before setting a simple lock, the lock variable must be initialized by
|
|
|
746 @code{omp_init_lock}. The calling thread is blocked until the lock
|
|
|
747 is available. If the lock is already held by the current thread,
|
|
|
748 a deadlock occurs.
|
|
|
749
|
|
|
750 @item @emph{C/C++}:
|
|
|
751 @multitable @columnfractions .20 .80
|
|
|
752 @item @emph{Prototype}: @tab @code{void omp_set_lock(omp_lock_t *lock);}
|
|
|
753 @end multitable
|
|
|
754
|
|
|
755 @item @emph{Fortran}:
|
|
|
756 @multitable @columnfractions .20 .80
|
|
|
757 @item @emph{Interface}: @tab @code{subroutine omp_set_lock(lock)}
|
|
|
758 @item @tab @code{integer(omp_lock_kind), intent(out) :: lock}
|
|
|
759 @end multitable
|
|
|
760
|
|
|
761 @item @emph{See also}:
|
|
|
762 @ref{omp_init_lock}, @ref{omp_test_lock}, @ref{omp_unset_lock}
|
|
|
763
|
|
|
764 @item @emph{Reference}:
|
|
|
765 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.3.
|
|
|
766 @end table
|
|
|
767
|
|
|
768
|
|
|
769
|
|
|
770 @node omp_test_lock
|
|
|
771 @section @code{omp_test_lock} -- Test and set simple lock if available
|
|
|
772 @table @asis
|
|
|
773 @item @emph{Description}:
|
|
|
774 Before setting a simple lock, the lock variable must be initialized by
|
|
|
775 @code{omp_init_lock}. Contrary to @code{omp_set_lock}, @code{omp_test_lock}
|
|
|
776 does not block if the lock is not available. This function returns
|
|
|
777 @code{true} upon success, @code{false} otherwise. Here, @code{true} and
|
|
|
778 @code{false} represent their language-specific counterparts.
|
|
|
779
|
|
|
780 @item @emph{C/C++}:
|
|
|
781 @multitable @columnfractions .20 .80
|
|
|
782 @item @emph{Prototype}: @tab @code{int omp_test_lock(omp_lock_t *lock);}
|
|
|
783 @end multitable
|
|
|
784
|
|
|
785 @item @emph{Fortran}:
|
|
|
786 @multitable @columnfractions .20 .80
|
|
|
787 @item @emph{Interface}: @tab @code{subroutine omp_test_lock(lock)}
|
|
|
788 @item @tab @code{logical(omp_logical_kind) :: omp_test_lock}
|
|
|
789 @item @tab @code{integer(omp_lock_kind), intent(out) :: lock}
|
|
|
790 @end multitable
|
|
|
791
|
|
|
792 @item @emph{See also}:
|
|
|
793 @ref{omp_init_lock}, @ref{omp_set_lock}, @ref{omp_set_lock}
|
|
|
794
|
|
|
795 @item @emph{Reference}:
|
|
|
796 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.5.
|
|
|
797 @end table
|
|
|
798
|
|
|
799
|
|
|
800
|
|
|
801 @node omp_unset_lock
|
|
|
802 @section @code{omp_unset_lock} -- Unset simple lock
|
|
|
803 @table @asis
|
|
|
804 @item @emph{Description}:
|
|
|
805 A simple lock about to be unset must have been locked by @code{omp_set_lock}
|
|
|
806 or @code{omp_test_lock} before. In addition, the lock must be held by the
|
|
|
807 thread calling @code{omp_unset_lock}. Then, the lock becomes unlocked. If one
|
|
|
808 ore more threads attempted to set the lock before, one of them is chosen to,
|
|
|
809 again, set the lock for itself.
|
|
|
810
|
|
|
811 @item @emph{C/C++}:
|
|
|
812 @multitable @columnfractions .20 .80
|
|
|
813 @item @emph{Prototype}: @tab @code{void omp_unset_lock(omp_lock_t *lock);}
|
|
|
814 @end multitable
|
|
|
815
|
|
|
816 @item @emph{Fortran}:
|
|
|
817 @multitable @columnfractions .20 .80
|
|
|
818 @item @emph{Interface}: @tab @code{subroutine omp_unset_lock(lock)}
|
|
|
819 @item @tab @code{integer(omp_lock_kind), intent(out) :: lock}
|
|
|
820 @end multitable
|
|
|
821
|
|
|
822 @item @emph{See also}:
|
|
|
823 @ref{omp_set_lock}, @ref{omp_test_lock}
|
|
|
824
|
|
|
825 @item @emph{Reference}:
|
|
|
826 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.4.
|
|
|
827 @end table
|
|
|
828
|
|
|
829
|
|
|
830
|
|
|
831 @node omp_destroy_lock
|
|
|
832 @section @code{omp_destroy_lock} -- Destroy simple lock
|
|
|
833 @table @asis
|
|
|
834 @item @emph{Description}:
|
|
|
835 Destroy a simple lock. In order to be destroyed, a simple lock must be
|
|
|
836 in the unlocked state.
|
|
|
837
|
|
|
838 @item @emph{C/C++}:
|
|
|
839 @multitable @columnfractions .20 .80
|
|
|
840 @item @emph{Prototype}: @tab @code{void omp_destroy_lock(omp_lock_t *);}
|
|
|
841 @end multitable
|
|
|
842
|
|
|
843 @item @emph{Fortran}:
|
|
|
844 @multitable @columnfractions .20 .80
|
|
|
845 @item @emph{Interface}: @tab @code{subroutine omp_destroy_lock(lock)}
|
|
|
846 @item @tab @code{integer(omp_lock_kind), intent(inout) :: lock}
|
|
|
847 @end multitable
|
|
|
848
|
|
|
849 @item @emph{See also}:
|
|
|
850 @ref{omp_init_lock}
|
|
|
851
|
|
|
852 @item @emph{Reference}:
|
|
|
853 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.2.
|
|
|
854 @end table
|
|
|
855
|
|
|
856
|
|
|
857
|
|
|
858 @node omp_init_nest_lock
|
|
|
859 @section @code{omp_init_nest_lock} -- Initialize nested lock
|
|
|
860 @table @asis
|
|
|
861 @item @emph{Description}:
|
|
|
862 Initialize a nested lock. After initialization, the lock is in
|
|
|
863 an unlocked state and the nesting count is set to zero.
|
|
|
864
|
|
|
865 @item @emph{C/C++}:
|
|
|
866 @multitable @columnfractions .20 .80
|
|
|
867 @item @emph{Prototype}: @tab @code{void omp_init_nest_lock(omp_nest_lock_t *lock);}
|
|
|
868 @end multitable
|
|
|
869
|
|
|
870 @item @emph{Fortran}:
|
|
|
871 @multitable @columnfractions .20 .80
|
|
|
872 @item @emph{Interface}: @tab @code{subroutine omp_init_nest_lock(lock)}
|
|
|
873 @item @tab @code{integer(omp_nest_lock_kind), intent(out) :: lock}
|
|
|
874 @end multitable
|
|
|
875
|
|
|
876 @item @emph{See also}:
|
|
|
877 @ref{omp_destroy_nest_lock}
|
|
|
878
|
|
|
879 @item @emph{Reference}:
|
|
|
880 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.1.
|
|
|
881 @end table
|
|
|
882
|
|
|
883
|
|
|
884 @node omp_set_nest_lock
|
|
|
885 @section @code{omp_set_nest_lock} -- Wait for and set simple lock
|
|
|
886 @table @asis
|
|
|
887 @item @emph{Description}:
|
|
|
888 Before setting a nested lock, the lock variable must be initialized by
|
|
|
889 @code{omp_init_nest_lock}. The calling thread is blocked until the lock
|
|
|
890 is available. If the lock is already held by the current thread, the
|
|
|
891 nesting count for the lock in incremented.
|
|
|
892
|
|
|
893 @item @emph{C/C++}:
|
|
|
894 @multitable @columnfractions .20 .80
|
|
|
895 @item @emph{Prototype}: @tab @code{void omp_set_nest_lock(omp_nest_lock_t *lock);}
|
|
|
896 @end multitable
|
|
|
897
|
|
|
898 @item @emph{Fortran}:
|
|
|
899 @multitable @columnfractions .20 .80
|
|
|
900 @item @emph{Interface}: @tab @code{subroutine omp_set_nest_lock(lock)}
|
|
|
901 @item @tab @code{integer(omp_nest_lock_kind), intent(out) :: lock}
|
|
|
902 @end multitable
|
|
|
903
|
|
|
904 @item @emph{See also}:
|
|
|
905 @ref{omp_init_nest_lock}, @ref{omp_unset_nest_lock}
|
|
|
906
|
|
|
907 @item @emph{Reference}:
|
|
|
908 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.3.
|
|
|
909 @end table
|
|
|
910
|
|
|
911
|
|
|
912
|
|
|
913 @node omp_test_nest_lock
|
|
|
914 @section @code{omp_test_nest_lock} -- Test and set nested lock if available
|
|
|
915 @table @asis
|
|
|
916 @item @emph{Description}:
|
|
|
917 Before setting a nested lock, the lock variable must be initialized by
|
|
|
918 @code{omp_init_nest_lock}. Contrary to @code{omp_set_nest_lock},
|
|
|
919 @code{omp_test_nest_lock} does not block if the lock is not available.
|
|
|
920 If the lock is already held by the current thread, the new nesting count
|
|
|
921 is returned. Otherwise, the return value equals zero.
|
|
|
922
|
|
|
923 @item @emph{C/C++}:
|
|
|
924 @multitable @columnfractions .20 .80
|
|
|
925 @item @emph{Prototype}: @tab @code{int omp_test_nest_lock(omp_nest_lock_t *lock);}
|
|
|
926 @end multitable
|
|
|
927
|
|
|
928 @item @emph{Fortran}:
|
|
|
929 @multitable @columnfractions .20 .80
|
|
|
930 @item @emph{Interface}: @tab @code{integer function omp_test_nest_lock(lock)}
|
|
|
931 @item @tab @code{integer(omp_integer_kind) :: omp_test_nest_lock}
|
|
|
932 @item @tab @code{integer(omp_nest_lock_kind), intent(inout) :: lock}
|
|
|
933 @end multitable
|
|
|
934
|
|
|
935
|
|
|
936 @item @emph{See also}:
|
|
|
937 @ref{omp_init_lock}, @ref{omp_set_lock}, @ref{omp_set_lock}
|
|
|
938
|
|
|
939 @item @emph{Reference}:
|
|
|
940 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.5.
|
|
|
941 @end table
|
|
|
942
|
|
|
943
|
|
|
944
|
|
|
945 @node omp_unset_nest_lock
|
|
|
946 @section @code{omp_unset_nest_lock} -- Unset nested lock
|
|
|
947 @table @asis
|
|
|
948 @item @emph{Description}:
|
|
|
949 A nested lock about to be unset must have been locked by @code{omp_set_nested_lock}
|
|
|
950 or @code{omp_test_nested_lock} before. In addition, the lock must be held by the
|
|
|
951 thread calling @code{omp_unset_nested_lock}. If the nesting count drops to zero, the
|
|
|
952 lock becomes unlocked. If one ore more threads attempted to set the lock before,
|
|
|
953 one of them is chosen to, again, set the lock for itself.
|
|
|
954
|
|
|
955 @item @emph{C/C++}:
|
|
|
956 @multitable @columnfractions .20 .80
|
|
|
957 @item @emph{Prototype}: @tab @code{void omp_unset_nest_lock(omp_nest_lock_t *lock);}
|
|
|
958 @end multitable
|
|
|
959
|
|
|
960 @item @emph{Fortran}:
|
|
|
961 @multitable @columnfractions .20 .80
|
|
|
962 @item @emph{Interface}: @tab @code{subroutine omp_unset_nest_lock(lock)}
|
|
|
963 @item @tab @code{integer(omp_nest_lock_kind), intent(out) :: lock}
|
|
|
964 @end multitable
|
|
|
965
|
|
|
966 @item @emph{See also}:
|
|
|
967 @ref{omp_set_nest_lock}
|
|
|
968
|
|
|
969 @item @emph{Reference}:
|
|
|
970 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.4.
|
|
|
971 @end table
|
|
|
972
|
|
|
973
|
|
|
974
|
|
|
975 @node omp_destroy_nest_lock
|
|
|
976 @section @code{omp_destroy_nest_lock} -- Destroy nested lock
|
|
|
977 @table @asis
|
|
|
978 @item @emph{Description}:
|
|
|
979 Destroy a nested lock. In order to be destroyed, a nested lock must be
|
|
|
980 in the unlocked state and its nesting count must equal zero.
|
|
|
981
|
|
|
982 @item @emph{C/C++}:
|
|
|
983 @multitable @columnfractions .20 .80
|
|
|
984 @item @emph{Prototype}: @tab @code{void omp_destroy_nest_lock(omp_nest_lock_t *);}
|
|
|
985 @end multitable
|
|
|
986
|
|
|
987 @item @emph{Fortran}:
|
|
|
988 @multitable @columnfractions .20 .80
|
|
|
989 @item @emph{Interface}: @tab @code{subroutine omp_destroy_nest_lock(lock)}
|
|
|
990 @item @tab @code{integer(omp_nest_lock_kind), intent(inout) :: lock}
|
|
|
991 @end multitable
|
|
|
992
|
|
|
993 @item @emph{See also}:
|
|
|
994 @ref{omp_init_lock}
|
|
|
995
|
|
|
996 @item @emph{Reference}:
|
|
|
997 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.3.2.
|
|
|
998 @end table
|
|
|
999
|
|
|
1000
|
|
|
1001
|
|
|
1002 @node omp_get_wtick
|
|
|
1003 @section @code{omp_get_wtick} -- Get timer precision
|
|
|
1004 @table @asis
|
|
|
1005 @item @emph{Description}:
|
|
|
1006 Gets the timer precision, i.e., the number of seconds between two
|
|
|
1007 successive clock ticks.
|
|
|
1008
|
|
|
1009 @item @emph{C/C++}:
|
|
|
1010 @multitable @columnfractions .20 .80
|
|
|
1011 @item @emph{Prototype}: @tab @code{double omp_get_wtick();}
|
|
|
1012 @end multitable
|
|
|
1013
|
|
|
1014 @item @emph{Fortran}:
|
|
|
1015 @multitable @columnfractions .20 .80
|
|
|
1016 @item @emph{Interface}: @tab @code{double precision function omp_get_wtick()}
|
|
|
1017 @end multitable
|
|
|
1018
|
|
|
1019 @item @emph{See also}:
|
|
|
1020 @ref{omp_get_wtime}
|
|
|
1021
|
|
|
1022 @item @emph{Reference}:
|
|
|
1023 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.4.2.
|
|
|
1024 @end table
|
|
|
1025
|
|
|
1026
|
|
|
1027
|
|
|
1028 @node omp_get_wtime
|
|
|
1029 @section @code{omp_get_wtime} -- Elapsed wall clock time
|
|
|
1030 @table @asis
|
|
|
1031 @item @emph{Description}:
|
|
|
1032 Elapsed wall clock time in seconds. The time is measured per thread, no
|
|
|
1033 guarantee can bee made that two distinct threads measure the same time.
|
|
|
1034 Time is measured from some "time in the past". On POSIX compliant systems
|
|
|
1035 the seconds since the Epoch (00:00:00 UTC, January 1, 1970) are returned.
|
|
|
1036
|
|
|
1037 @item @emph{C/C++}:
|
|
|
1038 @multitable @columnfractions .20 .80
|
|
|
1039 @item @emph{Prototype}: @tab @code{double omp_get_wtime();}
|
|
|
1040 @end multitable
|
|
|
1041
|
|
|
1042 @item @emph{Fortran}:
|
|
|
1043 @multitable @columnfractions .20 .80
|
|
|
1044 @item @emph{Interface}: @tab @code{double precision function omp_get_wtime()}
|
|
|
1045 @end multitable
|
|
|
1046
|
|
|
1047 @item @emph{See also}:
|
|
|
1048 @ref{omp_get_wtick}
|
|
|
1049
|
|
|
1050 @item @emph{Reference}:
|
|
|
1051 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 3.4.1.
|
|
|
1052 @end table
|
|
|
1053
|
|
|
1054
|
|
|
1055
|
|
|
1056 @c ---------------------------------------------------------------------
|
|
|
1057 @c Environment Variables
|
|
|
1058 @c ---------------------------------------------------------------------
|
|
|
1059
|
|
|
1060 @node Environment Variables
|
|
|
1061 @chapter Environment Variables
|
|
|
1062
|
|
|
1063 The variables @env{OMP_DYNAMIC}, @env{OMP_MAX_ACTIVE_LEVELS},
|
|
|
1064 @env{OMP_NESTED}, @env{OMP_NUM_THREADS}, @env{OMP_SCHEDULE},
|
|
|
1065 @env{OMP_STACKSIZE},@env{OMP_THREAD_LIMIT} and @env{OMP_WAIT_POLICY}
|
|
|
1066 are defined by section 4 of the OpenMP specifications in version 3.0,
|
|
|
1067 while @env{GOMP_CPU_AFFINITY} and @env{GOMP_STACKSIZE} are GNU
|
|
|
1068 extensions.
|
|
|
1069
|
|
|
1070 @menu
|
|
|
1071 * OMP_DYNAMIC:: Dynamic adjustment of threads
|
|
|
1072 * OMP_MAX_ACTIVE_LEVELS:: Set the maximal number of nested parallel regions
|
|
|
1073 * OMP_NESTED:: Nested parallel regions
|
|
|
1074 * OMP_NUM_THREADS:: Specifies the number of threads to use
|
|
|
1075 * OMP_STACKSIZE:: Set default thread stack size
|
|
|
1076 * OMP_SCHEDULE:: How threads are scheduled
|
|
|
1077 * OMP_THREAD_LIMIT:: Set the maximal number of threads
|
|
|
1078 * OMP_WAIT_POLICY:: How waiting threads are handled
|
|
|
1079 * GOMP_CPU_AFFINITY:: Bind threads to specific CPUs
|
|
|
1080 * GOMP_STACKSIZE:: Set default thread stack size
|
|
|
1081 @end menu
|
|
|
1082
|
|
|
1083
|
|
|
1084 @node OMP_DYNAMIC
|
|
|
1085 @section @env{OMP_DYNAMIC} -- Dynamic adjustment of threads
|
|
|
1086 @cindex Environment Variable
|
|
|
1087 @table @asis
|
|
|
1088 @item @emph{Description}:
|
|
|
1089 Enable or disable the dynamic adjustment of the number of threads
|
|
|
1090 within a team. The value of this environment variable shall be
|
|
|
1091 @code{TRUE} or @code{FALSE}. If undefined, dynamic adjustment is
|
|
|
1092 disabled by default.
|
|
|
1093
|
|
|
1094 @item @emph{See also}:
|
|
|
1095 @ref{omp_set_dynamic}
|
|
|
1096
|
|
|
1097 @item @emph{Reference}:
|
|
|
1098 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 4.3
|
|
|
1099 @end table
|
|
|
1100
|
|
|
1101
|
|
|
1102
|
|
|
1103 @node OMP_MAX_ACTIVE_LEVELS
|
|
|
1104 @section @env{OMP_MAX_ACTIVE_LEVELS} -- Set the maximal number of nested parallel regions
|
|
|
1105 @cindex Environment Variable
|
|
|
1106 @table @asis
|
|
|
1107 @item @emph{Description}:
|
|
|
1108 Specifies the initial value for the maximal number of nested parallel
|
|
|
1109 regions. The value of this variable shall be positive integer.
|
|
|
1110 If undefined, the number of active levels is unlimited.
|
|
|
1111
|
|
|
1112 @item @emph{See also}:
|
|
|
1113 @ref{omp_set_max_active_levels}
|
|
|
1114
|
|
|
1115 @item @emph{Reference}:
|
|
|
1116 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 4.7
|
|
|
1117 @end table
|
|
|
1118
|
|
|
1119
|
|
|
1120
|
|
|
1121 @node OMP_NESTED
|
|
|
1122 @section @env{OMP_NESTED} -- Nested parallel regions
|
|
|
1123 @cindex Environment Variable
|
|
|
1124 @cindex Implementation specific setting
|
|
|
1125 @table @asis
|
|
|
1126 @item @emph{Description}:
|
|
|
1127 Enable or disable nested parallel regions, i.e., whether team members
|
|
|
1128 are allowed to create new teams. The value of this environment variable
|
|
|
1129 shall be @code{TRUE} or @code{FALSE}. If undefined, nested parallel
|
|
|
1130 regions are disabled by default.
|
|
|
1131
|
|
|
1132 @item @emph{See also}:
|
|
|
1133 @ref{omp_set_nested}
|
|
|
1134
|
|
|
1135 @item @emph{Reference}:
|
|
|
1136 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 4.4
|
|
|
1137 @end table
|
|
|
1138
|
|
|
1139
|
|
|
1140
|
|
|
1141 @node OMP_NUM_THREADS
|
|
|
1142 @section @env{OMP_NUM_THREADS} -- Specifies the number of threads to use
|
|
|
1143 @cindex Environment Variable
|
|
|
1144 @cindex Implementation specific setting
|
|
|
1145 @table @asis
|
|
|
1146 @item @emph{Description}:
|
|
|
1147 Specifies the default number of threads to use in parallel regions. The
|
|
|
1148 value of this variable shall be positive integer. If undefined one thread
|
|
|
1149 per CPU online is used.
|
|
|
1150
|
|
|
1151 @item @emph{See also}:
|
|
|
1152 @ref{omp_set_num_threads}
|
|
|
1153
|
|
|
1154 @item @emph{Reference}:
|
|
|
1155 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 4.2
|
|
|
1156 @end table
|
|
|
1157
|
|
|
1158
|
|
|
1159
|
|
|
1160 @node OMP_SCHEDULE
|
|
|
1161 @section @env{OMP_SCHEDULE} -- How threads are scheduled
|
|
|
1162 @cindex Environment Variable
|
|
|
1163 @cindex Implementation specific setting
|
|
|
1164 @table @asis
|
|
|
1165 @item @emph{Description}:
|
|
|
1166 Allows to specify @code{schedule type} and @code{chunk size}.
|
|
|
1167 The value of the variable shall have the form: @code{type[,chunk]} where
|
|
|
1168 @code{type} is one of @code{static}, @code{dynamic}, @code{guided} or @code{auto}
|
|
|
1169 The optional @code{chunk} size shall be a positive integer. If undefined,
|
|
|
1170 dynamic scheduling and a chunk size of 1 is used.
|
|
|
1171
|
|
|
1172 @item @emph{See also}:
|
|
|
1173 @ref{omp_set_schedule}
|
|
|
1174
|
|
|
1175 @item @emph{Reference}:
|
|
|
1176 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, sections 2.5.1 and 4.1
|
|
|
1177 @end table
|
|
|
1178
|
|
|
1179
|
|
|
1180
|
|
|
1181 @node OMP_STACKSIZE
|
|
|
1182 @section @env{OMP_STACKSIZE} -- Set default thread stack size
|
|
|
1183 @cindex Environment Variable
|
|
|
1184 @table @asis
|
|
|
1185 @item @emph{Description}:
|
|
|
1186 Set the default thread stack size in kilobytes, unless the number
|
|
|
1187 is suffixed by @code{B}, @code{K}, @code{M} or @code{G}, in which
|
|
|
1188 case the size is, respectively, in bytes, kilobytes, megabytes
|
|
|
1189 or gigabytes. This is different from @code{pthread_attr_setstacksize}
|
|
|
1190 which gets the number of bytes as an argument. If the stacksize can not
|
|
|
1191 be set due to system constraints, an error is reported and the initial
|
|
|
1192 stacksize is left unchanged. If undefined, the stack size is system
|
|
|
1193 dependent.
|
|
|
1194
|
|
|
1195 @item @emph{Reference}:
|
|
|
1196 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, sections 4.5
|
|
|
1197 @end table
|
|
|
1198
|
|
|
1199
|
|
|
1200
|
|
|
1201 @node OMP_THREAD_LIMIT
|
|
|
1202 @section @env{OMP_THREAD_LIMIT} -- Set the maximal number of threads
|
|
|
1203 @cindex Environment Variable
|
|
|
1204 @table @asis
|
|
|
1205 @item @emph{Description}:
|
|
|
1206 Specifies the number of threads to use for the whole program. The
|
|
|
1207 value of this variable shall be positive integer. If undefined,
|
|
|
1208 the number of threads is not limited.
|
|
|
1209
|
|
|
1210 @item @emph{See also}:
|
|
|
1211 @ref{OMP_NUM_THREADS}
|
|
|
1212 @ref{omp_get_thread_limit}
|
|
|
1213
|
|
|
1214 @item @emph{Reference}:
|
|
|
1215 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, section 4.8
|
|
|
1216 @end table
|
|
|
1217
|
|
|
1218
|
|
|
1219
|
|
|
1220 @node OMP_WAIT_POLICY
|
|
|
1221 @section @env{OMP_WAIT_POLICY} -- How waiting threads are handled
|
|
|
1222 @cindex Environment Variable
|
|
|
1223 @table @asis
|
|
|
1224 @item @emph{Description}:
|
|
|
1225 Specifies whether waiting threads should be active or passive. If
|
|
|
1226 the value is @code{PASSIVE}, waiting threads should not consume CPU
|
|
|
1227 power while waiting; while the value is @code{ACTIVE} specifies that
|
|
|
1228 they should.
|
|
|
1229
|
|
|
1230 @item @emph{Reference}:
|
|
|
1231 @uref{http://www.openmp.org/, OpenMP specifications v3.0}, sections 4.6
|
|
|
1232 @end table
|
|
|
1233
|
|
|
1234
|
|
|
1235
|
|
|
1236 @node GOMP_CPU_AFFINITY
|
|
|
1237 @section @env{GOMP_CPU_AFFINITY} -- Bind threads to specific CPUs
|
|
|
1238 @cindex Environment Variable
|
|
|
1239 @table @asis
|
|
|
1240 @item @emph{Description}:
|
|
|
1241 Binds threads to specific CPUs. The variable should contain a space- or
|
|
|
1242 comma-separated list of CPUs. This list may contain different kind of
|
|
|
1243 entries: either single CPU numbers in any order, a range of CPUs (M-N)
|
|
|
1244 or a range with some stride (M-N:S). CPU numbers are zero based. For example,
|
|
|
1245 @code{GOMP_CPU_AFFINITY="0 3 1-2 4-15:2"} will bind the initial thread
|
|
|
1246 to CPU 0, the second to CPU 3, the third to CPU 1, the fourth to
|
|
|
1247 CPU 2, the fifth to CPU 4, the sixth through tenth to CPUs 6, 8, 10, 12,
|
|
|
1248 and 14 respectively and then start assigning back from the beginning of
|
|
|
1249 the list. @code{GOMP_CPU_AFFINITY=0} binds all threads to CPU 0.
|
|
|
1250
|
|
|
1251 There is no GNU OpenMP library routine to determine whether a CPU affinity
|
|
|
1252 specification is in effect. As a workaround, language-specific library
|
|
|
1253 functions, e.g., @code{getenv} in C or @code{GET_ENVIRONMENT_VARIABLE} in
|
|
|
1254 Fortran, may be used to query the setting of the @code{GOMP_CPU_AFFINITY}
|
|
|
1255 environment variable. A defined CPU affinity on startup cannot be changed
|
|
|
1256 or disabled during the runtime of the application.
|
|
|
1257
|
|
|
1258 If this environment variable is omitted, the host system will handle the
|
|
|
1259 assignment of threads to CPUs.
|
|
|
1260 @end table
|
|
|
1261
|
|
|
1262
|
|
|
1263
|
|
|
1264 @node GOMP_STACKSIZE
|
|
|
1265 @section @env{GOMP_STACKSIZE} -- Set default thread stack size
|
|
|
1266 @cindex Environment Variable
|
|
|
1267 @cindex Implementation specific setting
|
|
|
1268 @table @asis
|
|
|
1269 @item @emph{Description}:
|
|
|
1270 Set the default thread stack size in kilobytes. This is different from
|
|
|
1271 @code{pthread_attr_setstacksize} which gets the number of bytes as an
|
|
|
1272 argument. If the stacksize can not be set due to system constraints, an
|
|
|
1273 error is reported and the initial stacksize is left unchanged. If undefined,
|
|
|
1274 the stack size is system dependent.
|
|
|
1275
|
|
|
1276 @item @emph{See also}:
|
|
|
1277 @ref{GOMP_STACKSIZE}
|
|
|
1278
|
|
|
1279 @item @emph{Reference}:
|
|
|
1280 @uref{http://gcc.gnu.org/ml/gcc-patches/2006-06/msg00493.html,
|
|
|
1281 GCC Patches Mailinglist},
|
|
|
1282 @uref{http://gcc.gnu.org/ml/gcc-patches/2006-06/msg00496.html,
|
|
|
1283 GCC Patches Mailinglist}
|
|
|
1284 @end table
|
|
|
1285
|
|
|
1286
|
|
|
1287
|
|
|
1288 @c ---------------------------------------------------------------------
|
|
|
1289 @c The libgomp ABI
|
|
|
1290 @c ---------------------------------------------------------------------
|
|
|
1291
|
|
|
1292 @node The libgomp ABI
|
|
|
1293 @chapter The libgomp ABI
|
|
|
1294
|
|
|
1295 The following sections present notes on the external ABI as
|
|
|
1296 presented by libgomp. Only maintainers should need them.
|
|
|
1297
|
|
|
1298 @menu
|
|
|
1299 * Implementing MASTER construct::
|
|
|
1300 * Implementing CRITICAL construct::
|
|
|
1301 * Implementing ATOMIC construct::
|
|
|
1302 * Implementing FLUSH construct::
|
|
|
1303 * Implementing BARRIER construct::
|
|
|
1304 * Implementing THREADPRIVATE construct::
|
|
|
1305 * Implementing PRIVATE clause::
|
|
|
1306 * Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses::
|
|
|
1307 * Implementing REDUCTION clause::
|
|
|
1308 * Implementing PARALLEL construct::
|
|
|
1309 * Implementing FOR construct::
|
|
|
1310 * Implementing ORDERED construct::
|
|
|
1311 * Implementing SECTIONS construct::
|
|
|
1312 * Implementing SINGLE construct::
|
|
|
1313 @end menu
|
|
|
1314
|
|
|
1315
|
|
|
1316 @node Implementing MASTER construct
|
|
|
1317 @section Implementing MASTER construct
|
|
|
1318
|
|
|
1319 @smallexample
|
|
|
1320 if (omp_get_thread_num () == 0)
|
|
|
1321 block
|
|
|
1322 @end smallexample
|
|
|
1323
|
|
|
1324 Alternately, we generate two copies of the parallel subfunction
|
|
|
1325 and only include this in the version run by the master thread.
|
|
|
1326 Surely that's not worthwhile though...
|
|
|
1327
|
|
|
1328
|
|
|
1329
|
|
|
1330 @node Implementing CRITICAL construct
|
|
|
1331 @section Implementing CRITICAL construct
|
|
|
1332
|
|
|
1333 Without a specified name,
|
|
|
1334
|
|
|
1335 @smallexample
|
|
|
1336 void GOMP_critical_start (void);
|
|
|
1337 void GOMP_critical_end (void);
|
|
|
1338 @end smallexample
|
|
|
1339
|
|
|
1340 so that we don't get COPY relocations from libgomp to the main
|
|
|
1341 application.
|
|
|
1342
|
|
|
1343 With a specified name, use omp_set_lock and omp_unset_lock with
|
|
|
1344 name being transformed into a variable declared like
|
|
|
1345
|
|
|
1346 @smallexample
|
|
|
1347 omp_lock_t gomp_critical_user_<name> __attribute__((common))
|
|
|
1348 @end smallexample
|
|
|
1349
|
|
|
1350 Ideally the ABI would specify that all zero is a valid unlocked
|
|
|
1351 state, and so we wouldn't actually need to initialize this at
|
|
|
1352 startup.
|
|
|
1353
|
|
|
1354
|
|
|
1355
|
|
|
1356 @node Implementing ATOMIC construct
|
|
|
1357 @section Implementing ATOMIC construct
|
|
|
1358
|
|
|
1359 The target should implement the @code{__sync} builtins.
|
|
|
1360
|
|
|
1361 Failing that we could add
|
|
|
1362
|
|
|
1363 @smallexample
|
|
|
1364 void GOMP_atomic_enter (void)
|
|
|
1365 void GOMP_atomic_exit (void)
|
|
|
1366 @end smallexample
|
|
|
1367
|
|
|
1368 which reuses the regular lock code, but with yet another lock
|
|
|
1369 object private to the library.
|
|
|
1370
|
|
|
1371
|
|
|
1372
|
|
|
1373 @node Implementing FLUSH construct
|
|
|
1374 @section Implementing FLUSH construct
|
|
|
1375
|
|
|
1376 Expands to the @code{__sync_synchronize} builtin.
|
|
|
1377
|
|
|
1378
|
|
|
1379
|
|
|
1380 @node Implementing BARRIER construct
|
|
|
1381 @section Implementing BARRIER construct
|
|
|
1382
|
|
|
1383 @smallexample
|
|
|
1384 void GOMP_barrier (void)
|
|
|
1385 @end smallexample
|
|
|
1386
|
|
|
1387
|
|
|
1388 @node Implementing THREADPRIVATE construct
|
|
|
1389 @section Implementing THREADPRIVATE construct
|
|
|
1390
|
|
|
1391 In _most_ cases we can map this directly to @code{__thread}. Except
|
|
|
1392 that OMP allows constructors for C++ objects. We can either
|
|
|
1393 refuse to support this (how often is it used?) or we can
|
|
|
1394 implement something akin to .ctors.
|
|
|
1395
|
|
|
1396 Even more ideally, this ctor feature is handled by extensions
|
|
|
1397 to the main pthreads library. Failing that, we can have a set
|
|
|
1398 of entry points to register ctor functions to be called.
|
|
|
1399
|
|
|
1400
|
|
|
1401
|
|
|
1402 @node Implementing PRIVATE clause
|
|
|
1403 @section Implementing PRIVATE clause
|
|
|
1404
|
|
|
1405 In association with a PARALLEL, or within the lexical extent
|
|
|
1406 of a PARALLEL block, the variable becomes a local variable in
|
|
|
1407 the parallel subfunction.
|
|
|
1408
|
|
|
1409 In association with FOR or SECTIONS blocks, create a new
|
|
|
1410 automatic variable within the current function. This preserves
|
|
|
1411 the semantic of new variable creation.
|
|
|
1412
|
|
|
1413
|
|
|
1414
|
|
|
1415 @node Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses
|
|
|
1416 @section Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses
|
|
|
1417
|
|
|
1418 Seems simple enough for PARALLEL blocks. Create a private
|
|
|
1419 struct for communicating between parent and subfunction.
|
|
|
1420 In the parent, copy in values for scalar and "small" structs;
|
|
|
1421 copy in addresses for others TREE_ADDRESSABLE types. In the
|
|
|
1422 subfunction, copy the value into the local variable.
|
|
|
1423
|
|
|
1424 Not clear at all what to do with bare FOR or SECTION blocks.
|
|
|
1425 The only thing I can figure is that we do something like
|
|
|
1426
|
|
|
1427 @smallexample
|
|
|
1428 #pragma omp for firstprivate(x) lastprivate(y)
|
|
|
1429 for (int i = 0; i < n; ++i)
|
|
|
1430 body;
|
|
|
1431 @end smallexample
|
|
|
1432
|
|
|
1433 which becomes
|
|
|
1434
|
|
|
1435 @smallexample
|
|
|
1436 @{
|
|
|
1437 int x = x, y;
|
|
|
1438
|
|
|
1439 // for stuff
|
|
|
1440
|
|
|
1441 if (i == n)
|
|
|
1442 y = y;
|
|
|
1443 @}
|
|
|
1444 @end smallexample
|
|
|
1445
|
|
|
1446 where the "x=x" and "y=y" assignments actually have different
|
|
|
1447 uids for the two variables, i.e. not something you could write
|
|
|
1448 directly in C. Presumably this only makes sense if the "outer"
|
|
|
1449 x and y are global variables.
|
|
|
1450
|
|
|
1451 COPYPRIVATE would work the same way, except the structure
|
|
|
1452 broadcast would have to happen via SINGLE machinery instead.
|
|
|
1453
|
|
|
1454
|
|
|
1455
|
|
|
1456 @node Implementing REDUCTION clause
|
|
|
1457 @section Implementing REDUCTION clause
|
|
|
1458
|
|
|
1459 The private struct mentioned in the previous section should have
|
|
|
1460 a pointer to an array of the type of the variable, indexed by the
|
|
|
1461 thread's @var{team_id}. The thread stores its final value into the
|
|
|
1462 array, and after the barrier the master thread iterates over the
|
|
|
1463 array to collect the values.
|
|
|
1464
|
|
|
1465
|
|
|
1466 @node Implementing PARALLEL construct
|
|
|
1467 @section Implementing PARALLEL construct
|
|
|
1468
|
|
|
1469 @smallexample
|
|
|
1470 #pragma omp parallel
|
|
|
1471 @{
|
|
|
1472 body;
|
|
|
1473 @}
|
|
|
1474 @end smallexample
|
|
|
1475
|
|
|
1476 becomes
|
|
|
1477
|
|
|
1478 @smallexample
|
|
|
1479 void subfunction (void *data)
|
|
|
1480 @{
|
|
|
1481 use data;
|
|
|
1482 body;
|
|
|
1483 @}
|
|
|
1484
|
|
|
1485 setup data;
|
|
|
1486 GOMP_parallel_start (subfunction, &data, num_threads);
|
|
|
1487 subfunction (&data);
|
|
|
1488 GOMP_parallel_end ();
|
|
|
1489 @end smallexample
|
|
|
1490
|
|
|
1491 @smallexample
|
|
|
1492 void GOMP_parallel_start (void (*fn)(void *), void *data, unsigned num_threads)
|
|
|
1493 @end smallexample
|
|
|
1494
|
|
|
1495 The @var{FN} argument is the subfunction to be run in parallel.
|
|
|
1496
|
|
|
1497 The @var{DATA} argument is a pointer to a structure used to
|
|
|
1498 communicate data in and out of the subfunction, as discussed
|
|
|
1499 above with respect to FIRSTPRIVATE et al.
|
|
|
1500
|
|
|
1501 The @var{NUM_THREADS} argument is 1 if an IF clause is present
|
|
|
1502 and false, or the value of the NUM_THREADS clause, if
|
|
|
1503 present, or 0.
|
|
|
1504
|
|
|
1505 The function needs to create the appropriate number of
|
|
|
1506 threads and/or launch them from the dock. It needs to
|
|
|
1507 create the team structure and assign team ids.
|
|
|
1508
|
|
|
1509 @smallexample
|
|
|
1510 void GOMP_parallel_end (void)
|
|
|
1511 @end smallexample
|
|
|
1512
|
|
|
1513 Tears down the team and returns us to the previous @code{omp_in_parallel()} state.
|
|
|
1514
|
|
|
1515
|
|
|
1516
|
|
|
1517 @node Implementing FOR construct
|
|
|
1518 @section Implementing FOR construct
|
|
|
1519
|
|
|
1520 @smallexample
|
|
|
1521 #pragma omp parallel for
|
|
|
1522 for (i = lb; i <= ub; i++)
|
|
|
1523 body;
|
|
|
1524 @end smallexample
|
|
|
1525
|
|
|
1526 becomes
|
|
|
1527
|
|
|
1528 @smallexample
|
|
|
1529 void subfunction (void *data)
|
|
|
1530 @{
|
|
|
1531 long _s0, _e0;
|
|
|
1532 while (GOMP_loop_static_next (&_s0, &_e0))
|
|
|
1533 @{
|
|
|
1534 long _e1 = _e0, i;
|
|
|
1535 for (i = _s0; i < _e1; i++)
|
|
|
1536 body;
|
|
|
1537 @}
|
|
|
1538 GOMP_loop_end_nowait ();
|
|
|
1539 @}
|
|
|
1540
|
|
|
1541 GOMP_parallel_loop_static (subfunction, NULL, 0, lb, ub+1, 1, 0);
|
|
|
1542 subfunction (NULL);
|
|
|
1543 GOMP_parallel_end ();
|
|
|
1544 @end smallexample
|
|
|
1545
|
|
|
1546 @smallexample
|
|
|
1547 #pragma omp for schedule(runtime)
|
|
|
1548 for (i = 0; i < n; i++)
|
|
|
1549 body;
|
|
|
1550 @end smallexample
|
|
|
1551
|
|
|
1552 becomes
|
|
|
1553
|
|
|
1554 @smallexample
|
|
|
1555 @{
|
|
|
1556 long i, _s0, _e0;
|
|
|
1557 if (GOMP_loop_runtime_start (0, n, 1, &_s0, &_e0))
|
|
|
1558 do @{
|
|
|
1559 long _e1 = _e0;
|
|
|
1560 for (i = _s0, i < _e0; i++)
|
|
|
1561 body;
|
|
|
1562 @} while (GOMP_loop_runtime_next (&_s0, _&e0));
|
|
|
1563 GOMP_loop_end ();
|
|
|
1564 @}
|
|
|
1565 @end smallexample
|
|
|
1566
|
|
|
1567 Note that while it looks like there is trickyness to propagating
|
|
|
1568 a non-constant STEP, there isn't really. We're explicitly allowed
|
|
|
1569 to evaluate it as many times as we want, and any variables involved
|
|
|
1570 should automatically be handled as PRIVATE or SHARED like any other
|
|
|
1571 variables. So the expression should remain evaluable in the
|
|
|
1572 subfunction. We can also pull it into a local variable if we like,
|
|
|
1573 but since its supposed to remain unchanged, we can also not if we like.
|
|
|
1574
|
|
|
1575 If we have SCHEDULE(STATIC), and no ORDERED, then we ought to be
|
|
|
1576 able to get away with no work-sharing context at all, since we can
|
|
|
1577 simply perform the arithmetic directly in each thread to divide up
|
|
|
1578 the iterations. Which would mean that we wouldn't need to call any
|
|
|
1579 of these routines.
|
|
|
1580
|
|
|
1581 There are separate routines for handling loops with an ORDERED
|
|
|
1582 clause. Bookkeeping for that is non-trivial...
|
|
|
1583
|
|
|
1584
|
|
|
1585
|
|
|
1586 @node Implementing ORDERED construct
|
|
|
1587 @section Implementing ORDERED construct
|
|
|
1588
|
|
|
1589 @smallexample
|
|
|
1590 void GOMP_ordered_start (void)
|
|
|
1591 void GOMP_ordered_end (void)
|
|
|
1592 @end smallexample
|
|
|
1593
|
|
|
1594
|
|
|
1595
|
|
|
1596 @node Implementing SECTIONS construct
|
|
|
1597 @section Implementing SECTIONS construct
|
|
|
1598
|
|
|
1599 A block as
|
|
|
1600
|
|
|
1601 @smallexample
|
|
|
1602 #pragma omp sections
|
|
|
1603 @{
|
|
|
1604 #pragma omp section
|
|
|
1605 stmt1;
|
|
|
1606 #pragma omp section
|
|
|
1607 stmt2;
|
|
|
1608 #pragma omp section
|
|
|
1609 stmt3;
|
|
|
1610 @}
|
|
|
1611 @end smallexample
|
|
|
1612
|
|
|
1613 becomes
|
|
|
1614
|
|
|
1615 @smallexample
|
|
|
1616 for (i = GOMP_sections_start (3); i != 0; i = GOMP_sections_next ())
|
|
|
1617 switch (i)
|
|
|
1618 @{
|
|
|
1619 case 1:
|
|
|
1620 stmt1;
|
|
|
1621 break;
|
|
|
1622 case 2:
|
|
|
1623 stmt2;
|
|
|
1624 break;
|
|
|
1625 case 3:
|
|
|
1626 stmt3;
|
|
|
1627 break;
|
|
|
1628 @}
|
|
|
1629 GOMP_barrier ();
|
|
|
1630 @end smallexample
|
|
|
1631
|
|
|
1632
|
|
|
1633 @node Implementing SINGLE construct
|
|
|
1634 @section Implementing SINGLE construct
|
|
|
1635
|
|
|
1636 A block like
|
|
|
1637
|
|
|
1638 @smallexample
|
|
|
1639 #pragma omp single
|
|
|
1640 @{
|
|
|
1641 body;
|
|
|
1642 @}
|
|
|
1643 @end smallexample
|
|
|
1644
|
|
|
1645 becomes
|
|
|
1646
|
|
|
1647 @smallexample
|
|
|
1648 if (GOMP_single_start ())
|
|
|
1649 body;
|
|
|
1650 GOMP_barrier ();
|
|
|
1651 @end smallexample
|
|
|
1652
|
|
|
1653 while
|
|
|
1654
|
|
|
1655 @smallexample
|
|
|
1656 #pragma omp single copyprivate(x)
|
|
|
1657 body;
|
|
|
1658 @end smallexample
|
|
|
1659
|
|
|
1660 becomes
|
|
|
1661
|
|
|
1662 @smallexample
|
|
|
1663 datap = GOMP_single_copy_start ();
|
|
|
1664 if (datap == NULL)
|
|
|
1665 @{
|
|
|
1666 body;
|
|
|
1667 data.x = x;
|
|
|
1668 GOMP_single_copy_end (&data);
|
|
|
1669 @}
|
|
|
1670 else
|
|
|
1671 x = datap->x;
|
|
|
1672 GOMP_barrier ();
|
|
|
1673 @end smallexample
|
|
|
1674
|
|
|
1675
|
|
|
1676
|
|
|
1677 @c ---------------------------------------------------------------------
|
|
|
1678 @c
|
|
|
1679 @c ---------------------------------------------------------------------
|
|
|
1680
|
|
|
1681 @node Reporting Bugs
|
|
|
1682 @chapter Reporting Bugs
|
|
|
1683
|
|
|
1684 Bugs in the GNU OpenMP implementation should be reported via
|
|
|
1685 @uref{http://gcc.gnu.org/bugzilla/, bugzilla}. In all cases, please add
|
|
|
1686 "openmp" to the keywords field in the bug report.
|
|
|
1687
|
|
|
1688
|
|
|
1689
|
|
|
1690 @c ---------------------------------------------------------------------
|
|
|
1691 @c GNU General Public License
|
|
|
1692 @c ---------------------------------------------------------------------
|
|
|
1693
|
|
|
1694 @include gpl.texi
|
|
|
1695
|
|
|
1696
|
|
|
1697
|
|
|
1698 @c ---------------------------------------------------------------------
|
|
|
1699 @c GNU Free Documentation License
|
|
|
1700 @c ---------------------------------------------------------------------
|
|
|
1701
|
|
|
1702 @include fdl.texi
|
|
|
1703
|
|
|
1704
|
|
|
1705
|
|
|
1706 @c ---------------------------------------------------------------------
|
|
|
1707 @c Funding Free Software
|
|
|
1708 @c ---------------------------------------------------------------------
|
|
|
1709
|
|
|
1710 @include funding.texi
|
|
|
1711
|
|
|
1712 @c ---------------------------------------------------------------------
|
|
|
1713 @c Index
|
|
|
1714 @c ---------------------------------------------------------------------
|
|
|
1715
|
|
|
1716 @node Index
|
|
|
1717 @unnumbered Index
|
|
|
1718
|
|
|
1719 @printindex cp
|
|
|
1720
|
|
|
1721 @bye
|
