libgomp.info revision 1.1.1.2 1 1.1 mrg This is libgomp.info, produced by makeinfo version 4.12 from
2 1.1.1.2 mrg /space/rguenther/gcc-4.8.5/gcc-4.8.5/libgomp/libgomp.texi.
3 1.1 mrg
4 1.1.1.2 mrg Copyright (C) 2006-2013 Free Software Foundation, Inc.
5 1.1 mrg
6 1.1 mrg Permission is granted to copy, distribute and/or modify this document
7 1.1.1.2 mrg under the terms of the GNU Free Documentation License, Version 1.3 or
8 1.1 mrg any later version published by the Free Software Foundation; with the
9 1.1 mrg Invariant Sections being "Funding Free Software", the Front-Cover texts
10 1.1 mrg being (a) (see below), and with the Back-Cover Texts being (b) (see
11 1.1 mrg below). A copy of the license is included in the section entitled "GNU
12 1.1 mrg Free Documentation License".
13 1.1 mrg
14 1.1 mrg (a) The FSF's Front-Cover Text is:
15 1.1 mrg
16 1.1 mrg A GNU Manual
17 1.1 mrg
18 1.1 mrg (b) The FSF's Back-Cover Text is:
19 1.1 mrg
20 1.1 mrg You have freedom to copy and modify this GNU Manual, like GNU
21 1.1 mrg software. Copies published by the Free Software Foundation raise
22 1.1 mrg funds for GNU development.
23 1.1 mrg
24 1.1 mrg INFO-DIR-SECTION GNU Libraries
25 1.1 mrg START-INFO-DIR-ENTRY
26 1.1 mrg * libgomp: (libgomp). GNU OpenMP runtime library
27 1.1 mrg END-INFO-DIR-ENTRY
28 1.1 mrg
29 1.1 mrg This manual documents the GNU implementation of the OpenMP API for
30 1.1 mrg multi-platform shared-memory parallel programming in C/C++ and Fortran.
31 1.1 mrg
32 1.1 mrg Published by the Free Software Foundation 51 Franklin Street, Fifth
33 1.1 mrg Floor Boston, MA 02110-1301 USA
34 1.1 mrg
35 1.1.1.2 mrg Copyright (C) 2006-2013 Free Software Foundation, Inc.
36 1.1 mrg
37 1.1 mrg Permission is granted to copy, distribute and/or modify this document
38 1.1.1.2 mrg under the terms of the GNU Free Documentation License, Version 1.3 or
39 1.1 mrg any later version published by the Free Software Foundation; with the
40 1.1 mrg Invariant Sections being "Funding Free Software", the Front-Cover texts
41 1.1 mrg being (a) (see below), and with the Back-Cover Texts being (b) (see
42 1.1 mrg below). A copy of the license is included in the section entitled "GNU
43 1.1 mrg Free Documentation License".
44 1.1 mrg
45 1.1 mrg (a) The FSF's Front-Cover Text is:
46 1.1 mrg
47 1.1 mrg A GNU Manual
48 1.1 mrg
49 1.1 mrg (b) The FSF's Back-Cover Text is:
50 1.1 mrg
51 1.1 mrg You have freedom to copy and modify this GNU Manual, like GNU
52 1.1 mrg software. Copies published by the Free Software Foundation raise
53 1.1 mrg funds for GNU development.
54 1.1 mrg
55 1.1 mrg
56 1.1 mrg File: libgomp.info, Node: Top, Next: Enabling OpenMP, Up: (dir)
57 1.1 mrg
58 1.1 mrg Introduction
59 1.1 mrg ************
60 1.1 mrg
61 1.1 mrg This manual documents the usage of libgomp, the GNU implementation of
62 1.1 mrg the OpenMP (http://www.openmp.org) Application Programming Interface
63 1.1 mrg (API) for multi-platform shared-memory parallel programming in C/C++
64 1.1 mrg and Fortran.
65 1.1 mrg
66 1.1 mrg * Menu:
67 1.1 mrg
68 1.1 mrg * Enabling OpenMP:: How to enable OpenMP for your applications.
69 1.1 mrg * Runtime Library Routines:: The OpenMP runtime application programming
70 1.1 mrg interface.
71 1.1 mrg * Environment Variables:: Influencing runtime behavior with environment
72 1.1 mrg variables.
73 1.1 mrg * The libgomp ABI:: Notes on the external ABI presented by libgomp.
74 1.1 mrg * Reporting Bugs:: How to report bugs in GNU OpenMP.
75 1.1 mrg * Copying:: GNU general public license says
76 1.1 mrg how you can copy and share libgomp.
77 1.1 mrg * GNU Free Documentation License::
78 1.1 mrg How you can copy and share this manual.
79 1.1 mrg * Funding:: How to help assure continued work for free
80 1.1 mrg software.
81 1.1.1.2 mrg * Library Index:: Index of this documentation.
82 1.1 mrg
83 1.1 mrg
84 1.1 mrg File: libgomp.info, Node: Enabling OpenMP, Next: Runtime Library Routines, Prev: Top, Up: Top
85 1.1 mrg
86 1.1 mrg 1 Enabling OpenMP
87 1.1 mrg *****************
88 1.1 mrg
89 1.1 mrg To activate the OpenMP extensions for C/C++ and Fortran, the
90 1.1 mrg compile-time flag `-fopenmp' must be specified. This enables the OpenMP
91 1.1 mrg directive `#pragma omp' in C/C++ and `!$omp' directives in free form,
92 1.1 mrg `c$omp', `*$omp' and `!$omp' directives in fixed form, `!$' conditional
93 1.1 mrg compilation sentinels in free form and `c$', `*$' and `!$' sentinels in
94 1.1 mrg fixed form, for Fortran. The flag also arranges for automatic linking
95 1.1 mrg of the OpenMP runtime library (*note Runtime Library Routines::).
96 1.1 mrg
97 1.1 mrg A complete description of all OpenMP directives accepted may be
98 1.1 mrg found in the OpenMP Application Program Interface
99 1.1.1.2 mrg (http://www.openmp.org) manual, version 3.1.
100 1.1 mrg
101 1.1 mrg
102 1.1 mrg File: libgomp.info, Node: Runtime Library Routines, Next: Environment Variables, Prev: Enabling OpenMP, Up: Top
103 1.1 mrg
104 1.1 mrg 2 Runtime Library Routines
105 1.1 mrg **************************
106 1.1 mrg
107 1.1 mrg The runtime routines described here are defined by section 3 of the
108 1.1.1.2 mrg OpenMP specifications in version 3.1. The routines are structured in
109 1.1 mrg following three parts:
110 1.1 mrg
111 1.1 mrg Control threads, processors and the parallel environment.
112 1.1 mrg
113 1.1 mrg * Menu:
114 1.1 mrg
115 1.1 mrg * omp_get_active_level:: Number of active parallel regions
116 1.1 mrg * omp_get_ancestor_thread_num:: Ancestor thread ID
117 1.1 mrg * omp_get_dynamic:: Dynamic teams setting
118 1.1 mrg * omp_get_level:: Number of parallel regions
119 1.1.1.2 mrg * omp_get_max_active_levels:: Maximum number of active regions
120 1.1.1.2 mrg * omp_get_max_threads:: Maximum number of threads of parallel region
121 1.1 mrg * omp_get_nested:: Nested parallel regions
122 1.1 mrg * omp_get_num_procs:: Number of processors online
123 1.1 mrg * omp_get_num_threads:: Size of the active team
124 1.1 mrg * omp_get_schedule:: Obtain the runtime scheduling method
125 1.1 mrg * omp_get_team_size:: Number of threads in a team
126 1.1.1.2 mrg * omp_get_thread_limit:: Maximum number of threads
127 1.1 mrg * omp_get_thread_num:: Current thread ID
128 1.1 mrg * omp_in_parallel:: Whether a parallel region is active
129 1.1.1.2 mrg * omp_in_final:: Whether in final or included task region
130 1.1 mrg * omp_set_dynamic:: Enable/disable dynamic teams
131 1.1 mrg * omp_set_max_active_levels:: Limits the number of active parallel regions
132 1.1 mrg * omp_set_nested:: Enable/disable nested parallel regions
133 1.1 mrg * omp_set_num_threads:: Set upper team size limit
134 1.1 mrg * omp_set_schedule:: Set the runtime scheduling method
135 1.1 mrg
136 1.1 mrg Initialize, set, test, unset and destroy simple and nested locks.
137 1.1 mrg
138 1.1 mrg * Menu:
139 1.1 mrg
140 1.1 mrg * omp_init_lock:: Initialize simple lock
141 1.1 mrg * omp_set_lock:: Wait for and set simple lock
142 1.1 mrg * omp_test_lock:: Test and set simple lock if available
143 1.1 mrg * omp_unset_lock:: Unset simple lock
144 1.1 mrg * omp_destroy_lock:: Destroy simple lock
145 1.1 mrg * omp_init_nest_lock:: Initialize nested lock
146 1.1 mrg * omp_set_nest_lock:: Wait for and set simple lock
147 1.1 mrg * omp_test_nest_lock:: Test and set nested lock if available
148 1.1 mrg * omp_unset_nest_lock:: Unset nested lock
149 1.1 mrg * omp_destroy_nest_lock:: Destroy nested lock
150 1.1 mrg
151 1.1 mrg Portable, thread-based, wall clock timer.
152 1.1 mrg
153 1.1 mrg * Menu:
154 1.1 mrg
155 1.1 mrg * omp_get_wtick:: Get timer precision.
156 1.1 mrg * omp_get_wtime:: Elapsed wall clock time.
157 1.1 mrg
158 1.1 mrg
159 1.1 mrg File: libgomp.info, Node: omp_get_active_level, Next: omp_get_ancestor_thread_num, Up: Runtime Library Routines
160 1.1 mrg
161 1.1 mrg 2.1 `omp_get_active_level' - Number of parallel regions
162 1.1 mrg =======================================================
163 1.1 mrg
164 1.1 mrg _Description_:
165 1.1 mrg This function returns the nesting level for the active parallel
166 1.1 mrg blocks, which enclose the calling call.
167 1.1 mrg
168 1.1 mrg _C/C++_
169 1.1.1.2 mrg _Prototype_: `int omp_get_active_level(void);'
170 1.1 mrg
171 1.1 mrg _Fortran_:
172 1.1.1.2 mrg _Interface_: `integer function omp_get_active_level()'
173 1.1 mrg
174 1.1 mrg _See also_:
175 1.1 mrg *note omp_get_level::, *note omp_get_max_active_levels::, *note
176 1.1 mrg omp_set_max_active_levels::
177 1.1 mrg
178 1.1 mrg _Reference_:
179 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
180 1.1 mrg 3.2.19.
181 1.1 mrg
182 1.1 mrg
183 1.1 mrg File: libgomp.info, Node: omp_get_ancestor_thread_num, Next: omp_get_dynamic, Prev: omp_get_active_level, Up: Runtime Library Routines
184 1.1 mrg
185 1.1 mrg 2.2 `omp_get_ancestor_thread_num' - Ancestor thread ID
186 1.1 mrg ======================================================
187 1.1 mrg
188 1.1 mrg _Description_:
189 1.1 mrg This function returns the thread identification number for the
190 1.1 mrg given nesting level of the current thread. For values of LEVEL
191 1.1 mrg outside zero to `omp_get_level' -1 is returned; if LEVEL is
192 1.1 mrg `omp_get_level' the result is identical to `omp_get_thread_num'.
193 1.1 mrg
194 1.1 mrg _C/C++_
195 1.1 mrg _Prototype_: `int omp_get_ancestor_thread_num(int level);'
196 1.1 mrg
197 1.1 mrg _Fortran_:
198 1.1.1.2 mrg _Interface_: `integer function omp_get_ancestor_thread_num(level)'
199 1.1 mrg `integer level'
200 1.1 mrg
201 1.1 mrg _See also_:
202 1.1 mrg *note omp_get_level::, *note omp_get_thread_num::, *note
203 1.1 mrg omp_get_team_size::
204 1.1 mrg
205 1.1 mrg _Reference_:
206 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
207 1.1 mrg 3.2.17.
208 1.1 mrg
209 1.1 mrg
210 1.1 mrg File: libgomp.info, Node: omp_get_dynamic, Next: omp_get_level, Prev: omp_get_ancestor_thread_num, Up: Runtime Library Routines
211 1.1 mrg
212 1.1 mrg 2.3 `omp_get_dynamic' - Dynamic teams setting
213 1.1 mrg =============================================
214 1.1 mrg
215 1.1 mrg _Description_:
216 1.1 mrg This function returns `true' if enabled, `false' otherwise. Here,
217 1.1 mrg `true' and `false' represent their language-specific counterparts.
218 1.1 mrg
219 1.1 mrg The dynamic team setting may be initialized at startup by the
220 1.1 mrg `OMP_DYNAMIC' environment variable or at runtime using
221 1.1 mrg `omp_set_dynamic'. If undefined, dynamic adjustment is disabled by
222 1.1 mrg default.
223 1.1 mrg
224 1.1 mrg _C/C++_:
225 1.1.1.2 mrg _Prototype_: `int omp_get_dynamic(void);'
226 1.1 mrg
227 1.1 mrg _Fortran_:
228 1.1 mrg _Interface_: `logical function omp_get_dynamic()'
229 1.1 mrg
230 1.1 mrg _See also_:
231 1.1 mrg *note omp_set_dynamic::, *note OMP_DYNAMIC::
232 1.1 mrg
233 1.1 mrg _Reference_:
234 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.8.
235 1.1 mrg
236 1.1 mrg
237 1.1 mrg File: libgomp.info, Node: omp_get_level, Next: omp_get_max_active_levels, Prev: omp_get_dynamic, Up: Runtime Library Routines
238 1.1 mrg
239 1.1 mrg 2.4 `omp_get_level' - Obtain the current nesting level
240 1.1 mrg ======================================================
241 1.1 mrg
242 1.1 mrg _Description_:
243 1.1 mrg This function returns the nesting level for the parallel blocks,
244 1.1 mrg which enclose the calling call.
245 1.1 mrg
246 1.1 mrg _C/C++_
247 1.1.1.2 mrg _Prototype_: `int omp_get_level(void);'
248 1.1 mrg
249 1.1 mrg _Fortran_:
250 1.1.1.2 mrg _Interface_: `integer function omp_level()'
251 1.1 mrg
252 1.1 mrg _See also_:
253 1.1 mrg *note omp_get_active_level::
254 1.1 mrg
255 1.1 mrg _Reference_:
256 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
257 1.1 mrg 3.2.16.
258 1.1 mrg
259 1.1 mrg
260 1.1 mrg File: libgomp.info, Node: omp_get_max_active_levels, Next: omp_get_max_threads, Prev: omp_get_level, Up: Runtime Library Routines
261 1.1 mrg
262 1.1.1.2 mrg 2.5 `omp_get_max_active_levels' - Maximum number of active regions
263 1.1 mrg ==================================================================
264 1.1 mrg
265 1.1 mrg _Description_:
266 1.1.1.2 mrg This function obtains the maximum allowed number of nested, active
267 1.1.1.2 mrg parallel regions.
268 1.1 mrg
269 1.1 mrg _C/C++_
270 1.1.1.2 mrg _Prototype_: `int omp_get_max_active_levels(void);'
271 1.1 mrg
272 1.1 mrg _Fortran_:
273 1.1.1.2 mrg _Interface_: `integer function omp_get_max_active_levels()'
274 1.1 mrg
275 1.1 mrg _See also_:
276 1.1 mrg *note omp_set_max_active_levels::, *note omp_get_active_level::
277 1.1 mrg
278 1.1 mrg _Reference_:
279 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
280 1.1.1.2 mrg 3.2.15.
281 1.1 mrg
282 1.1 mrg
283 1.1 mrg File: libgomp.info, Node: omp_get_max_threads, Next: omp_get_nested, Prev: omp_get_max_active_levels, Up: Runtime Library Routines
284 1.1 mrg
285 1.1.1.2 mrg 2.6 `omp_get_max_threads' - Maximum number of threads of parallel region
286 1.1 mrg ========================================================================
287 1.1 mrg
288 1.1 mrg _Description_:
289 1.1.1.2 mrg Return the maximum number of threads used for the current parallel
290 1.1 mrg region that does not use the clause `num_threads'.
291 1.1 mrg
292 1.1 mrg _C/C++_:
293 1.1.1.2 mrg _Prototype_: `int omp_get_max_threads(void);'
294 1.1 mrg
295 1.1 mrg _Fortran_:
296 1.1 mrg _Interface_: `integer function omp_get_max_threads()'
297 1.1 mrg
298 1.1 mrg _See also_:
299 1.1 mrg *note omp_set_num_threads::, *note omp_set_dynamic::, *note
300 1.1 mrg omp_get_thread_limit::
301 1.1 mrg
302 1.1 mrg _Reference_:
303 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.3.
304 1.1 mrg
305 1.1 mrg
306 1.1 mrg File: libgomp.info, Node: omp_get_nested, Next: omp_get_num_procs, Prev: omp_get_max_threads, Up: Runtime Library Routines
307 1.1 mrg
308 1.1 mrg 2.7 `omp_get_nested' - Nested parallel regions
309 1.1 mrg ==============================================
310 1.1 mrg
311 1.1 mrg _Description_:
312 1.1 mrg This function returns `true' if nested parallel regions are
313 1.1 mrg enabled, `false' otherwise. Here, `true' and `false' represent
314 1.1 mrg their language-specific counterparts.
315 1.1 mrg
316 1.1 mrg Nested parallel regions may be initialized at startup by the
317 1.1 mrg `OMP_NESTED' environment variable or at runtime using
318 1.1 mrg `omp_set_nested'. If undefined, nested parallel regions are
319 1.1 mrg disabled by default.
320 1.1 mrg
321 1.1 mrg _C/C++_:
322 1.1.1.2 mrg _Prototype_: `int omp_get_nested(void);'
323 1.1 mrg
324 1.1 mrg _Fortran_:
325 1.1.1.2 mrg _Interface_: `logical function omp_get_nested()'
326 1.1 mrg
327 1.1 mrg _See also_:
328 1.1 mrg *note omp_set_nested::, *note OMP_NESTED::
329 1.1 mrg
330 1.1 mrg _Reference_:
331 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
332 1.1 mrg 3.2.10.
333 1.1 mrg
334 1.1 mrg
335 1.1 mrg File: libgomp.info, Node: omp_get_num_procs, Next: omp_get_num_threads, Prev: omp_get_nested, Up: Runtime Library Routines
336 1.1 mrg
337 1.1 mrg 2.8 `omp_get_num_procs' - Number of processors online
338 1.1 mrg =====================================================
339 1.1 mrg
340 1.1 mrg _Description_:
341 1.1 mrg Returns the number of processors online.
342 1.1 mrg
343 1.1 mrg _C/C++_:
344 1.1.1.2 mrg _Prototype_: `int omp_get_num_procs(void);'
345 1.1 mrg
346 1.1 mrg _Fortran_:
347 1.1 mrg _Interface_: `integer function omp_get_num_procs()'
348 1.1 mrg
349 1.1 mrg _Reference_:
350 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.5.
351 1.1 mrg
352 1.1 mrg
353 1.1 mrg File: libgomp.info, Node: omp_get_num_threads, Next: omp_get_schedule, Prev: omp_get_num_procs, Up: Runtime Library Routines
354 1.1 mrg
355 1.1 mrg 2.9 `omp_get_num_threads' - Size of the active team
356 1.1 mrg ===================================================
357 1.1 mrg
358 1.1 mrg _Description_:
359 1.1.1.2 mrg Returns the number of threads in the current team. In a sequential
360 1.1.1.2 mrg section of the program `omp_get_num_threads' returns 1.
361 1.1 mrg
362 1.1 mrg The default team size may be initialized at startup by the
363 1.1 mrg `OMP_NUM_THREADS' environment variable. At runtime, the size of
364 1.1 mrg the current team may be set either by the `NUM_THREADS' clause or
365 1.1 mrg by `omp_set_num_threads'. If none of the above were used to define
366 1.1 mrg a specific value and `OMP_DYNAMIC' is disabled, one thread per CPU
367 1.1 mrg online is used.
368 1.1 mrg
369 1.1 mrg _C/C++_:
370 1.1.1.2 mrg _Prototype_: `int omp_get_num_threads(void);'
371 1.1 mrg
372 1.1 mrg _Fortran_:
373 1.1 mrg _Interface_: `integer function omp_get_num_threads()'
374 1.1 mrg
375 1.1 mrg _See also_:
376 1.1 mrg *note omp_get_max_threads::, *note omp_set_num_threads::, *note
377 1.1 mrg OMP_NUM_THREADS::
378 1.1 mrg
379 1.1 mrg _Reference_:
380 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.2.
381 1.1 mrg
382 1.1 mrg
383 1.1 mrg File: libgomp.info, Node: omp_get_schedule, Next: omp_get_team_size, Prev: omp_get_num_threads, Up: Runtime Library Routines
384 1.1 mrg
385 1.1 mrg 2.10 `omp_get_schedule' - Obtain the runtime scheduling method
386 1.1 mrg ==============================================================
387 1.1 mrg
388 1.1 mrg _Description_:
389 1.1.1.2 mrg Obtain the runtime scheduling method. The KIND argument will be
390 1.1 mrg set to the value `omp_sched_static', `omp_sched_dynamic',
391 1.1.1.2 mrg `omp_sched_guided' or `omp_sched_auto'. The second argument,
392 1.1.1.2 mrg MODIFIER, is set to the chunk size.
393 1.1 mrg
394 1.1 mrg _C/C++_
395 1.1.1.2 mrg _Prototype_: `void omp_schedule(omp_sched_t *kind, int *modifier);'
396 1.1 mrg
397 1.1 mrg _Fortran_:
398 1.1 mrg _Interface_: `subroutine omp_schedule(kind, modifier)'
399 1.1 mrg `integer(kind=omp_sched_kind) kind'
400 1.1 mrg `integer modifier'
401 1.1 mrg
402 1.1 mrg _See also_:
403 1.1 mrg *note omp_set_schedule::, *note OMP_SCHEDULE::
404 1.1 mrg
405 1.1 mrg _Reference_:
406 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
407 1.1 mrg 3.2.12.
408 1.1 mrg
409 1.1 mrg
410 1.1 mrg File: libgomp.info, Node: omp_get_team_size, Next: omp_get_thread_limit, Prev: omp_get_schedule, Up: Runtime Library Routines
411 1.1 mrg
412 1.1 mrg 2.11 `omp_get_team_size' - Number of threads in a team
413 1.1 mrg ======================================================
414 1.1 mrg
415 1.1 mrg _Description_:
416 1.1 mrg This function returns the number of threads in a thread team to
417 1.1 mrg which either the current thread or its ancestor belongs. For
418 1.1.1.2 mrg values of LEVEL outside zero to `omp_get_level', -1 is returned;
419 1.1.1.2 mrg if LEVEL is zero, 1 is returned, and for `omp_get_level', the
420 1.1.1.2 mrg result is identical to `omp_get_num_threads'.
421 1.1 mrg
422 1.1 mrg _C/C++_:
423 1.1.1.2 mrg _Prototype_: `int omp_get_team_size(int level);'
424 1.1 mrg
425 1.1 mrg _Fortran_:
426 1.1 mrg _Interface_: `integer function omp_get_team_size(level)'
427 1.1 mrg `integer level'
428 1.1 mrg
429 1.1 mrg _See also_:
430 1.1 mrg *note omp_get_num_threads::, *note omp_get_level::, *note
431 1.1 mrg omp_get_ancestor_thread_num::
432 1.1 mrg
433 1.1 mrg _Reference_:
434 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
435 1.1 mrg 3.2.18.
436 1.1 mrg
437 1.1 mrg
438 1.1 mrg File: libgomp.info, Node: omp_get_thread_limit, Next: omp_get_thread_num, Prev: omp_get_team_size, Up: Runtime Library Routines
439 1.1 mrg
440 1.1.1.2 mrg 2.12 `omp_get_thread_limit' - Maximum number of threads
441 1.1 mrg =======================================================
442 1.1 mrg
443 1.1 mrg _Description_:
444 1.1.1.2 mrg Return the maximum number of threads of the program.
445 1.1 mrg
446 1.1 mrg _C/C++_:
447 1.1.1.2 mrg _Prototype_: `int omp_get_thread_limit(void);'
448 1.1 mrg
449 1.1 mrg _Fortran_:
450 1.1 mrg _Interface_: `integer function omp_get_thread_limit()'
451 1.1 mrg
452 1.1 mrg _See also_:
453 1.1 mrg *note omp_get_max_threads::, *note OMP_THREAD_LIMIT::
454 1.1 mrg
455 1.1 mrg _Reference_:
456 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
457 1.1 mrg 3.2.13.
458 1.1 mrg
459 1.1 mrg
460 1.1 mrg File: libgomp.info, Node: omp_get_thread_num, Next: omp_in_parallel, Prev: omp_get_thread_limit, Up: Runtime Library Routines
461 1.1 mrg
462 1.1 mrg 2.13 `omp_get_thread_num' - Current thread ID
463 1.1 mrg =============================================
464 1.1 mrg
465 1.1 mrg _Description_:
466 1.1.1.2 mrg Returns a unique thread identification number within the current
467 1.1.1.2 mrg team. In a sequential parts of the program, `omp_get_thread_num'
468 1.1.1.2 mrg always returns 0. In parallel regions the return value varies from
469 1.1.1.2 mrg 0 to `omp_get_num_threads'-1 inclusive. The return value of the
470 1.1.1.2 mrg master thread of a team is always 0.
471 1.1 mrg
472 1.1 mrg _C/C++_:
473 1.1.1.2 mrg _Prototype_: `int omp_get_thread_num(void);'
474 1.1 mrg
475 1.1 mrg _Fortran_:
476 1.1 mrg _Interface_: `integer function omp_get_thread_num()'
477 1.1 mrg
478 1.1 mrg _See also_:
479 1.1 mrg *note omp_get_num_threads::, *note omp_get_ancestor_thread_num::
480 1.1 mrg
481 1.1 mrg _Reference_:
482 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.4.
483 1.1 mrg
484 1.1 mrg
485 1.1.1.2 mrg File: libgomp.info, Node: omp_in_parallel, Next: omp_in_final, Prev: omp_get_thread_num, Up: Runtime Library Routines
486 1.1 mrg
487 1.1 mrg 2.14 `omp_in_parallel' - Whether a parallel region is active
488 1.1 mrg ============================================================
489 1.1 mrg
490 1.1 mrg _Description_:
491 1.1 mrg This function returns `true' if currently running in parallel,
492 1.1 mrg `false' otherwise. Here, `true' and `false' represent their
493 1.1 mrg language-specific counterparts.
494 1.1 mrg
495 1.1 mrg _C/C++_:
496 1.1.1.2 mrg _Prototype_: `int omp_in_parallel(void);'
497 1.1 mrg
498 1.1 mrg _Fortran_:
499 1.1 mrg _Interface_: `logical function omp_in_parallel()'
500 1.1 mrg
501 1.1 mrg _Reference_:
502 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.6.
503 1.1 mrg
504 1.1 mrg
505 1.1.1.2 mrg File: libgomp.info, Node: omp_in_final, Next: omp_set_dynamic, Prev: omp_in_parallel, Up: Runtime Library Routines
506 1.1.1.2 mrg
507 1.1.1.2 mrg 2.15 `omp_in_final' - Whether in final or included task region
508 1.1.1.2 mrg ==============================================================
509 1.1.1.2 mrg
510 1.1.1.2 mrg _Description_:
511 1.1.1.2 mrg This function returns `true' if currently running in a final or
512 1.1.1.2 mrg included task region, `false' otherwise. Here, `true' and `false'
513 1.1.1.2 mrg represent their language-specific counterparts.
514 1.1.1.2 mrg
515 1.1.1.2 mrg _C/C++_:
516 1.1.1.2 mrg _Prototype_: `int omp_in_final(void);'
517 1.1 mrg
518 1.1.1.2 mrg _Fortran_:
519 1.1.1.2 mrg _Interface_: `logical function omp_in_final()'
520 1.1.1.2 mrg
521 1.1.1.2 mrg _Reference_:
522 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
523 1.1.1.2 mrg 3.2.20.
524 1.1.1.2 mrg
525 1.1.1.2 mrg
526 1.1.1.2 mrg File: libgomp.info, Node: omp_set_dynamic, Next: omp_set_max_active_levels, Prev: omp_in_final, Up: Runtime Library Routines
527 1.1.1.2 mrg
528 1.1.1.2 mrg 2.16 `omp_set_dynamic' - Enable/disable dynamic teams
529 1.1 mrg =====================================================
530 1.1 mrg
531 1.1 mrg _Description_:
532 1.1 mrg Enable or disable the dynamic adjustment of the number of threads
533 1.1 mrg within a team. The function takes the language-specific equivalent
534 1.1 mrg of `true' and `false', where `true' enables dynamic adjustment of
535 1.1 mrg team sizes and `false' disables it.
536 1.1 mrg
537 1.1 mrg _C/C++_:
538 1.1.1.2 mrg _Prototype_: `void omp_set_dynamic(int set);'
539 1.1 mrg
540 1.1 mrg _Fortran_:
541 1.1 mrg _Interface_: `subroutine omp_set_dynamic(set)'
542 1.1.1.2 mrg `logical, intent(in) :: set'
543 1.1 mrg
544 1.1 mrg _See also_:
545 1.1 mrg *note OMP_DYNAMIC::, *note omp_get_dynamic::
546 1.1 mrg
547 1.1 mrg _Reference_:
548 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.7.
549 1.1 mrg
550 1.1 mrg
551 1.1 mrg File: libgomp.info, Node: omp_set_max_active_levels, Next: omp_set_nested, Prev: omp_set_dynamic, Up: Runtime Library Routines
552 1.1 mrg
553 1.1.1.2 mrg 2.17 `omp_set_max_active_levels' - Limits the number of active parallel regions
554 1.1 mrg ===============================================================================
555 1.1 mrg
556 1.1 mrg _Description_:
557 1.1.1.2 mrg This function limits the maximum allowed number of nested, active
558 1.1.1.2 mrg parallel regions.
559 1.1 mrg
560 1.1 mrg _C/C++_
561 1.1.1.2 mrg _Prototype_: `void omp_set_max_active_levels(int max_levels);'
562 1.1 mrg
563 1.1 mrg _Fortran_:
564 1.1.1.2 mrg _Interface_: `subroutine omp_set_max_active_levels(max_levels)'
565 1.1 mrg `integer max_levels'
566 1.1 mrg
567 1.1 mrg _See also_:
568 1.1 mrg *note omp_get_max_active_levels::, *note omp_get_active_level::
569 1.1 mrg
570 1.1 mrg _Reference_:
571 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
572 1.1 mrg 3.2.14.
573 1.1 mrg
574 1.1 mrg
575 1.1 mrg File: libgomp.info, Node: omp_set_nested, Next: omp_set_num_threads, Prev: omp_set_max_active_levels, Up: Runtime Library Routines
576 1.1 mrg
577 1.1.1.2 mrg 2.18 `omp_set_nested' - Enable/disable nested parallel regions
578 1.1 mrg ==============================================================
579 1.1 mrg
580 1.1 mrg _Description_:
581 1.1 mrg Enable or disable nested parallel regions, i.e., whether team
582 1.1 mrg members are allowed to create new teams. The function takes the
583 1.1 mrg language-specific equivalent of `true' and `false', where `true'
584 1.1 mrg enables dynamic adjustment of team sizes and `false' disables it.
585 1.1 mrg
586 1.1 mrg _C/C++_:
587 1.1.1.2 mrg _Prototype_: `void omp_set_nested(int set);'
588 1.1 mrg
589 1.1 mrg _Fortran_:
590 1.1.1.2 mrg _Interface_: `subroutine omp_set_nested(set)'
591 1.1.1.2 mrg `logical, intent(in) :: set'
592 1.1 mrg
593 1.1 mrg _See also_:
594 1.1 mrg *note OMP_NESTED::, *note omp_get_nested::
595 1.1 mrg
596 1.1 mrg _Reference_:
597 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.9.
598 1.1 mrg
599 1.1 mrg
600 1.1 mrg File: libgomp.info, Node: omp_set_num_threads, Next: omp_set_schedule, Prev: omp_set_nested, Up: Runtime Library Routines
601 1.1 mrg
602 1.1.1.2 mrg 2.19 `omp_set_num_threads' - Set upper team size limit
603 1.1 mrg ======================================================
604 1.1 mrg
605 1.1 mrg _Description_:
606 1.1 mrg Specifies the number of threads used by default in subsequent
607 1.1 mrg parallel sections, if those do not specify a `num_threads' clause.
608 1.1 mrg The argument of `omp_set_num_threads' shall be a positive integer.
609 1.1 mrg
610 1.1 mrg _C/C++_:
611 1.1.1.2 mrg _Prototype_: `void omp_set_num_threads(int n);'
612 1.1 mrg
613 1.1 mrg _Fortran_:
614 1.1.1.2 mrg _Interface_: `subroutine omp_set_num_threads(n)'
615 1.1.1.2 mrg `integer, intent(in) :: n'
616 1.1 mrg
617 1.1 mrg _See also_:
618 1.1 mrg *note OMP_NUM_THREADS::, *note omp_get_num_threads::, *note
619 1.1 mrg omp_get_max_threads::
620 1.1 mrg
621 1.1 mrg _Reference_:
622 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.2.1.
623 1.1 mrg
624 1.1 mrg
625 1.1 mrg File: libgomp.info, Node: omp_set_schedule, Next: omp_init_lock, Prev: omp_set_num_threads, Up: Runtime Library Routines
626 1.1 mrg
627 1.1.1.2 mrg 2.20 `omp_set_schedule' - Set the runtime scheduling method
628 1.1 mrg ===========================================================
629 1.1 mrg
630 1.1 mrg _Description_:
631 1.1 mrg Sets the runtime scheduling method. The KIND argument can have the
632 1.1.1.2 mrg value `omp_sched_static', `omp_sched_dynamic', `omp_sched_guided'
633 1.1 mrg or `omp_sched_auto'. Except for `omp_sched_auto', the chunk size
634 1.1.1.2 mrg is set to the value of MODIFIER if positive, or to the default
635 1.1 mrg value if zero or negative. For `omp_sched_auto' the MODIFIER
636 1.1 mrg argument is ignored.
637 1.1 mrg
638 1.1 mrg _C/C++_
639 1.1.1.2 mrg _Prototype_: `void omp_set_schedule(omp_sched_t *kind, int
640 1.1.1.2 mrg *modifier);'
641 1.1 mrg
642 1.1 mrg _Fortran_:
643 1.1.1.2 mrg _Interface_: `subroutine omp_set_schedule(kind, modifier)'
644 1.1 mrg `integer(kind=omp_sched_kind) kind'
645 1.1 mrg `integer modifier'
646 1.1 mrg
647 1.1 mrg _See also_:
648 1.1 mrg *note omp_get_schedule:: *note OMP_SCHEDULE::
649 1.1 mrg
650 1.1 mrg _Reference_:
651 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section
652 1.1 mrg 3.2.11.
653 1.1 mrg
654 1.1 mrg
655 1.1 mrg File: libgomp.info, Node: omp_init_lock, Next: omp_set_lock, Prev: omp_set_schedule, Up: Runtime Library Routines
656 1.1 mrg
657 1.1.1.2 mrg 2.21 `omp_init_lock' - Initialize simple lock
658 1.1 mrg =============================================
659 1.1 mrg
660 1.1 mrg _Description_:
661 1.1.1.2 mrg Initialize a simple lock. After initialization, the lock is in an
662 1.1 mrg unlocked state.
663 1.1 mrg
664 1.1 mrg _C/C++_:
665 1.1 mrg _Prototype_: `void omp_init_lock(omp_lock_t *lock);'
666 1.1 mrg
667 1.1 mrg _Fortran_:
668 1.1 mrg _Interface_: `subroutine omp_init_lock(lock)'
669 1.1 mrg `integer(omp_lock_kind), intent(out) :: lock'
670 1.1 mrg
671 1.1 mrg _See also_:
672 1.1 mrg *note omp_destroy_lock::
673 1.1 mrg
674 1.1 mrg _Reference_:
675 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.1.
676 1.1 mrg
677 1.1 mrg
678 1.1 mrg File: libgomp.info, Node: omp_set_lock, Next: omp_test_lock, Prev: omp_init_lock, Up: Runtime Library Routines
679 1.1 mrg
680 1.1.1.2 mrg 2.22 `omp_set_lock' - Wait for and set simple lock
681 1.1 mrg ==================================================
682 1.1 mrg
683 1.1 mrg _Description_:
684 1.1 mrg Before setting a simple lock, the lock variable must be
685 1.1 mrg initialized by `omp_init_lock'. The calling thread is blocked
686 1.1 mrg until the lock is available. If the lock is already held by the
687 1.1 mrg current thread, a deadlock occurs.
688 1.1 mrg
689 1.1 mrg _C/C++_:
690 1.1 mrg _Prototype_: `void omp_set_lock(omp_lock_t *lock);'
691 1.1 mrg
692 1.1 mrg _Fortran_:
693 1.1 mrg _Interface_: `subroutine omp_set_lock(lock)'
694 1.1.1.2 mrg `integer(omp_lock_kind), intent(inout) :: lock'
695 1.1 mrg
696 1.1 mrg _See also_:
697 1.1 mrg *note omp_init_lock::, *note omp_test_lock::, *note
698 1.1 mrg omp_unset_lock::
699 1.1 mrg
700 1.1 mrg _Reference_:
701 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.3.
702 1.1 mrg
703 1.1 mrg
704 1.1 mrg File: libgomp.info, Node: omp_test_lock, Next: omp_unset_lock, Prev: omp_set_lock, Up: Runtime Library Routines
705 1.1 mrg
706 1.1.1.2 mrg 2.23 `omp_test_lock' - Test and set simple lock if available
707 1.1 mrg ============================================================
708 1.1 mrg
709 1.1 mrg _Description_:
710 1.1 mrg Before setting a simple lock, the lock variable must be
711 1.1 mrg initialized by `omp_init_lock'. Contrary to `omp_set_lock',
712 1.1 mrg `omp_test_lock' does not block if the lock is not available. This
713 1.1 mrg function returns `true' upon success, `false' otherwise. Here,
714 1.1 mrg `true' and `false' represent their language-specific counterparts.
715 1.1 mrg
716 1.1 mrg _C/C++_:
717 1.1 mrg _Prototype_: `int omp_test_lock(omp_lock_t *lock);'
718 1.1 mrg
719 1.1 mrg _Fortran_:
720 1.1.1.2 mrg _Interface_: `logical function omp_test_lock(lock)'
721 1.1.1.2 mrg `integer(omp_lock_kind), intent(inout) :: lock'
722 1.1 mrg
723 1.1 mrg _See also_:
724 1.1 mrg *note omp_init_lock::, *note omp_set_lock::, *note omp_set_lock::
725 1.1 mrg
726 1.1 mrg _Reference_:
727 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.5.
728 1.1 mrg
729 1.1 mrg
730 1.1 mrg File: libgomp.info, Node: omp_unset_lock, Next: omp_destroy_lock, Prev: omp_test_lock, Up: Runtime Library Routines
731 1.1 mrg
732 1.1.1.2 mrg 2.24 `omp_unset_lock' - Unset simple lock
733 1.1 mrg =========================================
734 1.1 mrg
735 1.1 mrg _Description_:
736 1.1 mrg A simple lock about to be unset must have been locked by
737 1.1 mrg `omp_set_lock' or `omp_test_lock' before. In addition, the lock
738 1.1 mrg must be held by the thread calling `omp_unset_lock'. Then, the
739 1.1.1.2 mrg lock becomes unlocked. If one or more threads attempted to set the
740 1.1.1.2 mrg lock before, one of them is chosen to, again, set the lock to
741 1.1 mrg itself.
742 1.1 mrg
743 1.1 mrg _C/C++_:
744 1.1 mrg _Prototype_: `void omp_unset_lock(omp_lock_t *lock);'
745 1.1 mrg
746 1.1 mrg _Fortran_:
747 1.1 mrg _Interface_: `subroutine omp_unset_lock(lock)'
748 1.1.1.2 mrg `integer(omp_lock_kind), intent(inout) :: lock'
749 1.1 mrg
750 1.1 mrg _See also_:
751 1.1 mrg *note omp_set_lock::, *note omp_test_lock::
752 1.1 mrg
753 1.1 mrg _Reference_:
754 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.4.
755 1.1 mrg
756 1.1 mrg
757 1.1 mrg File: libgomp.info, Node: omp_destroy_lock, Next: omp_init_nest_lock, Prev: omp_unset_lock, Up: Runtime Library Routines
758 1.1 mrg
759 1.1.1.2 mrg 2.25 `omp_destroy_lock' - Destroy simple lock
760 1.1 mrg =============================================
761 1.1 mrg
762 1.1 mrg _Description_:
763 1.1 mrg Destroy a simple lock. In order to be destroyed, a simple lock
764 1.1 mrg must be in the unlocked state.
765 1.1 mrg
766 1.1 mrg _C/C++_:
767 1.1.1.2 mrg _Prototype_: `void omp_destroy_lock(omp_lock_t *lock);'
768 1.1 mrg
769 1.1 mrg _Fortran_:
770 1.1 mrg _Interface_: `subroutine omp_destroy_lock(lock)'
771 1.1 mrg `integer(omp_lock_kind), intent(inout) :: lock'
772 1.1 mrg
773 1.1 mrg _See also_:
774 1.1 mrg *note omp_init_lock::
775 1.1 mrg
776 1.1 mrg _Reference_:
777 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.2.
778 1.1 mrg
779 1.1 mrg
780 1.1 mrg File: libgomp.info, Node: omp_init_nest_lock, Next: omp_set_nest_lock, Prev: omp_destroy_lock, Up: Runtime Library Routines
781 1.1 mrg
782 1.1.1.2 mrg 2.26 `omp_init_nest_lock' - Initialize nested lock
783 1.1 mrg ==================================================
784 1.1 mrg
785 1.1 mrg _Description_:
786 1.1.1.2 mrg Initialize a nested lock. After initialization, the lock is in an
787 1.1 mrg unlocked state and the nesting count is set to zero.
788 1.1 mrg
789 1.1 mrg _C/C++_:
790 1.1 mrg _Prototype_: `void omp_init_nest_lock(omp_nest_lock_t *lock);'
791 1.1 mrg
792 1.1 mrg _Fortran_:
793 1.1 mrg _Interface_: `subroutine omp_init_nest_lock(lock)'
794 1.1 mrg `integer(omp_nest_lock_kind), intent(out) :: lock'
795 1.1 mrg
796 1.1 mrg _See also_:
797 1.1 mrg *note omp_destroy_nest_lock::
798 1.1 mrg
799 1.1 mrg _Reference_:
800 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.1.
801 1.1 mrg
802 1.1 mrg
803 1.1 mrg File: libgomp.info, Node: omp_set_nest_lock, Next: omp_test_nest_lock, Prev: omp_init_nest_lock, Up: Runtime Library Routines
804 1.1 mrg
805 1.1.1.2 mrg 2.27 `omp_set_nest_lock' - Wait for and set nested lock
806 1.1 mrg =======================================================
807 1.1 mrg
808 1.1 mrg _Description_:
809 1.1 mrg Before setting a nested lock, the lock variable must be
810 1.1 mrg initialized by `omp_init_nest_lock'. The calling thread is blocked
811 1.1 mrg until the lock is available. If the lock is already held by the
812 1.1.1.2 mrg current thread, the nesting count for the lock is incremented.
813 1.1 mrg
814 1.1 mrg _C/C++_:
815 1.1 mrg _Prototype_: `void omp_set_nest_lock(omp_nest_lock_t *lock);'
816 1.1 mrg
817 1.1 mrg _Fortran_:
818 1.1 mrg _Interface_: `subroutine omp_set_nest_lock(lock)'
819 1.1.1.2 mrg `integer(omp_nest_lock_kind), intent(inout) :: lock'
820 1.1 mrg
821 1.1 mrg _See also_:
822 1.1 mrg *note omp_init_nest_lock::, *note omp_unset_nest_lock::
823 1.1 mrg
824 1.1 mrg _Reference_:
825 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.3.
826 1.1 mrg
827 1.1 mrg
828 1.1 mrg File: libgomp.info, Node: omp_test_nest_lock, Next: omp_unset_nest_lock, Prev: omp_set_nest_lock, Up: Runtime Library Routines
829 1.1 mrg
830 1.1.1.2 mrg 2.28 `omp_test_nest_lock' - Test and set nested lock if available
831 1.1 mrg =================================================================
832 1.1 mrg
833 1.1 mrg _Description_:
834 1.1 mrg Before setting a nested lock, the lock variable must be
835 1.1 mrg initialized by `omp_init_nest_lock'. Contrary to
836 1.1 mrg `omp_set_nest_lock', `omp_test_nest_lock' does not block if the
837 1.1 mrg lock is not available. If the lock is already held by the current
838 1.1 mrg thread, the new nesting count is returned. Otherwise, the return
839 1.1 mrg value equals zero.
840 1.1 mrg
841 1.1 mrg _C/C++_:
842 1.1 mrg _Prototype_: `int omp_test_nest_lock(omp_nest_lock_t *lock);'
843 1.1 mrg
844 1.1 mrg _Fortran_:
845 1.1.1.2 mrg _Interface_: `logical function omp_test_nest_lock(lock)'
846 1.1 mrg `integer(omp_nest_lock_kind), intent(inout) :: lock'
847 1.1 mrg
848 1.1 mrg _See also_:
849 1.1 mrg *note omp_init_lock::, *note omp_set_lock::, *note omp_set_lock::
850 1.1 mrg
851 1.1 mrg _Reference_:
852 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.5.
853 1.1 mrg
854 1.1 mrg
855 1.1 mrg File: libgomp.info, Node: omp_unset_nest_lock, Next: omp_destroy_nest_lock, Prev: omp_test_nest_lock, Up: Runtime Library Routines
856 1.1 mrg
857 1.1.1.2 mrg 2.29 `omp_unset_nest_lock' - Unset nested lock
858 1.1 mrg ==============================================
859 1.1 mrg
860 1.1 mrg _Description_:
861 1.1 mrg A nested lock about to be unset must have been locked by
862 1.1 mrg `omp_set_nested_lock' or `omp_test_nested_lock' before. In
863 1.1 mrg addition, the lock must be held by the thread calling
864 1.1 mrg `omp_unset_nested_lock'. If the nesting count drops to zero, the
865 1.1 mrg lock becomes unlocked. If one ore more threads attempted to set
866 1.1.1.2 mrg the lock before, one of them is chosen to, again, set the lock to
867 1.1 mrg itself.
868 1.1 mrg
869 1.1 mrg _C/C++_:
870 1.1 mrg _Prototype_: `void omp_unset_nest_lock(omp_nest_lock_t *lock);'
871 1.1 mrg
872 1.1 mrg _Fortran_:
873 1.1 mrg _Interface_: `subroutine omp_unset_nest_lock(lock)'
874 1.1.1.2 mrg `integer(omp_nest_lock_kind), intent(inout) :: lock'
875 1.1 mrg
876 1.1 mrg _See also_:
877 1.1 mrg *note omp_set_nest_lock::
878 1.1 mrg
879 1.1 mrg _Reference_:
880 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.4.
881 1.1 mrg
882 1.1 mrg
883 1.1 mrg File: libgomp.info, Node: omp_destroy_nest_lock, Next: omp_get_wtick, Prev: omp_unset_nest_lock, Up: Runtime Library Routines
884 1.1 mrg
885 1.1.1.2 mrg 2.30 `omp_destroy_nest_lock' - Destroy nested lock
886 1.1 mrg ==================================================
887 1.1 mrg
888 1.1 mrg _Description_:
889 1.1 mrg Destroy a nested lock. In order to be destroyed, a nested lock
890 1.1 mrg must be in the unlocked state and its nesting count must equal
891 1.1 mrg zero.
892 1.1 mrg
893 1.1 mrg _C/C++_:
894 1.1 mrg _Prototype_: `void omp_destroy_nest_lock(omp_nest_lock_t *);'
895 1.1 mrg
896 1.1 mrg _Fortran_:
897 1.1 mrg _Interface_: `subroutine omp_destroy_nest_lock(lock)'
898 1.1 mrg `integer(omp_nest_lock_kind), intent(inout) :: lock'
899 1.1 mrg
900 1.1 mrg _See also_:
901 1.1 mrg *note omp_init_lock::
902 1.1 mrg
903 1.1 mrg _Reference_:
904 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.3.2.
905 1.1 mrg
906 1.1 mrg
907 1.1 mrg File: libgomp.info, Node: omp_get_wtick, Next: omp_get_wtime, Prev: omp_destroy_nest_lock, Up: Runtime Library Routines
908 1.1 mrg
909 1.1.1.2 mrg 2.31 `omp_get_wtick' - Get timer precision
910 1.1 mrg ==========================================
911 1.1 mrg
912 1.1 mrg _Description_:
913 1.1 mrg Gets the timer precision, i.e., the number of seconds between two
914 1.1 mrg successive clock ticks.
915 1.1 mrg
916 1.1 mrg _C/C++_:
917 1.1.1.2 mrg _Prototype_: `double omp_get_wtick(void);'
918 1.1 mrg
919 1.1 mrg _Fortran_:
920 1.1 mrg _Interface_: `double precision function omp_get_wtick()'
921 1.1 mrg
922 1.1 mrg _See also_:
923 1.1 mrg *note omp_get_wtime::
924 1.1 mrg
925 1.1 mrg _Reference_:
926 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.4.2.
927 1.1 mrg
928 1.1 mrg
929 1.1 mrg File: libgomp.info, Node: omp_get_wtime, Prev: omp_get_wtick, Up: Runtime Library Routines
930 1.1 mrg
931 1.1.1.2 mrg 2.32 `omp_get_wtime' - Elapsed wall clock time
932 1.1 mrg ==============================================
933 1.1 mrg
934 1.1 mrg _Description_:
935 1.1 mrg Elapsed wall clock time in seconds. The time is measured per
936 1.1.1.2 mrg thread, no guarantee can be made that two distinct threads measure
937 1.1.1.2 mrg the same time. Time is measured from some "time in the past",
938 1.1.1.2 mrg which is an arbitrary time guaranteed not to change during the
939 1.1.1.2 mrg execution of the program.
940 1.1 mrg
941 1.1 mrg _C/C++_:
942 1.1.1.2 mrg _Prototype_: `double omp_get_wtime(void);'
943 1.1 mrg
944 1.1 mrg _Fortran_:
945 1.1 mrg _Interface_: `double precision function omp_get_wtime()'
946 1.1 mrg
947 1.1 mrg _See also_:
948 1.1 mrg *note omp_get_wtick::
949 1.1 mrg
950 1.1 mrg _Reference_:
951 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 3.4.1.
952 1.1 mrg
953 1.1 mrg
954 1.1 mrg File: libgomp.info, Node: Environment Variables, Next: The libgomp ABI, Prev: Runtime Library Routines, Up: Top
955 1.1 mrg
956 1.1 mrg 3 Environment Variables
957 1.1 mrg ***********************
958 1.1 mrg
959 1.1 mrg The variables `OMP_DYNAMIC', `OMP_MAX_ACTIVE_LEVELS', `OMP_NESTED',
960 1.1 mrg `OMP_NUM_THREADS', `OMP_SCHEDULE', `OMP_STACKSIZE',`OMP_THREAD_LIMIT'
961 1.1 mrg and `OMP_WAIT_POLICY' are defined by section 4 of the OpenMP
962 1.1.1.2 mrg specifications in version 3.1, while `GOMP_CPU_AFFINITY' and
963 1.1 mrg `GOMP_STACKSIZE' are GNU extensions.
964 1.1 mrg
965 1.1 mrg * Menu:
966 1.1 mrg
967 1.1 mrg * OMP_DYNAMIC:: Dynamic adjustment of threads
968 1.1.1.2 mrg * OMP_MAX_ACTIVE_LEVELS:: Set the maximum number of nested parallel regions
969 1.1 mrg * OMP_NESTED:: Nested parallel regions
970 1.1 mrg * OMP_NUM_THREADS:: Specifies the number of threads to use
971 1.1 mrg * OMP_STACKSIZE:: Set default thread stack size
972 1.1 mrg * OMP_SCHEDULE:: How threads are scheduled
973 1.1.1.2 mrg * OMP_THREAD_LIMIT:: Set the maximum number of threads
974 1.1 mrg * OMP_WAIT_POLICY:: How waiting threads are handled
975 1.1.1.2 mrg * OMP_PROC_BIND:: Whether theads may be moved between CPUs
976 1.1 mrg * GOMP_CPU_AFFINITY:: Bind threads to specific CPUs
977 1.1 mrg * GOMP_STACKSIZE:: Set default thread stack size
978 1.1 mrg
979 1.1 mrg
980 1.1 mrg File: libgomp.info, Node: OMP_DYNAMIC, Next: OMP_MAX_ACTIVE_LEVELS, Up: Environment Variables
981 1.1 mrg
982 1.1 mrg 3.1 `OMP_DYNAMIC' - Dynamic adjustment of threads
983 1.1 mrg =================================================
984 1.1 mrg
985 1.1 mrg _Description_:
986 1.1 mrg Enable or disable the dynamic adjustment of the number of threads
987 1.1 mrg within a team. The value of this environment variable shall be
988 1.1 mrg `TRUE' or `FALSE'. If undefined, dynamic adjustment is disabled by
989 1.1 mrg default.
990 1.1 mrg
991 1.1 mrg _See also_:
992 1.1 mrg *note omp_set_dynamic::
993 1.1 mrg
994 1.1 mrg _Reference_:
995 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 4.3
996 1.1 mrg
997 1.1 mrg
998 1.1 mrg File: libgomp.info, Node: OMP_MAX_ACTIVE_LEVELS, Next: OMP_NESTED, Prev: OMP_DYNAMIC, Up: Environment Variables
999 1.1 mrg
1000 1.1.1.2 mrg 3.2 `OMP_MAX_ACTIVE_LEVELS' - Set the maximum number of nested parallel regions
1001 1.1 mrg ===============================================================================
1002 1.1 mrg
1003 1.1 mrg _Description_:
1004 1.1.1.2 mrg Specifies the initial value for the maximum number of nested
1005 1.1.1.2 mrg parallel regions. The value of this variable shall be a positive
1006 1.1 mrg integer. If undefined, the number of active levels is unlimited.
1007 1.1 mrg
1008 1.1 mrg _See also_:
1009 1.1 mrg *note omp_set_max_active_levels::
1010 1.1 mrg
1011 1.1 mrg _Reference_:
1012 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 4.8
1013 1.1 mrg
1014 1.1 mrg
1015 1.1 mrg File: libgomp.info, Node: OMP_NESTED, Next: OMP_NUM_THREADS, Prev: OMP_MAX_ACTIVE_LEVELS, Up: Environment Variables
1016 1.1 mrg
1017 1.1 mrg 3.3 `OMP_NESTED' - Nested parallel regions
1018 1.1 mrg ==========================================
1019 1.1 mrg
1020 1.1 mrg _Description_:
1021 1.1 mrg Enable or disable nested parallel regions, i.e., whether team
1022 1.1 mrg members are allowed to create new teams. The value of this
1023 1.1 mrg environment variable shall be `TRUE' or `FALSE'. If undefined,
1024 1.1 mrg nested parallel regions are disabled by default.
1025 1.1 mrg
1026 1.1 mrg _See also_:
1027 1.1 mrg *note omp_set_nested::
1028 1.1 mrg
1029 1.1 mrg _Reference_:
1030 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 4.5
1031 1.1 mrg
1032 1.1 mrg
1033 1.1 mrg File: libgomp.info, Node: OMP_NUM_THREADS, Next: OMP_STACKSIZE, Prev: OMP_NESTED, Up: Environment Variables
1034 1.1 mrg
1035 1.1 mrg 3.4 `OMP_NUM_THREADS' - Specifies the number of threads to use
1036 1.1 mrg ==============================================================
1037 1.1 mrg
1038 1.1 mrg _Description_:
1039 1.1 mrg Specifies the default number of threads to use in parallel
1040 1.1.1.2 mrg regions. The value of this variable shall be a comma-separated
1041 1.1.1.2 mrg list of positive integers; the value specified the number of
1042 1.1.1.2 mrg threads to use for the corresponding nested level. If undefined
1043 1.1.1.2 mrg one thread per CPU is used.
1044 1.1 mrg
1045 1.1 mrg _See also_:
1046 1.1 mrg *note omp_set_num_threads::
1047 1.1 mrg
1048 1.1 mrg _Reference_:
1049 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 4.2
1050 1.1 mrg
1051 1.1 mrg
1052 1.1 mrg File: libgomp.info, Node: OMP_SCHEDULE, Next: OMP_THREAD_LIMIT, Prev: OMP_STACKSIZE, Up: Environment Variables
1053 1.1 mrg
1054 1.1 mrg 3.5 `OMP_SCHEDULE' - How threads are scheduled
1055 1.1 mrg ==============================================
1056 1.1 mrg
1057 1.1 mrg _Description_:
1058 1.1 mrg Allows to specify `schedule type' and `chunk size'. The value of
1059 1.1 mrg the variable shall have the form: `type[,chunk]' where `type' is
1060 1.1 mrg one of `static', `dynamic', `guided' or `auto' The optional
1061 1.1 mrg `chunk' size shall be a positive integer. If undefined, dynamic
1062 1.1 mrg scheduling and a chunk size of 1 is used.
1063 1.1 mrg
1064 1.1 mrg _See also_:
1065 1.1 mrg *note omp_set_schedule::
1066 1.1 mrg
1067 1.1 mrg _Reference_:
1068 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), sections
1069 1.1 mrg 2.5.1 and 4.1
1070 1.1 mrg
1071 1.1 mrg
1072 1.1 mrg File: libgomp.info, Node: OMP_STACKSIZE, Next: OMP_SCHEDULE, Prev: OMP_NUM_THREADS, Up: Environment Variables
1073 1.1 mrg
1074 1.1 mrg 3.6 `OMP_STACKSIZE' - Set default thread stack size
1075 1.1 mrg ===================================================
1076 1.1 mrg
1077 1.1 mrg _Description_:
1078 1.1 mrg Set the default thread stack size in kilobytes, unless the number
1079 1.1 mrg is suffixed by `B', `K', `M' or `G', in which case the size is,
1080 1.1 mrg respectively, in bytes, kilobytes, megabytes or gigabytes. This is
1081 1.1 mrg different from `pthread_attr_setstacksize' which gets the number
1082 1.1.1.2 mrg of bytes as an argument. If the stack size cannot be set due to
1083 1.1.1.2 mrg system constraints, an error is reported and the initial stack
1084 1.1.1.2 mrg size is left unchanged. If undefined, the stack size is system
1085 1.1 mrg dependent.
1086 1.1 mrg
1087 1.1 mrg _Reference_:
1088 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), sections 4.6
1089 1.1 mrg
1090 1.1 mrg
1091 1.1 mrg File: libgomp.info, Node: OMP_THREAD_LIMIT, Next: OMP_WAIT_POLICY, Prev: OMP_SCHEDULE, Up: Environment Variables
1092 1.1 mrg
1093 1.1.1.2 mrg 3.7 `OMP_THREAD_LIMIT' - Set the maximum number of threads
1094 1.1 mrg ==========================================================
1095 1.1 mrg
1096 1.1 mrg _Description_:
1097 1.1 mrg Specifies the number of threads to use for the whole program. The
1098 1.1.1.2 mrg value of this variable shall be a positive integer. If undefined,
1099 1.1 mrg the number of threads is not limited.
1100 1.1 mrg
1101 1.1 mrg _See also_:
1102 1.1 mrg *note OMP_NUM_THREADS:: *note omp_get_thread_limit::
1103 1.1 mrg
1104 1.1 mrg _Reference_:
1105 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), section 4.9
1106 1.1 mrg
1107 1.1 mrg
1108 1.1.1.2 mrg File: libgomp.info, Node: OMP_WAIT_POLICY, Next: OMP_PROC_BIND, Prev: OMP_THREAD_LIMIT, Up: Environment Variables
1109 1.1 mrg
1110 1.1 mrg 3.8 `OMP_WAIT_POLICY' - How waiting threads are handled
1111 1.1 mrg =======================================================
1112 1.1 mrg
1113 1.1 mrg _Description_:
1114 1.1 mrg Specifies whether waiting threads should be active or passive. If
1115 1.1 mrg the value is `PASSIVE', waiting threads should not consume CPU
1116 1.1 mrg power while waiting; while the value is `ACTIVE' specifies that
1117 1.1 mrg they should.
1118 1.1 mrg
1119 1.1 mrg _Reference_:
1120 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), sections 4.7
1121 1.1 mrg
1122 1.1 mrg
1123 1.1.1.2 mrg File: libgomp.info, Node: OMP_PROC_BIND, Next: GOMP_CPU_AFFINITY, Prev: OMP_WAIT_POLICY, Up: Environment Variables
1124 1.1 mrg
1125 1.1.1.2 mrg 3.9 `OMP_PROC_BIND' - Whether theads may be moved between CPUs
1126 1.1.1.2 mrg ==============================================================
1127 1.1.1.2 mrg
1128 1.1.1.2 mrg _Description_:
1129 1.1.1.2 mrg Specifies whether threads may be moved between processors. If set
1130 1.1.1.2 mrg to `true', OpenMP theads should not be moved, if set to `false'
1131 1.1.1.2 mrg they may be moved.
1132 1.1.1.2 mrg
1133 1.1.1.2 mrg _See also_:
1134 1.1.1.2 mrg *note GOMP_CPU_AFFINITY::
1135 1.1.1.2 mrg
1136 1.1.1.2 mrg _Reference_:
1137 1.1.1.2 mrg OpenMP specifications v3.1 (http://www.openmp.org/), sections 4.4
1138 1.1.1.2 mrg
1139 1.1.1.2 mrg
1140 1.1.1.2 mrg File: libgomp.info, Node: GOMP_CPU_AFFINITY, Next: GOMP_STACKSIZE, Prev: OMP_PROC_BIND, Up: Environment Variables
1141 1.1.1.2 mrg
1142 1.1.1.2 mrg 3.10 `GOMP_CPU_AFFINITY' - Bind threads to specific CPUs
1143 1.1.1.2 mrg ========================================================
1144 1.1 mrg
1145 1.1 mrg _Description_:
1146 1.1 mrg Binds threads to specific CPUs. The variable should contain a
1147 1.1.1.2 mrg space-separated or comma-separated list of CPUs. This list may
1148 1.1.1.2 mrg contain different kinds of entries: either single CPU numbers in
1149 1.1.1.2 mrg any order, a range of CPUs (M-N) or a range with some stride
1150 1.1.1.2 mrg (M-N:S). CPU numbers are zero based. For example,
1151 1.1.1.2 mrg `GOMP_CPU_AFFINITY="0 3 1-2 4-15:2"' will bind the initial thread
1152 1.1.1.2 mrg to CPU 0, the second to CPU 3, the third to CPU 1, the fourth to
1153 1.1.1.2 mrg CPU 2, the fifth to CPU 4, the sixth through tenth to CPUs 6, 8,
1154 1.1.1.2 mrg 10, 12, and 14 respectively and then start assigning back from the
1155 1.1.1.2 mrg beginning of the list. `GOMP_CPU_AFFINITY=0' binds all threads to
1156 1.1.1.2 mrg CPU 0.
1157 1.1 mrg
1158 1.1 mrg There is no GNU OpenMP library routine to determine whether a CPU
1159 1.1 mrg affinity specification is in effect. As a workaround,
1160 1.1 mrg language-specific library functions, e.g., `getenv' in C or
1161 1.1 mrg `GET_ENVIRONMENT_VARIABLE' in Fortran, may be used to query the
1162 1.1 mrg setting of the `GOMP_CPU_AFFINITY' environment variable. A defined
1163 1.1 mrg CPU affinity on startup cannot be changed or disabled during the
1164 1.1 mrg runtime of the application.
1165 1.1 mrg
1166 1.1 mrg If this environment variable is omitted, the host system will
1167 1.1 mrg handle the assignment of threads to CPUs.
1168 1.1 mrg
1169 1.1.1.2 mrg _See also_:
1170 1.1.1.2 mrg *note OMP_PROC_BIND::
1171 1.1.1.2 mrg
1172 1.1 mrg
1173 1.1 mrg File: libgomp.info, Node: GOMP_STACKSIZE, Prev: GOMP_CPU_AFFINITY, Up: Environment Variables
1174 1.1 mrg
1175 1.1.1.2 mrg 3.11 `GOMP_STACKSIZE' - Set default thread stack size
1176 1.1 mrg =====================================================
1177 1.1 mrg
1178 1.1 mrg _Description_:
1179 1.1 mrg Set the default thread stack size in kilobytes. This is different
1180 1.1 mrg from `pthread_attr_setstacksize' which gets the number of bytes as
1181 1.1.1.2 mrg an argument. If the stack size cannot be set due to system
1182 1.1.1.2 mrg constraints, an error is reported and the initial stack size is
1183 1.1 mrg left unchanged. If undefined, the stack size is system dependent.
1184 1.1 mrg
1185 1.1 mrg _See also_:
1186 1.1.1.2 mrg *note OMP_STACKSIZE::
1187 1.1 mrg
1188 1.1 mrg _Reference_:
1189 1.1 mrg GCC Patches Mailinglist
1190 1.1 mrg (http://gcc.gnu.org/ml/gcc-patches/2006-06/msg00493.html), GCC
1191 1.1 mrg Patches Mailinglist
1192 1.1 mrg (http://gcc.gnu.org/ml/gcc-patches/2006-06/msg00496.html)
1193 1.1 mrg
1194 1.1 mrg
1195 1.1 mrg File: libgomp.info, Node: The libgomp ABI, Next: Reporting Bugs, Prev: Environment Variables, Up: Top
1196 1.1 mrg
1197 1.1 mrg 4 The libgomp ABI
1198 1.1 mrg *****************
1199 1.1 mrg
1200 1.1 mrg The following sections present notes on the external ABI as presented
1201 1.1.1.2 mrg by libgomp. Only maintainers should need them.
1202 1.1 mrg
1203 1.1 mrg * Menu:
1204 1.1 mrg
1205 1.1 mrg * Implementing MASTER construct::
1206 1.1 mrg * Implementing CRITICAL construct::
1207 1.1 mrg * Implementing ATOMIC construct::
1208 1.1 mrg * Implementing FLUSH construct::
1209 1.1 mrg * Implementing BARRIER construct::
1210 1.1 mrg * Implementing THREADPRIVATE construct::
1211 1.1 mrg * Implementing PRIVATE clause::
1212 1.1 mrg * Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses::
1213 1.1 mrg * Implementing REDUCTION clause::
1214 1.1 mrg * Implementing PARALLEL construct::
1215 1.1 mrg * Implementing FOR construct::
1216 1.1 mrg * Implementing ORDERED construct::
1217 1.1 mrg * Implementing SECTIONS construct::
1218 1.1 mrg * Implementing SINGLE construct::
1219 1.1 mrg
1220 1.1 mrg
1221 1.1 mrg File: libgomp.info, Node: Implementing MASTER construct, Next: Implementing CRITICAL construct, Up: The libgomp ABI
1222 1.1 mrg
1223 1.1 mrg 4.1 Implementing MASTER construct
1224 1.1 mrg =================================
1225 1.1 mrg
1226 1.1 mrg if (omp_get_thread_num () == 0)
1227 1.1 mrg block
1228 1.1 mrg
1229 1.1 mrg Alternately, we generate two copies of the parallel subfunction and
1230 1.1.1.2 mrg only include this in the version run by the master thread. Surely this
1231 1.1.1.2 mrg is not worthwhile though...
1232 1.1 mrg
1233 1.1 mrg
1234 1.1 mrg File: libgomp.info, Node: Implementing CRITICAL construct, Next: Implementing ATOMIC construct, Prev: Implementing MASTER construct, Up: The libgomp ABI
1235 1.1 mrg
1236 1.1 mrg 4.2 Implementing CRITICAL construct
1237 1.1 mrg ===================================
1238 1.1 mrg
1239 1.1 mrg Without a specified name,
1240 1.1 mrg
1241 1.1 mrg void GOMP_critical_start (void);
1242 1.1 mrg void GOMP_critical_end (void);
1243 1.1 mrg
1244 1.1 mrg so that we don't get COPY relocations from libgomp to the main
1245 1.1 mrg application.
1246 1.1 mrg
1247 1.1 mrg With a specified name, use omp_set_lock and omp_unset_lock with name
1248 1.1 mrg being transformed into a variable declared like
1249 1.1 mrg
1250 1.1 mrg omp_lock_t gomp_critical_user_<name> __attribute__((common))
1251 1.1 mrg
1252 1.1 mrg Ideally the ABI would specify that all zero is a valid unlocked
1253 1.1.1.2 mrg state, and so we wouldn't need to initialize this at startup.
1254 1.1 mrg
1255 1.1 mrg
1256 1.1 mrg File: libgomp.info, Node: Implementing ATOMIC construct, Next: Implementing FLUSH construct, Prev: Implementing CRITICAL construct, Up: The libgomp ABI
1257 1.1 mrg
1258 1.1 mrg 4.3 Implementing ATOMIC construct
1259 1.1 mrg =================================
1260 1.1 mrg
1261 1.1 mrg The target should implement the `__sync' builtins.
1262 1.1 mrg
1263 1.1 mrg Failing that we could add
1264 1.1 mrg
1265 1.1 mrg void GOMP_atomic_enter (void)
1266 1.1 mrg void GOMP_atomic_exit (void)
1267 1.1 mrg
1268 1.1 mrg which reuses the regular lock code, but with yet another lock object
1269 1.1 mrg private to the library.
1270 1.1 mrg
1271 1.1 mrg
1272 1.1 mrg File: libgomp.info, Node: Implementing FLUSH construct, Next: Implementing BARRIER construct, Prev: Implementing ATOMIC construct, Up: The libgomp ABI
1273 1.1 mrg
1274 1.1 mrg 4.4 Implementing FLUSH construct
1275 1.1 mrg ================================
1276 1.1 mrg
1277 1.1 mrg Expands to the `__sync_synchronize' builtin.
1278 1.1 mrg
1279 1.1 mrg
1280 1.1 mrg File: libgomp.info, Node: Implementing BARRIER construct, Next: Implementing THREADPRIVATE construct, Prev: Implementing FLUSH construct, Up: The libgomp ABI
1281 1.1 mrg
1282 1.1 mrg 4.5 Implementing BARRIER construct
1283 1.1 mrg ==================================
1284 1.1 mrg
1285 1.1 mrg void GOMP_barrier (void)
1286 1.1 mrg
1287 1.1 mrg
1288 1.1 mrg File: libgomp.info, Node: Implementing THREADPRIVATE construct, Next: Implementing PRIVATE clause, Prev: Implementing BARRIER construct, Up: The libgomp ABI
1289 1.1 mrg
1290 1.1 mrg 4.6 Implementing THREADPRIVATE construct
1291 1.1 mrg ========================================
1292 1.1 mrg
1293 1.1 mrg In _most_ cases we can map this directly to `__thread'. Except that
1294 1.1 mrg OMP allows constructors for C++ objects. We can either refuse to
1295 1.1 mrg support this (how often is it used?) or we can implement something akin
1296 1.1 mrg to .ctors.
1297 1.1 mrg
1298 1.1 mrg Even more ideally, this ctor feature is handled by extensions to the
1299 1.1 mrg main pthreads library. Failing that, we can have a set of entry points
1300 1.1 mrg to register ctor functions to be called.
1301 1.1 mrg
1302 1.1 mrg
1303 1.1 mrg File: libgomp.info, Node: Implementing PRIVATE clause, Next: Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses, Prev: Implementing THREADPRIVATE construct, Up: The libgomp ABI
1304 1.1 mrg
1305 1.1 mrg 4.7 Implementing PRIVATE clause
1306 1.1 mrg ===============================
1307 1.1 mrg
1308 1.1 mrg In association with a PARALLEL, or within the lexical extent of a
1309 1.1 mrg PARALLEL block, the variable becomes a local variable in the parallel
1310 1.1 mrg subfunction.
1311 1.1 mrg
1312 1.1 mrg In association with FOR or SECTIONS blocks, create a new automatic
1313 1.1 mrg variable within the current function. This preserves the semantic of
1314 1.1 mrg new variable creation.
1315 1.1 mrg
1316 1.1 mrg
1317 1.1 mrg File: libgomp.info, Node: Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses, Next: Implementing REDUCTION clause, Prev: Implementing PRIVATE clause, Up: The libgomp ABI
1318 1.1 mrg
1319 1.1 mrg 4.8 Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses
1320 1.1 mrg ========================================================================
1321 1.1 mrg
1322 1.1.1.2 mrg This seems simple enough for PARALLEL blocks. Create a private struct
1323 1.1.1.2 mrg for communicating between the parent and subfunction. In the parent,
1324 1.1.1.2 mrg copy in values for scalar and "small" structs; copy in addresses for
1325 1.1.1.2 mrg others TREE_ADDRESSABLE types. In the subfunction, copy the value into
1326 1.1.1.2 mrg the local variable.
1327 1.1 mrg
1328 1.1.1.2 mrg It is not clear what to do with bare FOR or SECTION blocks. The
1329 1.1.1.2 mrg only thing I can figure is that we do something like:
1330 1.1 mrg
1331 1.1 mrg #pragma omp for firstprivate(x) lastprivate(y)
1332 1.1 mrg for (int i = 0; i < n; ++i)
1333 1.1 mrg body;
1334 1.1 mrg
1335 1.1 mrg which becomes
1336 1.1 mrg
1337 1.1 mrg {
1338 1.1 mrg int x = x, y;
1339 1.1 mrg
1340 1.1 mrg // for stuff
1341 1.1 mrg
1342 1.1 mrg if (i == n)
1343 1.1 mrg y = y;
1344 1.1 mrg }
1345 1.1 mrg
1346 1.1 mrg where the "x=x" and "y=y" assignments actually have different uids
1347 1.1 mrg for the two variables, i.e. not something you could write directly in
1348 1.1 mrg C. Presumably this only makes sense if the "outer" x and y are global
1349 1.1 mrg variables.
1350 1.1 mrg
1351 1.1 mrg COPYPRIVATE would work the same way, except the structure broadcast
1352 1.1 mrg would have to happen via SINGLE machinery instead.
1353 1.1 mrg
1354 1.1 mrg
1355 1.1 mrg File: libgomp.info, Node: Implementing REDUCTION clause, Next: Implementing PARALLEL construct, Prev: Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses, Up: The libgomp ABI
1356 1.1 mrg
1357 1.1 mrg 4.9 Implementing REDUCTION clause
1358 1.1 mrg =================================
1359 1.1 mrg
1360 1.1 mrg The private struct mentioned in the previous section should have a
1361 1.1 mrg pointer to an array of the type of the variable, indexed by the
1362 1.1 mrg thread's TEAM_ID. The thread stores its final value into the array,
1363 1.1.1.2 mrg and after the barrier, the master thread iterates over the array to
1364 1.1 mrg collect the values.
1365 1.1 mrg
1366 1.1 mrg
1367 1.1 mrg File: libgomp.info, Node: Implementing PARALLEL construct, Next: Implementing FOR construct, Prev: Implementing REDUCTION clause, Up: The libgomp ABI
1368 1.1 mrg
1369 1.1 mrg 4.10 Implementing PARALLEL construct
1370 1.1 mrg ====================================
1371 1.1 mrg
1372 1.1 mrg #pragma omp parallel
1373 1.1 mrg {
1374 1.1 mrg body;
1375 1.1 mrg }
1376 1.1 mrg
1377 1.1 mrg becomes
1378 1.1 mrg
1379 1.1 mrg void subfunction (void *data)
1380 1.1 mrg {
1381 1.1 mrg use data;
1382 1.1 mrg body;
1383 1.1 mrg }
1384 1.1 mrg
1385 1.1 mrg setup data;
1386 1.1 mrg GOMP_parallel_start (subfunction, &data, num_threads);
1387 1.1 mrg subfunction (&data);
1388 1.1 mrg GOMP_parallel_end ();
1389 1.1 mrg
1390 1.1 mrg void GOMP_parallel_start (void (*fn)(void *), void *data, unsigned num_threads)
1391 1.1 mrg
1392 1.1 mrg The FN argument is the subfunction to be run in parallel.
1393 1.1 mrg
1394 1.1 mrg The DATA argument is a pointer to a structure used to communicate
1395 1.1 mrg data in and out of the subfunction, as discussed above with respect to
1396 1.1 mrg FIRSTPRIVATE et al.
1397 1.1 mrg
1398 1.1 mrg The NUM_THREADS argument is 1 if an IF clause is present and false,
1399 1.1 mrg or the value of the NUM_THREADS clause, if present, or 0.
1400 1.1 mrg
1401 1.1 mrg The function needs to create the appropriate number of threads
1402 1.1 mrg and/or launch them from the dock. It needs to create the team
1403 1.1 mrg structure and assign team ids.
1404 1.1 mrg
1405 1.1 mrg void GOMP_parallel_end (void)
1406 1.1 mrg
1407 1.1 mrg Tears down the team and returns us to the previous
1408 1.1 mrg `omp_in_parallel()' state.
1409 1.1 mrg
1410 1.1 mrg
1411 1.1 mrg File: libgomp.info, Node: Implementing FOR construct, Next: Implementing ORDERED construct, Prev: Implementing PARALLEL construct, Up: The libgomp ABI
1412 1.1 mrg
1413 1.1 mrg 4.11 Implementing FOR construct
1414 1.1 mrg ===============================
1415 1.1 mrg
1416 1.1 mrg #pragma omp parallel for
1417 1.1 mrg for (i = lb; i <= ub; i++)
1418 1.1 mrg body;
1419 1.1 mrg
1420 1.1 mrg becomes
1421 1.1 mrg
1422 1.1 mrg void subfunction (void *data)
1423 1.1 mrg {
1424 1.1 mrg long _s0, _e0;
1425 1.1 mrg while (GOMP_loop_static_next (&_s0, &_e0))
1426 1.1 mrg {
1427 1.1 mrg long _e1 = _e0, i;
1428 1.1 mrg for (i = _s0; i < _e1; i++)
1429 1.1 mrg body;
1430 1.1 mrg }
1431 1.1 mrg GOMP_loop_end_nowait ();
1432 1.1 mrg }
1433 1.1 mrg
1434 1.1 mrg GOMP_parallel_loop_static (subfunction, NULL, 0, lb, ub+1, 1, 0);
1435 1.1 mrg subfunction (NULL);
1436 1.1 mrg GOMP_parallel_end ();
1437 1.1 mrg
1438 1.1 mrg #pragma omp for schedule(runtime)
1439 1.1 mrg for (i = 0; i < n; i++)
1440 1.1 mrg body;
1441 1.1 mrg
1442 1.1 mrg becomes
1443 1.1 mrg
1444 1.1 mrg {
1445 1.1 mrg long i, _s0, _e0;
1446 1.1 mrg if (GOMP_loop_runtime_start (0, n, 1, &_s0, &_e0))
1447 1.1 mrg do {
1448 1.1 mrg long _e1 = _e0;
1449 1.1 mrg for (i = _s0, i < _e0; i++)
1450 1.1 mrg body;
1451 1.1 mrg } while (GOMP_loop_runtime_next (&_s0, _&e0));
1452 1.1 mrg GOMP_loop_end ();
1453 1.1 mrg }
1454 1.1 mrg
1455 1.1.1.2 mrg Note that while it looks like there is trickiness to propagating a
1456 1.1 mrg non-constant STEP, there isn't really. We're explicitly allowed to
1457 1.1 mrg evaluate it as many times as we want, and any variables involved should
1458 1.1 mrg automatically be handled as PRIVATE or SHARED like any other variables.
1459 1.1 mrg So the expression should remain evaluable in the subfunction. We can
1460 1.1 mrg also pull it into a local variable if we like, but since its supposed
1461 1.1 mrg to remain unchanged, we can also not if we like.
1462 1.1 mrg
1463 1.1 mrg If we have SCHEDULE(STATIC), and no ORDERED, then we ought to be
1464 1.1 mrg able to get away with no work-sharing context at all, since we can
1465 1.1 mrg simply perform the arithmetic directly in each thread to divide up the
1466 1.1 mrg iterations. Which would mean that we wouldn't need to call any of
1467 1.1 mrg these routines.
1468 1.1 mrg
1469 1.1 mrg There are separate routines for handling loops with an ORDERED
1470 1.1 mrg clause. Bookkeeping for that is non-trivial...
1471 1.1 mrg
1472 1.1 mrg
1473 1.1 mrg File: libgomp.info, Node: Implementing ORDERED construct, Next: Implementing SECTIONS construct, Prev: Implementing FOR construct, Up: The libgomp ABI
1474 1.1 mrg
1475 1.1 mrg 4.12 Implementing ORDERED construct
1476 1.1 mrg ===================================
1477 1.1 mrg
1478 1.1 mrg void GOMP_ordered_start (void)
1479 1.1 mrg void GOMP_ordered_end (void)
1480 1.1 mrg
1481 1.1 mrg
1482 1.1 mrg File: libgomp.info, Node: Implementing SECTIONS construct, Next: Implementing SINGLE construct, Prev: Implementing ORDERED construct, Up: The libgomp ABI
1483 1.1 mrg
1484 1.1 mrg 4.13 Implementing SECTIONS construct
1485 1.1 mrg ====================================
1486 1.1 mrg
1487 1.1 mrg A block as
1488 1.1 mrg
1489 1.1 mrg #pragma omp sections
1490 1.1 mrg {
1491 1.1 mrg #pragma omp section
1492 1.1 mrg stmt1;
1493 1.1 mrg #pragma omp section
1494 1.1 mrg stmt2;
1495 1.1 mrg #pragma omp section
1496 1.1 mrg stmt3;
1497 1.1 mrg }
1498 1.1 mrg
1499 1.1 mrg becomes
1500 1.1 mrg
1501 1.1 mrg for (i = GOMP_sections_start (3); i != 0; i = GOMP_sections_next ())
1502 1.1 mrg switch (i)
1503 1.1 mrg {
1504 1.1 mrg case 1:
1505 1.1 mrg stmt1;
1506 1.1 mrg break;
1507 1.1 mrg case 2:
1508 1.1 mrg stmt2;
1509 1.1 mrg break;
1510 1.1 mrg case 3:
1511 1.1 mrg stmt3;
1512 1.1 mrg break;
1513 1.1 mrg }
1514 1.1 mrg GOMP_barrier ();
1515 1.1 mrg
1516 1.1 mrg
1517 1.1 mrg File: libgomp.info, Node: Implementing SINGLE construct, Prev: Implementing SECTIONS construct, Up: The libgomp ABI
1518 1.1 mrg
1519 1.1 mrg 4.14 Implementing SINGLE construct
1520 1.1 mrg ==================================
1521 1.1 mrg
1522 1.1 mrg A block like
1523 1.1 mrg
1524 1.1 mrg #pragma omp single
1525 1.1 mrg {
1526 1.1 mrg body;
1527 1.1 mrg }
1528 1.1 mrg
1529 1.1 mrg becomes
1530 1.1 mrg
1531 1.1 mrg if (GOMP_single_start ())
1532 1.1 mrg body;
1533 1.1 mrg GOMP_barrier ();
1534 1.1 mrg
1535 1.1 mrg while
1536 1.1 mrg
1537 1.1 mrg #pragma omp single copyprivate(x)
1538 1.1 mrg body;
1539 1.1 mrg
1540 1.1 mrg becomes
1541 1.1 mrg
1542 1.1 mrg datap = GOMP_single_copy_start ();
1543 1.1 mrg if (datap == NULL)
1544 1.1 mrg {
1545 1.1 mrg body;
1546 1.1 mrg data.x = x;
1547 1.1 mrg GOMP_single_copy_end (&data);
1548 1.1 mrg }
1549 1.1 mrg else
1550 1.1 mrg x = datap->x;
1551 1.1 mrg GOMP_barrier ();
1552 1.1 mrg
1553 1.1 mrg
1554 1.1 mrg File: libgomp.info, Node: Reporting Bugs, Next: Copying, Prev: The libgomp ABI, Up: Top
1555 1.1 mrg
1556 1.1 mrg 5 Reporting Bugs
1557 1.1 mrg ****************
1558 1.1 mrg
1559 1.1 mrg Bugs in the GNU OpenMP implementation should be reported via bugzilla
1560 1.1.1.2 mrg (http://gcc.gnu.org/bugzilla/). For all cases, please add "openmp" to
1561 1.1 mrg the keywords field in the bug report.
1562 1.1 mrg
1563 1.1 mrg
1564 1.1 mrg File: libgomp.info, Node: Copying, Next: GNU Free Documentation License, Prev: Reporting Bugs, Up: Top
1565 1.1 mrg
1566 1.1.1.2 mrg GNU General Public License
1567 1.1 mrg **************************
1568 1.1 mrg
1569 1.1.1.2 mrg Version 3, 29 June 2007
1570 1.1 mrg
1571 1.1.1.2 mrg Copyright (C) 2007 Free Software Foundation, Inc. `http://fsf.org/'
1572 1.1 mrg
1573 1.1.1.2 mrg Everyone is permitted to copy and distribute verbatim copies of this
1574 1.1.1.2 mrg license document, but changing it is not allowed.
1575 1.1 mrg
1576 1.1 mrg Preamble
1577 1.1 mrg ========
1578 1.1 mrg
1579 1.1.1.2 mrg The GNU General Public License is a free, copyleft license for software
1580 1.1.1.2 mrg and other kinds of works.
1581 1.1.1.2 mrg
1582 1.1.1.2 mrg The licenses for most software and other practical works are designed
1583 1.1.1.2 mrg to take away your freedom to share and change the works. By contrast,
1584 1.1.1.2 mrg the GNU General Public License is intended to guarantee your freedom to
1585 1.1.1.2 mrg share and change all versions of a program-to make sure it remains free
1586 1.1.1.2 mrg software for all its users. We, the Free Software Foundation, use the
1587 1.1.1.2 mrg GNU General Public License for most of our software; it applies also to
1588 1.1.1.2 mrg any other work released this way by its authors. You can apply it to
1589 1.1 mrg your programs, too.
1590 1.1 mrg
1591 1.1 mrg When we speak of free software, we are referring to freedom, not
1592 1.1 mrg price. Our General Public Licenses are designed to make sure that you
1593 1.1 mrg have the freedom to distribute copies of free software (and charge for
1594 1.1.1.2 mrg them if you wish), that you receive source code or can get it if you
1595 1.1.1.2 mrg want it, that you can change the software or use pieces of it in new
1596 1.1.1.2 mrg free programs, and that you know you can do these things.
1597 1.1.1.2 mrg
1598 1.1.1.2 mrg To protect your rights, we need to prevent others from denying you
1599 1.1.1.2 mrg these rights or asking you to surrender the rights. Therefore, you
1600 1.1.1.2 mrg have certain responsibilities if you distribute copies of the software,
1601 1.1.1.2 mrg or if you modify it: responsibilities to respect the freedom of others.
1602 1.1 mrg
1603 1.1 mrg For example, if you distribute copies of such a program, whether
1604 1.1.1.2 mrg gratis or for a fee, you must pass on to the recipients the same
1605 1.1.1.2 mrg freedoms that you received. You must make sure that they, too, receive
1606 1.1.1.2 mrg or can get the source code. And you must show them these terms so they
1607 1.1.1.2 mrg know their rights.
1608 1.1.1.2 mrg
1609 1.1.1.2 mrg Developers that use the GNU GPL protect your rights with two steps:
1610 1.1.1.2 mrg (1) assert copyright on the software, and (2) offer you this License
1611 1.1.1.2 mrg giving you legal permission to copy, distribute and/or modify it.
1612 1.1.1.2 mrg
1613 1.1.1.2 mrg For the developers' and authors' protection, the GPL clearly explains
1614 1.1.1.2 mrg that there is no warranty for this free software. For both users' and
1615 1.1.1.2 mrg authors' sake, the GPL requires that modified versions be marked as
1616 1.1.1.2 mrg changed, so that their problems will not be attributed erroneously to
1617 1.1.1.2 mrg authors of previous versions.
1618 1.1.1.2 mrg
1619 1.1.1.2 mrg Some devices are designed to deny users access to install or run
1620 1.1.1.2 mrg modified versions of the software inside them, although the
1621 1.1.1.2 mrg manufacturer can do so. This is fundamentally incompatible with the
1622 1.1.1.2 mrg aim of protecting users' freedom to change the software. The
1623 1.1.1.2 mrg systematic pattern of such abuse occurs in the area of products for
1624 1.1.1.2 mrg individuals to use, which is precisely where it is most unacceptable.
1625 1.1.1.2 mrg Therefore, we have designed this version of the GPL to prohibit the
1626 1.1.1.2 mrg practice for those products. If such problems arise substantially in
1627 1.1.1.2 mrg other domains, we stand ready to extend this provision to those domains
1628 1.1.1.2 mrg in future versions of the GPL, as needed to protect the freedom of
1629 1.1.1.2 mrg users.
1630 1.1.1.2 mrg
1631 1.1.1.2 mrg Finally, every program is threatened constantly by software patents.
1632 1.1.1.2 mrg States should not allow patents to restrict development and use of
1633 1.1.1.2 mrg software on general-purpose computers, but in those that do, we wish to
1634 1.1.1.2 mrg avoid the special danger that patents applied to a free program could
1635 1.1.1.2 mrg make it effectively proprietary. To prevent this, the GPL assures that
1636 1.1.1.2 mrg patents cannot be used to render the program non-free.
1637 1.1 mrg
1638 1.1 mrg The precise terms and conditions for copying, distribution and
1639 1.1 mrg modification follow.
1640 1.1 mrg
1641 1.1.1.2 mrg TERMS AND CONDITIONS
1642 1.1.1.2 mrg ====================
1643 1.1 mrg
1644 1.1.1.2 mrg 0. Definitions.
1645 1.1.1.2 mrg
1646 1.1.1.2 mrg "This License" refers to version 3 of the GNU General Public
1647 1.1.1.2 mrg License.
1648 1.1.1.2 mrg
1649 1.1.1.2 mrg "Copyright" also means copyright-like laws that apply to other
1650 1.1.1.2 mrg kinds of works, such as semiconductor masks.
1651 1.1.1.2 mrg
1652 1.1.1.2 mrg "The Program" refers to any copyrightable work licensed under this
1653 1.1.1.2 mrg License. Each licensee is addressed as "you". "Licensees" and
1654 1.1.1.2 mrg "recipients" may be individuals or organizations.
1655 1.1.1.2 mrg
1656 1.1.1.2 mrg To "modify" a work means to copy from or adapt all or part of the
1657 1.1.1.2 mrg work in a fashion requiring copyright permission, other than the
1658 1.1.1.2 mrg making of an exact copy. The resulting work is called a "modified
1659 1.1.1.2 mrg version" of the earlier work or a work "based on" the earlier work.
1660 1.1.1.2 mrg
1661 1.1.1.2 mrg A "covered work" means either the unmodified Program or a work
1662 1.1.1.2 mrg based on the Program.
1663 1.1.1.2 mrg
1664 1.1.1.2 mrg To "propagate" a work means to do anything with it that, without
1665 1.1.1.2 mrg permission, would make you directly or secondarily liable for
1666 1.1.1.2 mrg infringement under applicable copyright law, except executing it
1667 1.1.1.2 mrg on a computer or modifying a private copy. Propagation includes
1668 1.1.1.2 mrg copying, distribution (with or without modification), making
1669 1.1.1.2 mrg available to the public, and in some countries other activities as
1670 1.1.1.2 mrg well.
1671 1.1.1.2 mrg
1672 1.1.1.2 mrg To "convey" a work means any kind of propagation that enables other
1673 1.1.1.2 mrg parties to make or receive copies. Mere interaction with a user
1674 1.1.1.2 mrg through a computer network, with no transfer of a copy, is not
1675 1.1.1.2 mrg conveying.
1676 1.1.1.2 mrg
1677 1.1.1.2 mrg An interactive user interface displays "Appropriate Legal Notices"
1678 1.1.1.2 mrg to the extent that it includes a convenient and prominently visible
1679 1.1.1.2 mrg feature that (1) displays an appropriate copyright notice, and (2)
1680 1.1.1.2 mrg tells the user that there is no warranty for the work (except to
1681 1.1.1.2 mrg the extent that warranties are provided), that licensees may
1682 1.1.1.2 mrg convey the work under this License, and how to view a copy of this
1683 1.1.1.2 mrg License. If the interface presents a list of user commands or
1684 1.1.1.2 mrg options, such as a menu, a prominent item in the list meets this
1685 1.1.1.2 mrg criterion.
1686 1.1.1.2 mrg
1687 1.1.1.2 mrg 1. Source Code.
1688 1.1.1.2 mrg
1689 1.1.1.2 mrg The "source code" for a work means the preferred form of the work
1690 1.1.1.2 mrg for making modifications to it. "Object code" means any
1691 1.1.1.2 mrg non-source form of a work.
1692 1.1.1.2 mrg
1693 1.1.1.2 mrg A "Standard Interface" means an interface that either is an
1694 1.1.1.2 mrg official standard defined by a recognized standards body, or, in
1695 1.1.1.2 mrg the case of interfaces specified for a particular programming
1696 1.1.1.2 mrg language, one that is widely used among developers working in that
1697 1.1.1.2 mrg language.
1698 1.1.1.2 mrg
1699 1.1.1.2 mrg The "System Libraries" of an executable work include anything,
1700 1.1.1.2 mrg other than the work as a whole, that (a) is included in the normal
1701 1.1.1.2 mrg form of packaging a Major Component, but which is not part of that
1702 1.1.1.2 mrg Major Component, and (b) serves only to enable use of the work
1703 1.1.1.2 mrg with that Major Component, or to implement a Standard Interface
1704 1.1.1.2 mrg for which an implementation is available to the public in source
1705 1.1.1.2 mrg code form. A "Major Component", in this context, means a major
1706 1.1.1.2 mrg essential component (kernel, window system, and so on) of the
1707 1.1.1.2 mrg specific operating system (if any) on which the executable work
1708 1.1.1.2 mrg runs, or a compiler used to produce the work, or an object code
1709 1.1.1.2 mrg interpreter used to run it.
1710 1.1.1.2 mrg
1711 1.1.1.2 mrg The "Corresponding Source" for a work in object code form means all
1712 1.1.1.2 mrg the source code needed to generate, install, and (for an executable
1713 1.1.1.2 mrg work) run the object code and to modify the work, including
1714 1.1.1.2 mrg scripts to control those activities. However, it does not include
1715 1.1.1.2 mrg the work's System Libraries, or general-purpose tools or generally
1716 1.1.1.2 mrg available free programs which are used unmodified in performing
1717 1.1.1.2 mrg those activities but which are not part of the work. For example,
1718 1.1.1.2 mrg Corresponding Source includes interface definition files
1719 1.1.1.2 mrg associated with source files for the work, and the source code for
1720 1.1.1.2 mrg shared libraries and dynamically linked subprograms that the work
1721 1.1.1.2 mrg is specifically designed to require, such as by intimate data
1722 1.1.1.2 mrg communication or control flow between those subprograms and other
1723 1.1.1.2 mrg parts of the work.
1724 1.1.1.2 mrg
1725 1.1.1.2 mrg The Corresponding Source need not include anything that users can
1726 1.1.1.2 mrg regenerate automatically from other parts of the Corresponding
1727 1.1.1.2 mrg Source.
1728 1.1.1.2 mrg
1729 1.1.1.2 mrg The Corresponding Source for a work in source code form is that
1730 1.1.1.2 mrg same work.
1731 1.1.1.2 mrg
1732 1.1.1.2 mrg 2. Basic Permissions.
1733 1.1.1.2 mrg
1734 1.1.1.2 mrg All rights granted under this License are granted for the term of
1735 1.1.1.2 mrg copyright on the Program, and are irrevocable provided the stated
1736 1.1.1.2 mrg conditions are met. This License explicitly affirms your unlimited
1737 1.1.1.2 mrg permission to run the unmodified Program. The output from running
1738 1.1.1.2 mrg a covered work is covered by this License only if the output,
1739 1.1.1.2 mrg given its content, constitutes a covered work. This License
1740 1.1.1.2 mrg acknowledges your rights of fair use or other equivalent, as
1741 1.1.1.2 mrg provided by copyright law.
1742 1.1.1.2 mrg
1743 1.1.1.2 mrg You may make, run and propagate covered works that you do not
1744 1.1.1.2 mrg convey, without conditions so long as your license otherwise
1745 1.1.1.2 mrg remains in force. You may convey covered works to others for the
1746 1.1.1.2 mrg sole purpose of having them make modifications exclusively for
1747 1.1.1.2 mrg you, or provide you with facilities for running those works,
1748 1.1.1.2 mrg provided that you comply with the terms of this License in
1749 1.1.1.2 mrg conveying all material for which you do not control copyright.
1750 1.1.1.2 mrg Those thus making or running the covered works for you must do so
1751 1.1.1.2 mrg exclusively on your behalf, under your direction and control, on
1752 1.1.1.2 mrg terms that prohibit them from making any copies of your
1753 1.1.1.2 mrg copyrighted material outside their relationship with you.
1754 1.1.1.2 mrg
1755 1.1.1.2 mrg Conveying under any other circumstances is permitted solely under
1756 1.1.1.2 mrg the conditions stated below. Sublicensing is not allowed; section
1757 1.1.1.2 mrg 10 makes it unnecessary.
1758 1.1.1.2 mrg
1759 1.1.1.2 mrg 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
1760 1.1.1.2 mrg
1761 1.1.1.2 mrg No covered work shall be deemed part of an effective technological
1762 1.1.1.2 mrg measure under any applicable law fulfilling obligations under
1763 1.1.1.2 mrg article 11 of the WIPO copyright treaty adopted on 20 December
1764 1.1.1.2 mrg 1996, or similar laws prohibiting or restricting circumvention of
1765 1.1.1.2 mrg such measures.
1766 1.1.1.2 mrg
1767 1.1.1.2 mrg When you convey a covered work, you waive any legal power to forbid
1768 1.1.1.2 mrg circumvention of technological measures to the extent such
1769 1.1.1.2 mrg circumvention is effected by exercising rights under this License
1770 1.1.1.2 mrg with respect to the covered work, and you disclaim any intention
1771 1.1.1.2 mrg to limit operation or modification of the work as a means of
1772 1.1.1.2 mrg enforcing, against the work's users, your or third parties' legal
1773 1.1.1.2 mrg rights to forbid circumvention of technological measures.
1774 1.1.1.2 mrg
1775 1.1.1.2 mrg 4. Conveying Verbatim Copies.
1776 1.1.1.2 mrg
1777 1.1.1.2 mrg You may convey verbatim copies of the Program's source code as you
1778 1.1.1.2 mrg receive it, in any medium, provided that you conspicuously and
1779 1.1.1.2 mrg appropriately publish on each copy an appropriate copyright notice;
1780 1.1.1.2 mrg keep intact all notices stating that this License and any
1781 1.1.1.2 mrg non-permissive terms added in accord with section 7 apply to the
1782 1.1.1.2 mrg code; keep intact all notices of the absence of any warranty; and
1783 1.1.1.2 mrg give all recipients a copy of this License along with the Program.
1784 1.1.1.2 mrg
1785 1.1.1.2 mrg You may charge any price or no price for each copy that you convey,
1786 1.1.1.2 mrg and you may offer support or warranty protection for a fee.
1787 1.1.1.2 mrg
1788 1.1.1.2 mrg 5. Conveying Modified Source Versions.
1789 1.1.1.2 mrg
1790 1.1.1.2 mrg You may convey a work based on the Program, or the modifications to
1791 1.1.1.2 mrg produce it from the Program, in the form of source code under the
1792 1.1.1.2 mrg terms of section 4, provided that you also meet all of these
1793 1.1.1.2 mrg conditions:
1794 1.1.1.2 mrg
1795 1.1.1.2 mrg a. The work must carry prominent notices stating that you
1796 1.1.1.2 mrg modified it, and giving a relevant date.
1797 1.1.1.2 mrg
1798 1.1.1.2 mrg b. The work must carry prominent notices stating that it is
1799 1.1.1.2 mrg released under this License and any conditions added under
1800 1.1.1.2 mrg section 7. This requirement modifies the requirement in
1801 1.1.1.2 mrg section 4 to "keep intact all notices".
1802 1.1.1.2 mrg
1803 1.1.1.2 mrg c. You must license the entire work, as a whole, under this
1804 1.1.1.2 mrg License to anyone who comes into possession of a copy. This
1805 1.1.1.2 mrg License will therefore apply, along with any applicable
1806 1.1.1.2 mrg section 7 additional terms, to the whole of the work, and all
1807 1.1.1.2 mrg its parts, regardless of how they are packaged. This License
1808 1.1.1.2 mrg gives no permission to license the work in any other way, but
1809 1.1.1.2 mrg it does not invalidate such permission if you have separately
1810 1.1.1.2 mrg received it.
1811 1.1.1.2 mrg
1812 1.1.1.2 mrg d. If the work has interactive user interfaces, each must display
1813 1.1.1.2 mrg Appropriate Legal Notices; however, if the Program has
1814 1.1.1.2 mrg interactive interfaces that do not display Appropriate Legal
1815 1.1.1.2 mrg Notices, your work need not make them do so.
1816 1.1.1.2 mrg
1817 1.1.1.2 mrg A compilation of a covered work with other separate and independent
1818 1.1.1.2 mrg works, which are not by their nature extensions of the covered
1819 1.1.1.2 mrg work, and which are not combined with it such as to form a larger
1820 1.1.1.2 mrg program, in or on a volume of a storage or distribution medium, is
1821 1.1.1.2 mrg called an "aggregate" if the compilation and its resulting
1822 1.1.1.2 mrg copyright are not used to limit the access or legal rights of the
1823 1.1.1.2 mrg compilation's users beyond what the individual works permit.
1824 1.1.1.2 mrg Inclusion of a covered work in an aggregate does not cause this
1825 1.1.1.2 mrg License to apply to the other parts of the aggregate.
1826 1.1.1.2 mrg
1827 1.1.1.2 mrg 6. Conveying Non-Source Forms.
1828 1.1.1.2 mrg
1829 1.1.1.2 mrg You may convey a covered work in object code form under the terms
1830 1.1.1.2 mrg of sections 4 and 5, provided that you also convey the
1831 1.1.1.2 mrg machine-readable Corresponding Source under the terms of this
1832 1.1.1.2 mrg License, in one of these ways:
1833 1.1.1.2 mrg
1834 1.1.1.2 mrg a. Convey the object code in, or embodied in, a physical product
1835 1.1.1.2 mrg (including a physical distribution medium), accompanied by the
1836 1.1.1.2 mrg Corresponding Source fixed on a durable physical medium
1837 1.1.1.2 mrg customarily used for software interchange.
1838 1.1.1.2 mrg
1839 1.1.1.2 mrg b. Convey the object code in, or embodied in, a physical product
1840 1.1.1.2 mrg (including a physical distribution medium), accompanied by a
1841 1.1.1.2 mrg written offer, valid for at least three years and valid for
1842 1.1.1.2 mrg as long as you offer spare parts or customer support for that
1843 1.1.1.2 mrg product model, to give anyone who possesses the object code
1844 1.1.1.2 mrg either (1) a copy of the Corresponding Source for all the
1845 1.1.1.2 mrg software in the product that is covered by this License, on a
1846 1.1.1.2 mrg durable physical medium customarily used for software
1847 1.1.1.2 mrg interchange, for a price no more than your reasonable cost of
1848 1.1.1.2 mrg physically performing this conveying of source, or (2) access
1849 1.1.1.2 mrg to copy the Corresponding Source from a network server at no
1850 1.1.1.2 mrg charge.
1851 1.1.1.2 mrg
1852 1.1.1.2 mrg c. Convey individual copies of the object code with a copy of
1853 1.1.1.2 mrg the written offer to provide the Corresponding Source. This
1854 1.1.1.2 mrg alternative is allowed only occasionally and noncommercially,
1855 1.1.1.2 mrg and only if you received the object code with such an offer,
1856 1.1.1.2 mrg in accord with subsection 6b.
1857 1.1.1.2 mrg
1858 1.1.1.2 mrg d. Convey the object code by offering access from a designated
1859 1.1.1.2 mrg place (gratis or for a charge), and offer equivalent access
1860 1.1.1.2 mrg to the Corresponding Source in the same way through the same
1861 1.1.1.2 mrg place at no further charge. You need not require recipients
1862 1.1.1.2 mrg to copy the Corresponding Source along with the object code.
1863 1.1.1.2 mrg If the place to copy the object code is a network server, the
1864 1.1.1.2 mrg Corresponding Source may be on a different server (operated
1865 1.1.1.2 mrg by you or a third party) that supports equivalent copying
1866 1.1.1.2 mrg facilities, provided you maintain clear directions next to
1867 1.1.1.2 mrg the object code saying where to find the Corresponding Source.
1868 1.1.1.2 mrg Regardless of what server hosts the Corresponding Source, you
1869 1.1.1.2 mrg remain obligated to ensure that it is available for as long
1870 1.1.1.2 mrg as needed to satisfy these requirements.
1871 1.1.1.2 mrg
1872 1.1.1.2 mrg e. Convey the object code using peer-to-peer transmission,
1873 1.1.1.2 mrg provided you inform other peers where the object code and
1874 1.1.1.2 mrg Corresponding Source of the work are being offered to the
1875 1.1.1.2 mrg general public at no charge under subsection 6d.
1876 1.1.1.2 mrg
1877 1.1.1.2 mrg
1878 1.1.1.2 mrg A separable portion of the object code, whose source code is
1879 1.1.1.2 mrg excluded from the Corresponding Source as a System Library, need
1880 1.1.1.2 mrg not be included in conveying the object code work.
1881 1.1.1.2 mrg
1882 1.1.1.2 mrg A "User Product" is either (1) a "consumer product", which means
1883 1.1.1.2 mrg any tangible personal property which is normally used for personal,
1884 1.1.1.2 mrg family, or household purposes, or (2) anything designed or sold for
1885 1.1.1.2 mrg incorporation into a dwelling. In determining whether a product
1886 1.1.1.2 mrg is a consumer product, doubtful cases shall be resolved in favor of
1887 1.1.1.2 mrg coverage. For a particular product received by a particular user,
1888 1.1.1.2 mrg "normally used" refers to a typical or common use of that class of
1889 1.1.1.2 mrg product, regardless of the status of the particular user or of the
1890 1.1.1.2 mrg way in which the particular user actually uses, or expects or is
1891 1.1.1.2 mrg expected to use, the product. A product is a consumer product
1892 1.1.1.2 mrg regardless of whether the product has substantial commercial,
1893 1.1.1.2 mrg industrial or non-consumer uses, unless such uses represent the
1894 1.1.1.2 mrg only significant mode of use of the product.
1895 1.1.1.2 mrg
1896 1.1.1.2 mrg "Installation Information" for a User Product means any methods,
1897 1.1.1.2 mrg procedures, authorization keys, or other information required to
1898 1.1.1.2 mrg install and execute modified versions of a covered work in that
1899 1.1.1.2 mrg User Product from a modified version of its Corresponding Source.
1900 1.1.1.2 mrg The information must suffice to ensure that the continued
1901 1.1.1.2 mrg functioning of the modified object code is in no case prevented or
1902 1.1.1.2 mrg interfered with solely because modification has been made.
1903 1.1.1.2 mrg
1904 1.1.1.2 mrg If you convey an object code work under this section in, or with,
1905 1.1.1.2 mrg or specifically for use in, a User Product, and the conveying
1906 1.1.1.2 mrg occurs as part of a transaction in which the right of possession
1907 1.1.1.2 mrg and use of the User Product is transferred to the recipient in
1908 1.1.1.2 mrg perpetuity or for a fixed term (regardless of how the transaction
1909 1.1.1.2 mrg is characterized), the Corresponding Source conveyed under this
1910 1.1.1.2 mrg section must be accompanied by the Installation Information. But
1911 1.1.1.2 mrg this requirement does not apply if neither you nor any third party
1912 1.1.1.2 mrg retains the ability to install modified object code on the User
1913 1.1.1.2 mrg Product (for example, the work has been installed in ROM).
1914 1.1.1.2 mrg
1915 1.1.1.2 mrg The requirement to provide Installation Information does not
1916 1.1.1.2 mrg include a requirement to continue to provide support service,
1917 1.1.1.2 mrg warranty, or updates for a work that has been modified or
1918 1.1.1.2 mrg installed by the recipient, or for the User Product in which it
1919 1.1.1.2 mrg has been modified or installed. Access to a network may be denied
1920 1.1.1.2 mrg when the modification itself materially and adversely affects the
1921 1.1.1.2 mrg operation of the network or violates the rules and protocols for
1922 1.1.1.2 mrg communication across the network.
1923 1.1.1.2 mrg
1924 1.1.1.2 mrg Corresponding Source conveyed, and Installation Information
1925 1.1.1.2 mrg provided, in accord with this section must be in a format that is
1926 1.1.1.2 mrg publicly documented (and with an implementation available to the
1927 1.1.1.2 mrg public in source code form), and must require no special password
1928 1.1.1.2 mrg or key for unpacking, reading or copying.
1929 1.1.1.2 mrg
1930 1.1.1.2 mrg 7. Additional Terms.
1931 1.1.1.2 mrg
1932 1.1.1.2 mrg "Additional permissions" are terms that supplement the terms of
1933 1.1.1.2 mrg this License by making exceptions from one or more of its
1934 1.1.1.2 mrg conditions. Additional permissions that are applicable to the
1935 1.1.1.2 mrg entire Program shall be treated as though they were included in
1936 1.1.1.2 mrg this License, to the extent that they are valid under applicable
1937 1.1.1.2 mrg law. If additional permissions apply only to part of the Program,
1938 1.1.1.2 mrg that part may be used separately under those permissions, but the
1939 1.1.1.2 mrg entire Program remains governed by this License without regard to
1940 1.1.1.2 mrg the additional permissions.
1941 1.1.1.2 mrg
1942 1.1.1.2 mrg When you convey a copy of a covered work, you may at your option
1943 1.1.1.2 mrg remove any additional permissions from that copy, or from any part
1944 1.1.1.2 mrg of it. (Additional permissions may be written to require their own
1945 1.1.1.2 mrg removal in certain cases when you modify the work.) You may place
1946 1.1.1.2 mrg additional permissions on material, added by you to a covered work,
1947 1.1.1.2 mrg for which you have or can give appropriate copyright permission.
1948 1.1.1.2 mrg
1949 1.1.1.2 mrg Notwithstanding any other provision of this License, for material
1950 1.1.1.2 mrg you add to a covered work, you may (if authorized by the copyright
1951 1.1.1.2 mrg holders of that material) supplement the terms of this License
1952 1.1.1.2 mrg with terms:
1953 1.1.1.2 mrg
1954 1.1.1.2 mrg a. Disclaiming warranty or limiting liability differently from
1955 1.1.1.2 mrg the terms of sections 15 and 16 of this License; or
1956 1.1.1.2 mrg
1957 1.1.1.2 mrg b. Requiring preservation of specified reasonable legal notices
1958 1.1.1.2 mrg or author attributions in that material or in the Appropriate
1959 1.1.1.2 mrg Legal Notices displayed by works containing it; or
1960 1.1.1.2 mrg
1961 1.1.1.2 mrg c. Prohibiting misrepresentation of the origin of that material,
1962 1.1.1.2 mrg or requiring that modified versions of such material be
1963 1.1.1.2 mrg marked in reasonable ways as different from the original
1964 1.1.1.2 mrg version; or
1965 1.1.1.2 mrg
1966 1.1.1.2 mrg d. Limiting the use for publicity purposes of names of licensors
1967 1.1.1.2 mrg or authors of the material; or
1968 1.1.1.2 mrg
1969 1.1.1.2 mrg e. Declining to grant rights under trademark law for use of some
1970 1.1.1.2 mrg trade names, trademarks, or service marks; or
1971 1.1.1.2 mrg
1972 1.1.1.2 mrg f. Requiring indemnification of licensors and authors of that
1973 1.1.1.2 mrg material by anyone who conveys the material (or modified
1974 1.1.1.2 mrg versions of it) with contractual assumptions of liability to
1975 1.1.1.2 mrg the recipient, for any liability that these contractual
1976 1.1.1.2 mrg assumptions directly impose on those licensors and authors.
1977 1.1.1.2 mrg
1978 1.1.1.2 mrg All other non-permissive additional terms are considered "further
1979 1.1.1.2 mrg restrictions" within the meaning of section 10. If the Program as
1980 1.1.1.2 mrg you received it, or any part of it, contains a notice stating that
1981 1.1.1.2 mrg it is governed by this License along with a term that is a further
1982 1.1.1.2 mrg restriction, you may remove that term. If a license document
1983 1.1.1.2 mrg contains a further restriction but permits relicensing or
1984 1.1.1.2 mrg conveying under this License, you may add to a covered work
1985 1.1.1.2 mrg material governed by the terms of that license document, provided
1986 1.1.1.2 mrg that the further restriction does not survive such relicensing or
1987 1.1.1.2 mrg conveying.
1988 1.1.1.2 mrg
1989 1.1.1.2 mrg If you add terms to a covered work in accord with this section, you
1990 1.1.1.2 mrg must place, in the relevant source files, a statement of the
1991 1.1.1.2 mrg additional terms that apply to those files, or a notice indicating
1992 1.1.1.2 mrg where to find the applicable terms.
1993 1.1.1.2 mrg
1994 1.1.1.2 mrg Additional terms, permissive or non-permissive, may be stated in
1995 1.1.1.2 mrg the form of a separately written license, or stated as exceptions;
1996 1.1.1.2 mrg the above requirements apply either way.
1997 1.1.1.2 mrg
1998 1.1.1.2 mrg 8. Termination.
1999 1.1.1.2 mrg
2000 1.1.1.2 mrg You may not propagate or modify a covered work except as expressly
2001 1.1.1.2 mrg provided under this License. Any attempt otherwise to propagate or
2002 1.1.1.2 mrg modify it is void, and will automatically terminate your rights
2003 1.1.1.2 mrg under this License (including any patent licenses granted under
2004 1.1.1.2 mrg the third paragraph of section 11).
2005 1.1.1.2 mrg
2006 1.1.1.2 mrg However, if you cease all violation of this License, then your
2007 1.1.1.2 mrg license from a particular copyright holder is reinstated (a)
2008 1.1.1.2 mrg provisionally, unless and until the copyright holder explicitly
2009 1.1.1.2 mrg and finally terminates your license, and (b) permanently, if the
2010 1.1.1.2 mrg copyright holder fails to notify you of the violation by some
2011 1.1.1.2 mrg reasonable means prior to 60 days after the cessation.
2012 1.1.1.2 mrg
2013 1.1.1.2 mrg Moreover, your license from a particular copyright holder is
2014 1.1.1.2 mrg reinstated permanently if the copyright holder notifies you of the
2015 1.1.1.2 mrg violation by some reasonable means, this is the first time you have
2016 1.1.1.2 mrg received notice of violation of this License (for any work) from
2017 1.1.1.2 mrg that copyright holder, and you cure the violation prior to 30 days
2018 1.1.1.2 mrg after your receipt of the notice.
2019 1.1.1.2 mrg
2020 1.1.1.2 mrg Termination of your rights under this section does not terminate
2021 1.1.1.2 mrg the licenses of parties who have received copies or rights from
2022 1.1.1.2 mrg you under this License. If your rights have been terminated and
2023 1.1.1.2 mrg not permanently reinstated, you do not qualify to receive new
2024 1.1.1.2 mrg licenses for the same material under section 10.
2025 1.1.1.2 mrg
2026 1.1.1.2 mrg 9. Acceptance Not Required for Having Copies.
2027 1.1.1.2 mrg
2028 1.1.1.2 mrg You are not required to accept this License in order to receive or
2029 1.1.1.2 mrg run a copy of the Program. Ancillary propagation of a covered work
2030 1.1.1.2 mrg occurring solely as a consequence of using peer-to-peer
2031 1.1.1.2 mrg transmission to receive a copy likewise does not require
2032 1.1.1.2 mrg acceptance. However, nothing other than this License grants you
2033 1.1.1.2 mrg permission to propagate or modify any covered work. These actions
2034 1.1.1.2 mrg infringe copyright if you do not accept this License. Therefore,
2035 1.1.1.2 mrg by modifying or propagating a covered work, you indicate your
2036 1.1.1.2 mrg acceptance of this License to do so.
2037 1.1.1.2 mrg
2038 1.1.1.2 mrg 10. Automatic Licensing of Downstream Recipients.
2039 1.1.1.2 mrg
2040 1.1.1.2 mrg Each time you convey a covered work, the recipient automatically
2041 1.1.1.2 mrg receives a license from the original licensors, to run, modify and
2042 1.1.1.2 mrg propagate that work, subject to this License. You are not
2043 1.1.1.2 mrg responsible for enforcing compliance by third parties with this
2044 1.1.1.2 mrg License.
2045 1.1.1.2 mrg
2046 1.1.1.2 mrg An "entity transaction" is a transaction transferring control of an
2047 1.1.1.2 mrg organization, or substantially all assets of one, or subdividing an
2048 1.1.1.2 mrg organization, or merging organizations. If propagation of a
2049 1.1.1.2 mrg covered work results from an entity transaction, each party to that
2050 1.1.1.2 mrg transaction who receives a copy of the work also receives whatever
2051 1.1.1.2 mrg licenses to the work the party's predecessor in interest had or
2052 1.1.1.2 mrg could give under the previous paragraph, plus a right to
2053 1.1.1.2 mrg possession of the Corresponding Source of the work from the
2054 1.1.1.2 mrg predecessor in interest, if the predecessor has it or can get it
2055 1.1.1.2 mrg with reasonable efforts.
2056 1.1.1.2 mrg
2057 1.1.1.2 mrg You may not impose any further restrictions on the exercise of the
2058 1.1.1.2 mrg rights granted or affirmed under this License. For example, you
2059 1.1.1.2 mrg may not impose a license fee, royalty, or other charge for
2060 1.1.1.2 mrg exercise of rights granted under this License, and you may not
2061 1.1.1.2 mrg initiate litigation (including a cross-claim or counterclaim in a
2062 1.1.1.2 mrg lawsuit) alleging that any patent claim is infringed by making,
2063 1.1.1.2 mrg using, selling, offering for sale, or importing the Program or any
2064 1.1.1.2 mrg portion of it.
2065 1.1.1.2 mrg
2066 1.1.1.2 mrg 11. Patents.
2067 1.1.1.2 mrg
2068 1.1.1.2 mrg A "contributor" is a copyright holder who authorizes use under this
2069 1.1.1.2 mrg License of the Program or a work on which the Program is based.
2070 1.1.1.2 mrg The work thus licensed is called the contributor's "contributor
2071 1.1.1.2 mrg version".
2072 1.1.1.2 mrg
2073 1.1.1.2 mrg A contributor's "essential patent claims" are all patent claims
2074 1.1.1.2 mrg owned or controlled by the contributor, whether already acquired or
2075 1.1.1.2 mrg hereafter acquired, that would be infringed by some manner,
2076 1.1.1.2 mrg permitted by this License, of making, using, or selling its
2077 1.1.1.2 mrg contributor version, but do not include claims that would be
2078 1.1.1.2 mrg infringed only as a consequence of further modification of the
2079 1.1.1.2 mrg contributor version. For purposes of this definition, "control"
2080 1.1.1.2 mrg includes the right to grant patent sublicenses in a manner
2081 1.1.1.2 mrg consistent with the requirements of this License.
2082 1.1.1.2 mrg
2083 1.1.1.2 mrg Each contributor grants you a non-exclusive, worldwide,
2084 1.1.1.2 mrg royalty-free patent license under the contributor's essential
2085 1.1.1.2 mrg patent claims, to make, use, sell, offer for sale, import and
2086 1.1.1.2 mrg otherwise run, modify and propagate the contents of its
2087 1.1.1.2 mrg contributor version.
2088 1.1.1.2 mrg
2089 1.1.1.2 mrg In the following three paragraphs, a "patent license" is any
2090 1.1.1.2 mrg express agreement or commitment, however denominated, not to
2091 1.1.1.2 mrg enforce a patent (such as an express permission to practice a
2092 1.1.1.2 mrg patent or covenant not to sue for patent infringement). To
2093 1.1.1.2 mrg "grant" such a patent license to a party means to make such an
2094 1.1.1.2 mrg agreement or commitment not to enforce a patent against the party.
2095 1.1.1.2 mrg
2096 1.1.1.2 mrg If you convey a covered work, knowingly relying on a patent
2097 1.1.1.2 mrg license, and the Corresponding Source of the work is not available
2098 1.1.1.2 mrg for anyone to copy, free of charge and under the terms of this
2099 1.1.1.2 mrg License, through a publicly available network server or other
2100 1.1.1.2 mrg readily accessible means, then you must either (1) cause the
2101 1.1.1.2 mrg Corresponding Source to be so available, or (2) arrange to deprive
2102 1.1.1.2 mrg yourself of the benefit of the patent license for this particular
2103 1.1.1.2 mrg work, or (3) arrange, in a manner consistent with the requirements
2104 1.1.1.2 mrg of this License, to extend the patent license to downstream
2105 1.1.1.2 mrg recipients. "Knowingly relying" means you have actual knowledge
2106 1.1.1.2 mrg that, but for the patent license, your conveying the covered work
2107 1.1.1.2 mrg in a country, or your recipient's use of the covered work in a
2108 1.1.1.2 mrg country, would infringe one or more identifiable patents in that
2109 1.1.1.2 mrg country that you have reason to believe are valid.
2110 1.1.1.2 mrg
2111 1.1.1.2 mrg If, pursuant to or in connection with a single transaction or
2112 1.1.1.2 mrg arrangement, you convey, or propagate by procuring conveyance of, a
2113 1.1.1.2 mrg covered work, and grant a patent license to some of the parties
2114 1.1.1.2 mrg receiving the covered work authorizing them to use, propagate,
2115 1.1.1.2 mrg modify or convey a specific copy of the covered work, then the
2116 1.1.1.2 mrg patent license you grant is automatically extended to all
2117 1.1.1.2 mrg recipients of the covered work and works based on it.
2118 1.1.1.2 mrg
2119 1.1.1.2 mrg A patent license is "discriminatory" if it does not include within
2120 1.1.1.2 mrg the scope of its coverage, prohibits the exercise of, or is
2121 1.1.1.2 mrg conditioned on the non-exercise of one or more of the rights that
2122 1.1.1.2 mrg are specifically granted under this License. You may not convey a
2123 1.1.1.2 mrg covered work if you are a party to an arrangement with a third
2124 1.1.1.2 mrg party that is in the business of distributing software, under
2125 1.1.1.2 mrg which you make payment to the third party based on the extent of
2126 1.1.1.2 mrg your activity of conveying the work, and under which the third
2127 1.1.1.2 mrg party grants, to any of the parties who would receive the covered
2128 1.1.1.2 mrg work from you, a discriminatory patent license (a) in connection
2129 1.1.1.2 mrg with copies of the covered work conveyed by you (or copies made
2130 1.1.1.2 mrg from those copies), or (b) primarily for and in connection with
2131 1.1.1.2 mrg specific products or compilations that contain the covered work,
2132 1.1.1.2 mrg unless you entered into that arrangement, or that patent license
2133 1.1.1.2 mrg was granted, prior to 28 March 2007.
2134 1.1.1.2 mrg
2135 1.1.1.2 mrg Nothing in this License shall be construed as excluding or limiting
2136 1.1.1.2 mrg any implied license or other defenses to infringement that may
2137 1.1.1.2 mrg otherwise be available to you under applicable patent law.
2138 1.1.1.2 mrg
2139 1.1.1.2 mrg 12. No Surrender of Others' Freedom.
2140 1.1.1.2 mrg
2141 1.1.1.2 mrg If conditions are imposed on you (whether by court order,
2142 1.1 mrg agreement or otherwise) that contradict the conditions of this
2143 1.1 mrg License, they do not excuse you from the conditions of this
2144 1.1.1.2 mrg License. If you cannot convey a covered work so as to satisfy
2145 1.1.1.2 mrg simultaneously your obligations under this License and any other
2146 1.1.1.2 mrg pertinent obligations, then as a consequence you may not convey it
2147 1.1.1.2 mrg at all. For example, if you agree to terms that obligate you to
2148 1.1.1.2 mrg collect a royalty for further conveying from those to whom you
2149 1.1.1.2 mrg convey the Program, the only way you could satisfy both those
2150 1.1.1.2 mrg terms and this License would be to refrain entirely from conveying
2151 1.1.1.2 mrg the Program.
2152 1.1.1.2 mrg
2153 1.1.1.2 mrg 13. Use with the GNU Affero General Public License.
2154 1.1.1.2 mrg
2155 1.1.1.2 mrg Notwithstanding any other provision of this License, you have
2156 1.1.1.2 mrg permission to link or combine any covered work with a work licensed
2157 1.1.1.2 mrg under version 3 of the GNU Affero General Public License into a
2158 1.1.1.2 mrg single combined work, and to convey the resulting work. The terms
2159 1.1.1.2 mrg of this License will continue to apply to the part which is the
2160 1.1.1.2 mrg covered work, but the special requirements of the GNU Affero
2161 1.1.1.2 mrg General Public License, section 13, concerning interaction through
2162 1.1.1.2 mrg a network will apply to the combination as such.
2163 1.1.1.2 mrg
2164 1.1.1.2 mrg 14. Revised Versions of this License.
2165 1.1.1.2 mrg
2166 1.1.1.2 mrg The Free Software Foundation may publish revised and/or new
2167 1.1.1.2 mrg versions of the GNU General Public License from time to time.
2168 1.1.1.2 mrg Such new versions will be similar in spirit to the present
2169 1.1.1.2 mrg version, but may differ in detail to address new problems or
2170 1.1.1.2 mrg concerns.
2171 1.1 mrg
2172 1.1 mrg Each version is given a distinguishing version number. If the
2173 1.1.1.2 mrg Program specifies that a certain numbered version of the GNU
2174 1.1.1.2 mrg General Public License "or any later version" applies to it, you
2175 1.1.1.2 mrg have the option of following the terms and conditions either of
2176 1.1.1.2 mrg that numbered version or of any later version published by the
2177 1.1.1.2 mrg Free Software Foundation. If the Program does not specify a
2178 1.1.1.2 mrg version number of the GNU General Public License, you may choose
2179 1.1 mrg any version ever published by the Free Software Foundation.
2180 1.1 mrg
2181 1.1.1.2 mrg If the Program specifies that a proxy can decide which future
2182 1.1.1.2 mrg versions of the GNU General Public License can be used, that
2183 1.1.1.2 mrg proxy's public statement of acceptance of a version permanently
2184 1.1.1.2 mrg authorizes you to choose that version for the Program.
2185 1.1.1.2 mrg
2186 1.1.1.2 mrg Later license versions may give you additional or different
2187 1.1.1.2 mrg permissions. However, no additional obligations are imposed on any
2188 1.1.1.2 mrg author or copyright holder as a result of your choosing to follow a
2189 1.1.1.2 mrg later version.
2190 1.1.1.2 mrg
2191 1.1.1.2 mrg 15. Disclaimer of Warranty.
2192 1.1.1.2 mrg
2193 1.1.1.2 mrg THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
2194 1.1.1.2 mrg APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE
2195 1.1.1.2 mrg COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
2196 1.1.1.2 mrg WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED,
2197 1.1.1.2 mrg INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
2198 1.1.1.2 mrg MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE
2199 1.1.1.2 mrg RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.
2200 1.1.1.2 mrg SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL
2201 1.1.1.2 mrg NECESSARY SERVICING, REPAIR OR CORRECTION.
2202 1.1.1.2 mrg
2203 1.1.1.2 mrg 16. Limitation of Liability.
2204 1.1.1.2 mrg
2205 1.1.1.2 mrg IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
2206 1.1.1.2 mrg WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES
2207 1.1.1.2 mrg AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU
2208 1.1.1.2 mrg FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
2209 1.1.1.2 mrg CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE
2210 1.1.1.2 mrg THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA
2211 1.1.1.2 mrg BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
2212 1.1.1.2 mrg PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
2213 1.1.1.2 mrg PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF
2214 1.1.1.2 mrg THE POSSIBILITY OF SUCH DAMAGES.
2215 1.1.1.2 mrg
2216 1.1.1.2 mrg 17. Interpretation of Sections 15 and 16.
2217 1.1.1.2 mrg
2218 1.1.1.2 mrg If the disclaimer of warranty and limitation of liability provided
2219 1.1.1.2 mrg above cannot be given local legal effect according to their terms,
2220 1.1.1.2 mrg reviewing courts shall apply local law that most closely
2221 1.1.1.2 mrg approximates an absolute waiver of all civil liability in
2222 1.1.1.2 mrg connection with the Program, unless a warranty or assumption of
2223 1.1.1.2 mrg liability accompanies a copy of the Program in return for a fee.
2224 1.1 mrg
2225 1.1.1.2 mrg
2226 1.1.1.2 mrg END OF TERMS AND CONDITIONS
2227 1.1.1.2 mrg ===========================
2228 1.1.1.2 mrg
2229 1.1.1.2 mrg How to Apply These Terms to Your New Programs
2230 1.1.1.2 mrg =============================================
2231 1.1 mrg
2232 1.1 mrg If you develop a new program, and you want it to be of the greatest
2233 1.1 mrg possible use to the public, the best way to achieve this is to make it
2234 1.1 mrg free software which everyone can redistribute and change under these
2235 1.1 mrg terms.
2236 1.1 mrg
2237 1.1 mrg To do so, attach the following notices to the program. It is safest
2238 1.1 mrg to attach them to the start of each source file to most effectively
2239 1.1.1.2 mrg state the exclusion of warranty; and each file should have at least the
2240 1.1.1.2 mrg "copyright" line and a pointer to where the full notice is found.
2241 1.1 mrg
2242 1.1 mrg ONE LINE TO GIVE THE PROGRAM'S NAME AND A BRIEF IDEA OF WHAT IT DOES.
2243 1.1.1.2 mrg Copyright (C) YEAR NAME OF AUTHOR
2244 1.1 mrg
2245 1.1.1.2 mrg This program is free software: you can redistribute it and/or modify
2246 1.1 mrg it under the terms of the GNU General Public License as published by
2247 1.1.1.2 mrg the Free Software Foundation, either version 3 of the License, or (at
2248 1.1.1.2 mrg your option) any later version.
2249 1.1 mrg
2250 1.1.1.2 mrg This program is distributed in the hope that it will be useful, but
2251 1.1.1.2 mrg WITHOUT ANY WARRANTY; without even the implied warranty of
2252 1.1.1.2 mrg MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
2253 1.1.1.2 mrg General Public License for more details.
2254 1.1 mrg
2255 1.1 mrg You should have received a copy of the GNU General Public License
2256 1.1.1.2 mrg along with this program. If not, see `http://www.gnu.org/licenses/'.
2257 1.1 mrg
2258 1.1 mrg Also add information on how to contact you by electronic and paper
2259 1.1 mrg mail.
2260 1.1 mrg
2261 1.1.1.2 mrg If the program does terminal interaction, make it output a short
2262 1.1.1.2 mrg notice like this when it starts in an interactive mode:
2263 1.1 mrg
2264 1.1.1.2 mrg PROGRAM Copyright (C) YEAR NAME OF AUTHOR
2265 1.1.1.2 mrg This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
2266 1.1 mrg This is free software, and you are welcome to redistribute it
2267 1.1 mrg under certain conditions; type `show c' for details.
2268 1.1 mrg
2269 1.1 mrg The hypothetical commands `show w' and `show c' should show the
2270 1.1.1.2 mrg appropriate parts of the General Public License. Of course, your
2271 1.1.1.2 mrg program's commands might be different; for a GUI interface, you would
2272 1.1.1.2 mrg use an "about box".
2273 1.1 mrg
2274 1.1 mrg You should also get your employer (if you work as a programmer) or
2275 1.1.1.2 mrg school, if any, to sign a "copyright disclaimer" for the program, if
2276 1.1.1.2 mrg necessary. For more information on this, and how to apply and follow
2277 1.1.1.2 mrg the GNU GPL, see `http://www.gnu.org/licenses/'.
2278 1.1 mrg
2279 1.1.1.2 mrg The GNU General Public License does not permit incorporating your
2280 1.1 mrg program into proprietary programs. If your program is a subroutine
2281 1.1 mrg library, you may consider it more useful to permit linking proprietary
2282 1.1 mrg applications with the library. If this is what you want to do, use the
2283 1.1.1.2 mrg GNU Lesser General Public License instead of this License. But first,
2284 1.1.1.2 mrg please read `http://www.gnu.org/philosophy/why-not-lgpl.html'.
2285 1.1 mrg
2286 1.1 mrg
2287 1.1 mrg File: libgomp.info, Node: GNU Free Documentation License, Next: Funding, Prev: Copying, Up: Top
2288 1.1 mrg
2289 1.1 mrg GNU Free Documentation License
2290 1.1 mrg ******************************
2291 1.1 mrg
2292 1.1.1.2 mrg Version 1.3, 3 November 2008
2293 1.1 mrg
2294 1.1.1.2 mrg Copyright (C) 2000, 2001, 2002, 2007, 2008 Free Software Foundation, Inc.
2295 1.1.1.2 mrg `http://fsf.org/'
2296 1.1 mrg
2297 1.1 mrg Everyone is permitted to copy and distribute verbatim copies
2298 1.1 mrg of this license document, but changing it is not allowed.
2299 1.1 mrg
2300 1.1 mrg 0. PREAMBLE
2301 1.1 mrg
2302 1.1 mrg The purpose of this License is to make a manual, textbook, or other
2303 1.1 mrg functional and useful document "free" in the sense of freedom: to
2304 1.1 mrg assure everyone the effective freedom to copy and redistribute it,
2305 1.1 mrg with or without modifying it, either commercially or
2306 1.1 mrg noncommercially. Secondarily, this License preserves for the
2307 1.1 mrg author and publisher a way to get credit for their work, while not
2308 1.1 mrg being considered responsible for modifications made by others.
2309 1.1 mrg
2310 1.1 mrg This License is a kind of "copyleft", which means that derivative
2311 1.1 mrg works of the document must themselves be free in the same sense.
2312 1.1 mrg It complements the GNU General Public License, which is a copyleft
2313 1.1 mrg license designed for free software.
2314 1.1 mrg
2315 1.1 mrg We have designed this License in order to use it for manuals for
2316 1.1 mrg free software, because free software needs free documentation: a
2317 1.1 mrg free program should come with manuals providing the same freedoms
2318 1.1 mrg that the software does. But this License is not limited to
2319 1.1 mrg software manuals; it can be used for any textual work, regardless
2320 1.1 mrg of subject matter or whether it is published as a printed book.
2321 1.1 mrg We recommend this License principally for works whose purpose is
2322 1.1 mrg instruction or reference.
2323 1.1 mrg
2324 1.1 mrg 1. APPLICABILITY AND DEFINITIONS
2325 1.1 mrg
2326 1.1 mrg This License applies to any manual or other work, in any medium,
2327 1.1 mrg that contains a notice placed by the copyright holder saying it
2328 1.1 mrg can be distributed under the terms of this License. Such a notice
2329 1.1 mrg grants a world-wide, royalty-free license, unlimited in duration,
2330 1.1 mrg to use that work under the conditions stated herein. The
2331 1.1 mrg "Document", below, refers to any such manual or work. Any member
2332 1.1 mrg of the public is a licensee, and is addressed as "you". You
2333 1.1 mrg accept the license if you copy, modify or distribute the work in a
2334 1.1 mrg way requiring permission under copyright law.
2335 1.1 mrg
2336 1.1 mrg A "Modified Version" of the Document means any work containing the
2337 1.1 mrg Document or a portion of it, either copied verbatim, or with
2338 1.1 mrg modifications and/or translated into another language.
2339 1.1 mrg
2340 1.1 mrg A "Secondary Section" is a named appendix or a front-matter section
2341 1.1 mrg of the Document that deals exclusively with the relationship of the
2342 1.1 mrg publishers or authors of the Document to the Document's overall
2343 1.1 mrg subject (or to related matters) and contains nothing that could
2344 1.1 mrg fall directly within that overall subject. (Thus, if the Document
2345 1.1 mrg is in part a textbook of mathematics, a Secondary Section may not
2346 1.1 mrg explain any mathematics.) The relationship could be a matter of
2347 1.1 mrg historical connection with the subject or with related matters, or
2348 1.1 mrg of legal, commercial, philosophical, ethical or political position
2349 1.1 mrg regarding them.
2350 1.1 mrg
2351 1.1 mrg The "Invariant Sections" are certain Secondary Sections whose
2352 1.1 mrg titles are designated, as being those of Invariant Sections, in
2353 1.1 mrg the notice that says that the Document is released under this
2354 1.1 mrg License. If a section does not fit the above definition of
2355 1.1 mrg Secondary then it is not allowed to be designated as Invariant.
2356 1.1 mrg The Document may contain zero Invariant Sections. If the Document
2357 1.1 mrg does not identify any Invariant Sections then there are none.
2358 1.1 mrg
2359 1.1 mrg The "Cover Texts" are certain short passages of text that are
2360 1.1 mrg listed, as Front-Cover Texts or Back-Cover Texts, in the notice
2361 1.1 mrg that says that the Document is released under this License. A
2362 1.1 mrg Front-Cover Text may be at most 5 words, and a Back-Cover Text may
2363 1.1 mrg be at most 25 words.
2364 1.1 mrg
2365 1.1 mrg A "Transparent" copy of the Document means a machine-readable copy,
2366 1.1 mrg represented in a format whose specification is available to the
2367 1.1 mrg general public, that is suitable for revising the document
2368 1.1 mrg straightforwardly with generic text editors or (for images
2369 1.1 mrg composed of pixels) generic paint programs or (for drawings) some
2370 1.1 mrg widely available drawing editor, and that is suitable for input to
2371 1.1 mrg text formatters or for automatic translation to a variety of
2372 1.1 mrg formats suitable for input to text formatters. A copy made in an
2373 1.1 mrg otherwise Transparent file format whose markup, or absence of
2374 1.1 mrg markup, has been arranged to thwart or discourage subsequent
2375 1.1 mrg modification by readers is not Transparent. An image format is
2376 1.1 mrg not Transparent if used for any substantial amount of text. A
2377 1.1 mrg copy that is not "Transparent" is called "Opaque".
2378 1.1 mrg
2379 1.1 mrg Examples of suitable formats for Transparent copies include plain
2380 1.1 mrg ASCII without markup, Texinfo input format, LaTeX input format,
2381 1.1 mrg SGML or XML using a publicly available DTD, and
2382 1.1 mrg standard-conforming simple HTML, PostScript or PDF designed for
2383 1.1 mrg human modification. Examples of transparent image formats include
2384 1.1 mrg PNG, XCF and JPG. Opaque formats include proprietary formats that
2385 1.1 mrg can be read and edited only by proprietary word processors, SGML or
2386 1.1 mrg XML for which the DTD and/or processing tools are not generally
2387 1.1 mrg available, and the machine-generated HTML, PostScript or PDF
2388 1.1 mrg produced by some word processors for output purposes only.
2389 1.1 mrg
2390 1.1 mrg The "Title Page" means, for a printed book, the title page itself,
2391 1.1 mrg plus such following pages as are needed to hold, legibly, the
2392 1.1 mrg material this License requires to appear in the title page. For
2393 1.1 mrg works in formats which do not have any title page as such, "Title
2394 1.1 mrg Page" means the text near the most prominent appearance of the
2395 1.1 mrg work's title, preceding the beginning of the body of the text.
2396 1.1 mrg
2397 1.1.1.2 mrg The "publisher" means any person or entity that distributes copies
2398 1.1.1.2 mrg of the Document to the public.
2399 1.1.1.2 mrg
2400 1.1 mrg A section "Entitled XYZ" means a named subunit of the Document
2401 1.1 mrg whose title either is precisely XYZ or contains XYZ in parentheses
2402 1.1 mrg following text that translates XYZ in another language. (Here XYZ
2403 1.1 mrg stands for a specific section name mentioned below, such as
2404 1.1 mrg "Acknowledgements", "Dedications", "Endorsements", or "History".)
2405 1.1 mrg To "Preserve the Title" of such a section when you modify the
2406 1.1 mrg Document means that it remains a section "Entitled XYZ" according
2407 1.1 mrg to this definition.
2408 1.1 mrg
2409 1.1 mrg The Document may include Warranty Disclaimers next to the notice
2410 1.1 mrg which states that this License applies to the Document. These
2411 1.1 mrg Warranty Disclaimers are considered to be included by reference in
2412 1.1 mrg this License, but only as regards disclaiming warranties: any other
2413 1.1 mrg implication that these Warranty Disclaimers may have is void and
2414 1.1 mrg has no effect on the meaning of this License.
2415 1.1 mrg
2416 1.1 mrg 2. VERBATIM COPYING
2417 1.1 mrg
2418 1.1 mrg You may copy and distribute the Document in any medium, either
2419 1.1 mrg commercially or noncommercially, provided that this License, the
2420 1.1 mrg copyright notices, and the license notice saying this License
2421 1.1 mrg applies to the Document are reproduced in all copies, and that you
2422 1.1 mrg add no other conditions whatsoever to those of this License. You
2423 1.1 mrg may not use technical measures to obstruct or control the reading
2424 1.1 mrg or further copying of the copies you make or distribute. However,
2425 1.1 mrg you may accept compensation in exchange for copies. If you
2426 1.1 mrg distribute a large enough number of copies you must also follow
2427 1.1 mrg the conditions in section 3.
2428 1.1 mrg
2429 1.1 mrg You may also lend copies, under the same conditions stated above,
2430 1.1 mrg and you may publicly display copies.
2431 1.1 mrg
2432 1.1 mrg 3. COPYING IN QUANTITY
2433 1.1 mrg
2434 1.1 mrg If you publish printed copies (or copies in media that commonly
2435 1.1 mrg have printed covers) of the Document, numbering more than 100, and
2436 1.1 mrg the Document's license notice requires Cover Texts, you must
2437 1.1 mrg enclose the copies in covers that carry, clearly and legibly, all
2438 1.1 mrg these Cover Texts: Front-Cover Texts on the front cover, and
2439 1.1 mrg Back-Cover Texts on the back cover. Both covers must also clearly
2440 1.1 mrg and legibly identify you as the publisher of these copies. The
2441 1.1 mrg front cover must present the full title with all words of the
2442 1.1 mrg title equally prominent and visible. You may add other material
2443 1.1 mrg on the covers in addition. Copying with changes limited to the
2444 1.1 mrg covers, as long as they preserve the title of the Document and
2445 1.1 mrg satisfy these conditions, can be treated as verbatim copying in
2446 1.1 mrg other respects.
2447 1.1 mrg
2448 1.1 mrg If the required texts for either cover are too voluminous to fit
2449 1.1 mrg legibly, you should put the first ones listed (as many as fit
2450 1.1 mrg reasonably) on the actual cover, and continue the rest onto
2451 1.1 mrg adjacent pages.
2452 1.1 mrg
2453 1.1 mrg If you publish or distribute Opaque copies of the Document
2454 1.1 mrg numbering more than 100, you must either include a
2455 1.1 mrg machine-readable Transparent copy along with each Opaque copy, or
2456 1.1 mrg state in or with each Opaque copy a computer-network location from
2457 1.1 mrg which the general network-using public has access to download
2458 1.1 mrg using public-standard network protocols a complete Transparent
2459 1.1 mrg copy of the Document, free of added material. If you use the
2460 1.1 mrg latter option, you must take reasonably prudent steps, when you
2461 1.1 mrg begin distribution of Opaque copies in quantity, to ensure that
2462 1.1 mrg this Transparent copy will remain thus accessible at the stated
2463 1.1 mrg location until at least one year after the last time you
2464 1.1 mrg distribute an Opaque copy (directly or through your agents or
2465 1.1 mrg retailers) of that edition to the public.
2466 1.1 mrg
2467 1.1 mrg It is requested, but not required, that you contact the authors of
2468 1.1 mrg the Document well before redistributing any large number of
2469 1.1 mrg copies, to give them a chance to provide you with an updated
2470 1.1 mrg version of the Document.
2471 1.1 mrg
2472 1.1 mrg 4. MODIFICATIONS
2473 1.1 mrg
2474 1.1 mrg You may copy and distribute a Modified Version of the Document
2475 1.1 mrg under the conditions of sections 2 and 3 above, provided that you
2476 1.1 mrg release the Modified Version under precisely this License, with
2477 1.1 mrg the Modified Version filling the role of the Document, thus
2478 1.1 mrg licensing distribution and modification of the Modified Version to
2479 1.1 mrg whoever possesses a copy of it. In addition, you must do these
2480 1.1 mrg things in the Modified Version:
2481 1.1 mrg
2482 1.1 mrg A. Use in the Title Page (and on the covers, if any) a title
2483 1.1 mrg distinct from that of the Document, and from those of
2484 1.1 mrg previous versions (which should, if there were any, be listed
2485 1.1 mrg in the History section of the Document). You may use the
2486 1.1 mrg same title as a previous version if the original publisher of
2487 1.1 mrg that version gives permission.
2488 1.1 mrg
2489 1.1 mrg B. List on the Title Page, as authors, one or more persons or
2490 1.1 mrg entities responsible for authorship of the modifications in
2491 1.1 mrg the Modified Version, together with at least five of the
2492 1.1 mrg principal authors of the Document (all of its principal
2493 1.1 mrg authors, if it has fewer than five), unless they release you
2494 1.1 mrg from this requirement.
2495 1.1 mrg
2496 1.1 mrg C. State on the Title page the name of the publisher of the
2497 1.1 mrg Modified Version, as the publisher.
2498 1.1 mrg
2499 1.1 mrg D. Preserve all the copyright notices of the Document.
2500 1.1 mrg
2501 1.1 mrg E. Add an appropriate copyright notice for your modifications
2502 1.1 mrg adjacent to the other copyright notices.
2503 1.1 mrg
2504 1.1 mrg F. Include, immediately after the copyright notices, a license
2505 1.1 mrg notice giving the public permission to use the Modified
2506 1.1 mrg Version under the terms of this License, in the form shown in
2507 1.1 mrg the Addendum below.
2508 1.1 mrg
2509 1.1 mrg G. Preserve in that license notice the full lists of Invariant
2510 1.1 mrg Sections and required Cover Texts given in the Document's
2511 1.1 mrg license notice.
2512 1.1 mrg
2513 1.1 mrg H. Include an unaltered copy of this License.
2514 1.1 mrg
2515 1.1 mrg I. Preserve the section Entitled "History", Preserve its Title,
2516 1.1 mrg and add to it an item stating at least the title, year, new
2517 1.1 mrg authors, and publisher of the Modified Version as given on
2518 1.1 mrg the Title Page. If there is no section Entitled "History" in
2519 1.1 mrg the Document, create one stating the title, year, authors,
2520 1.1 mrg and publisher of the Document as given on its Title Page,
2521 1.1 mrg then add an item describing the Modified Version as stated in
2522 1.1 mrg the previous sentence.
2523 1.1 mrg
2524 1.1 mrg J. Preserve the network location, if any, given in the Document
2525 1.1 mrg for public access to a Transparent copy of the Document, and
2526 1.1 mrg likewise the network locations given in the Document for
2527 1.1 mrg previous versions it was based on. These may be placed in
2528 1.1 mrg the "History" section. You may omit a network location for a
2529 1.1 mrg work that was published at least four years before the
2530 1.1 mrg Document itself, or if the original publisher of the version
2531 1.1 mrg it refers to gives permission.
2532 1.1 mrg
2533 1.1 mrg K. For any section Entitled "Acknowledgements" or "Dedications",
2534 1.1 mrg Preserve the Title of the section, and preserve in the
2535 1.1 mrg section all the substance and tone of each of the contributor
2536 1.1 mrg acknowledgements and/or dedications given therein.
2537 1.1 mrg
2538 1.1 mrg L. Preserve all the Invariant Sections of the Document,
2539 1.1 mrg unaltered in their text and in their titles. Section numbers
2540 1.1 mrg or the equivalent are not considered part of the section
2541 1.1 mrg titles.
2542 1.1 mrg
2543 1.1 mrg M. Delete any section Entitled "Endorsements". Such a section
2544 1.1 mrg may not be included in the Modified Version.
2545 1.1 mrg
2546 1.1 mrg N. Do not retitle any existing section to be Entitled
2547 1.1 mrg "Endorsements" or to conflict in title with any Invariant
2548 1.1 mrg Section.
2549 1.1 mrg
2550 1.1 mrg O. Preserve any Warranty Disclaimers.
2551 1.1 mrg
2552 1.1 mrg If the Modified Version includes new front-matter sections or
2553 1.1 mrg appendices that qualify as Secondary Sections and contain no
2554 1.1 mrg material copied from the Document, you may at your option
2555 1.1 mrg designate some or all of these sections as invariant. To do this,
2556 1.1 mrg add their titles to the list of Invariant Sections in the Modified
2557 1.1 mrg Version's license notice. These titles must be distinct from any
2558 1.1 mrg other section titles.
2559 1.1 mrg
2560 1.1 mrg You may add a section Entitled "Endorsements", provided it contains
2561 1.1 mrg nothing but endorsements of your Modified Version by various
2562 1.1 mrg parties--for example, statements of peer review or that the text
2563 1.1 mrg has been approved by an organization as the authoritative
2564 1.1 mrg definition of a standard.
2565 1.1 mrg
2566 1.1 mrg You may add a passage of up to five words as a Front-Cover Text,
2567 1.1 mrg and a passage of up to 25 words as a Back-Cover Text, to the end
2568 1.1 mrg of the list of Cover Texts in the Modified Version. Only one
2569 1.1 mrg passage of Front-Cover Text and one of Back-Cover Text may be
2570 1.1 mrg added by (or through arrangements made by) any one entity. If the
2571 1.1 mrg Document already includes a cover text for the same cover,
2572 1.1 mrg previously added by you or by arrangement made by the same entity
2573 1.1 mrg you are acting on behalf of, you may not add another; but you may
2574 1.1 mrg replace the old one, on explicit permission from the previous
2575 1.1 mrg publisher that added the old one.
2576 1.1 mrg
2577 1.1 mrg The author(s) and publisher(s) of the Document do not by this
2578 1.1 mrg License give permission to use their names for publicity for or to
2579 1.1 mrg assert or imply endorsement of any Modified Version.
2580 1.1 mrg
2581 1.1 mrg 5. COMBINING DOCUMENTS
2582 1.1 mrg
2583 1.1 mrg You may combine the Document with other documents released under
2584 1.1 mrg this License, under the terms defined in section 4 above for
2585 1.1 mrg modified versions, provided that you include in the combination
2586 1.1 mrg all of the Invariant Sections of all of the original documents,
2587 1.1 mrg unmodified, and list them all as Invariant Sections of your
2588 1.1 mrg combined work in its license notice, and that you preserve all
2589 1.1 mrg their Warranty Disclaimers.
2590 1.1 mrg
2591 1.1 mrg The combined work need only contain one copy of this License, and
2592 1.1 mrg multiple identical Invariant Sections may be replaced with a single
2593 1.1 mrg copy. If there are multiple Invariant Sections with the same name
2594 1.1 mrg but different contents, make the title of each such section unique
2595 1.1 mrg by adding at the end of it, in parentheses, the name of the
2596 1.1 mrg original author or publisher of that section if known, or else a
2597 1.1 mrg unique number. Make the same adjustment to the section titles in
2598 1.1 mrg the list of Invariant Sections in the license notice of the
2599 1.1 mrg combined work.
2600 1.1 mrg
2601 1.1 mrg In the combination, you must combine any sections Entitled
2602 1.1 mrg "History" in the various original documents, forming one section
2603 1.1 mrg Entitled "History"; likewise combine any sections Entitled
2604 1.1 mrg "Acknowledgements", and any sections Entitled "Dedications". You
2605 1.1 mrg must delete all sections Entitled "Endorsements."
2606 1.1 mrg
2607 1.1 mrg 6. COLLECTIONS OF DOCUMENTS
2608 1.1 mrg
2609 1.1 mrg You may make a collection consisting of the Document and other
2610 1.1 mrg documents released under this License, and replace the individual
2611 1.1 mrg copies of this License in the various documents with a single copy
2612 1.1 mrg that is included in the collection, provided that you follow the
2613 1.1 mrg rules of this License for verbatim copying of each of the
2614 1.1 mrg documents in all other respects.
2615 1.1 mrg
2616 1.1 mrg You may extract a single document from such a collection, and
2617 1.1 mrg distribute it individually under this License, provided you insert
2618 1.1 mrg a copy of this License into the extracted document, and follow
2619 1.1 mrg this License in all other respects regarding verbatim copying of
2620 1.1 mrg that document.
2621 1.1 mrg
2622 1.1 mrg 7. AGGREGATION WITH INDEPENDENT WORKS
2623 1.1 mrg
2624 1.1 mrg A compilation of the Document or its derivatives with other
2625 1.1 mrg separate and independent documents or works, in or on a volume of
2626 1.1 mrg a storage or distribution medium, is called an "aggregate" if the
2627 1.1 mrg copyright resulting from the compilation is not used to limit the
2628 1.1 mrg legal rights of the compilation's users beyond what the individual
2629 1.1 mrg works permit. When the Document is included in an aggregate, this
2630 1.1 mrg License does not apply to the other works in the aggregate which
2631 1.1 mrg are not themselves derivative works of the Document.
2632 1.1 mrg
2633 1.1 mrg If the Cover Text requirement of section 3 is applicable to these
2634 1.1 mrg copies of the Document, then if the Document is less than one half
2635 1.1 mrg of the entire aggregate, the Document's Cover Texts may be placed
2636 1.1 mrg on covers that bracket the Document within the aggregate, or the
2637 1.1 mrg electronic equivalent of covers if the Document is in electronic
2638 1.1 mrg form. Otherwise they must appear on printed covers that bracket
2639 1.1 mrg the whole aggregate.
2640 1.1 mrg
2641 1.1 mrg 8. TRANSLATION
2642 1.1 mrg
2643 1.1 mrg Translation is considered a kind of modification, so you may
2644 1.1 mrg distribute translations of the Document under the terms of section
2645 1.1 mrg 4. Replacing Invariant Sections with translations requires special
2646 1.1 mrg permission from their copyright holders, but you may include
2647 1.1 mrg translations of some or all Invariant Sections in addition to the
2648 1.1 mrg original versions of these Invariant Sections. You may include a
2649 1.1 mrg translation of this License, and all the license notices in the
2650 1.1 mrg Document, and any Warranty Disclaimers, provided that you also
2651 1.1 mrg include the original English version of this License and the
2652 1.1 mrg original versions of those notices and disclaimers. In case of a
2653 1.1 mrg disagreement between the translation and the original version of
2654 1.1 mrg this License or a notice or disclaimer, the original version will
2655 1.1 mrg prevail.
2656 1.1 mrg
2657 1.1 mrg If a section in the Document is Entitled "Acknowledgements",
2658 1.1 mrg "Dedications", or "History", the requirement (section 4) to
2659 1.1 mrg Preserve its Title (section 1) will typically require changing the
2660 1.1 mrg actual title.
2661 1.1 mrg
2662 1.1 mrg 9. TERMINATION
2663 1.1 mrg
2664 1.1 mrg You may not copy, modify, sublicense, or distribute the Document
2665 1.1.1.2 mrg except as expressly provided under this License. Any attempt
2666 1.1.1.2 mrg otherwise to copy, modify, sublicense, or distribute it is void,
2667 1.1.1.2 mrg and will automatically terminate your rights under this License.
2668 1.1.1.2 mrg
2669 1.1.1.2 mrg However, if you cease all violation of this License, then your
2670 1.1.1.2 mrg license from a particular copyright holder is reinstated (a)
2671 1.1.1.2 mrg provisionally, unless and until the copyright holder explicitly
2672 1.1.1.2 mrg and finally terminates your license, and (b) permanently, if the
2673 1.1.1.2 mrg copyright holder fails to notify you of the violation by some
2674 1.1.1.2 mrg reasonable means prior to 60 days after the cessation.
2675 1.1.1.2 mrg
2676 1.1.1.2 mrg Moreover, your license from a particular copyright holder is
2677 1.1.1.2 mrg reinstated permanently if the copyright holder notifies you of the
2678 1.1.1.2 mrg violation by some reasonable means, this is the first time you have
2679 1.1.1.2 mrg received notice of violation of this License (for any work) from
2680 1.1.1.2 mrg that copyright holder, and you cure the violation prior to 30 days
2681 1.1.1.2 mrg after your receipt of the notice.
2682 1.1.1.2 mrg
2683 1.1.1.2 mrg Termination of your rights under this section does not terminate
2684 1.1.1.2 mrg the licenses of parties who have received copies or rights from
2685 1.1.1.2 mrg you under this License. If your rights have been terminated and
2686 1.1.1.2 mrg not permanently reinstated, receipt of a copy of some or all of
2687 1.1.1.2 mrg the same material does not give you any rights to use it.
2688 1.1 mrg
2689 1.1 mrg 10. FUTURE REVISIONS OF THIS LICENSE
2690 1.1 mrg
2691 1.1 mrg The Free Software Foundation may publish new, revised versions of
2692 1.1 mrg the GNU Free Documentation License from time to time. Such new
2693 1.1 mrg versions will be similar in spirit to the present version, but may
2694 1.1 mrg differ in detail to address new problems or concerns. See
2695 1.1 mrg `http://www.gnu.org/copyleft/'.
2696 1.1 mrg
2697 1.1 mrg Each version of the License is given a distinguishing version
2698 1.1 mrg number. If the Document specifies that a particular numbered
2699 1.1 mrg version of this License "or any later version" applies to it, you
2700 1.1 mrg have the option of following the terms and conditions either of
2701 1.1 mrg that specified version or of any later version that has been
2702 1.1 mrg published (not as a draft) by the Free Software Foundation. If
2703 1.1 mrg the Document does not specify a version number of this License,
2704 1.1 mrg you may choose any version ever published (not as a draft) by the
2705 1.1.1.2 mrg Free Software Foundation. If the Document specifies that a proxy
2706 1.1.1.2 mrg can decide which future versions of this License can be used, that
2707 1.1.1.2 mrg proxy's public statement of acceptance of a version permanently
2708 1.1.1.2 mrg authorizes you to choose that version for the Document.
2709 1.1.1.2 mrg
2710 1.1.1.2 mrg 11. RELICENSING
2711 1.1.1.2 mrg
2712 1.1.1.2 mrg "Massive Multiauthor Collaboration Site" (or "MMC Site") means any
2713 1.1.1.2 mrg World Wide Web server that publishes copyrightable works and also
2714 1.1.1.2 mrg provides prominent facilities for anybody to edit those works. A
2715 1.1.1.2 mrg public wiki that anybody can edit is an example of such a server.
2716 1.1.1.2 mrg A "Massive Multiauthor Collaboration" (or "MMC") contained in the
2717 1.1.1.2 mrg site means any set of copyrightable works thus published on the MMC
2718 1.1.1.2 mrg site.
2719 1.1.1.2 mrg
2720 1.1.1.2 mrg "CC-BY-SA" means the Creative Commons Attribution-Share Alike 3.0
2721 1.1.1.2 mrg license published by Creative Commons Corporation, a not-for-profit
2722 1.1.1.2 mrg corporation with a principal place of business in San Francisco,
2723 1.1.1.2 mrg California, as well as future copyleft versions of that license
2724 1.1.1.2 mrg published by that same organization.
2725 1.1.1.2 mrg
2726 1.1.1.2 mrg "Incorporate" means to publish or republish a Document, in whole or
2727 1.1.1.2 mrg in part, as part of another Document.
2728 1.1.1.2 mrg
2729 1.1.1.2 mrg An MMC is "eligible for relicensing" if it is licensed under this
2730 1.1.1.2 mrg License, and if all works that were first published under this
2731 1.1.1.2 mrg License somewhere other than this MMC, and subsequently
2732 1.1.1.2 mrg incorporated in whole or in part into the MMC, (1) had no cover
2733 1.1.1.2 mrg texts or invariant sections, and (2) were thus incorporated prior
2734 1.1.1.2 mrg to November 1, 2008.
2735 1.1.1.2 mrg
2736 1.1.1.2 mrg The operator of an MMC Site may republish an MMC contained in the
2737 1.1.1.2 mrg site under CC-BY-SA on the same site at any time before August 1,
2738 1.1.1.2 mrg 2009, provided the MMC is eligible for relicensing.
2739 1.1.1.2 mrg
2740 1.1 mrg
2741 1.1 mrg ADDENDUM: How to use this License for your documents
2742 1.1 mrg ====================================================
2743 1.1 mrg
2744 1.1 mrg To use this License in a document you have written, include a copy of
2745 1.1 mrg the License in the document and put the following copyright and license
2746 1.1 mrg notices just after the title page:
2747 1.1 mrg
2748 1.1 mrg Copyright (C) YEAR YOUR NAME.
2749 1.1 mrg Permission is granted to copy, distribute and/or modify this document
2750 1.1.1.2 mrg under the terms of the GNU Free Documentation License, Version 1.3
2751 1.1 mrg or any later version published by the Free Software Foundation;
2752 1.1 mrg with no Invariant Sections, no Front-Cover Texts, and no Back-Cover
2753 1.1 mrg Texts. A copy of the license is included in the section entitled ``GNU
2754 1.1 mrg Free Documentation License''.
2755 1.1 mrg
2756 1.1 mrg If you have Invariant Sections, Front-Cover Texts and Back-Cover
2757 1.1 mrg Texts, replace the "with...Texts." line with this:
2758 1.1 mrg
2759 1.1 mrg with the Invariant Sections being LIST THEIR TITLES, with
2760 1.1 mrg the Front-Cover Texts being LIST, and with the Back-Cover Texts
2761 1.1 mrg being LIST.
2762 1.1 mrg
2763 1.1 mrg If you have Invariant Sections without Cover Texts, or some other
2764 1.1 mrg combination of the three, merge those two alternatives to suit the
2765 1.1 mrg situation.
2766 1.1 mrg
2767 1.1 mrg If your document contains nontrivial examples of program code, we
2768 1.1 mrg recommend releasing these examples in parallel under your choice of
2769 1.1 mrg free software license, such as the GNU General Public License, to
2770 1.1 mrg permit their use in free software.
2771 1.1 mrg
2772 1.1 mrg
2773 1.1.1.2 mrg File: libgomp.info, Node: Funding, Next: Library Index, Prev: GNU Free Documentation License, Up: Top
2774 1.1 mrg
2775 1.1 mrg Funding Free Software
2776 1.1 mrg *********************
2777 1.1 mrg
2778 1.1 mrg If you want to have more free software a few years from now, it makes
2779 1.1 mrg sense for you to help encourage people to contribute funds for its
2780 1.1 mrg development. The most effective approach known is to encourage
2781 1.1 mrg commercial redistributors to donate.
2782 1.1 mrg
2783 1.1 mrg Users of free software systems can boost the pace of development by
2784 1.1 mrg encouraging for-a-fee distributors to donate part of their selling price
2785 1.1 mrg to free software developers--the Free Software Foundation, and others.
2786 1.1 mrg
2787 1.1 mrg The way to convince distributors to do this is to demand it and
2788 1.1 mrg expect it from them. So when you compare distributors, judge them
2789 1.1 mrg partly by how much they give to free software development. Show
2790 1.1 mrg distributors they must compete to be the one who gives the most.
2791 1.1 mrg
2792 1.1 mrg To make this approach work, you must insist on numbers that you can
2793 1.1 mrg compare, such as, "We will donate ten dollars to the Frobnitz project
2794 1.1 mrg for each disk sold." Don't be satisfied with a vague promise, such as
2795 1.1 mrg "A portion of the profits are donated," since it doesn't give a basis
2796 1.1 mrg for comparison.
2797 1.1 mrg
2798 1.1 mrg Even a precise fraction "of the profits from this disk" is not very
2799 1.1 mrg meaningful, since creative accounting and unrelated business decisions
2800 1.1 mrg can greatly alter what fraction of the sales price counts as profit.
2801 1.1 mrg If the price you pay is $50, ten percent of the profit is probably less
2802 1.1 mrg than a dollar; it might be a few cents, or nothing at all.
2803 1.1 mrg
2804 1.1 mrg Some redistributors do development work themselves. This is useful
2805 1.1 mrg too; but to keep everyone honest, you need to inquire how much they do,
2806 1.1 mrg and what kind. Some kinds of development make much more long-term
2807 1.1 mrg difference than others. For example, maintaining a separate version of
2808 1.1 mrg a program contributes very little; maintaining the standard version of a
2809 1.1 mrg program for the whole community contributes much. Easy new ports
2810 1.1 mrg contribute little, since someone else would surely do them; difficult
2811 1.1 mrg ports such as adding a new CPU to the GNU Compiler Collection
2812 1.1 mrg contribute more; major new features or packages contribute the most.
2813 1.1 mrg
2814 1.1 mrg By establishing the idea that supporting further development is "the
2815 1.1 mrg proper thing to do" when distributing free software for a fee, we can
2816 1.1 mrg assure a steady flow of resources into making more free software.
2817 1.1 mrg
2818 1.1 mrg Copyright (C) 1994 Free Software Foundation, Inc.
2819 1.1 mrg Verbatim copying and redistribution of this section is permitted
2820 1.1 mrg without royalty; alteration is not permitted.
2821 1.1 mrg
2822 1.1 mrg
2823 1.1.1.2 mrg File: libgomp.info, Node: Library Index, Prev: Funding, Up: Top
2824 1.1 mrg
2825 1.1.1.2 mrg Library Index
2826 1.1.1.2 mrg *************
2827 1.1 mrg
2828 1.1 mrg [index]
2829 1.1 mrg * Menu:
2830 1.1 mrg
2831 1.1 mrg * Environment Variable <1>: GOMP_STACKSIZE. (line 6)
2832 1.1 mrg * Environment Variable <2>: GOMP_CPU_AFFINITY. (line 6)
2833 1.1.1.2 mrg * Environment Variable <3>: OMP_PROC_BIND. (line 6)
2834 1.1.1.2 mrg * Environment Variable <4>: OMP_WAIT_POLICY. (line 6)
2835 1.1.1.2 mrg * Environment Variable <5>: OMP_THREAD_LIMIT. (line 6)
2836 1.1.1.2 mrg * Environment Variable <6>: OMP_STACKSIZE. (line 6)
2837 1.1.1.2 mrg * Environment Variable <7>: OMP_SCHEDULE. (line 6)
2838 1.1.1.2 mrg * Environment Variable <8>: OMP_NUM_THREADS. (line 6)
2839 1.1.1.2 mrg * Environment Variable <9>: OMP_NESTED. (line 6)
2840 1.1.1.2 mrg * Environment Variable <10>: OMP_MAX_ACTIVE_LEVELS. (line 6)
2841 1.1 mrg * Environment Variable: OMP_DYNAMIC. (line 6)
2842 1.1 mrg * FDL, GNU Free Documentation License: GNU Free Documentation License.
2843 1.1 mrg (line 6)
2844 1.1 mrg * Implementation specific setting <1>: GOMP_STACKSIZE. (line 6)
2845 1.1 mrg * Implementation specific setting <2>: OMP_SCHEDULE. (line 6)
2846 1.1 mrg * Implementation specific setting <3>: OMP_NUM_THREADS. (line 6)
2847 1.1 mrg * Implementation specific setting: OMP_NESTED. (line 6)
2848 1.1 mrg * Introduction: Top. (line 6)
2849 1.1 mrg
2850 1.1 mrg
2851 1.1 mrg
2852 1.1 mrg Tag Table:
2853 1.1.1.2 mrg Node: Top2039
2854 1.1.1.2 mrg Node: Enabling OpenMP3233
2855 1.1.1.2 mrg Node: Runtime Library Routines4018
2856 1.1.1.2 mrg Node: omp_get_active_level6466
2857 1.1.1.2 mrg Node: omp_get_ancestor_thread_num7170
2858 1.1.1.2 mrg Node: omp_get_dynamic8097
2859 1.1.1.2 mrg Node: omp_get_level8975
2860 1.1.1.2 mrg Node: omp_get_max_active_levels9599
2861 1.1.1.2 mrg Node: omp_get_max_threads10302
2862 1.1.1.2 mrg Node: omp_get_nested11058
2863 1.1.1.2 mrg Node: omp_get_num_procs11970
2864 1.1.1.2 mrg Node: omp_get_num_threads12488
2865 1.1.1.2 mrg Node: omp_get_schedule13570
2866 1.1.1.2 mrg Node: omp_get_team_size14491
2867 1.1.1.2 mrg Node: omp_get_thread_limit15453
2868 1.1.1.2 mrg Node: omp_get_thread_num16076
2869 1.1.1.2 mrg Node: omp_in_parallel16944
2870 1.1.1.2 mrg Node: omp_in_final17591
2871 1.1.1.2 mrg Node: omp_set_dynamic18262
2872 1.1.1.2 mrg Node: omp_set_max_active_levels19099
2873 1.1.1.2 mrg Node: omp_set_nested19879
2874 1.1.1.2 mrg Node: omp_set_num_threads20758
2875 1.1.1.2 mrg Node: omp_set_schedule21594
2876 1.1.1.2 mrg Node: omp_init_lock22666
2877 1.1.1.2 mrg Node: omp_set_lock23317
2878 1.1.1.2 mrg Node: omp_test_lock24168
2879 1.1.1.2 mrg Node: omp_unset_lock25139
2880 1.1.1.2 mrg Node: omp_destroy_lock26065
2881 1.1.1.2 mrg Node: omp_init_nest_lock26739
2882 1.1.1.2 mrg Node: omp_set_nest_lock27472
2883 1.1.1.2 mrg Node: omp_test_nest_lock28383
2884 1.1.1.2 mrg Node: omp_unset_nest_lock29412
2885 1.1.1.2 mrg Node: omp_destroy_nest_lock30422
2886 1.1.1.2 mrg Node: omp_get_wtick31170
2887 1.1.1.2 mrg Node: omp_get_wtime31761
2888 1.1.1.2 mrg Node: Environment Variables32535
2889 1.1.1.2 mrg Node: OMP_DYNAMIC33663
2890 1.1.1.2 mrg Node: OMP_MAX_ACTIVE_LEVELS34231
2891 1.1.1.2 mrg Node: OMP_NESTED34870
2892 1.1.1.2 mrg Node: OMP_NUM_THREADS35474
2893 1.1.1.2 mrg Node: OMP_SCHEDULE36162
2894 1.1.1.2 mrg Node: OMP_STACKSIZE36856
2895 1.1.1.2 mrg Node: OMP_THREAD_LIMIT37682
2896 1.1.1.2 mrg Node: OMP_WAIT_POLICY38277
2897 1.1.1.2 mrg Node: OMP_PROC_BIND38838
2898 1.1.1.2 mrg Node: GOMP_CPU_AFFINITY39396
2899 1.1.1.2 mrg Node: GOMP_STACKSIZE40937
2900 1.1.1.2 mrg Node: The libgomp ABI41747
2901 1.1.1.2 mrg Node: Implementing MASTER construct42546
2902 1.1.1.2 mrg Node: Implementing CRITICAL construct42960
2903 1.1.1.2 mrg Node: Implementing ATOMIC construct43699
2904 1.1.1.2 mrg Node: Implementing FLUSH construct44180
2905 1.1.1.2 mrg Node: Implementing BARRIER construct44451
2906 1.1.1.2 mrg Node: Implementing THREADPRIVATE construct44720
2907 1.1.1.2 mrg Node: Implementing PRIVATE clause45372
2908 1.1.1.2 mrg Node: Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses45953
2909 1.1.1.2 mrg Node: Implementing REDUCTION clause47277
2910 1.1.1.2 mrg Node: Implementing PARALLEL construct47834
2911 1.1.1.2 mrg Node: Implementing FOR construct49091
2912 1.1.1.2 mrg Node: Implementing ORDERED construct51089
2913 1.1.1.2 mrg Node: Implementing SECTIONS construct51395
2914 1.1.1.2 mrg Node: Implementing SINGLE construct52161
2915 1.1.1.2 mrg Node: Reporting Bugs52823
2916 1.1.1.2 mrg Node: Copying53133
2917 1.1.1.2 mrg Node: GNU Free Documentation License90698
2918 1.1.1.2 mrg Node: Funding115840
2919 1.1.1.2 mrg Node: Library Index118365
2920 1.1 mrg
2921 1.1 mrg End Tag Table
2922