]>
Commit | Line | Data |
---|---|---|
3721b9e1 DF |
1 | \input texinfo @c -*-texinfo-*- |
2 | ||
3 | @c %**start of header | |
4 | @setfilename libgomp.info | |
5 | @settitle GNU libgomp | |
6 | @c %**end of header | |
7 | ||
8 | ||
9 | @copying | |
4b24d500 | 10 | Copyright @copyright{} 2006-2021 Free Software Foundation, Inc. |
3721b9e1 DF |
11 | |
12 | Permission is granted to copy, distribute and/or modify this document | |
07a67d6a | 13 | under the terms of the GNU Free Documentation License, Version 1.3 or |
3721b9e1 | 14 | any later version published by the Free Software Foundation; with the |
70b1e376 | 15 | Invariant Sections being ``Funding Free Software'', the Front-Cover |
3721b9e1 DF |
16 | texts being (a) (see below), and with the Back-Cover Texts being (b) |
17 | (see below). A copy of the license is included in the section entitled | |
18 | ``GNU Free Documentation License''. | |
19 | ||
20 | (a) The FSF's Front-Cover Text is: | |
21 | ||
22 | A GNU Manual | |
23 | ||
24 | (b) The FSF's Back-Cover Text is: | |
25 | ||
26 | You have freedom to copy and modify this GNU Manual, like GNU | |
27 | software. Copies published by the Free Software Foundation raise | |
28 | funds for GNU development. | |
29 | @end copying | |
30 | ||
31 | @ifinfo | |
32 | @dircategory GNU Libraries | |
33 | @direntry | |
f1f3453e | 34 | * libgomp: (libgomp). GNU Offloading and Multi Processing Runtime Library. |
3721b9e1 DF |
35 | @end direntry |
36 | ||
f1f3453e | 37 | This manual documents libgomp, the GNU Offloading and Multi Processing |
41dbbb37 TS |
38 | Runtime library. This is the GNU implementation of the OpenMP and |
39 | OpenACC APIs for parallel and accelerator programming in C/C++ and | |
40 | Fortran. | |
3721b9e1 DF |
41 | |
42 | Published by the Free Software Foundation | |
43 | 51 Franklin Street, Fifth Floor | |
44 | Boston, MA 02110-1301 USA | |
45 | ||
46 | @insertcopying | |
47 | @end ifinfo | |
48 | ||
49 | ||
50 | @setchapternewpage odd | |
51 | ||
52 | @titlepage | |
f1f3453e | 53 | @title GNU Offloading and Multi Processing Runtime Library |
41dbbb37 | 54 | @subtitle The GNU OpenMP and OpenACC Implementation |
3721b9e1 DF |
55 | @page |
56 | @vskip 0pt plus 1filll | |
57 | @comment For the @value{version-GCC} Version* | |
58 | @sp 1 | |
59 | Published by the Free Software Foundation @* | |
60 | 51 Franklin Street, Fifth Floor@* | |
61 | Boston, MA 02110-1301, USA@* | |
62 | @sp 1 | |
63 | @insertcopying | |
64 | @end titlepage | |
65 | ||
66 | @summarycontents | |
67 | @contents | |
68 | @page | |
69 | ||
70 | ||
c33fd160 | 71 | @node Top, Enabling OpenMP |
3721b9e1 DF |
72 | @top Introduction |
73 | @cindex Introduction | |
74 | ||
f1f3453e | 75 | This manual documents the usage of libgomp, the GNU Offloading and |
41dbbb37 | 76 | Multi Processing Runtime Library. This includes the GNU |
1a6d1d24 | 77 | implementation of the @uref{https://www.openmp.org, OpenMP} Application |
41dbbb37 TS |
78 | Programming Interface (API) for multi-platform shared-memory parallel |
79 | programming in C/C++ and Fortran, and the GNU implementation of the | |
9651fbaf | 80 | @uref{https://www.openacc.org, OpenACC} Application Programming |
41dbbb37 TS |
81 | Interface (API) for offloading of code to accelerator devices in C/C++ |
82 | and Fortran. | |
3721b9e1 | 83 | |
41dbbb37 TS |
84 | Originally, libgomp implemented the GNU OpenMP Runtime Library. Based |
85 | on this, support for OpenACC and offloading (both OpenACC and OpenMP | |
86 | 4's target construct) has been added later on, and the library's name | |
87 | changed to GNU Offloading and Multi Processing Runtime Library. | |
f1f3453e | 88 | |
3721b9e1 DF |
89 | |
90 | ||
91 | @comment | |
92 | @comment When you add a new menu item, please keep the right hand | |
93 | @comment aligned to the same column. Do not use tabs. This provides | |
94 | @comment better formatting. | |
95 | @comment | |
96 | @menu | |
97 | * Enabling OpenMP:: How to enable OpenMP for your applications. | |
cff72ef4 | 98 | * OpenMP Implementation Status:: List of implemented features by OpenMP version |
4102bda6 TS |
99 | * OpenMP Runtime Library Routines: Runtime Library Routines. |
100 | The OpenMP runtime application programming | |
3721b9e1 | 101 | interface. |
4102bda6 TS |
102 | * OpenMP Environment Variables: Environment Variables. |
103 | Influencing OpenMP runtime behavior with | |
104 | environment variables. | |
cdf6119d JN |
105 | * Enabling OpenACC:: How to enable OpenACC for your |
106 | applications. | |
107 | * OpenACC Runtime Library Routines:: The OpenACC runtime application | |
108 | programming interface. | |
109 | * OpenACC Environment Variables:: Influencing OpenACC runtime behavior with | |
110 | environment variables. | |
111 | * CUDA Streams Usage:: Notes on the implementation of | |
112 | asynchronous operations. | |
113 | * OpenACC Library Interoperability:: OpenACC library interoperability with the | |
114 | NVIDIA CUBLAS library. | |
5fae049d | 115 | * OpenACC Profiling Interface:: |
3721b9e1 | 116 | * The libgomp ABI:: Notes on the external ABI presented by libgomp. |
f1f3453e TS |
117 | * Reporting Bugs:: How to report bugs in the GNU Offloading and |
118 | Multi Processing Runtime Library. | |
3721b9e1 DF |
119 | * Copying:: GNU general public license says |
120 | how you can copy and share libgomp. | |
121 | * GNU Free Documentation License:: | |
122 | How you can copy and share this manual. | |
123 | * Funding:: How to help assure continued work for free | |
124 | software. | |
3d3949df | 125 | * Library Index:: Index of this documentation. |
3721b9e1 DF |
126 | @end menu |
127 | ||
128 | ||
129 | @c --------------------------------------------------------------------- | |
130 | @c Enabling OpenMP | |
131 | @c --------------------------------------------------------------------- | |
132 | ||
133 | @node Enabling OpenMP | |
134 | @chapter Enabling OpenMP | |
135 | ||
136 | To activate the OpenMP extensions for C/C++ and Fortran, the compile-time | |
83fd6c5b | 137 | flag @command{-fopenmp} must be specified. This enables the OpenMP directive |
3721b9e1 DF |
138 | @code{#pragma omp} in C/C++ and @code{!$omp} directives in free form, |
139 | @code{c$omp}, @code{*$omp} and @code{!$omp} directives in fixed form, | |
140 | @code{!$} conditional compilation sentinels in free form and @code{c$}, | |
83fd6c5b | 141 | @code{*$} and @code{!$} sentinels in fixed form, for Fortran. The flag also |
3721b9e1 DF |
142 | arranges for automatic linking of the OpenMP runtime library |
143 | (@ref{Runtime Library Routines}). | |
144 | ||
cff72ef4 TB |
145 | A complete description of all OpenMP directives may be found in the |
146 | @uref{https://www.openmp.org, OpenMP Application Program Interface} manuals. | |
147 | See also @ref{OpenMP Implementation Status}. | |
148 | ||
149 | ||
150 | @c --------------------------------------------------------------------- | |
151 | @c OpenMP Implementation Status | |
152 | @c --------------------------------------------------------------------- | |
153 | ||
154 | @node OpenMP Implementation Status | |
155 | @chapter OpenMP Implementation Status | |
156 | ||
157 | @menu | |
158 | * OpenMP 4.5:: Feature completion status to 4.5 specification | |
159 | * OpenMP 5.0:: Feature completion status to 5.0 specification | |
160 | * OpenMP 5.1:: Feature completion status to 5.1 specification | |
161 | @end menu | |
162 | ||
163 | The @code{_OPENMP} preprocessor macro and Fortran's @code{openmp_version} | |
164 | parameter, provided by @code{omp_lib.h} and the @code{omp_lib} module, have | |
165 | the value @code{201511} (i.e. OpenMP 4.5). | |
166 | ||
167 | @node OpenMP 4.5 | |
168 | @section OpenMP 4.5 | |
169 | ||
170 | The OpenMP 4.5 specification is fully supported. | |
171 | ||
172 | @node OpenMP 5.0 | |
173 | @section OpenMP 5.0 | |
174 | ||
ff7bc505 TB |
175 | @unnumberedsubsec New features listed in Appendix B of the OpenMP specification |
176 | @c This list is sorted as in OpenMP 5.1's B.3 not as in OpenMP 5.0's B.2 | |
177 | ||
178 | @multitable @columnfractions .60 .10 .25 | |
179 | @headitem Description @tab Status @tab Comments | |
180 | @item Array shaping @tab N @tab | |
181 | @item Array sections with non-unit strides in C and C++ @tab N @tab | |
182 | @item Iterators @tab Y @tab | |
183 | @item @code{metadirective} directive @tab N @tab | |
184 | @item @code{declare variant} directive | |
185 | @tab P @tab Only C and C++, simd traits not handled correctly | |
186 | @item @emph{target-offload-var} ICV and @code{OMP_TARGET_OFFLOAD} | |
187 | env variable @tab Y @tab | |
188 | @item Nested-parallel changes to @emph{max-active-levels-var} ICV @tab Y @tab | |
189 | @item @code{requires} directive @tab P | |
190 | @tab Only fulfillable requirement is @code{atomic_default_mem_order} | |
191 | @item @code{teams} construct outside an enclosing target region @tab Y @tab | |
192 | @item Non-rectangular loop nests @tab Y @tab | |
193 | @item @code{!=} as relational-op in canonical loop form for C/C++ @tab Y @tab | |
194 | @item @code{nonmonotonic} as default loop schedule modifier for worksharing-loop | |
195 | constructs @tab Y @tab | |
196 | @item Collapse of associated loops that are imperfectly nested loops @tab N @tab | |
197 | @item Clauses @code{if}, @code{nontemporal} and @code{order(concurrent)} in | |
198 | @code{simd} construct @tab Y @tab | |
199 | @item @code{atomic} constructs in @code{simd} @tab Y @tab | |
200 | @item @code{loop} construct @tab Y @tab | |
201 | @item @code{order(concurrent)} clause @tab Y @tab | |
202 | @item @code{scan} directive and @code{in_scan} modifier for the | |
203 | @code{reduction} clause @tab Y @tab | |
204 | @item @code{in_reduction} clause on @code{task} constructs @tab Y @tab | |
205 | @item @code{in_reduction} clause on @code{target} constructs @tab P | |
206 | @tab Only C/C++, @code{nowait} only stub | |
207 | @item @code{task_reduction} clause with @code{taskgroup} @tab Y @tab | |
208 | @item @code{task} modifier to @code{reduction} clause @tab Y @tab | |
209 | @item @code{affinity} clause to @code{task} construct @tab Y @tab Stub only | |
210 | @item @code{detach} clause to @code{task} construct @tab Y @tab | |
211 | @item @code{omp_fulfill_event} runtime routine @tab Y @tab | |
212 | @item @code{reduction} and @code{in_reduction} clauses on @code{taskloop} | |
213 | and @code{taskloop simd} constructs @tab Y @tab | |
214 | @item @code{taskloop} construct cancelable by @code{cancel} construct | |
215 | @tab Y @tab | |
216 | @item @code{mutexinouset} @emph{dependence-type} for @code{depend} clause | |
217 | @tab Y @tab | |
218 | @item Predefined memory spaces, memory allocators, allocator traits | |
219 | @tab Y @tab Some are only stubs | |
220 | @item Memory management routines @tab Y @tab | |
221 | @item @code{allocate} directive @tab N @tab | |
222 | @item @code{allocate} clause @tab P @tab initial support in C/C++ only | |
223 | @item @code{use_device_addr} clause on @code{target data} @tab Y @tab | |
224 | @item @code{ancestor} modifier on @code{device} clause | |
225 | @tab P @tab Reverse offload unsupported | |
226 | @item Implicit declare target directive @tab Y @tab | |
227 | @item Discontiguous array section with @code{target update} construct | |
228 | @tab N @tab | |
229 | @item C/C++'s lvalue expressions in @code{to}, @code{from} | |
230 | and @code{map} clauses @tab N @tab | |
231 | @item C/C++'s lvalue expressions in @code{depend} clauses @tab Y @tab | |
232 | @item Nested @code{declare target} directive @tab Y @tab | |
233 | @item Combined @code{master} constructs @tab Y @tab | |
234 | @item @code{depend} clause on @code{taskwait} @tab Y @tab | |
235 | @item Weak memory ordering clauses on @code{atomic} and @code{flush} construct | |
236 | @tab Y @tab | |
237 | @item @code{hint} clause on the @code{atomic} construct @tab Y @tab Stub only | |
238 | @item @code{depobj} construct and depend objects @tab Y @tab | |
239 | @item Lock hints were renamed to synchronization hints @tab Y @tab | |
240 | @item @code{conditional} modifier to @code{lastprivate} clause @tab Y @tab | |
241 | @item Map-order clarifications @tab P @tab | |
242 | @item @code{close} @emph{map-type-modifier} @tab Y @tab | |
243 | @item Mapping C/C++ pointer variables and to assign the address of | |
244 | device memory mapped by an array section @tab P @tab | |
245 | @item Mapping of Fortran pointer and allocatable variables, including pointer | |
246 | and allocatable components of variables | |
247 | @tab P @tab Mapping of vars with allocatable components unspported | |
248 | @item @code{defaultmap} extensions @tab Y @tab | |
249 | @item @code{declare mapper} directive @tab N @tab | |
250 | @item @code{omp_get_supported_active_levels} routine @tab Y @tab | |
251 | @item Runtime routines and environment variables to display runtime thread | |
252 | affinity information @tab Y @tab | |
253 | @item @code{omp_pause_resource} and @code{omp_pause_resource_all} runtime | |
254 | routines @tab Y @tab | |
255 | @item @code{omp_get_device_num} runtime routine @tab Y @tab | |
256 | @item OMPT interface @tab N @tab | |
257 | @item OMPD interface @tab N @tab | |
258 | @end multitable | |
259 | ||
260 | @unnumberedsubsec Other new OpenMP 5.0 features | |
261 | ||
262 | @multitable @columnfractions .60 .10 .25 | |
263 | @headitem Description @tab Status @tab Comments | |
264 | @item Supporting C++'s range-based for loop @tab Y @tab | |
265 | @end multitable | |
266 | ||
cff72ef4 TB |
267 | |
268 | @node OpenMP 5.1 | |
269 | @section OpenMP 5.1 | |
270 | ||
271 | @unnumberedsubsec New features listed in Appendix B of the OpenMP specification | |
272 | ||
273 | @multitable @columnfractions .60 .10 .25 | |
274 | @headitem Description @tab Status @tab Comments | |
275 | @item OpenMP directive as C++ attribute specifiers @tab Y @tab | |
276 | @item @code{omp_all_memory} reserved locator @tab N @tab | |
277 | @item @emph{target_device trait} in OpenMP Context @tab N @tab | |
278 | @item @code{target_device} selector set in context selectors @tab N @tab | |
4a7842bb | 279 | @item C/C++'s @code{declare variant} directive: elision support of |
cff72ef4 | 280 | preprocessed code @tab N @tab |
4a7842bb | 281 | @item @code{declare variant}: new clauses @code{adjust_args} and |
cff72ef4 TB |
282 | @code{append_args} @tab N @tab |
283 | @item @code{dispatch} construct @tab N @tab | |
284 | @item device-specific ICV settings the environment variables @tab N @tab | |
285 | @item assume directive @tab N @tab | |
286 | @item @code{nothing} directive @tab Y @tab | |
287 | @item @code{error} directive @tab Y @tab | |
288 | @item @code{masked} construct @tab Y @tab | |
289 | @item @code{scope} directive @tab Y @tab | |
290 | @item Loop transformation constructs @tab N @tab | |
291 | @item @code{strict} modifier in the @code{grainsize} and @code{num_tasks} | |
292 | clauses of the taskloop construct @tab Y @tab | |
293 | @item @code{align} clause/modifier in @code{allocate} directive/clause | |
294 | and @code{allocator} directive @tab N @tab | |
295 | @item @code{thread_limit} clause to @code{target} construct @tab N @tab | |
296 | @item @code{has_device_addr} clause to @code{target} construct @tab N @tab | |
297 | @item iterators in @code{target update} motion clauses and @code{map} | |
298 | clauses @tab N @tab | |
299 | @item indirect calls to the device version of a procedure or function in | |
300 | @code{target} regions @tab N @tab | |
301 | @item @code{interop} directive @tab N @tab | |
302 | @item @code{omp_interop_t} object support in runtime routines @tab N @tab | |
303 | @item @code{nowait} clause in @code{taskwait} directive @tab N @tab | |
304 | @item Extensions to the @code{atomic} directive @tab N @tab | |
305 | @item @code{seq_cst} clause on a @code{flush} construct @tab Y @tab | |
306 | @item @code{inoutset} argument to the @code{depend} clause @tab N @tab | |
307 | @item @code{private} and @code{firstprivate} argument to @code{default} | |
308 | clause in C and C++ @tab N @tab | |
309 | @item @code{present} argument to @code{defaultmap} clause @tab N @tab | |
310 | @item @code{omp_set_num_teams}, @code{omp_set_teams_thread_limit}, | |
311 | @code{omp_get_max_teams}, @code{omp_get_teams_thread_limit} runtime | |
312 | routines @tab N @tab | |
313 | @item @code{omp_target_is_accessible} runtime routine @tab N @tab | |
314 | @item @code{omp_target_memcpy_async} and @code{omp_target_memcpy_rect_async} | |
315 | runtime routines @tab N @tab | |
316 | @item @code{omp_get_mapped_ptr} runtime routine @tab N @tab | |
317 | @item @code{omp_calloc}, @code{omp_realloc}, @code{omp_aligned_alloc} and | |
318 | @code{omp_aligned_calloc} runtime routines @tab N @tab | |
319 | @item @code{omp_alloctrait_key_t} enum: @code{omp_atv_serialized} added, | |
320 | @code{omp_atv_default} changed @tab Y @tab | |
321 | @item @code{omp_display_env} runtime routine @tab P | |
322 | @tab Not inside @code{target} regions | |
323 | @item @code{ompt_scope_endpoint_t} enum: @code{ompt_scope_beginend} @tab N @tab | |
324 | @item @code{ompt_sync_region_t} enum additions @tab N @tab | |
325 | @item @code{ompt_state_t} enum: @code{ompt_state_wait_barrier_implementation} | |
326 | and @code{ompt_state_wait_barrier_teams} @tab N @tab | |
327 | @item @code{ompt_callback_target_data_op_emi_t}, | |
328 | @code{ompt_callback_target_emi_t}, @code{ompt_callback_target_map_emi_t} | |
329 | and @code{ompt_callback_target_submit_emi_t} @tab N @tab | |
330 | @item @code{ompt_callback_error_t} type @tab N @tab | |
331 | @item @code{OMP_PLACES} syntax was extension @tab N @tab | |
332 | @item @code{OMP_NUM_TEAMS} and @code{OMP_TEAMS_THREAD_LIMIT} environment | |
333 | variables @tab N @tab | |
334 | @end multitable | |
335 | ||
336 | @unnumberedsubsec Other new OpenMP 5.1 features | |
337 | ||
338 | @multitable @columnfractions .60 .10 .25 | |
339 | @headitem Description @tab Status @tab Comments | |
340 | @item Suppport of strictly structured blocks in Fortran @tab N @tab | |
341 | @end multitable | |
3721b9e1 DF |
342 | |
343 | ||
344 | @c --------------------------------------------------------------------- | |
4102bda6 | 345 | @c OpenMP Runtime Library Routines |
3721b9e1 DF |
346 | @c --------------------------------------------------------------------- |
347 | ||
348 | @node Runtime Library Routines | |
4102bda6 | 349 | @chapter OpenMP Runtime Library Routines |
3721b9e1 | 350 | |
83fd6c5b | 351 | The runtime routines described here are defined by Section 3 of the OpenMP |
00b9bd52 | 352 | specification in version 4.5. The routines are structured in following |
5c6ed53a | 353 | three parts: |
3721b9e1 | 354 | |
72832460 | 355 | @menu |
83fd6c5b TB |
356 | Control threads, processors and the parallel environment. They have C |
357 | linkage, and do not throw exceptions. | |
f5745bed | 358 | |
5c6ed53a TB |
359 | * omp_get_active_level:: Number of active parallel regions |
360 | * omp_get_ancestor_thread_num:: Ancestor thread ID | |
83fd6c5b TB |
361 | * omp_get_cancellation:: Whether cancellation support is enabled |
362 | * omp_get_default_device:: Get the default device for target regions | |
0bac793e | 363 | * omp_get_device_num:: Get device that current thread is running on |
5c6ed53a | 364 | * omp_get_dynamic:: Dynamic teams setting |
74c9882b | 365 | * omp_get_initial_device:: Device number of host device |
5c6ed53a | 366 | * omp_get_level:: Number of parallel regions |
445567b2 | 367 | * omp_get_max_active_levels:: Current maximum number of active regions |
d9a6bd32 | 368 | * omp_get_max_task_priority:: Maximum task priority value that can be set |
6a2ba183 | 369 | * omp_get_max_threads:: Maximum number of threads of parallel region |
5c6ed53a | 370 | * omp_get_nested:: Nested parallel regions |
83fd6c5b | 371 | * omp_get_num_devices:: Number of target devices |
5c6ed53a | 372 | * omp_get_num_procs:: Number of processors online |
83fd6c5b | 373 | * omp_get_num_teams:: Number of teams |
5c6ed53a | 374 | * omp_get_num_threads:: Size of the active team |
83fd6c5b | 375 | * omp_get_proc_bind:: Whether theads may be moved between CPUs |
5c6ed53a | 376 | * omp_get_schedule:: Obtain the runtime scheduling method |
445567b2 | 377 | * omp_get_supported_active_levels:: Maximum number of active regions supported |
83fd6c5b | 378 | * omp_get_team_num:: Get team number |
5c6ed53a | 379 | * omp_get_team_size:: Number of threads in a team |
6a2ba183 | 380 | * omp_get_thread_limit:: Maximum number of threads |
5c6ed53a TB |
381 | * omp_get_thread_num:: Current thread ID |
382 | * omp_in_parallel:: Whether a parallel region is active | |
20906c66 | 383 | * omp_in_final:: Whether in final or included task region |
83fd6c5b TB |
384 | * omp_is_initial_device:: Whether executing on the host device |
385 | * omp_set_default_device:: Set the default device for target regions | |
5c6ed53a TB |
386 | * omp_set_dynamic:: Enable/disable dynamic teams |
387 | * omp_set_max_active_levels:: Limits the number of active parallel regions | |
388 | * omp_set_nested:: Enable/disable nested parallel regions | |
389 | * omp_set_num_threads:: Set upper team size limit | |
390 | * omp_set_schedule:: Set the runtime scheduling method | |
3721b9e1 DF |
391 | |
392 | Initialize, set, test, unset and destroy simple and nested locks. | |
393 | ||
3721b9e1 DF |
394 | * omp_init_lock:: Initialize simple lock |
395 | * omp_set_lock:: Wait for and set simple lock | |
396 | * omp_test_lock:: Test and set simple lock if available | |
397 | * omp_unset_lock:: Unset simple lock | |
398 | * omp_destroy_lock:: Destroy simple lock | |
399 | * omp_init_nest_lock:: Initialize nested lock | |
400 | * omp_set_nest_lock:: Wait for and set simple lock | |
401 | * omp_test_nest_lock:: Test and set nested lock if available | |
402 | * omp_unset_nest_lock:: Unset nested lock | |
403 | * omp_destroy_nest_lock:: Destroy nested lock | |
3721b9e1 DF |
404 | |
405 | Portable, thread-based, wall clock timer. | |
406 | ||
3721b9e1 DF |
407 | * omp_get_wtick:: Get timer precision. |
408 | * omp_get_wtime:: Elapsed wall clock time. | |
0194e2f0 KCY |
409 | |
410 | Support for event objects. | |
411 | ||
412 | * omp_fulfill_event:: Fulfill and destroy an OpenMP event. | |
3721b9e1 DF |
413 | @end menu |
414 | ||
5c6ed53a TB |
415 | |
416 | ||
417 | @node omp_get_active_level | |
418 | @section @code{omp_get_active_level} -- Number of parallel regions | |
419 | @table @asis | |
420 | @item @emph{Description}: | |
421 | This function returns the nesting level for the active parallel blocks, | |
422 | which enclose the calling call. | |
423 | ||
424 | @item @emph{C/C++} | |
425 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 426 | @item @emph{Prototype}: @tab @code{int omp_get_active_level(void);} |
5c6ed53a TB |
427 | @end multitable |
428 | ||
429 | @item @emph{Fortran}: | |
430 | @multitable @columnfractions .20 .80 | |
acb5c916 | 431 | @item @emph{Interface}: @tab @code{integer function omp_get_active_level()} |
5c6ed53a TB |
432 | @end multitable |
433 | ||
434 | @item @emph{See also}: | |
435 | @ref{omp_get_level}, @ref{omp_get_max_active_levels}, @ref{omp_set_max_active_levels} | |
436 | ||
437 | @item @emph{Reference}: | |
1a6d1d24 | 438 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.20. |
5c6ed53a TB |
439 | @end table |
440 | ||
441 | ||
442 | ||
443 | @node omp_get_ancestor_thread_num | |
444 | @section @code{omp_get_ancestor_thread_num} -- Ancestor thread ID | |
445 | @table @asis | |
446 | @item @emph{Description}: | |
447 | This function returns the thread identification number for the given | |
83fd6c5b | 448 | nesting level of the current thread. For values of @var{level} outside |
5c6ed53a TB |
449 | zero to @code{omp_get_level} -1 is returned; if @var{level} is |
450 | @code{omp_get_level} the result is identical to @code{omp_get_thread_num}. | |
451 | ||
452 | @item @emph{C/C++} | |
453 | @multitable @columnfractions .20 .80 | |
454 | @item @emph{Prototype}: @tab @code{int omp_get_ancestor_thread_num(int level);} | |
455 | @end multitable | |
456 | ||
457 | @item @emph{Fortran}: | |
458 | @multitable @columnfractions .20 .80 | |
acb5c916 | 459 | @item @emph{Interface}: @tab @code{integer function omp_get_ancestor_thread_num(level)} |
5c6ed53a TB |
460 | @item @tab @code{integer level} |
461 | @end multitable | |
462 | ||
463 | @item @emph{See also}: | |
464 | @ref{omp_get_level}, @ref{omp_get_thread_num}, @ref{omp_get_team_size} | |
465 | ||
466 | @item @emph{Reference}: | |
1a6d1d24 | 467 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.18. |
83fd6c5b TB |
468 | @end table |
469 | ||
470 | ||
471 | ||
472 | @node omp_get_cancellation | |
473 | @section @code{omp_get_cancellation} -- Whether cancellation support is enabled | |
474 | @table @asis | |
475 | @item @emph{Description}: | |
476 | This function returns @code{true} if cancellation is activated, @code{false} | |
477 | otherwise. Here, @code{true} and @code{false} represent their language-specific | |
478 | counterparts. Unless @env{OMP_CANCELLATION} is set true, cancellations are | |
479 | deactivated. | |
480 | ||
481 | @item @emph{C/C++}: | |
482 | @multitable @columnfractions .20 .80 | |
483 | @item @emph{Prototype}: @tab @code{int omp_get_cancellation(void);} | |
484 | @end multitable | |
485 | ||
486 | @item @emph{Fortran}: | |
487 | @multitable @columnfractions .20 .80 | |
488 | @item @emph{Interface}: @tab @code{logical function omp_get_cancellation()} | |
489 | @end multitable | |
490 | ||
491 | @item @emph{See also}: | |
492 | @ref{OMP_CANCELLATION} | |
493 | ||
494 | @item @emph{Reference}: | |
1a6d1d24 | 495 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.9. |
83fd6c5b TB |
496 | @end table |
497 | ||
498 | ||
499 | ||
500 | @node omp_get_default_device | |
501 | @section @code{omp_get_default_device} -- Get the default device for target regions | |
502 | @table @asis | |
503 | @item @emph{Description}: | |
504 | Get the default device for target regions without device clause. | |
505 | ||
506 | @item @emph{C/C++}: | |
507 | @multitable @columnfractions .20 .80 | |
508 | @item @emph{Prototype}: @tab @code{int omp_get_default_device(void);} | |
509 | @end multitable | |
510 | ||
511 | @item @emph{Fortran}: | |
512 | @multitable @columnfractions .20 .80 | |
513 | @item @emph{Interface}: @tab @code{integer function omp_get_default_device()} | |
514 | @end multitable | |
515 | ||
516 | @item @emph{See also}: | |
517 | @ref{OMP_DEFAULT_DEVICE}, @ref{omp_set_default_device} | |
518 | ||
519 | @item @emph{Reference}: | |
1a6d1d24 | 520 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.30. |
5c6ed53a TB |
521 | @end table |
522 | ||
523 | ||
524 | ||
3721b9e1 DF |
525 | @node omp_get_dynamic |
526 | @section @code{omp_get_dynamic} -- Dynamic teams setting | |
527 | @table @asis | |
528 | @item @emph{Description}: | |
529 | This function returns @code{true} if enabled, @code{false} otherwise. | |
530 | Here, @code{true} and @code{false} represent their language-specific | |
531 | counterparts. | |
532 | ||
14734fc7 | 533 | The dynamic team setting may be initialized at startup by the |
83fd6c5b TB |
534 | @env{OMP_DYNAMIC} environment variable or at runtime using |
535 | @code{omp_set_dynamic}. If undefined, dynamic adjustment is | |
14734fc7 DF |
536 | disabled by default. |
537 | ||
3721b9e1 DF |
538 | @item @emph{C/C++}: |
539 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 540 | @item @emph{Prototype}: @tab @code{int omp_get_dynamic(void);} |
3721b9e1 DF |
541 | @end multitable |
542 | ||
543 | @item @emph{Fortran}: | |
544 | @multitable @columnfractions .20 .80 | |
545 | @item @emph{Interface}: @tab @code{logical function omp_get_dynamic()} | |
546 | @end multitable | |
547 | ||
548 | @item @emph{See also}: | |
14734fc7 | 549 | @ref{omp_set_dynamic}, @ref{OMP_DYNAMIC} |
3721b9e1 DF |
550 | |
551 | @item @emph{Reference}: | |
1a6d1d24 | 552 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.8. |
5c6ed53a TB |
553 | @end table |
554 | ||
555 | ||
556 | ||
74c9882b JJ |
557 | @node omp_get_initial_device |
558 | @section @code{omp_get_initial_device} -- Return device number of initial device | |
559 | @table @asis | |
560 | @item @emph{Description}: | |
561 | This function returns a device number that represents the host device. | |
562 | For OpenMP 5.1, this must be equal to the value returned by the | |
563 | @code{omp_get_num_devices} function. | |
564 | ||
565 | @item @emph{C/C++} | |
566 | @multitable @columnfractions .20 .80 | |
567 | @item @emph{Prototype}: @tab @code{int omp_get_initial_device(void);} | |
568 | @end multitable | |
569 | ||
570 | @item @emph{Fortran}: | |
571 | @multitable @columnfractions .20 .80 | |
572 | @item @emph{Interface}: @tab @code{integer function omp_get_initial_device()} | |
573 | @end multitable | |
574 | ||
575 | @item @emph{See also}: | |
576 | @ref{omp_get_num_devices} | |
577 | ||
578 | @item @emph{Reference}: | |
579 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.35. | |
580 | @end table | |
581 | ||
582 | ||
583 | ||
0bac793e CLT |
584 | @node omp_get_device_num |
585 | @section @code{omp_get_device_num} -- Return device number of current device | |
586 | @table @asis | |
587 | @item @emph{Description}: | |
588 | This function returns a device number that represents the device that the | |
589 | current thread is executing on. For OpenMP 5.0, this must be equal to the | |
590 | value returned by the @code{omp_get_initial_device} function when called | |
591 | from the host. | |
592 | ||
593 | @item @emph{C/C++} | |
594 | @multitable @columnfractions .20 .80 | |
595 | @item @emph{Prototype}: @tab @code{int omp_get_device_num(void);} | |
596 | @end multitable | |
597 | ||
598 | @item @emph{Fortran}: | |
599 | @multitable @columnfractions .20 .80 | |
600 | @item @emph{Interface}: @tab @code{integer function omp_get_device_num()} | |
601 | @end multitable | |
602 | ||
603 | @item @emph{See also}: | |
604 | @ref{omp_get_initial_device} | |
605 | ||
606 | @item @emph{Reference}: | |
607 | @uref{https://www.openmp.org, OpenMP specification v5.0}, Section 3.2.37. | |
608 | @end table | |
609 | ||
610 | ||
611 | ||
5c6ed53a TB |
612 | @node omp_get_level |
613 | @section @code{omp_get_level} -- Obtain the current nesting level | |
614 | @table @asis | |
615 | @item @emph{Description}: | |
616 | This function returns the nesting level for the parallel blocks, | |
617 | which enclose the calling call. | |
618 | ||
619 | @item @emph{C/C++} | |
620 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 621 | @item @emph{Prototype}: @tab @code{int omp_get_level(void);} |
5c6ed53a TB |
622 | @end multitable |
623 | ||
624 | @item @emph{Fortran}: | |
625 | @multitable @columnfractions .20 .80 | |
acb5c916 | 626 | @item @emph{Interface}: @tab @code{integer function omp_level()} |
5c6ed53a TB |
627 | @end multitable |
628 | ||
629 | @item @emph{See also}: | |
630 | @ref{omp_get_active_level} | |
631 | ||
632 | @item @emph{Reference}: | |
1a6d1d24 | 633 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.17. |
5c6ed53a TB |
634 | @end table |
635 | ||
636 | ||
637 | ||
638 | @node omp_get_max_active_levels | |
445567b2 | 639 | @section @code{omp_get_max_active_levels} -- Current maximum number of active regions |
5c6ed53a TB |
640 | @table @asis |
641 | @item @emph{Description}: | |
6a2ba183 | 642 | This function obtains the maximum allowed number of nested, active parallel regions. |
5c6ed53a TB |
643 | |
644 | @item @emph{C/C++} | |
645 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 646 | @item @emph{Prototype}: @tab @code{int omp_get_max_active_levels(void);} |
5c6ed53a TB |
647 | @end multitable |
648 | ||
649 | @item @emph{Fortran}: | |
650 | @multitable @columnfractions .20 .80 | |
acb5c916 | 651 | @item @emph{Interface}: @tab @code{integer function omp_get_max_active_levels()} |
5c6ed53a TB |
652 | @end multitable |
653 | ||
654 | @item @emph{See also}: | |
655 | @ref{omp_set_max_active_levels}, @ref{omp_get_active_level} | |
656 | ||
657 | @item @emph{Reference}: | |
1a6d1d24 | 658 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.16. |
3721b9e1 DF |
659 | @end table |
660 | ||
661 | ||
d9a6bd32 JJ |
662 | @node omp_get_max_task_priority |
663 | @section @code{omp_get_max_task_priority} -- Maximum priority value | |
664 | that can be set for tasks. | |
665 | @table @asis | |
666 | @item @emph{Description}: | |
667 | This function obtains the maximum allowed priority number for tasks. | |
668 | ||
669 | @item @emph{C/C++} | |
670 | @multitable @columnfractions .20 .80 | |
671 | @item @emph{Prototype}: @tab @code{int omp_get_max_task_priority(void);} | |
672 | @end multitable | |
673 | ||
674 | @item @emph{Fortran}: | |
675 | @multitable @columnfractions .20 .80 | |
676 | @item @emph{Interface}: @tab @code{integer function omp_get_max_task_priority()} | |
677 | @end multitable | |
678 | ||
679 | @item @emph{Reference}: | |
1a6d1d24 | 680 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.29. |
d9a6bd32 JJ |
681 | @end table |
682 | ||
3721b9e1 DF |
683 | |
684 | @node omp_get_max_threads | |
6a2ba183 | 685 | @section @code{omp_get_max_threads} -- Maximum number of threads of parallel region |
3721b9e1 DF |
686 | @table @asis |
687 | @item @emph{Description}: | |
6a2ba183 | 688 | Return the maximum number of threads used for the current parallel region |
5c6ed53a | 689 | that does not use the clause @code{num_threads}. |
3721b9e1 DF |
690 | |
691 | @item @emph{C/C++}: | |
692 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 693 | @item @emph{Prototype}: @tab @code{int omp_get_max_threads(void);} |
3721b9e1 DF |
694 | @end multitable |
695 | ||
696 | @item @emph{Fortran}: | |
697 | @multitable @columnfractions .20 .80 | |
698 | @item @emph{Interface}: @tab @code{integer function omp_get_max_threads()} | |
699 | @end multitable | |
700 | ||
701 | @item @emph{See also}: | |
5c6ed53a | 702 | @ref{omp_set_num_threads}, @ref{omp_set_dynamic}, @ref{omp_get_thread_limit} |
3721b9e1 DF |
703 | |
704 | @item @emph{Reference}: | |
1a6d1d24 | 705 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.3. |
3721b9e1 DF |
706 | @end table |
707 | ||
708 | ||
709 | ||
710 | @node omp_get_nested | |
711 | @section @code{omp_get_nested} -- Nested parallel regions | |
712 | @table @asis | |
713 | @item @emph{Description}: | |
714 | This function returns @code{true} if nested parallel regions are | |
83fd6c5b | 715 | enabled, @code{false} otherwise. Here, @code{true} and @code{false} |
3721b9e1 DF |
716 | represent their language-specific counterparts. |
717 | ||
6fae7eda KCY |
718 | The state of nested parallel regions at startup depends on several |
719 | environment variables. If @env{OMP_MAX_ACTIVE_LEVELS} is defined | |
720 | and is set to greater than one, then nested parallel regions will be | |
721 | enabled. If not defined, then the value of the @env{OMP_NESTED} | |
722 | environment variable will be followed if defined. If neither are | |
723 | defined, then if either @env{OMP_NUM_THREADS} or @env{OMP_PROC_BIND} | |
724 | are defined with a list of more than one value, then nested parallel | |
725 | regions are enabled. If none of these are defined, then nested parallel | |
726 | regions are disabled by default. | |
727 | ||
728 | Nested parallel regions can be enabled or disabled at runtime using | |
729 | @code{omp_set_nested}, or by setting the maximum number of nested | |
730 | regions with @code{omp_set_max_active_levels} to one to disable, or | |
731 | above one to enable. | |
14734fc7 | 732 | |
3721b9e1 DF |
733 | @item @emph{C/C++}: |
734 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 735 | @item @emph{Prototype}: @tab @code{int omp_get_nested(void);} |
3721b9e1 DF |
736 | @end multitable |
737 | ||
738 | @item @emph{Fortran}: | |
739 | @multitable @columnfractions .20 .80 | |
87350d4a | 740 | @item @emph{Interface}: @tab @code{logical function omp_get_nested()} |
3721b9e1 DF |
741 | @end multitable |
742 | ||
743 | @item @emph{See also}: | |
6fae7eda KCY |
744 | @ref{omp_set_max_active_levels}, @ref{omp_set_nested}, |
745 | @ref{OMP_MAX_ACTIVE_LEVELS}, @ref{OMP_NESTED} | |
3721b9e1 DF |
746 | |
747 | @item @emph{Reference}: | |
1a6d1d24 | 748 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.11. |
83fd6c5b TB |
749 | @end table |
750 | ||
751 | ||
752 | ||
753 | @node omp_get_num_devices | |
754 | @section @code{omp_get_num_devices} -- Number of target devices | |
755 | @table @asis | |
756 | @item @emph{Description}: | |
757 | Returns the number of target devices. | |
758 | ||
759 | @item @emph{C/C++}: | |
760 | @multitable @columnfractions .20 .80 | |
761 | @item @emph{Prototype}: @tab @code{int omp_get_num_devices(void);} | |
762 | @end multitable | |
763 | ||
764 | @item @emph{Fortran}: | |
765 | @multitable @columnfractions .20 .80 | |
766 | @item @emph{Interface}: @tab @code{integer function omp_get_num_devices()} | |
767 | @end multitable | |
768 | ||
769 | @item @emph{Reference}: | |
1a6d1d24 | 770 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.31. |
3721b9e1 DF |
771 | @end table |
772 | ||
773 | ||
774 | ||
775 | @node omp_get_num_procs | |
776 | @section @code{omp_get_num_procs} -- Number of processors online | |
777 | @table @asis | |
778 | @item @emph{Description}: | |
83fd6c5b | 779 | Returns the number of processors online on that device. |
3721b9e1 DF |
780 | |
781 | @item @emph{C/C++}: | |
782 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 783 | @item @emph{Prototype}: @tab @code{int omp_get_num_procs(void);} |
3721b9e1 DF |
784 | @end multitable |
785 | ||
786 | @item @emph{Fortran}: | |
787 | @multitable @columnfractions .20 .80 | |
788 | @item @emph{Interface}: @tab @code{integer function omp_get_num_procs()} | |
789 | @end multitable | |
790 | ||
791 | @item @emph{Reference}: | |
1a6d1d24 | 792 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.5. |
83fd6c5b TB |
793 | @end table |
794 | ||
795 | ||
796 | ||
797 | @node omp_get_num_teams | |
798 | @section @code{omp_get_num_teams} -- Number of teams | |
799 | @table @asis | |
800 | @item @emph{Description}: | |
801 | Returns the number of teams in the current team region. | |
802 | ||
803 | @item @emph{C/C++}: | |
804 | @multitable @columnfractions .20 .80 | |
805 | @item @emph{Prototype}: @tab @code{int omp_get_num_teams(void);} | |
806 | @end multitable | |
807 | ||
808 | @item @emph{Fortran}: | |
809 | @multitable @columnfractions .20 .80 | |
810 | @item @emph{Interface}: @tab @code{integer function omp_get_num_teams()} | |
811 | @end multitable | |
812 | ||
813 | @item @emph{Reference}: | |
1a6d1d24 | 814 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.32. |
3721b9e1 DF |
815 | @end table |
816 | ||
817 | ||
818 | ||
819 | @node omp_get_num_threads | |
820 | @section @code{omp_get_num_threads} -- Size of the active team | |
821 | @table @asis | |
822 | @item @emph{Description}: | |
83fd6c5b | 823 | Returns the number of threads in the current team. In a sequential section of |
3721b9e1 DF |
824 | the program @code{omp_get_num_threads} returns 1. |
825 | ||
14734fc7 | 826 | The default team size may be initialized at startup by the |
83fd6c5b | 827 | @env{OMP_NUM_THREADS} environment variable. At runtime, the size |
14734fc7 | 828 | of the current team may be set either by the @code{NUM_THREADS} |
83fd6c5b TB |
829 | clause or by @code{omp_set_num_threads}. If none of the above were |
830 | used to define a specific value and @env{OMP_DYNAMIC} is disabled, | |
14734fc7 DF |
831 | one thread per CPU online is used. |
832 | ||
3721b9e1 DF |
833 | @item @emph{C/C++}: |
834 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 835 | @item @emph{Prototype}: @tab @code{int omp_get_num_threads(void);} |
3721b9e1 DF |
836 | @end multitable |
837 | ||
838 | @item @emph{Fortran}: | |
839 | @multitable @columnfractions .20 .80 | |
840 | @item @emph{Interface}: @tab @code{integer function omp_get_num_threads()} | |
841 | @end multitable | |
842 | ||
843 | @item @emph{See also}: | |
844 | @ref{omp_get_max_threads}, @ref{omp_set_num_threads}, @ref{OMP_NUM_THREADS} | |
845 | ||
846 | @item @emph{Reference}: | |
1a6d1d24 | 847 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.2. |
83fd6c5b TB |
848 | @end table |
849 | ||
850 | ||
851 | ||
852 | @node omp_get_proc_bind | |
853 | @section @code{omp_get_proc_bind} -- Whether theads may be moved between CPUs | |
854 | @table @asis | |
855 | @item @emph{Description}: | |
856 | This functions returns the currently active thread affinity policy, which is | |
857 | set via @env{OMP_PROC_BIND}. Possible values are @code{omp_proc_bind_false}, | |
432de084 TB |
858 | @code{omp_proc_bind_true}, @code{omp_proc_bind_primary}, |
859 | @code{omp_proc_bind_master}, @code{omp_proc_bind_close} and @code{omp_proc_bind_spread}, | |
860 | where @code{omp_proc_bind_master} is an alias for @code{omp_proc_bind_primary}. | |
83fd6c5b TB |
861 | |
862 | @item @emph{C/C++}: | |
863 | @multitable @columnfractions .20 .80 | |
864 | @item @emph{Prototype}: @tab @code{omp_proc_bind_t omp_get_proc_bind(void);} | |
865 | @end multitable | |
866 | ||
867 | @item @emph{Fortran}: | |
868 | @multitable @columnfractions .20 .80 | |
869 | @item @emph{Interface}: @tab @code{integer(kind=omp_proc_bind_kind) function omp_get_proc_bind()} | |
870 | @end multitable | |
871 | ||
872 | @item @emph{See also}: | |
873 | @ref{OMP_PROC_BIND}, @ref{OMP_PLACES}, @ref{GOMP_CPU_AFFINITY}, | |
874 | ||
875 | @item @emph{Reference}: | |
1a6d1d24 | 876 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.22. |
5c6ed53a TB |
877 | @end table |
878 | ||
879 | ||
880 | ||
881 | @node omp_get_schedule | |
882 | @section @code{omp_get_schedule} -- Obtain the runtime scheduling method | |
883 | @table @asis | |
884 | @item @emph{Description}: | |
83fd6c5b | 885 | Obtain the runtime scheduling method. The @var{kind} argument will be |
5c6ed53a | 886 | set to the value @code{omp_sched_static}, @code{omp_sched_dynamic}, |
83fd6c5b | 887 | @code{omp_sched_guided} or @code{omp_sched_auto}. The second argument, |
d9a6bd32 | 888 | @var{chunk_size}, is set to the chunk size. |
5c6ed53a TB |
889 | |
890 | @item @emph{C/C++} | |
891 | @multitable @columnfractions .20 .80 | |
d9a6bd32 | 892 | @item @emph{Prototype}: @tab @code{void omp_get_schedule(omp_sched_t *kind, int *chunk_size);} |
5c6ed53a TB |
893 | @end multitable |
894 | ||
895 | @item @emph{Fortran}: | |
896 | @multitable @columnfractions .20 .80 | |
d9a6bd32 | 897 | @item @emph{Interface}: @tab @code{subroutine omp_get_schedule(kind, chunk_size)} |
5c6ed53a | 898 | @item @tab @code{integer(kind=omp_sched_kind) kind} |
d9a6bd32 | 899 | @item @tab @code{integer chunk_size} |
5c6ed53a TB |
900 | @end multitable |
901 | ||
902 | @item @emph{See also}: | |
903 | @ref{omp_set_schedule}, @ref{OMP_SCHEDULE} | |
904 | ||
905 | @item @emph{Reference}: | |
1a6d1d24 | 906 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.13. |
83fd6c5b TB |
907 | @end table |
908 | ||
909 | ||
8949b985 KCY |
910 | @node omp_get_supported_active_levels |
911 | @section @code{omp_get_supported_active_levels} -- Maximum number of active regions supported | |
912 | @table @asis | |
913 | @item @emph{Description}: | |
914 | This function returns the maximum number of nested, active parallel regions | |
915 | supported by this implementation. | |
916 | ||
917 | @item @emph{C/C++} | |
918 | @multitable @columnfractions .20 .80 | |
919 | @item @emph{Prototype}: @tab @code{int omp_get_supported_active_levels(void);} | |
920 | @end multitable | |
921 | ||
922 | @item @emph{Fortran}: | |
923 | @multitable @columnfractions .20 .80 | |
924 | @item @emph{Interface}: @tab @code{integer function omp_get_supported_active_levels()} | |
925 | @end multitable | |
926 | ||
927 | @item @emph{See also}: | |
928 | @ref{omp_get_max_active_levels}, @ref{omp_set_max_active_levels} | |
929 | ||
930 | @item @emph{Reference}: | |
931 | @uref{https://www.openmp.org, OpenMP specification v5.0}, Section 3.2.15. | |
932 | @end table | |
933 | ||
934 | ||
83fd6c5b TB |
935 | |
936 | @node omp_get_team_num | |
937 | @section @code{omp_get_team_num} -- Get team number | |
938 | @table @asis | |
939 | @item @emph{Description}: | |
940 | Returns the team number of the calling thread. | |
941 | ||
942 | @item @emph{C/C++}: | |
943 | @multitable @columnfractions .20 .80 | |
944 | @item @emph{Prototype}: @tab @code{int omp_get_team_num(void);} | |
945 | @end multitable | |
946 | ||
947 | @item @emph{Fortran}: | |
948 | @multitable @columnfractions .20 .80 | |
949 | @item @emph{Interface}: @tab @code{integer function omp_get_team_num()} | |
950 | @end multitable | |
951 | ||
952 | @item @emph{Reference}: | |
1a6d1d24 | 953 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.33. |
5c6ed53a TB |
954 | @end table |
955 | ||
956 | ||
957 | ||
958 | @node omp_get_team_size | |
959 | @section @code{omp_get_team_size} -- Number of threads in a team | |
960 | @table @asis | |
961 | @item @emph{Description}: | |
962 | This function returns the number of threads in a thread team to which | |
83fd6c5b | 963 | either the current thread or its ancestor belongs. For values of @var{level} |
6a2ba183 AH |
964 | outside zero to @code{omp_get_level}, -1 is returned; if @var{level} is zero, |
965 | 1 is returned, and for @code{omp_get_level}, the result is identical | |
5c6ed53a TB |
966 | to @code{omp_get_num_threads}. |
967 | ||
968 | @item @emph{C/C++}: | |
969 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 970 | @item @emph{Prototype}: @tab @code{int omp_get_team_size(int level);} |
5c6ed53a TB |
971 | @end multitable |
972 | ||
973 | @item @emph{Fortran}: | |
974 | @multitable @columnfractions .20 .80 | |
975 | @item @emph{Interface}: @tab @code{integer function omp_get_team_size(level)} | |
976 | @item @tab @code{integer level} | |
977 | @end multitable | |
978 | ||
979 | @item @emph{See also}: | |
980 | @ref{omp_get_num_threads}, @ref{omp_get_level}, @ref{omp_get_ancestor_thread_num} | |
981 | ||
982 | @item @emph{Reference}: | |
1a6d1d24 | 983 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.19. |
5c6ed53a TB |
984 | @end table |
985 | ||
986 | ||
987 | ||
988 | @node omp_get_thread_limit | |
6a2ba183 | 989 | @section @code{omp_get_thread_limit} -- Maximum number of threads |
5c6ed53a TB |
990 | @table @asis |
991 | @item @emph{Description}: | |
6a2ba183 | 992 | Return the maximum number of threads of the program. |
5c6ed53a TB |
993 | |
994 | @item @emph{C/C++}: | |
995 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 996 | @item @emph{Prototype}: @tab @code{int omp_get_thread_limit(void);} |
5c6ed53a TB |
997 | @end multitable |
998 | ||
999 | @item @emph{Fortran}: | |
1000 | @multitable @columnfractions .20 .80 | |
1001 | @item @emph{Interface}: @tab @code{integer function omp_get_thread_limit()} | |
1002 | @end multitable | |
1003 | ||
1004 | @item @emph{See also}: | |
1005 | @ref{omp_get_max_threads}, @ref{OMP_THREAD_LIMIT} | |
1006 | ||
1007 | @item @emph{Reference}: | |
1a6d1d24 | 1008 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.14. |
3721b9e1 DF |
1009 | @end table |
1010 | ||
1011 | ||
1012 | ||
83fd6c5b | 1013 | @node omp_get_thread_num |
3721b9e1 DF |
1014 | @section @code{omp_get_thread_num} -- Current thread ID |
1015 | @table @asis | |
1016 | @item @emph{Description}: | |
6a2ba183 | 1017 | Returns a unique thread identification number within the current team. |
5c6ed53a | 1018 | In a sequential parts of the program, @code{omp_get_thread_num} |
83fd6c5b TB |
1019 | always returns 0. In parallel regions the return value varies |
1020 | from 0 to @code{omp_get_num_threads}-1 inclusive. The return | |
432de084 | 1021 | value of the primary thread of a team is always 0. |
3721b9e1 DF |
1022 | |
1023 | @item @emph{C/C++}: | |
1024 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1025 | @item @emph{Prototype}: @tab @code{int omp_get_thread_num(void);} |
3721b9e1 DF |
1026 | @end multitable |
1027 | ||
1028 | @item @emph{Fortran}: | |
1029 | @multitable @columnfractions .20 .80 | |
1030 | @item @emph{Interface}: @tab @code{integer function omp_get_thread_num()} | |
1031 | @end multitable | |
1032 | ||
1033 | @item @emph{See also}: | |
5c6ed53a | 1034 | @ref{omp_get_num_threads}, @ref{omp_get_ancestor_thread_num} |
3721b9e1 DF |
1035 | |
1036 | @item @emph{Reference}: | |
1a6d1d24 | 1037 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.4. |
3721b9e1 DF |
1038 | @end table |
1039 | ||
1040 | ||
1041 | ||
1042 | @node omp_in_parallel | |
1043 | @section @code{omp_in_parallel} -- Whether a parallel region is active | |
1044 | @table @asis | |
1045 | @item @emph{Description}: | |
83fd6c5b TB |
1046 | This function returns @code{true} if currently running in parallel, |
1047 | @code{false} otherwise. Here, @code{true} and @code{false} represent | |
3721b9e1 DF |
1048 | their language-specific counterparts. |
1049 | ||
1050 | @item @emph{C/C++}: | |
1051 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1052 | @item @emph{Prototype}: @tab @code{int omp_in_parallel(void);} |
3721b9e1 DF |
1053 | @end multitable |
1054 | ||
1055 | @item @emph{Fortran}: | |
1056 | @multitable @columnfractions .20 .80 | |
1057 | @item @emph{Interface}: @tab @code{logical function omp_in_parallel()} | |
1058 | @end multitable | |
1059 | ||
1060 | @item @emph{Reference}: | |
1a6d1d24 | 1061 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.6. |
20906c66 JJ |
1062 | @end table |
1063 | ||
1064 | ||
1065 | @node omp_in_final | |
1066 | @section @code{omp_in_final} -- Whether in final or included task region | |
1067 | @table @asis | |
1068 | @item @emph{Description}: | |
1069 | This function returns @code{true} if currently running in a final | |
83fd6c5b | 1070 | or included task region, @code{false} otherwise. Here, @code{true} |
20906c66 JJ |
1071 | and @code{false} represent their language-specific counterparts. |
1072 | ||
1073 | @item @emph{C/C++}: | |
1074 | @multitable @columnfractions .20 .80 | |
1075 | @item @emph{Prototype}: @tab @code{int omp_in_final(void);} | |
1076 | @end multitable | |
1077 | ||
1078 | @item @emph{Fortran}: | |
1079 | @multitable @columnfractions .20 .80 | |
1080 | @item @emph{Interface}: @tab @code{logical function omp_in_final()} | |
1081 | @end multitable | |
1082 | ||
1083 | @item @emph{Reference}: | |
1a6d1d24 | 1084 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.21. |
3721b9e1 DF |
1085 | @end table |
1086 | ||
1087 | ||
83fd6c5b TB |
1088 | |
1089 | @node omp_is_initial_device | |
1090 | @section @code{omp_is_initial_device} -- Whether executing on the host device | |
1091 | @table @asis | |
1092 | @item @emph{Description}: | |
1093 | This function returns @code{true} if currently running on the host device, | |
1094 | @code{false} otherwise. Here, @code{true} and @code{false} represent | |
1095 | their language-specific counterparts. | |
1096 | ||
1097 | @item @emph{C/C++}: | |
1098 | @multitable @columnfractions .20 .80 | |
1099 | @item @emph{Prototype}: @tab @code{int omp_is_initial_device(void);} | |
1100 | @end multitable | |
1101 | ||
1102 | @item @emph{Fortran}: | |
1103 | @multitable @columnfractions .20 .80 | |
1104 | @item @emph{Interface}: @tab @code{logical function omp_is_initial_device()} | |
1105 | @end multitable | |
1106 | ||
1107 | @item @emph{Reference}: | |
1a6d1d24 | 1108 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.34. |
83fd6c5b TB |
1109 | @end table |
1110 | ||
1111 | ||
1112 | ||
1113 | @node omp_set_default_device | |
1114 | @section @code{omp_set_default_device} -- Set the default device for target regions | |
1115 | @table @asis | |
1116 | @item @emph{Description}: | |
1117 | Set the default device for target regions without device clause. The argument | |
1118 | shall be a nonnegative device number. | |
1119 | ||
1120 | @item @emph{C/C++}: | |
1121 | @multitable @columnfractions .20 .80 | |
1122 | @item @emph{Prototype}: @tab @code{void omp_set_default_device(int device_num);} | |
1123 | @end multitable | |
1124 | ||
1125 | @item @emph{Fortran}: | |
1126 | @multitable @columnfractions .20 .80 | |
1127 | @item @emph{Interface}: @tab @code{subroutine omp_set_default_device(device_num)} | |
1128 | @item @tab @code{integer device_num} | |
1129 | @end multitable | |
1130 | ||
1131 | @item @emph{See also}: | |
1132 | @ref{OMP_DEFAULT_DEVICE}, @ref{omp_get_default_device} | |
1133 | ||
1134 | @item @emph{Reference}: | |
1a6d1d24 | 1135 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.29. |
83fd6c5b TB |
1136 | @end table |
1137 | ||
1138 | ||
1139 | ||
3721b9e1 DF |
1140 | @node omp_set_dynamic |
1141 | @section @code{omp_set_dynamic} -- Enable/disable dynamic teams | |
1142 | @table @asis | |
1143 | @item @emph{Description}: | |
1144 | Enable or disable the dynamic adjustment of the number of threads | |
83fd6c5b | 1145 | within a team. The function takes the language-specific equivalent |
3721b9e1 DF |
1146 | of @code{true} and @code{false}, where @code{true} enables dynamic |
1147 | adjustment of team sizes and @code{false} disables it. | |
1148 | ||
1149 | @item @emph{C/C++}: | |
1150 | @multitable @columnfractions .20 .80 | |
4fed6b25 | 1151 | @item @emph{Prototype}: @tab @code{void omp_set_dynamic(int dynamic_threads);} |
3721b9e1 DF |
1152 | @end multitable |
1153 | ||
1154 | @item @emph{Fortran}: | |
1155 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1156 | @item @emph{Interface}: @tab @code{subroutine omp_set_dynamic(dynamic_threads)} |
1157 | @item @tab @code{logical, intent(in) :: dynamic_threads} | |
3721b9e1 DF |
1158 | @end multitable |
1159 | ||
1160 | @item @emph{See also}: | |
1161 | @ref{OMP_DYNAMIC}, @ref{omp_get_dynamic} | |
1162 | ||
1163 | @item @emph{Reference}: | |
1a6d1d24 | 1164 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.7. |
5c6ed53a TB |
1165 | @end table |
1166 | ||
1167 | ||
1168 | ||
1169 | @node omp_set_max_active_levels | |
1170 | @section @code{omp_set_max_active_levels} -- Limits the number of active parallel regions | |
1171 | @table @asis | |
1172 | @item @emph{Description}: | |
6a2ba183 | 1173 | This function limits the maximum allowed number of nested, active |
8949b985 KCY |
1174 | parallel regions. @var{max_levels} must be less or equal to |
1175 | the value returned by @code{omp_get_supported_active_levels}. | |
5c6ed53a TB |
1176 | |
1177 | @item @emph{C/C++} | |
1178 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1179 | @item @emph{Prototype}: @tab @code{void omp_set_max_active_levels(int max_levels);} |
5c6ed53a TB |
1180 | @end multitable |
1181 | ||
1182 | @item @emph{Fortran}: | |
1183 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1184 | @item @emph{Interface}: @tab @code{subroutine omp_set_max_active_levels(max_levels)} |
5c6ed53a TB |
1185 | @item @tab @code{integer max_levels} |
1186 | @end multitable | |
1187 | ||
1188 | @item @emph{See also}: | |
8949b985 KCY |
1189 | @ref{omp_get_max_active_levels}, @ref{omp_get_active_level}, |
1190 | @ref{omp_get_supported_active_levels} | |
5c6ed53a TB |
1191 | |
1192 | @item @emph{Reference}: | |
1a6d1d24 | 1193 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.15. |
3721b9e1 DF |
1194 | @end table |
1195 | ||
1196 | ||
1197 | ||
1198 | @node omp_set_nested | |
1199 | @section @code{omp_set_nested} -- Enable/disable nested parallel regions | |
1200 | @table @asis | |
1201 | @item @emph{Description}: | |
f1b0882e | 1202 | Enable or disable nested parallel regions, i.e., whether team members |
83fd6c5b | 1203 | are allowed to create new teams. The function takes the language-specific |
3721b9e1 DF |
1204 | equivalent of @code{true} and @code{false}, where @code{true} enables |
1205 | dynamic adjustment of team sizes and @code{false} disables it. | |
1206 | ||
6fae7eda KCY |
1207 | Enabling nested parallel regions will also set the maximum number of |
1208 | active nested regions to the maximum supported. Disabling nested parallel | |
1209 | regions will set the maximum number of active nested regions to one. | |
1210 | ||
3721b9e1 DF |
1211 | @item @emph{C/C++}: |
1212 | @multitable @columnfractions .20 .80 | |
4fed6b25 | 1213 | @item @emph{Prototype}: @tab @code{void omp_set_nested(int nested);} |
3721b9e1 DF |
1214 | @end multitable |
1215 | ||
1216 | @item @emph{Fortran}: | |
1217 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1218 | @item @emph{Interface}: @tab @code{subroutine omp_set_nested(nested)} |
1219 | @item @tab @code{logical, intent(in) :: nested} | |
3721b9e1 DF |
1220 | @end multitable |
1221 | ||
1222 | @item @emph{See also}: | |
6fae7eda KCY |
1223 | @ref{omp_get_nested}, @ref{omp_set_max_active_levels}, |
1224 | @ref{OMP_MAX_ACTIVE_LEVELS}, @ref{OMP_NESTED} | |
3721b9e1 DF |
1225 | |
1226 | @item @emph{Reference}: | |
1a6d1d24 | 1227 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.10. |
3721b9e1 DF |
1228 | @end table |
1229 | ||
1230 | ||
1231 | ||
1232 | @node omp_set_num_threads | |
1233 | @section @code{omp_set_num_threads} -- Set upper team size limit | |
1234 | @table @asis | |
1235 | @item @emph{Description}: | |
1236 | Specifies the number of threads used by default in subsequent parallel | |
83fd6c5b TB |
1237 | sections, if those do not specify a @code{num_threads} clause. The |
1238 | argument of @code{omp_set_num_threads} shall be a positive integer. | |
3721b9e1 | 1239 | |
3721b9e1 DF |
1240 | @item @emph{C/C++}: |
1241 | @multitable @columnfractions .20 .80 | |
4fed6b25 | 1242 | @item @emph{Prototype}: @tab @code{void omp_set_num_threads(int num_threads);} |
3721b9e1 DF |
1243 | @end multitable |
1244 | ||
1245 | @item @emph{Fortran}: | |
1246 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1247 | @item @emph{Interface}: @tab @code{subroutine omp_set_num_threads(num_threads)} |
1248 | @item @tab @code{integer, intent(in) :: num_threads} | |
3721b9e1 DF |
1249 | @end multitable |
1250 | ||
1251 | @item @emph{See also}: | |
1252 | @ref{OMP_NUM_THREADS}, @ref{omp_get_num_threads}, @ref{omp_get_max_threads} | |
1253 | ||
1254 | @item @emph{Reference}: | |
1a6d1d24 | 1255 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.1. |
5c6ed53a TB |
1256 | @end table |
1257 | ||
1258 | ||
1259 | ||
1260 | @node omp_set_schedule | |
1261 | @section @code{omp_set_schedule} -- Set the runtime scheduling method | |
1262 | @table @asis | |
1263 | @item @emph{Description}: | |
83fd6c5b | 1264 | Sets the runtime scheduling method. The @var{kind} argument can have the |
5c6ed53a | 1265 | value @code{omp_sched_static}, @code{omp_sched_dynamic}, |
83fd6c5b | 1266 | @code{omp_sched_guided} or @code{omp_sched_auto}. Except for |
5c6ed53a | 1267 | @code{omp_sched_auto}, the chunk size is set to the value of |
d9a6bd32 JJ |
1268 | @var{chunk_size} if positive, or to the default value if zero or negative. |
1269 | For @code{omp_sched_auto} the @var{chunk_size} argument is ignored. | |
5c6ed53a TB |
1270 | |
1271 | @item @emph{C/C++} | |
1272 | @multitable @columnfractions .20 .80 | |
d9a6bd32 | 1273 | @item @emph{Prototype}: @tab @code{void omp_set_schedule(omp_sched_t kind, int chunk_size);} |
5c6ed53a TB |
1274 | @end multitable |
1275 | ||
1276 | @item @emph{Fortran}: | |
1277 | @multitable @columnfractions .20 .80 | |
d9a6bd32 | 1278 | @item @emph{Interface}: @tab @code{subroutine omp_set_schedule(kind, chunk_size)} |
5c6ed53a | 1279 | @item @tab @code{integer(kind=omp_sched_kind) kind} |
d9a6bd32 | 1280 | @item @tab @code{integer chunk_size} |
5c6ed53a TB |
1281 | @end multitable |
1282 | ||
1283 | @item @emph{See also}: | |
1284 | @ref{omp_get_schedule} | |
1285 | @ref{OMP_SCHEDULE} | |
1286 | ||
1287 | @item @emph{Reference}: | |
1a6d1d24 | 1288 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.2.12. |
3721b9e1 DF |
1289 | @end table |
1290 | ||
1291 | ||
1292 | ||
1293 | @node omp_init_lock | |
1294 | @section @code{omp_init_lock} -- Initialize simple lock | |
1295 | @table @asis | |
1296 | @item @emph{Description}: | |
83fd6c5b | 1297 | Initialize a simple lock. After initialization, the lock is in |
3721b9e1 DF |
1298 | an unlocked state. |
1299 | ||
1300 | @item @emph{C/C++}: | |
1301 | @multitable @columnfractions .20 .80 | |
1302 | @item @emph{Prototype}: @tab @code{void omp_init_lock(omp_lock_t *lock);} | |
1303 | @end multitable | |
1304 | ||
1305 | @item @emph{Fortran}: | |
1306 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1307 | @item @emph{Interface}: @tab @code{subroutine omp_init_lock(svar)} |
1308 | @item @tab @code{integer(omp_lock_kind), intent(out) :: svar} | |
3721b9e1 DF |
1309 | @end multitable |
1310 | ||
1311 | @item @emph{See also}: | |
1312 | @ref{omp_destroy_lock} | |
1313 | ||
1314 | @item @emph{Reference}: | |
1a6d1d24 | 1315 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.1. |
3721b9e1 DF |
1316 | @end table |
1317 | ||
1318 | ||
1319 | ||
1320 | @node omp_set_lock | |
1321 | @section @code{omp_set_lock} -- Wait for and set simple lock | |
1322 | @table @asis | |
1323 | @item @emph{Description}: | |
1324 | Before setting a simple lock, the lock variable must be initialized by | |
83fd6c5b TB |
1325 | @code{omp_init_lock}. The calling thread is blocked until the lock |
1326 | is available. If the lock is already held by the current thread, | |
3721b9e1 DF |
1327 | a deadlock occurs. |
1328 | ||
1329 | @item @emph{C/C++}: | |
1330 | @multitable @columnfractions .20 .80 | |
1331 | @item @emph{Prototype}: @tab @code{void omp_set_lock(omp_lock_t *lock);} | |
1332 | @end multitable | |
1333 | ||
1334 | @item @emph{Fortran}: | |
1335 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1336 | @item @emph{Interface}: @tab @code{subroutine omp_set_lock(svar)} |
1337 | @item @tab @code{integer(omp_lock_kind), intent(inout) :: svar} | |
3721b9e1 DF |
1338 | @end multitable |
1339 | ||
1340 | @item @emph{See also}: | |
1341 | @ref{omp_init_lock}, @ref{omp_test_lock}, @ref{omp_unset_lock} | |
1342 | ||
1343 | @item @emph{Reference}: | |
1a6d1d24 | 1344 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.4. |
3721b9e1 DF |
1345 | @end table |
1346 | ||
1347 | ||
1348 | ||
1349 | @node omp_test_lock | |
1350 | @section @code{omp_test_lock} -- Test and set simple lock if available | |
1351 | @table @asis | |
1352 | @item @emph{Description}: | |
1353 | Before setting a simple lock, the lock variable must be initialized by | |
83fd6c5b TB |
1354 | @code{omp_init_lock}. Contrary to @code{omp_set_lock}, @code{omp_test_lock} |
1355 | does not block if the lock is not available. This function returns | |
1356 | @code{true} upon success, @code{false} otherwise. Here, @code{true} and | |
3721b9e1 DF |
1357 | @code{false} represent their language-specific counterparts. |
1358 | ||
1359 | @item @emph{C/C++}: | |
1360 | @multitable @columnfractions .20 .80 | |
1361 | @item @emph{Prototype}: @tab @code{int omp_test_lock(omp_lock_t *lock);} | |
1362 | @end multitable | |
1363 | ||
1364 | @item @emph{Fortran}: | |
1365 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1366 | @item @emph{Interface}: @tab @code{logical function omp_test_lock(svar)} |
1367 | @item @tab @code{integer(omp_lock_kind), intent(inout) :: svar} | |
3721b9e1 DF |
1368 | @end multitable |
1369 | ||
1370 | @item @emph{See also}: | |
1371 | @ref{omp_init_lock}, @ref{omp_set_lock}, @ref{omp_set_lock} | |
1372 | ||
1373 | @item @emph{Reference}: | |
1a6d1d24 | 1374 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.6. |
3721b9e1 DF |
1375 | @end table |
1376 | ||
1377 | ||
1378 | ||
1379 | @node omp_unset_lock | |
1380 | @section @code{omp_unset_lock} -- Unset simple lock | |
1381 | @table @asis | |
1382 | @item @emph{Description}: | |
1383 | A simple lock about to be unset must have been locked by @code{omp_set_lock} | |
83fd6c5b TB |
1384 | or @code{omp_test_lock} before. In addition, the lock must be held by the |
1385 | thread calling @code{omp_unset_lock}. Then, the lock becomes unlocked. If one | |
1386 | or more threads attempted to set the lock before, one of them is chosen to, | |
20906c66 | 1387 | again, set the lock to itself. |
3721b9e1 DF |
1388 | |
1389 | @item @emph{C/C++}: | |
1390 | @multitable @columnfractions .20 .80 | |
1391 | @item @emph{Prototype}: @tab @code{void omp_unset_lock(omp_lock_t *lock);} | |
1392 | @end multitable | |
1393 | ||
1394 | @item @emph{Fortran}: | |
1395 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1396 | @item @emph{Interface}: @tab @code{subroutine omp_unset_lock(svar)} |
1397 | @item @tab @code{integer(omp_lock_kind), intent(inout) :: svar} | |
3721b9e1 DF |
1398 | @end multitable |
1399 | ||
1400 | @item @emph{See also}: | |
1401 | @ref{omp_set_lock}, @ref{omp_test_lock} | |
1402 | ||
1403 | @item @emph{Reference}: | |
1a6d1d24 | 1404 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.5. |
3721b9e1 DF |
1405 | @end table |
1406 | ||
1407 | ||
1408 | ||
1409 | @node omp_destroy_lock | |
1410 | @section @code{omp_destroy_lock} -- Destroy simple lock | |
1411 | @table @asis | |
1412 | @item @emph{Description}: | |
83fd6c5b | 1413 | Destroy a simple lock. In order to be destroyed, a simple lock must be |
3721b9e1 DF |
1414 | in the unlocked state. |
1415 | ||
1416 | @item @emph{C/C++}: | |
1417 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1418 | @item @emph{Prototype}: @tab @code{void omp_destroy_lock(omp_lock_t *lock);} |
3721b9e1 DF |
1419 | @end multitable |
1420 | ||
1421 | @item @emph{Fortran}: | |
1422 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1423 | @item @emph{Interface}: @tab @code{subroutine omp_destroy_lock(svar)} |
1424 | @item @tab @code{integer(omp_lock_kind), intent(inout) :: svar} | |
3721b9e1 DF |
1425 | @end multitable |
1426 | ||
1427 | @item @emph{See also}: | |
1428 | @ref{omp_init_lock} | |
1429 | ||
1430 | @item @emph{Reference}: | |
1a6d1d24 | 1431 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.3. |
3721b9e1 DF |
1432 | @end table |
1433 | ||
1434 | ||
1435 | ||
1436 | @node omp_init_nest_lock | |
1437 | @section @code{omp_init_nest_lock} -- Initialize nested lock | |
1438 | @table @asis | |
1439 | @item @emph{Description}: | |
83fd6c5b | 1440 | Initialize a nested lock. After initialization, the lock is in |
3721b9e1 DF |
1441 | an unlocked state and the nesting count is set to zero. |
1442 | ||
1443 | @item @emph{C/C++}: | |
1444 | @multitable @columnfractions .20 .80 | |
1445 | @item @emph{Prototype}: @tab @code{void omp_init_nest_lock(omp_nest_lock_t *lock);} | |
1446 | @end multitable | |
1447 | ||
1448 | @item @emph{Fortran}: | |
1449 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1450 | @item @emph{Interface}: @tab @code{subroutine omp_init_nest_lock(nvar)} |
1451 | @item @tab @code{integer(omp_nest_lock_kind), intent(out) :: nvar} | |
3721b9e1 DF |
1452 | @end multitable |
1453 | ||
1454 | @item @emph{See also}: | |
1455 | @ref{omp_destroy_nest_lock} | |
1456 | ||
1457 | @item @emph{Reference}: | |
1a6d1d24 | 1458 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.1. |
3721b9e1 DF |
1459 | @end table |
1460 | ||
1461 | ||
1462 | @node omp_set_nest_lock | |
6a2ba183 | 1463 | @section @code{omp_set_nest_lock} -- Wait for and set nested lock |
3721b9e1 DF |
1464 | @table @asis |
1465 | @item @emph{Description}: | |
1466 | Before setting a nested lock, the lock variable must be initialized by | |
83fd6c5b TB |
1467 | @code{omp_init_nest_lock}. The calling thread is blocked until the lock |
1468 | is available. If the lock is already held by the current thread, the | |
20906c66 | 1469 | nesting count for the lock is incremented. |
3721b9e1 DF |
1470 | |
1471 | @item @emph{C/C++}: | |
1472 | @multitable @columnfractions .20 .80 | |
1473 | @item @emph{Prototype}: @tab @code{void omp_set_nest_lock(omp_nest_lock_t *lock);} | |
1474 | @end multitable | |
1475 | ||
1476 | @item @emph{Fortran}: | |
1477 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1478 | @item @emph{Interface}: @tab @code{subroutine omp_set_nest_lock(nvar)} |
1479 | @item @tab @code{integer(omp_nest_lock_kind), intent(inout) :: nvar} | |
3721b9e1 DF |
1480 | @end multitable |
1481 | ||
1482 | @item @emph{See also}: | |
1483 | @ref{omp_init_nest_lock}, @ref{omp_unset_nest_lock} | |
1484 | ||
1485 | @item @emph{Reference}: | |
1a6d1d24 | 1486 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.4. |
3721b9e1 DF |
1487 | @end table |
1488 | ||
1489 | ||
1490 | ||
1491 | @node omp_test_nest_lock | |
1492 | @section @code{omp_test_nest_lock} -- Test and set nested lock if available | |
1493 | @table @asis | |
1494 | @item @emph{Description}: | |
1495 | Before setting a nested lock, the lock variable must be initialized by | |
83fd6c5b | 1496 | @code{omp_init_nest_lock}. Contrary to @code{omp_set_nest_lock}, |
3721b9e1 DF |
1497 | @code{omp_test_nest_lock} does not block if the lock is not available. |
1498 | If the lock is already held by the current thread, the new nesting count | |
83fd6c5b | 1499 | is returned. Otherwise, the return value equals zero. |
3721b9e1 DF |
1500 | |
1501 | @item @emph{C/C++}: | |
1502 | @multitable @columnfractions .20 .80 | |
1503 | @item @emph{Prototype}: @tab @code{int omp_test_nest_lock(omp_nest_lock_t *lock);} | |
1504 | @end multitable | |
1505 | ||
1506 | @item @emph{Fortran}: | |
1507 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1508 | @item @emph{Interface}: @tab @code{logical function omp_test_nest_lock(nvar)} |
1509 | @item @tab @code{integer(omp_nest_lock_kind), intent(inout) :: nvar} | |
3721b9e1 DF |
1510 | @end multitable |
1511 | ||
1512 | ||
1513 | @item @emph{See also}: | |
1514 | @ref{omp_init_lock}, @ref{omp_set_lock}, @ref{omp_set_lock} | |
1515 | ||
1516 | @item @emph{Reference}: | |
1a6d1d24 | 1517 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.6. |
3721b9e1 DF |
1518 | @end table |
1519 | ||
1520 | ||
1521 | ||
1522 | @node omp_unset_nest_lock | |
1523 | @section @code{omp_unset_nest_lock} -- Unset nested lock | |
1524 | @table @asis | |
1525 | @item @emph{Description}: | |
1526 | A nested lock about to be unset must have been locked by @code{omp_set_nested_lock} | |
83fd6c5b TB |
1527 | or @code{omp_test_nested_lock} before. In addition, the lock must be held by the |
1528 | thread calling @code{omp_unset_nested_lock}. If the nesting count drops to zero, the | |
1529 | lock becomes unlocked. If one ore more threads attempted to set the lock before, | |
20906c66 | 1530 | one of them is chosen to, again, set the lock to itself. |
3721b9e1 DF |
1531 | |
1532 | @item @emph{C/C++}: | |
1533 | @multitable @columnfractions .20 .80 | |
1534 | @item @emph{Prototype}: @tab @code{void omp_unset_nest_lock(omp_nest_lock_t *lock);} | |
1535 | @end multitable | |
1536 | ||
1537 | @item @emph{Fortran}: | |
1538 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1539 | @item @emph{Interface}: @tab @code{subroutine omp_unset_nest_lock(nvar)} |
1540 | @item @tab @code{integer(omp_nest_lock_kind), intent(inout) :: nvar} | |
3721b9e1 DF |
1541 | @end multitable |
1542 | ||
1543 | @item @emph{See also}: | |
1544 | @ref{omp_set_nest_lock} | |
1545 | ||
1546 | @item @emph{Reference}: | |
1a6d1d24 | 1547 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.5. |
3721b9e1 DF |
1548 | @end table |
1549 | ||
1550 | ||
1551 | ||
1552 | @node omp_destroy_nest_lock | |
1553 | @section @code{omp_destroy_nest_lock} -- Destroy nested lock | |
1554 | @table @asis | |
1555 | @item @emph{Description}: | |
83fd6c5b | 1556 | Destroy a nested lock. In order to be destroyed, a nested lock must be |
3721b9e1 DF |
1557 | in the unlocked state and its nesting count must equal zero. |
1558 | ||
1559 | @item @emph{C/C++}: | |
1560 | @multitable @columnfractions .20 .80 | |
1561 | @item @emph{Prototype}: @tab @code{void omp_destroy_nest_lock(omp_nest_lock_t *);} | |
1562 | @end multitable | |
1563 | ||
1564 | @item @emph{Fortran}: | |
1565 | @multitable @columnfractions .20 .80 | |
4fed6b25 TB |
1566 | @item @emph{Interface}: @tab @code{subroutine omp_destroy_nest_lock(nvar)} |
1567 | @item @tab @code{integer(omp_nest_lock_kind), intent(inout) :: nvar} | |
3721b9e1 DF |
1568 | @end multitable |
1569 | ||
1570 | @item @emph{See also}: | |
1571 | @ref{omp_init_lock} | |
1572 | ||
1573 | @item @emph{Reference}: | |
1a6d1d24 | 1574 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.3.3. |
3721b9e1 DF |
1575 | @end table |
1576 | ||
1577 | ||
1578 | ||
1579 | @node omp_get_wtick | |
1580 | @section @code{omp_get_wtick} -- Get timer precision | |
1581 | @table @asis | |
1582 | @item @emph{Description}: | |
f1b0882e | 1583 | Gets the timer precision, i.e., the number of seconds between two |
3721b9e1 DF |
1584 | successive clock ticks. |
1585 | ||
1586 | @item @emph{C/C++}: | |
1587 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1588 | @item @emph{Prototype}: @tab @code{double omp_get_wtick(void);} |
3721b9e1 DF |
1589 | @end multitable |
1590 | ||
1591 | @item @emph{Fortran}: | |
1592 | @multitable @columnfractions .20 .80 | |
1593 | @item @emph{Interface}: @tab @code{double precision function omp_get_wtick()} | |
1594 | @end multitable | |
1595 | ||
1596 | @item @emph{See also}: | |
1597 | @ref{omp_get_wtime} | |
1598 | ||
1599 | @item @emph{Reference}: | |
1a6d1d24 | 1600 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.4.2. |
3721b9e1 DF |
1601 | @end table |
1602 | ||
1603 | ||
1604 | ||
1605 | @node omp_get_wtime | |
1606 | @section @code{omp_get_wtime} -- Elapsed wall clock time | |
1607 | @table @asis | |
1608 | @item @emph{Description}: | |
83fd6c5b | 1609 | Elapsed wall clock time in seconds. The time is measured per thread, no |
6a2ba183 | 1610 | guarantee can be made that two distinct threads measure the same time. |
21e1e594 JJ |
1611 | Time is measured from some "time in the past", which is an arbitrary time |
1612 | guaranteed not to change during the execution of the program. | |
3721b9e1 DF |
1613 | |
1614 | @item @emph{C/C++}: | |
1615 | @multitable @columnfractions .20 .80 | |
6a2ba183 | 1616 | @item @emph{Prototype}: @tab @code{double omp_get_wtime(void);} |
3721b9e1 DF |
1617 | @end multitable |
1618 | ||
1619 | @item @emph{Fortran}: | |
1620 | @multitable @columnfractions .20 .80 | |
1621 | @item @emph{Interface}: @tab @code{double precision function omp_get_wtime()} | |
1622 | @end multitable | |
1623 | ||
1624 | @item @emph{See also}: | |
1625 | @ref{omp_get_wtick} | |
1626 | ||
1627 | @item @emph{Reference}: | |
1a6d1d24 | 1628 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 3.4.1. |
3721b9e1 DF |
1629 | @end table |
1630 | ||
1631 | ||
1632 | ||
0194e2f0 KCY |
1633 | @node omp_fulfill_event |
1634 | @section @code{omp_fulfill_event} -- Fulfill and destroy an OpenMP event | |
1635 | @table @asis | |
1636 | @item @emph{Description}: | |
1637 | Fulfill the event associated with the event handle argument. Currently, it | |
1638 | is only used to fulfill events generated by detach clauses on task | |
1639 | constructs - the effect of fulfilling the event is to allow the task to | |
1640 | complete. | |
1641 | ||
1642 | The result of calling @code{omp_fulfill_event} with an event handle other | |
1643 | than that generated by a detach clause is undefined. Calling it with an | |
1644 | event handle that has already been fulfilled is also undefined. | |
1645 | ||
1646 | @item @emph{C/C++}: | |
1647 | @multitable @columnfractions .20 .80 | |
1648 | @item @emph{Prototype}: @tab @code{void omp_fulfill_event(omp_event_handle_t event);} | |
1649 | @end multitable | |
1650 | ||
1651 | @item @emph{Fortran}: | |
1652 | @multitable @columnfractions .20 .80 | |
1653 | @item @emph{Interface}: @tab @code{subroutine omp_fulfill_event(event)} | |
1654 | @item @tab @code{integer (kind=omp_event_handle_kind) :: event} | |
1655 | @end multitable | |
1656 | ||
1657 | @item @emph{Reference}: | |
1658 | @uref{https://www.openmp.org, OpenMP specification v5.0}, Section 3.5.1. | |
1659 | @end table | |
1660 | ||
1661 | ||
1662 | ||
3721b9e1 | 1663 | @c --------------------------------------------------------------------- |
4102bda6 | 1664 | @c OpenMP Environment Variables |
3721b9e1 DF |
1665 | @c --------------------------------------------------------------------- |
1666 | ||
1667 | @node Environment Variables | |
4102bda6 | 1668 | @chapter OpenMP Environment Variables |
3721b9e1 | 1669 | |
acf0174b | 1670 | The environment variables which beginning with @env{OMP_} are defined by |
00b9bd52 | 1671 | section 4 of the OpenMP specification in version 4.5, while those |
acf0174b | 1672 | beginning with @env{GOMP_} are GNU extensions. |
3721b9e1 DF |
1673 | |
1674 | @menu | |
06441dd5 SH |
1675 | * OMP_CANCELLATION:: Set whether cancellation is activated |
1676 | * OMP_DISPLAY_ENV:: Show OpenMP version and environment variables | |
1677 | * OMP_DEFAULT_DEVICE:: Set the device used in target regions | |
1678 | * OMP_DYNAMIC:: Dynamic adjustment of threads | |
1679 | * OMP_MAX_ACTIVE_LEVELS:: Set the maximum number of nested parallel regions | |
d9a6bd32 | 1680 | * OMP_MAX_TASK_PRIORITY:: Set the maximum task priority value |
06441dd5 SH |
1681 | * OMP_NESTED:: Nested parallel regions |
1682 | * OMP_NUM_THREADS:: Specifies the number of threads to use | |
1683 | * OMP_PROC_BIND:: Whether theads may be moved between CPUs | |
1684 | * OMP_PLACES:: Specifies on which CPUs the theads should be placed | |
1685 | * OMP_STACKSIZE:: Set default thread stack size | |
1686 | * OMP_SCHEDULE:: How threads are scheduled | |
1bfc07d1 | 1687 | * OMP_TARGET_OFFLOAD:: Controls offloading behaviour |
06441dd5 SH |
1688 | * OMP_THREAD_LIMIT:: Set the maximum number of threads |
1689 | * OMP_WAIT_POLICY:: How waiting threads are handled | |
1690 | * GOMP_CPU_AFFINITY:: Bind threads to specific CPUs | |
1691 | * GOMP_DEBUG:: Enable debugging output | |
1692 | * GOMP_STACKSIZE:: Set default thread stack size | |
1693 | * GOMP_SPINCOUNT:: Set the busy-wait spin count | |
1694 | * GOMP_RTEMS_THREAD_POOLS:: Set the RTEMS specific thread pools | |
3721b9e1 DF |
1695 | @end menu |
1696 | ||
1697 | ||
83fd6c5b TB |
1698 | @node OMP_CANCELLATION |
1699 | @section @env{OMP_CANCELLATION} -- Set whether cancellation is activated | |
1700 | @cindex Environment Variable | |
1701 | @table @asis | |
1702 | @item @emph{Description}: | |
1703 | If set to @code{TRUE}, the cancellation is activated. If set to @code{FALSE} or | |
1704 | if unset, cancellation is disabled and the @code{cancel} construct is ignored. | |
1705 | ||
1706 | @item @emph{See also}: | |
1707 | @ref{omp_get_cancellation} | |
1708 | ||
1709 | @item @emph{Reference}: | |
1a6d1d24 | 1710 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.11 |
83fd6c5b TB |
1711 | @end table |
1712 | ||
1713 | ||
1714 | ||
1715 | @node OMP_DISPLAY_ENV | |
1716 | @section @env{OMP_DISPLAY_ENV} -- Show OpenMP version and environment variables | |
1717 | @cindex Environment Variable | |
1718 | @table @asis | |
1719 | @item @emph{Description}: | |
1720 | If set to @code{TRUE}, the OpenMP version number and the values | |
1721 | associated with the OpenMP environment variables are printed to @code{stderr}. | |
1722 | If set to @code{VERBOSE}, it additionally shows the value of the environment | |
1723 | variables which are GNU extensions. If undefined or set to @code{FALSE}, | |
1724 | this information will not be shown. | |
1725 | ||
1726 | ||
1727 | @item @emph{Reference}: | |
1a6d1d24 | 1728 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.12 |
83fd6c5b TB |
1729 | @end table |
1730 | ||
1731 | ||
1732 | ||
1733 | @node OMP_DEFAULT_DEVICE | |
1734 | @section @env{OMP_DEFAULT_DEVICE} -- Set the device used in target regions | |
1735 | @cindex Environment Variable | |
1736 | @table @asis | |
1737 | @item @emph{Description}: | |
1738 | Set to choose the device which is used in a @code{target} region, unless the | |
1739 | value is overridden by @code{omp_set_default_device} or by a @code{device} | |
1740 | clause. The value shall be the nonnegative device number. If no device with | |
1741 | the given device number exists, the code is executed on the host. If unset, | |
1742 | device number 0 will be used. | |
1743 | ||
1744 | ||
1745 | @item @emph{See also}: | |
1746 | @ref{omp_get_default_device}, @ref{omp_set_default_device}, | |
1747 | ||
1748 | @item @emph{Reference}: | |
1a6d1d24 | 1749 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.13 |
83fd6c5b TB |
1750 | @end table |
1751 | ||
1752 | ||
1753 | ||
3721b9e1 DF |
1754 | @node OMP_DYNAMIC |
1755 | @section @env{OMP_DYNAMIC} -- Dynamic adjustment of threads | |
1756 | @cindex Environment Variable | |
1757 | @table @asis | |
1758 | @item @emph{Description}: | |
1759 | Enable or disable the dynamic adjustment of the number of threads | |
83fd6c5b TB |
1760 | within a team. The value of this environment variable shall be |
1761 | @code{TRUE} or @code{FALSE}. If undefined, dynamic adjustment is | |
7c2b7f45 | 1762 | disabled by default. |
3721b9e1 DF |
1763 | |
1764 | @item @emph{See also}: | |
1765 | @ref{omp_set_dynamic} | |
1766 | ||
1767 | @item @emph{Reference}: | |
1a6d1d24 | 1768 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.3 |
5c6ed53a TB |
1769 | @end table |
1770 | ||
1771 | ||
1772 | ||
1773 | @node OMP_MAX_ACTIVE_LEVELS | |
6a2ba183 | 1774 | @section @env{OMP_MAX_ACTIVE_LEVELS} -- Set the maximum number of nested parallel regions |
5c6ed53a TB |
1775 | @cindex Environment Variable |
1776 | @table @asis | |
1777 | @item @emph{Description}: | |
6a2ba183 | 1778 | Specifies the initial value for the maximum number of nested parallel |
83fd6c5b | 1779 | regions. The value of this variable shall be a positive integer. |
6fae7eda KCY |
1780 | If undefined, then if @env{OMP_NESTED} is defined and set to true, or |
1781 | if @env{OMP_NUM_THREADS} or @env{OMP_PROC_BIND} are defined and set to | |
1782 | a list with more than one item, the maximum number of nested parallel | |
1783 | regions will be initialized to the largest number supported, otherwise | |
1784 | it will be set to one. | |
5c6ed53a TB |
1785 | |
1786 | @item @emph{See also}: | |
6fae7eda | 1787 | @ref{omp_set_max_active_levels}, @ref{OMP_NESTED} |
5c6ed53a TB |
1788 | |
1789 | @item @emph{Reference}: | |
1a6d1d24 | 1790 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.9 |
3721b9e1 DF |
1791 | @end table |
1792 | ||
1793 | ||
1794 | ||
d9a6bd32 JJ |
1795 | @node OMP_MAX_TASK_PRIORITY |
1796 | @section @env{OMP_MAX_TASK_PRIORITY} -- Set the maximum priority | |
1797 | number that can be set for a task. | |
1798 | @cindex Environment Variable | |
1799 | @table @asis | |
1800 | @item @emph{Description}: | |
1801 | Specifies the initial value for the maximum priority value that can be | |
1802 | set for a task. The value of this variable shall be a non-negative | |
1803 | integer, and zero is allowed. If undefined, the default priority is | |
1804 | 0. | |
1805 | ||
1806 | @item @emph{See also}: | |
1807 | @ref{omp_get_max_task_priority} | |
1808 | ||
1809 | @item @emph{Reference}: | |
1a6d1d24 | 1810 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.14 |
d9a6bd32 JJ |
1811 | @end table |
1812 | ||
1813 | ||
1814 | ||
3721b9e1 DF |
1815 | @node OMP_NESTED |
1816 | @section @env{OMP_NESTED} -- Nested parallel regions | |
1817 | @cindex Environment Variable | |
14734fc7 | 1818 | @cindex Implementation specific setting |
3721b9e1 DF |
1819 | @table @asis |
1820 | @item @emph{Description}: | |
f1b0882e | 1821 | Enable or disable nested parallel regions, i.e., whether team members |
83fd6c5b | 1822 | are allowed to create new teams. The value of this environment variable |
6fae7eda KCY |
1823 | shall be @code{TRUE} or @code{FALSE}. If set to @code{TRUE}, the number |
1824 | of maximum active nested regions supported will by default be set to the | |
1825 | maximum supported, otherwise it will be set to one. If | |
1826 | @env{OMP_MAX_ACTIVE_LEVELS} is defined, its setting will override this | |
1827 | setting. If both are undefined, nested parallel regions are enabled if | |
1828 | @env{OMP_NUM_THREADS} or @env{OMP_PROC_BINDS} are defined to a list with | |
1829 | more than one item, otherwise they are disabled by default. | |
3721b9e1 DF |
1830 | |
1831 | @item @emph{See also}: | |
6fae7eda | 1832 | @ref{omp_set_max_active_levels}, @ref{omp_set_nested} |
3721b9e1 DF |
1833 | |
1834 | @item @emph{Reference}: | |
1a6d1d24 | 1835 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.6 |
3721b9e1 DF |
1836 | @end table |
1837 | ||
1838 | ||
1839 | ||
1840 | @node OMP_NUM_THREADS | |
1841 | @section @env{OMP_NUM_THREADS} -- Specifies the number of threads to use | |
1842 | @cindex Environment Variable | |
14734fc7 | 1843 | @cindex Implementation specific setting |
3721b9e1 DF |
1844 | @table @asis |
1845 | @item @emph{Description}: | |
83fd6c5b | 1846 | Specifies the default number of threads to use in parallel regions. The |
20906c66 | 1847 | value of this variable shall be a comma-separated list of positive integers; |
6fae7eda KCY |
1848 | the value specifies the number of threads to use for the corresponding nested |
1849 | level. Specifying more than one item in the list will automatically enable | |
1850 | nesting by default. If undefined one thread per CPU is used. | |
3721b9e1 DF |
1851 | |
1852 | @item @emph{See also}: | |
6fae7eda | 1853 | @ref{omp_set_num_threads}, @ref{OMP_NESTED} |
3721b9e1 DF |
1854 | |
1855 | @item @emph{Reference}: | |
1a6d1d24 | 1856 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.2 |
83fd6c5b TB |
1857 | @end table |
1858 | ||
1859 | ||
1860 | ||
72832460 UB |
1861 | @node OMP_PROC_BIND |
1862 | @section @env{OMP_PROC_BIND} -- Whether theads may be moved between CPUs | |
1863 | @cindex Environment Variable | |
1864 | @table @asis | |
1865 | @item @emph{Description}: | |
1866 | Specifies whether threads may be moved between processors. If set to | |
1867 | @code{TRUE}, OpenMP theads should not be moved; if set to @code{FALSE} | |
1868 | they may be moved. Alternatively, a comma separated list with the | |
432de084 TB |
1869 | values @code{PRIMARY}, @code{MASTER}, @code{CLOSE} and @code{SPREAD} can |
1870 | be used to specify the thread affinity policy for the corresponding nesting | |
1871 | level. With @code{PRIMARY} and @code{MASTER} the worker threads are in the | |
1872 | same place partition as the primary thread. With @code{CLOSE} those are | |
1873 | kept close to the primary thread in contiguous place partitions. And | |
1874 | with @code{SPREAD} a sparse distribution | |
6fae7eda KCY |
1875 | across the place partitions is used. Specifying more than one item in the |
1876 | list will automatically enable nesting by default. | |
72832460 UB |
1877 | |
1878 | When undefined, @env{OMP_PROC_BIND} defaults to @code{TRUE} when | |
1879 | @env{OMP_PLACES} or @env{GOMP_CPU_AFFINITY} is set and @code{FALSE} otherwise. | |
1880 | ||
1881 | @item @emph{See also}: | |
6fae7eda KCY |
1882 | @ref{omp_get_proc_bind}, @ref{GOMP_CPU_AFFINITY}, |
1883 | @ref{OMP_NESTED}, @ref{OMP_PLACES} | |
72832460 UB |
1884 | |
1885 | @item @emph{Reference}: | |
1a6d1d24 | 1886 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.4 |
72832460 UB |
1887 | @end table |
1888 | ||
1889 | ||
1890 | ||
83fd6c5b TB |
1891 | @node OMP_PLACES |
1892 | @section @env{OMP_PLACES} -- Specifies on which CPUs the theads should be placed | |
1893 | @cindex Environment Variable | |
1894 | @table @asis | |
1895 | @item @emph{Description}: | |
1896 | The thread placement can be either specified using an abstract name or by an | |
1897 | explicit list of the places. The abstract names @code{threads}, @code{cores} | |
1898 | and @code{sockets} can be optionally followed by a positive number in | |
1899 | parentheses, which denotes the how many places shall be created. With | |
1900 | @code{threads} each place corresponds to a single hardware thread; @code{cores} | |
1901 | to a single core with the corresponding number of hardware threads; and with | |
1902 | @code{sockets} the place corresponds to a single socket. The resulting | |
1903 | placement can be shown by setting the @env{OMP_DISPLAY_ENV} environment | |
1904 | variable. | |
1905 | ||
1906 | Alternatively, the placement can be specified explicitly as comma-separated | |
1907 | list of places. A place is specified by set of nonnegative numbers in curly | |
1908 | braces, denoting the denoting the hardware threads. The hardware threads | |
1909 | belonging to a place can either be specified as comma-separated list of | |
1910 | nonnegative thread numbers or using an interval. Multiple places can also be | |
1911 | either specified by a comma-separated list of places or by an interval. To | |
1912 | specify an interval, a colon followed by the count is placed after after | |
1913 | the hardware thread number or the place. Optionally, the length can be | |
1914 | followed by a colon and the stride number -- otherwise a unit stride is | |
1915 | assumed. For instance, the following specifies the same places list: | |
1916 | @code{"@{0,1,2@}, @{3,4,6@}, @{7,8,9@}, @{10,11,12@}"}; | |
1917 | @code{"@{0:3@}, @{3:3@}, @{7:3@}, @{10:3@}"}; and @code{"@{0:2@}:4:3"}. | |
1918 | ||
1919 | If @env{OMP_PLACES} and @env{GOMP_CPU_AFFINITY} are unset and | |
1920 | @env{OMP_PROC_BIND} is either unset or @code{false}, threads may be moved | |
1921 | between CPUs following no placement policy. | |
1922 | ||
1923 | @item @emph{See also}: | |
1924 | @ref{OMP_PROC_BIND}, @ref{GOMP_CPU_AFFINITY}, @ref{omp_get_proc_bind}, | |
1925 | @ref{OMP_DISPLAY_ENV} | |
1926 | ||
1927 | @item @emph{Reference}: | |
1a6d1d24 | 1928 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.5 |
83fd6c5b TB |
1929 | @end table |
1930 | ||
1931 | ||
1932 | ||
72832460 UB |
1933 | @node OMP_STACKSIZE |
1934 | @section @env{OMP_STACKSIZE} -- Set default thread stack size | |
83fd6c5b TB |
1935 | @cindex Environment Variable |
1936 | @table @asis | |
1937 | @item @emph{Description}: | |
72832460 UB |
1938 | Set the default thread stack size in kilobytes, unless the number |
1939 | is suffixed by @code{B}, @code{K}, @code{M} or @code{G}, in which | |
1940 | case the size is, respectively, in bytes, kilobytes, megabytes | |
1941 | or gigabytes. This is different from @code{pthread_attr_setstacksize} | |
1942 | which gets the number of bytes as an argument. If the stack size cannot | |
1943 | be set due to system constraints, an error is reported and the initial | |
1944 | stack size is left unchanged. If undefined, the stack size is system | |
1945 | dependent. | |
83fd6c5b | 1946 | |
72832460 | 1947 | @item @emph{Reference}: |
1a6d1d24 | 1948 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.7 |
3721b9e1 DF |
1949 | @end table |
1950 | ||
1951 | ||
1952 | ||
1953 | @node OMP_SCHEDULE | |
1954 | @section @env{OMP_SCHEDULE} -- How threads are scheduled | |
1955 | @cindex Environment Variable | |
14734fc7 | 1956 | @cindex Implementation specific setting |
3721b9e1 DF |
1957 | @table @asis |
1958 | @item @emph{Description}: | |
1959 | Allows to specify @code{schedule type} and @code{chunk size}. | |
1960 | The value of the variable shall have the form: @code{type[,chunk]} where | |
5c6ed53a | 1961 | @code{type} is one of @code{static}, @code{dynamic}, @code{guided} or @code{auto} |
83fd6c5b | 1962 | The optional @code{chunk} size shall be a positive integer. If undefined, |
7c2b7f45 | 1963 | dynamic scheduling and a chunk size of 1 is used. |
3721b9e1 | 1964 | |
5c6ed53a TB |
1965 | @item @emph{See also}: |
1966 | @ref{omp_set_schedule} | |
1967 | ||
1968 | @item @emph{Reference}: | |
1a6d1d24 | 1969 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Sections 2.7.1.1 and 4.1 |
5c6ed53a TB |
1970 | @end table |
1971 | ||
1972 | ||
1973 | ||
1bfc07d1 KCY |
1974 | @node OMP_TARGET_OFFLOAD |
1975 | @section @env{OMP_TARGET_OFFLOAD} -- Controls offloading behaviour | |
1976 | @cindex Environment Variable | |
1977 | @cindex Implementation specific setting | |
1978 | @table @asis | |
1979 | @item @emph{Description}: | |
1980 | Specifies the behaviour with regard to offloading code to a device. This | |
1981 | variable can be set to one of three values - @code{MANDATORY}, @code{DISABLED} | |
1982 | or @code{DEFAULT}. | |
1983 | ||
1984 | If set to @code{MANDATORY}, the program will terminate with an error if | |
1985 | the offload device is not present or is not supported. If set to | |
1986 | @code{DISABLED}, then offloading is disabled and all code will run on the | |
1987 | host. If set to @code{DEFAULT}, the program will try offloading to the | |
1988 | device first, then fall back to running code on the host if it cannot. | |
1989 | ||
1990 | If undefined, then the program will behave as if @code{DEFAULT} was set. | |
1991 | ||
1992 | @item @emph{Reference}: | |
1993 | @uref{https://www.openmp.org, OpenMP specification v5.0}, Section 6.17 | |
1994 | @end table | |
1995 | ||
1996 | ||
1997 | ||
5c6ed53a | 1998 | @node OMP_THREAD_LIMIT |
6a2ba183 | 1999 | @section @env{OMP_THREAD_LIMIT} -- Set the maximum number of threads |
5c6ed53a TB |
2000 | @cindex Environment Variable |
2001 | @table @asis | |
2002 | @item @emph{Description}: | |
83fd6c5b TB |
2003 | Specifies the number of threads to use for the whole program. The |
2004 | value of this variable shall be a positive integer. If undefined, | |
5c6ed53a TB |
2005 | the number of threads is not limited. |
2006 | ||
2007 | @item @emph{See also}: | |
83fd6c5b | 2008 | @ref{OMP_NUM_THREADS}, @ref{omp_get_thread_limit} |
5c6ed53a TB |
2009 | |
2010 | @item @emph{Reference}: | |
1a6d1d24 | 2011 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.10 |
5c6ed53a TB |
2012 | @end table |
2013 | ||
2014 | ||
2015 | ||
2016 | @node OMP_WAIT_POLICY | |
2017 | @section @env{OMP_WAIT_POLICY} -- How waiting threads are handled | |
2018 | @cindex Environment Variable | |
2019 | @table @asis | |
2020 | @item @emph{Description}: | |
83fd6c5b | 2021 | Specifies whether waiting threads should be active or passive. If |
5c6ed53a TB |
2022 | the value is @code{PASSIVE}, waiting threads should not consume CPU |
2023 | power while waiting; while the value is @code{ACTIVE} specifies that | |
83fd6c5b | 2024 | they should. If undefined, threads wait actively for a short time |
acf0174b JJ |
2025 | before waiting passively. |
2026 | ||
2027 | @item @emph{See also}: | |
2028 | @ref{GOMP_SPINCOUNT} | |
5c6ed53a TB |
2029 | |
2030 | @item @emph{Reference}: | |
1a6d1d24 | 2031 | @uref{https://www.openmp.org, OpenMP specification v4.5}, Section 4.8 |
3721b9e1 DF |
2032 | @end table |
2033 | ||
2034 | ||
2035 | ||
2036 | @node GOMP_CPU_AFFINITY | |
2037 | @section @env{GOMP_CPU_AFFINITY} -- Bind threads to specific CPUs | |
2038 | @cindex Environment Variable | |
2039 | @table @asis | |
2040 | @item @emph{Description}: | |
83fd6c5b TB |
2041 | Binds threads to specific CPUs. The variable should contain a space-separated |
2042 | or comma-separated list of CPUs. This list may contain different kinds of | |
06785a48 | 2043 | entries: either single CPU numbers in any order, a range of CPUs (M-N) |
83fd6c5b | 2044 | or a range with some stride (M-N:S). CPU numbers are zero based. For example, |
06785a48 DF |
2045 | @code{GOMP_CPU_AFFINITY="0 3 1-2 4-15:2"} will bind the initial thread |
2046 | to CPU 0, the second to CPU 3, the third to CPU 1, the fourth to | |
2047 | CPU 2, the fifth to CPU 4, the sixth through tenth to CPUs 6, 8, 10, 12, | |
2048 | and 14 respectively and then start assigning back from the beginning of | |
6a2ba183 | 2049 | the list. @code{GOMP_CPU_AFFINITY=0} binds all threads to CPU 0. |
06785a48 | 2050 | |
f1f3453e | 2051 | There is no libgomp library routine to determine whether a CPU affinity |
83fd6c5b | 2052 | specification is in effect. As a workaround, language-specific library |
06785a48 DF |
2053 | functions, e.g., @code{getenv} in C or @code{GET_ENVIRONMENT_VARIABLE} in |
2054 | Fortran, may be used to query the setting of the @code{GOMP_CPU_AFFINITY} | |
83fd6c5b | 2055 | environment variable. A defined CPU affinity on startup cannot be changed |
06785a48 DF |
2056 | or disabled during the runtime of the application. |
2057 | ||
83fd6c5b TB |
2058 | If both @env{GOMP_CPU_AFFINITY} and @env{OMP_PROC_BIND} are set, |
2059 | @env{OMP_PROC_BIND} has a higher precedence. If neither has been set and | |
2060 | @env{OMP_PROC_BIND} is unset, or when @env{OMP_PROC_BIND} is set to | |
2061 | @code{FALSE}, the host system will handle the assignment of threads to CPUs. | |
20906c66 JJ |
2062 | |
2063 | @item @emph{See also}: | |
83fd6c5b | 2064 | @ref{OMP_PLACES}, @ref{OMP_PROC_BIND} |
3721b9e1 DF |
2065 | @end table |
2066 | ||
2067 | ||
2068 | ||
41dbbb37 TS |
2069 | @node GOMP_DEBUG |
2070 | @section @env{GOMP_DEBUG} -- Enable debugging output | |
2071 | @cindex Environment Variable | |
2072 | @table @asis | |
2073 | @item @emph{Description}: | |
2074 | Enable debugging output. The variable should be set to @code{0} | |
2075 | (disabled, also the default if not set), or @code{1} (enabled). | |
2076 | ||
2077 | If enabled, some debugging output will be printed during execution. | |
2078 | This is currently not specified in more detail, and subject to change. | |
2079 | @end table | |
2080 | ||
2081 | ||
2082 | ||
3721b9e1 DF |
2083 | @node GOMP_STACKSIZE |
2084 | @section @env{GOMP_STACKSIZE} -- Set default thread stack size | |
2085 | @cindex Environment Variable | |
14734fc7 | 2086 | @cindex Implementation specific setting |
3721b9e1 DF |
2087 | @table @asis |
2088 | @item @emph{Description}: | |
83fd6c5b | 2089 | Set the default thread stack size in kilobytes. This is different from |
5c6ed53a | 2090 | @code{pthread_attr_setstacksize} which gets the number of bytes as an |
83fd6c5b TB |
2091 | argument. If the stack size cannot be set due to system constraints, an |
2092 | error is reported and the initial stack size is left unchanged. If undefined, | |
7c2b7f45 | 2093 | the stack size is system dependent. |
3721b9e1 | 2094 | |
5c6ed53a | 2095 | @item @emph{See also}: |
0024f1af | 2096 | @ref{OMP_STACKSIZE} |
5c6ed53a | 2097 | |
3721b9e1 | 2098 | @item @emph{Reference}: |
c1030b5c | 2099 | @uref{https://gcc.gnu.org/ml/gcc-patches/2006-06/msg00493.html, |
3721b9e1 | 2100 | GCC Patches Mailinglist}, |
c1030b5c | 2101 | @uref{https://gcc.gnu.org/ml/gcc-patches/2006-06/msg00496.html, |
3721b9e1 DF |
2102 | GCC Patches Mailinglist} |
2103 | @end table | |
2104 | ||
2105 | ||
2106 | ||
acf0174b JJ |
2107 | @node GOMP_SPINCOUNT |
2108 | @section @env{GOMP_SPINCOUNT} -- Set the busy-wait spin count | |
2109 | @cindex Environment Variable | |
2110 | @cindex Implementation specific setting | |
2111 | @table @asis | |
2112 | @item @emph{Description}: | |
2113 | Determines how long a threads waits actively with consuming CPU power | |
83fd6c5b | 2114 | before waiting passively without consuming CPU power. The value may be |
acf0174b | 2115 | either @code{INFINITE}, @code{INFINITY} to always wait actively or an |
83fd6c5b | 2116 | integer which gives the number of spins of the busy-wait loop. The |
acf0174b JJ |
2117 | integer may optionally be followed by the following suffixes acting |
2118 | as multiplication factors: @code{k} (kilo, thousand), @code{M} (mega, | |
2119 | million), @code{G} (giga, billion), or @code{T} (tera, trillion). | |
2120 | If undefined, 0 is used when @env{OMP_WAIT_POLICY} is @code{PASSIVE}, | |
2121 | 300,000 is used when @env{OMP_WAIT_POLICY} is undefined and | |
2122 | 30 billion is used when @env{OMP_WAIT_POLICY} is @code{ACTIVE}. | |
2123 | If there are more OpenMP threads than available CPUs, 1000 and 100 | |
2124 | spins are used for @env{OMP_WAIT_POLICY} being @code{ACTIVE} or | |
2125 | undefined, respectively; unless the @env{GOMP_SPINCOUNT} is lower | |
2126 | or @env{OMP_WAIT_POLICY} is @code{PASSIVE}. | |
2127 | ||
2128 | @item @emph{See also}: | |
2129 | @ref{OMP_WAIT_POLICY} | |
2130 | @end table | |
2131 | ||
2132 | ||
2133 | ||
06441dd5 SH |
2134 | @node GOMP_RTEMS_THREAD_POOLS |
2135 | @section @env{GOMP_RTEMS_THREAD_POOLS} -- Set the RTEMS specific thread pools | |
2136 | @cindex Environment Variable | |
2137 | @cindex Implementation specific setting | |
2138 | @table @asis | |
2139 | @item @emph{Description}: | |
2140 | This environment variable is only used on the RTEMS real-time operating system. | |
2141 | It determines the scheduler instance specific thread pools. The format for | |
2142 | @env{GOMP_RTEMS_THREAD_POOLS} is a list of optional | |
2143 | @code{<thread-pool-count>[$<priority>]@@<scheduler-name>} configurations | |
2144 | separated by @code{:} where: | |
2145 | @itemize @bullet | |
2146 | @item @code{<thread-pool-count>} is the thread pool count for this scheduler | |
2147 | instance. | |
2148 | @item @code{$<priority>} is an optional priority for the worker threads of a | |
2149 | thread pool according to @code{pthread_setschedparam}. In case a priority | |
2150 | value is omitted, then a worker thread will inherit the priority of the OpenMP | |
432de084 TB |
2151 | primary thread that created it. The priority of the worker thread is not |
2152 | changed after creation, even if a new OpenMP primary thread using the worker has | |
06441dd5 SH |
2153 | a different priority. |
2154 | @item @code{@@<scheduler-name>} is the scheduler instance name according to the | |
2155 | RTEMS application configuration. | |
2156 | @end itemize | |
2157 | In case no thread pool configuration is specified for a scheduler instance, | |
432de084 | 2158 | then each OpenMP primary thread of this scheduler instance will use its own |
06441dd5 | 2159 | dynamically allocated thread pool. To limit the worker thread count of the |
432de084 | 2160 | thread pools, each OpenMP primary thread must call @code{omp_set_num_threads}. |
06441dd5 SH |
2161 | @item @emph{Example}: |
2162 | Lets suppose we have three scheduler instances @code{IO}, @code{WRK0}, and | |
2163 | @code{WRK1} with @env{GOMP_RTEMS_THREAD_POOLS} set to | |
2164 | @code{"1@@WRK0:3$4@@WRK1"}. Then there are no thread pool restrictions for | |
2165 | scheduler instance @code{IO}. In the scheduler instance @code{WRK0} there is | |
2166 | one thread pool available. Since no priority is specified for this scheduler | |
432de084 | 2167 | instance, the worker thread inherits the priority of the OpenMP primary thread |
06441dd5 SH |
2168 | that created it. In the scheduler instance @code{WRK1} there are three thread |
2169 | pools available and their worker threads run at priority four. | |
2170 | @end table | |
2171 | ||
2172 | ||
2173 | ||
cdf6119d JN |
2174 | @c --------------------------------------------------------------------- |
2175 | @c Enabling OpenACC | |
2176 | @c --------------------------------------------------------------------- | |
2177 | ||
2178 | @node Enabling OpenACC | |
2179 | @chapter Enabling OpenACC | |
2180 | ||
2181 | To activate the OpenACC extensions for C/C++ and Fortran, the compile-time | |
2182 | flag @option{-fopenacc} must be specified. This enables the OpenACC directive | |
c1030b5c | 2183 | @code{#pragma acc} in C/C++ and @code{!$acc} directives in free form, |
cdf6119d JN |
2184 | @code{c$acc}, @code{*$acc} and @code{!$acc} directives in fixed form, |
2185 | @code{!$} conditional compilation sentinels in free form and @code{c$}, | |
2186 | @code{*$} and @code{!$} sentinels in fixed form, for Fortran. The flag also | |
2187 | arranges for automatic linking of the OpenACC runtime library | |
2188 | (@ref{OpenACC Runtime Library Routines}). | |
2189 | ||
8d1a1cb1 TB |
2190 | See @uref{https://gcc.gnu.org/wiki/OpenACC} for more information. |
2191 | ||
cdf6119d | 2192 | A complete description of all OpenACC directives accepted may be found in |
9651fbaf | 2193 | the @uref{https://www.openacc.org, OpenACC} Application Programming |
e464fc90 | 2194 | Interface manual, version 2.6. |
cdf6119d | 2195 | |
cdf6119d JN |
2196 | |
2197 | ||
2198 | @c --------------------------------------------------------------------- | |
2199 | @c OpenACC Runtime Library Routines | |
2200 | @c --------------------------------------------------------------------- | |
2201 | ||
2202 | @node OpenACC Runtime Library Routines | |
2203 | @chapter OpenACC Runtime Library Routines | |
2204 | ||
2205 | The runtime routines described here are defined by section 3 of the OpenACC | |
e464fc90 | 2206 | specifications in version 2.6. |
cdf6119d JN |
2207 | They have C linkage, and do not throw exceptions. |
2208 | Generally, they are available only for the host, with the exception of | |
2209 | @code{acc_on_device}, which is available for both the host and the | |
2210 | acceleration device. | |
2211 | ||
2212 | @menu | |
2213 | * acc_get_num_devices:: Get number of devices for the given device | |
2214 | type. | |
2215 | * acc_set_device_type:: Set type of device accelerator to use. | |
2216 | * acc_get_device_type:: Get type of device accelerator to be used. | |
2217 | * acc_set_device_num:: Set device number to use. | |
2218 | * acc_get_device_num:: Get device number to be used. | |
6c84c8bf | 2219 | * acc_get_property:: Get device property. |
cdf6119d JN |
2220 | * acc_async_test:: Tests for completion of a specific asynchronous |
2221 | operation. | |
c1030b5c | 2222 | * acc_async_test_all:: Tests for completion of all asynchronous |
cdf6119d JN |
2223 | operations. |
2224 | * acc_wait:: Wait for completion of a specific asynchronous | |
2225 | operation. | |
c1030b5c | 2226 | * acc_wait_all:: Waits for completion of all asynchronous |
cdf6119d JN |
2227 | operations. |
2228 | * acc_wait_all_async:: Wait for completion of all asynchronous | |
2229 | operations. | |
2230 | * acc_wait_async:: Wait for completion of asynchronous operations. | |
2231 | * acc_init:: Initialize runtime for a specific device type. | |
2232 | * acc_shutdown:: Shuts down the runtime for a specific device | |
2233 | type. | |
2234 | * acc_on_device:: Whether executing on a particular device | |
2235 | * acc_malloc:: Allocate device memory. | |
2236 | * acc_free:: Free device memory. | |
2237 | * acc_copyin:: Allocate device memory and copy host memory to | |
2238 | it. | |
2239 | * acc_present_or_copyin:: If the data is not present on the device, | |
2240 | allocate device memory and copy from host | |
2241 | memory. | |
2242 | * acc_create:: Allocate device memory and map it to host | |
2243 | memory. | |
2244 | * acc_present_or_create:: If the data is not present on the device, | |
2245 | allocate device memory and map it to host | |
2246 | memory. | |
2247 | * acc_copyout:: Copy device memory to host memory. | |
2248 | * acc_delete:: Free device memory. | |
2249 | * acc_update_device:: Update device memory from mapped host memory. | |
2250 | * acc_update_self:: Update host memory from mapped device memory. | |
2251 | * acc_map_data:: Map previously allocated device memory to host | |
2252 | memory. | |
2253 | * acc_unmap_data:: Unmap device memory from host memory. | |
2254 | * acc_deviceptr:: Get device pointer associated with specific | |
2255 | host address. | |
2256 | * acc_hostptr:: Get host pointer associated with specific | |
2257 | device address. | |
93d90219 | 2258 | * acc_is_present:: Indicate whether host variable / array is |
cdf6119d JN |
2259 | present on device. |
2260 | * acc_memcpy_to_device:: Copy host memory to device memory. | |
2261 | * acc_memcpy_from_device:: Copy device memory to host memory. | |
e464fc90 TB |
2262 | * acc_attach:: Let device pointer point to device-pointer target. |
2263 | * acc_detach:: Let device pointer point to host-pointer target. | |
cdf6119d JN |
2264 | |
2265 | API routines for target platforms. | |
2266 | ||
2267 | * acc_get_current_cuda_device:: Get CUDA device handle. | |
2268 | * acc_get_current_cuda_context::Get CUDA context handle. | |
2269 | * acc_get_cuda_stream:: Get CUDA stream handle. | |
2270 | * acc_set_cuda_stream:: Set CUDA stream handle. | |
5fae049d TS |
2271 | |
2272 | API routines for the OpenACC Profiling Interface. | |
2273 | ||
2274 | * acc_prof_register:: Register callbacks. | |
2275 | * acc_prof_unregister:: Unregister callbacks. | |
2276 | * acc_prof_lookup:: Obtain inquiry functions. | |
2277 | * acc_register_library:: Library registration. | |
cdf6119d JN |
2278 | @end menu |
2279 | ||
2280 | ||
2281 | ||
2282 | @node acc_get_num_devices | |
2283 | @section @code{acc_get_num_devices} -- Get number of devices for given device type | |
2284 | @table @asis | |
2285 | @item @emph{Description} | |
2286 | This function returns a value indicating the number of devices available | |
2287 | for the device type specified in @var{devicetype}. | |
2288 | ||
2289 | @item @emph{C/C++}: | |
2290 | @multitable @columnfractions .20 .80 | |
2291 | @item @emph{Prototype}: @tab @code{int acc_get_num_devices(acc_device_t devicetype);} | |
2292 | @end multitable | |
2293 | ||
2294 | @item @emph{Fortran}: | |
2295 | @multitable @columnfractions .20 .80 | |
2296 | @item @emph{Interface}: @tab @code{integer function acc_get_num_devices(devicetype)} | |
2297 | @item @tab @code{integer(kind=acc_device_kind) devicetype} | |
2298 | @end multitable | |
2299 | ||
2300 | @item @emph{Reference}: | |
e464fc90 | 2301 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
2302 | 3.2.1. |
2303 | @end table | |
2304 | ||
2305 | ||
2306 | ||
2307 | @node acc_set_device_type | |
2308 | @section @code{acc_set_device_type} -- Set type of device accelerator to use. | |
2309 | @table @asis | |
2310 | @item @emph{Description} | |
c1030b5c | 2311 | This function indicates to the runtime library which device type, specified |
cdf6119d JN |
2312 | in @var{devicetype}, to use when executing a parallel or kernels region. |
2313 | ||
2314 | @item @emph{C/C++}: | |
2315 | @multitable @columnfractions .20 .80 | |
2316 | @item @emph{Prototype}: @tab @code{acc_set_device_type(acc_device_t devicetype);} | |
2317 | @end multitable | |
2318 | ||
2319 | @item @emph{Fortran}: | |
2320 | @multitable @columnfractions .20 .80 | |
2321 | @item @emph{Interface}: @tab @code{subroutine acc_set_device_type(devicetype)} | |
2322 | @item @tab @code{integer(kind=acc_device_kind) devicetype} | |
2323 | @end multitable | |
2324 | ||
2325 | @item @emph{Reference}: | |
e464fc90 | 2326 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
2327 | 3.2.2. |
2328 | @end table | |
2329 | ||
2330 | ||
2331 | ||
2332 | @node acc_get_device_type | |
2333 | @section @code{acc_get_device_type} -- Get type of device accelerator to be used. | |
2334 | @table @asis | |
2335 | @item @emph{Description} | |
2336 | This function returns what device type will be used when executing a | |
2337 | parallel or kernels region. | |
2338 | ||
b52643ab KCY |
2339 | This function returns @code{acc_device_none} if |
2340 | @code{acc_get_device_type} is called from | |
2341 | @code{acc_ev_device_init_start}, @code{acc_ev_device_init_end} | |
2342 | callbacks of the OpenACC Profiling Interface (@ref{OpenACC Profiling | |
2343 | Interface}), that is, if the device is currently being initialized. | |
2344 | ||
cdf6119d JN |
2345 | @item @emph{C/C++}: |
2346 | @multitable @columnfractions .20 .80 | |
2347 | @item @emph{Prototype}: @tab @code{acc_device_t acc_get_device_type(void);} | |
2348 | @end multitable | |
2349 | ||
2350 | @item @emph{Fortran}: | |
2351 | @multitable @columnfractions .20 .80 | |
2352 | @item @emph{Interface}: @tab @code{function acc_get_device_type(void)} | |
2353 | @item @tab @code{integer(kind=acc_device_kind) acc_get_device_type} | |
2354 | @end multitable | |
2355 | ||
2356 | @item @emph{Reference}: | |
e464fc90 | 2357 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
2358 | 3.2.3. |
2359 | @end table | |
2360 | ||
2361 | ||
2362 | ||
2363 | @node acc_set_device_num | |
2364 | @section @code{acc_set_device_num} -- Set device number to use. | |
2365 | @table @asis | |
2366 | @item @emph{Description} | |
2367 | This function will indicate to the runtime which device number, | |
8d1a1cb1 | 2368 | specified by @var{devicenum}, associated with the specified device |
cdf6119d JN |
2369 | type @var{devicetype}. |
2370 | ||
2371 | @item @emph{C/C++}: | |
2372 | @multitable @columnfractions .20 .80 | |
8d1a1cb1 | 2373 | @item @emph{Prototype}: @tab @code{acc_set_device_num(int devicenum, acc_device_t devicetype);} |
cdf6119d JN |
2374 | @end multitable |
2375 | ||
2376 | @item @emph{Fortran}: | |
2377 | @multitable @columnfractions .20 .80 | |
2378 | @item @emph{Interface}: @tab @code{subroutine acc_set_device_num(devicenum, devicetype)} | |
2379 | @item @tab @code{integer devicenum} | |
2380 | @item @tab @code{integer(kind=acc_device_kind) devicetype} | |
2381 | @end multitable | |
2382 | ||
2383 | @item @emph{Reference}: | |
e464fc90 | 2384 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
2385 | 3.2.4. |
2386 | @end table | |
2387 | ||
2388 | ||
2389 | ||
2390 | @node acc_get_device_num | |
2391 | @section @code{acc_get_device_num} -- Get device number to be used. | |
2392 | @table @asis | |
2393 | @item @emph{Description} | |
2394 | This function returns which device number associated with the specified device | |
2395 | type @var{devicetype}, will be used when executing a parallel or kernels | |
2396 | region. | |
2397 | ||
2398 | @item @emph{C/C++}: | |
2399 | @multitable @columnfractions .20 .80 | |
2400 | @item @emph{Prototype}: @tab @code{int acc_get_device_num(acc_device_t devicetype);} | |
2401 | @end multitable | |
2402 | ||
2403 | @item @emph{Fortran}: | |
2404 | @multitable @columnfractions .20 .80 | |
2405 | @item @emph{Interface}: @tab @code{function acc_get_device_num(devicetype)} | |
2406 | @item @tab @code{integer(kind=acc_device_kind) devicetype} | |
2407 | @item @tab @code{integer acc_get_device_num} | |
2408 | @end multitable | |
2409 | ||
2410 | @item @emph{Reference}: | |
e464fc90 | 2411 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
2412 | 3.2.5. |
2413 | @end table | |
2414 | ||
2415 | ||
2416 | ||
6c84c8bf MR |
2417 | @node acc_get_property |
2418 | @section @code{acc_get_property} -- Get device property. | |
2419 | @cindex acc_get_property | |
2420 | @cindex acc_get_property_string | |
2421 | @table @asis | |
2422 | @item @emph{Description} | |
2423 | These routines return the value of the specified @var{property} for the | |
2424 | device being queried according to @var{devicenum} and @var{devicetype}. | |
2425 | Integer-valued and string-valued properties are returned by | |
2426 | @code{acc_get_property} and @code{acc_get_property_string} respectively. | |
2427 | The Fortran @code{acc_get_property_string} subroutine returns the string | |
2428 | retrieved in its fourth argument while the remaining entry points are | |
2429 | functions, which pass the return value as their result. | |
2430 | ||
8d1a1cb1 TB |
2431 | Note for Fortran, only: the OpenACC technical committee corrected and, hence, |
2432 | modified the interface introduced in OpenACC 2.6. The kind-value parameter | |
2433 | @code{acc_device_property} has been renamed to @code{acc_device_property_kind} | |
2434 | for consistency and the return type of the @code{acc_get_property} function is | |
2435 | now a @code{c_size_t} integer instead of a @code{acc_device_property} integer. | |
2436 | The parameter @code{acc_device_property} will continue to be provided, | |
2437 | but might be removed in a future version of GCC. | |
2438 | ||
6c84c8bf MR |
2439 | @item @emph{C/C++}: |
2440 | @multitable @columnfractions .20 .80 | |
2441 | @item @emph{Prototype}: @tab @code{size_t acc_get_property(int devicenum, acc_device_t devicetype, acc_device_property_t property);} | |
2442 | @item @emph{Prototype}: @tab @code{const char *acc_get_property_string(int devicenum, acc_device_t devicetype, acc_device_property_t property);} | |
2443 | @end multitable | |
2444 | ||
2445 | @item @emph{Fortran}: | |
2446 | @multitable @columnfractions .20 .80 | |
2447 | @item @emph{Interface}: @tab @code{function acc_get_property(devicenum, devicetype, property)} | |
2448 | @item @emph{Interface}: @tab @code{subroutine acc_get_property_string(devicenum, devicetype, property, string)} | |
8d1a1cb1 | 2449 | @item @tab @code{use ISO_C_Binding, only: c_size_t} |
6c84c8bf MR |
2450 | @item @tab @code{integer devicenum} |
2451 | @item @tab @code{integer(kind=acc_device_kind) devicetype} | |
8d1a1cb1 TB |
2452 | @item @tab @code{integer(kind=acc_device_property_kind) property} |
2453 | @item @tab @code{integer(kind=c_size_t) acc_get_property} | |
6c84c8bf MR |
2454 | @item @tab @code{character(*) string} |
2455 | @end multitable | |
2456 | ||
2457 | @item @emph{Reference}: | |
2458 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
2459 | 3.2.6. | |
2460 | @end table | |
2461 | ||
2462 | ||
2463 | ||
cdf6119d JN |
2464 | @node acc_async_test |
2465 | @section @code{acc_async_test} -- Test for completion of a specific asynchronous operation. | |
2466 | @table @asis | |
2467 | @item @emph{Description} | |
93d90219 | 2468 | This function tests for completion of the asynchronous operation specified |
cdf6119d JN |
2469 | in @var{arg}. In C/C++, a non-zero value will be returned to indicate |
2470 | the specified asynchronous operation has completed. While Fortran will return | |
93d90219 | 2471 | a @code{true}. If the asynchronous operation has not completed, C/C++ returns |
cdf6119d JN |
2472 | a zero and Fortran returns a @code{false}. |
2473 | ||
2474 | @item @emph{C/C++}: | |
2475 | @multitable @columnfractions .20 .80 | |
2476 | @item @emph{Prototype}: @tab @code{int acc_async_test(int arg);} | |
2477 | @end multitable | |
2478 | ||
2479 | @item @emph{Fortran}: | |
2480 | @multitable @columnfractions .20 .80 | |
2481 | @item @emph{Interface}: @tab @code{function acc_async_test(arg)} | |
2482 | @item @tab @code{integer(kind=acc_handle_kind) arg} | |
2483 | @item @tab @code{logical acc_async_test} | |
2484 | @end multitable | |
2485 | ||
2486 | @item @emph{Reference}: | |
e464fc90 TB |
2487 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2488 | 3.2.9. | |
cdf6119d JN |
2489 | @end table |
2490 | ||
2491 | ||
2492 | ||
2493 | @node acc_async_test_all | |
2494 | @section @code{acc_async_test_all} -- Tests for completion of all asynchronous operations. | |
2495 | @table @asis | |
2496 | @item @emph{Description} | |
93d90219 | 2497 | This function tests for completion of all asynchronous operations. |
cdf6119d JN |
2498 | In C/C++, a non-zero value will be returned to indicate all asynchronous |
2499 | operations have completed. While Fortran will return a @code{true}. If | |
2500 | any asynchronous operation has not completed, C/C++ returns a zero and | |
2501 | Fortran returns a @code{false}. | |
2502 | ||
2503 | @item @emph{C/C++}: | |
2504 | @multitable @columnfractions .20 .80 | |
2505 | @item @emph{Prototype}: @tab @code{int acc_async_test_all(void);} | |
2506 | @end multitable | |
2507 | ||
2508 | @item @emph{Fortran}: | |
2509 | @multitable @columnfractions .20 .80 | |
2510 | @item @emph{Interface}: @tab @code{function acc_async_test()} | |
2511 | @item @tab @code{logical acc_get_device_num} | |
2512 | @end multitable | |
2513 | ||
2514 | @item @emph{Reference}: | |
e464fc90 TB |
2515 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2516 | 3.2.10. | |
cdf6119d JN |
2517 | @end table |
2518 | ||
2519 | ||
2520 | ||
2521 | @node acc_wait | |
2522 | @section @code{acc_wait} -- Wait for completion of a specific asynchronous operation. | |
2523 | @table @asis | |
2524 | @item @emph{Description} | |
2525 | This function waits for completion of the asynchronous operation | |
2526 | specified in @var{arg}. | |
2527 | ||
2528 | @item @emph{C/C++}: | |
2529 | @multitable @columnfractions .20 .80 | |
2530 | @item @emph{Prototype}: @tab @code{acc_wait(arg);} | |
7ce64403 | 2531 | @item @emph{Prototype (OpenACC 1.0 compatibility)}: @tab @code{acc_async_wait(arg);} |
cdf6119d JN |
2532 | @end multitable |
2533 | ||
2534 | @item @emph{Fortran}: | |
2535 | @multitable @columnfractions .20 .80 | |
2536 | @item @emph{Interface}: @tab @code{subroutine acc_wait(arg)} | |
2537 | @item @tab @code{integer(acc_handle_kind) arg} | |
7ce64403 TS |
2538 | @item @emph{Interface (OpenACC 1.0 compatibility)}: @tab @code{subroutine acc_async_wait(arg)} |
2539 | @item @tab @code{integer(acc_handle_kind) arg} | |
cdf6119d JN |
2540 | @end multitable |
2541 | ||
2542 | @item @emph{Reference}: | |
e464fc90 TB |
2543 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2544 | 3.2.11. | |
cdf6119d JN |
2545 | @end table |
2546 | ||
2547 | ||
2548 | ||
2549 | @node acc_wait_all | |
2550 | @section @code{acc_wait_all} -- Waits for completion of all asynchronous operations. | |
2551 | @table @asis | |
2552 | @item @emph{Description} | |
2553 | This function waits for the completion of all asynchronous operations. | |
2554 | ||
2555 | @item @emph{C/C++}: | |
2556 | @multitable @columnfractions .20 .80 | |
2557 | @item @emph{Prototype}: @tab @code{acc_wait_all(void);} | |
7ce64403 | 2558 | @item @emph{Prototype (OpenACC 1.0 compatibility)}: @tab @code{acc_async_wait_all(void);} |
cdf6119d JN |
2559 | @end multitable |
2560 | ||
2561 | @item @emph{Fortran}: | |
2562 | @multitable @columnfractions .20 .80 | |
7ce64403 TS |
2563 | @item @emph{Interface}: @tab @code{subroutine acc_wait_all()} |
2564 | @item @emph{Interface (OpenACC 1.0 compatibility)}: @tab @code{subroutine acc_async_wait_all()} | |
cdf6119d JN |
2565 | @end multitable |
2566 | ||
2567 | @item @emph{Reference}: | |
e464fc90 TB |
2568 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2569 | 3.2.13. | |
cdf6119d JN |
2570 | @end table |
2571 | ||
2572 | ||
2573 | ||
2574 | @node acc_wait_all_async | |
2575 | @section @code{acc_wait_all_async} -- Wait for completion of all asynchronous operations. | |
2576 | @table @asis | |
2577 | @item @emph{Description} | |
2578 | This function enqueues a wait operation on the queue @var{async} for any | |
2579 | and all asynchronous operations that have been previously enqueued on | |
2580 | any queue. | |
2581 | ||
2582 | @item @emph{C/C++}: | |
2583 | @multitable @columnfractions .20 .80 | |
2584 | @item @emph{Prototype}: @tab @code{acc_wait_all_async(int async);} | |
2585 | @end multitable | |
2586 | ||
2587 | @item @emph{Fortran}: | |
2588 | @multitable @columnfractions .20 .80 | |
2589 | @item @emph{Interface}: @tab @code{subroutine acc_wait_all_async(async)} | |
2590 | @item @tab @code{integer(acc_handle_kind) async} | |
2591 | @end multitable | |
2592 | ||
2593 | @item @emph{Reference}: | |
e464fc90 TB |
2594 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2595 | 3.2.14. | |
cdf6119d JN |
2596 | @end table |
2597 | ||
2598 | ||
2599 | ||
2600 | @node acc_wait_async | |
2601 | @section @code{acc_wait_async} -- Wait for completion of asynchronous operations. | |
2602 | @table @asis | |
2603 | @item @emph{Description} | |
2604 | This function enqueues a wait operation on queue @var{async} for any and all | |
2605 | asynchronous operations enqueued on queue @var{arg}. | |
2606 | ||
2607 | @item @emph{C/C++}: | |
2608 | @multitable @columnfractions .20 .80 | |
2609 | @item @emph{Prototype}: @tab @code{acc_wait_async(int arg, int async);} | |
2610 | @end multitable | |
2611 | ||
2612 | @item @emph{Fortran}: | |
2613 | @multitable @columnfractions .20 .80 | |
2614 | @item @emph{Interface}: @tab @code{subroutine acc_wait_async(arg, async)} | |
2615 | @item @tab @code{integer(acc_handle_kind) arg, async} | |
2616 | @end multitable | |
2617 | ||
2618 | @item @emph{Reference}: | |
e464fc90 TB |
2619 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2620 | 3.2.12. | |
cdf6119d JN |
2621 | @end table |
2622 | ||
2623 | ||
2624 | ||
2625 | @node acc_init | |
2626 | @section @code{acc_init} -- Initialize runtime for a specific device type. | |
2627 | @table @asis | |
2628 | @item @emph{Description} | |
2629 | This function initializes the runtime for the device type specified in | |
2630 | @var{devicetype}. | |
2631 | ||
2632 | @item @emph{C/C++}: | |
2633 | @multitable @columnfractions .20 .80 | |
2634 | @item @emph{Prototype}: @tab @code{acc_init(acc_device_t devicetype);} | |
2635 | @end multitable | |
2636 | ||
2637 | @item @emph{Fortran}: | |
2638 | @multitable @columnfractions .20 .80 | |
2639 | @item @emph{Interface}: @tab @code{subroutine acc_init(devicetype)} | |
2640 | @item @tab @code{integer(acc_device_kind) devicetype} | |
2641 | @end multitable | |
2642 | ||
2643 | @item @emph{Reference}: | |
e464fc90 TB |
2644 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2645 | 3.2.7. | |
cdf6119d JN |
2646 | @end table |
2647 | ||
2648 | ||
2649 | ||
2650 | @node acc_shutdown | |
2651 | @section @code{acc_shutdown} -- Shuts down the runtime for a specific device type. | |
2652 | @table @asis | |
2653 | @item @emph{Description} | |
2654 | This function shuts down the runtime for the device type specified in | |
2655 | @var{devicetype}. | |
2656 | ||
2657 | @item @emph{C/C++}: | |
2658 | @multitable @columnfractions .20 .80 | |
2659 | @item @emph{Prototype}: @tab @code{acc_shutdown(acc_device_t devicetype);} | |
2660 | @end multitable | |
2661 | ||
2662 | @item @emph{Fortran}: | |
2663 | @multitable @columnfractions .20 .80 | |
2664 | @item @emph{Interface}: @tab @code{subroutine acc_shutdown(devicetype)} | |
2665 | @item @tab @code{integer(acc_device_kind) devicetype} | |
2666 | @end multitable | |
2667 | ||
2668 | @item @emph{Reference}: | |
e464fc90 TB |
2669 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2670 | 3.2.8. | |
cdf6119d JN |
2671 | @end table |
2672 | ||
2673 | ||
2674 | ||
2675 | @node acc_on_device | |
2676 | @section @code{acc_on_device} -- Whether executing on a particular device | |
2677 | @table @asis | |
2678 | @item @emph{Description}: | |
2679 | This function returns whether the program is executing on a particular | |
2680 | device specified in @var{devicetype}. In C/C++ a non-zero value is | |
93d90219 | 2681 | returned to indicate the device is executing on the specified device type. |
cdf6119d JN |
2682 | In Fortran, @code{true} will be returned. If the program is not executing |
2683 | on the specified device type C/C++ will return a zero, while Fortran will | |
2684 | return @code{false}. | |
2685 | ||
2686 | @item @emph{C/C++}: | |
2687 | @multitable @columnfractions .20 .80 | |
2688 | @item @emph{Prototype}: @tab @code{acc_on_device(acc_device_t devicetype);} | |
2689 | @end multitable | |
2690 | ||
2691 | @item @emph{Fortran}: | |
2692 | @multitable @columnfractions .20 .80 | |
2693 | @item @emph{Interface}: @tab @code{function acc_on_device(devicetype)} | |
2694 | @item @tab @code{integer(acc_device_kind) devicetype} | |
2695 | @item @tab @code{logical acc_on_device} | |
2696 | @end multitable | |
2697 | ||
2698 | ||
2699 | @item @emph{Reference}: | |
e464fc90 TB |
2700 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2701 | 3.2.17. | |
cdf6119d JN |
2702 | @end table |
2703 | ||
2704 | ||
2705 | ||
2706 | @node acc_malloc | |
2707 | @section @code{acc_malloc} -- Allocate device memory. | |
2708 | @table @asis | |
2709 | @item @emph{Description} | |
2710 | This function allocates @var{len} bytes of device memory. It returns | |
2711 | the device address of the allocated memory. | |
2712 | ||
2713 | @item @emph{C/C++}: | |
2714 | @multitable @columnfractions .20 .80 | |
2715 | @item @emph{Prototype}: @tab @code{d_void* acc_malloc(size_t len);} | |
2716 | @end multitable | |
2717 | ||
2718 | @item @emph{Reference}: | |
e464fc90 TB |
2719 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2720 | 3.2.18. | |
cdf6119d JN |
2721 | @end table |
2722 | ||
2723 | ||
2724 | ||
2725 | @node acc_free | |
2726 | @section @code{acc_free} -- Free device memory. | |
2727 | @table @asis | |
2728 | @item @emph{Description} | |
2729 | Free previously allocated device memory at the device address @code{a}. | |
2730 | ||
2731 | @item @emph{C/C++}: | |
2732 | @multitable @columnfractions .20 .80 | |
2733 | @item @emph{Prototype}: @tab @code{acc_free(d_void *a);} | |
2734 | @end multitable | |
2735 | ||
2736 | @item @emph{Reference}: | |
e464fc90 TB |
2737 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2738 | 3.2.19. | |
cdf6119d JN |
2739 | @end table |
2740 | ||
2741 | ||
2742 | ||
2743 | @node acc_copyin | |
2744 | @section @code{acc_copyin} -- Allocate device memory and copy host memory to it. | |
2745 | @table @asis | |
2746 | @item @emph{Description} | |
2747 | In C/C++, this function allocates @var{len} bytes of device memory | |
2748 | and maps it to the specified host address in @var{a}. The device | |
2749 | address of the newly allocated device memory is returned. | |
2750 | ||
2751 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
2752 | a contiguous array section. The second form @var{a} specifies a | |
2753 | variable or array element and @var{len} specifies the length in bytes. | |
2754 | ||
2755 | @item @emph{C/C++}: | |
2756 | @multitable @columnfractions .20 .80 | |
2757 | @item @emph{Prototype}: @tab @code{void *acc_copyin(h_void *a, size_t len);} | |
e464fc90 | 2758 | @item @emph{Prototype}: @tab @code{void *acc_copyin_async(h_void *a, size_t len, int async);} |
cdf6119d JN |
2759 | @end multitable |
2760 | ||
2761 | @item @emph{Fortran}: | |
2762 | @multitable @columnfractions .20 .80 | |
2763 | @item @emph{Interface}: @tab @code{subroutine acc_copyin(a)} | |
2764 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2765 | @item @emph{Interface}: @tab @code{subroutine acc_copyin(a, len)} | |
2766 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2767 | @item @tab @code{integer len} | |
e464fc90 TB |
2768 | @item @emph{Interface}: @tab @code{subroutine acc_copyin_async(a, async)} |
2769 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2770 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2771 | @item @emph{Interface}: @tab @code{subroutine acc_copyin_async(a, len, async)} | |
2772 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2773 | @item @tab @code{integer len} | |
2774 | @item @tab @code{integer(acc_handle_kind) :: async} | |
cdf6119d JN |
2775 | @end multitable |
2776 | ||
2777 | @item @emph{Reference}: | |
e464fc90 TB |
2778 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2779 | 3.2.20. | |
cdf6119d JN |
2780 | @end table |
2781 | ||
2782 | ||
2783 | ||
2784 | @node acc_present_or_copyin | |
2785 | @section @code{acc_present_or_copyin} -- If the data is not present on the device, allocate device memory and copy from host memory. | |
2786 | @table @asis | |
2787 | @item @emph{Description} | |
c1030b5c | 2788 | This function tests if the host data specified by @var{a} and of length |
cdf6119d JN |
2789 | @var{len} is present or not. If it is not present, then device memory |
2790 | will be allocated and the host memory copied. The device address of | |
2791 | the newly allocated device memory is returned. | |
2792 | ||
2793 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
2794 | a contiguous array section. The second form @var{a} specifies a variable or | |
2795 | array element and @var{len} specifies the length in bytes. | |
2796 | ||
e464fc90 TB |
2797 | Note that @code{acc_present_or_copyin} and @code{acc_pcopyin} exist for |
2798 | backward compatibility with OpenACC 2.0; use @ref{acc_copyin} instead. | |
2799 | ||
cdf6119d JN |
2800 | @item @emph{C/C++}: |
2801 | @multitable @columnfractions .20 .80 | |
2802 | @item @emph{Prototype}: @tab @code{void *acc_present_or_copyin(h_void *a, size_t len);} | |
2803 | @item @emph{Prototype}: @tab @code{void *acc_pcopyin(h_void *a, size_t len);} | |
2804 | @end multitable | |
2805 | ||
2806 | @item @emph{Fortran}: | |
2807 | @multitable @columnfractions .20 .80 | |
2808 | @item @emph{Interface}: @tab @code{subroutine acc_present_or_copyin(a)} | |
2809 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2810 | @item @emph{Interface}: @tab @code{subroutine acc_present_or_copyin(a, len)} | |
2811 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2812 | @item @tab @code{integer len} | |
2813 | @item @emph{Interface}: @tab @code{subroutine acc_pcopyin(a)} | |
2814 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2815 | @item @emph{Interface}: @tab @code{subroutine acc_pcopyin(a, len)} | |
2816 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2817 | @item @tab @code{integer len} | |
2818 | @end multitable | |
2819 | ||
2820 | @item @emph{Reference}: | |
e464fc90 TB |
2821 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2822 | 3.2.20. | |
cdf6119d JN |
2823 | @end table |
2824 | ||
2825 | ||
2826 | ||
2827 | @node acc_create | |
2828 | @section @code{acc_create} -- Allocate device memory and map it to host memory. | |
2829 | @table @asis | |
2830 | @item @emph{Description} | |
2831 | This function allocates device memory and maps it to host memory specified | |
2832 | by the host address @var{a} with a length of @var{len} bytes. In C/C++, | |
2833 | the function returns the device address of the allocated device memory. | |
2834 | ||
2835 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
2836 | a contiguous array section. The second form @var{a} specifies a variable or | |
2837 | array element and @var{len} specifies the length in bytes. | |
2838 | ||
2839 | @item @emph{C/C++}: | |
2840 | @multitable @columnfractions .20 .80 | |
2841 | @item @emph{Prototype}: @tab @code{void *acc_create(h_void *a, size_t len);} | |
e464fc90 | 2842 | @item @emph{Prototype}: @tab @code{void *acc_create_async(h_void *a, size_t len, int async);} |
cdf6119d JN |
2843 | @end multitable |
2844 | ||
2845 | @item @emph{Fortran}: | |
2846 | @multitable @columnfractions .20 .80 | |
2847 | @item @emph{Interface}: @tab @code{subroutine acc_create(a)} | |
2848 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2849 | @item @emph{Interface}: @tab @code{subroutine acc_create(a, len)} | |
2850 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2851 | @item @tab @code{integer len} | |
e464fc90 TB |
2852 | @item @emph{Interface}: @tab @code{subroutine acc_create_async(a, async)} |
2853 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2854 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2855 | @item @emph{Interface}: @tab @code{subroutine acc_create_async(a, len, async)} | |
2856 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2857 | @item @tab @code{integer len} | |
2858 | @item @tab @code{integer(acc_handle_kind) :: async} | |
cdf6119d JN |
2859 | @end multitable |
2860 | ||
2861 | @item @emph{Reference}: | |
e464fc90 TB |
2862 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2863 | 3.2.21. | |
cdf6119d JN |
2864 | @end table |
2865 | ||
2866 | ||
2867 | ||
2868 | @node acc_present_or_create | |
2869 | @section @code{acc_present_or_create} -- If the data is not present on the device, allocate device memory and map it to host memory. | |
2870 | @table @asis | |
2871 | @item @emph{Description} | |
c1030b5c | 2872 | This function tests if the host data specified by @var{a} and of length |
cdf6119d JN |
2873 | @var{len} is present or not. If it is not present, then device memory |
2874 | will be allocated and mapped to host memory. In C/C++, the device address | |
2875 | of the newly allocated device memory is returned. | |
2876 | ||
2877 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
2878 | a contiguous array section. The second form @var{a} specifies a variable or | |
2879 | array element and @var{len} specifies the length in bytes. | |
2880 | ||
e464fc90 TB |
2881 | Note that @code{acc_present_or_create} and @code{acc_pcreate} exist for |
2882 | backward compatibility with OpenACC 2.0; use @ref{acc_create} instead. | |
cdf6119d JN |
2883 | |
2884 | @item @emph{C/C++}: | |
2885 | @multitable @columnfractions .20 .80 | |
2886 | @item @emph{Prototype}: @tab @code{void *acc_present_or_create(h_void *a, size_t len)} | |
2887 | @item @emph{Prototype}: @tab @code{void *acc_pcreate(h_void *a, size_t len)} | |
2888 | @end multitable | |
2889 | ||
2890 | @item @emph{Fortran}: | |
2891 | @multitable @columnfractions .20 .80 | |
2892 | @item @emph{Interface}: @tab @code{subroutine acc_present_or_create(a)} | |
2893 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2894 | @item @emph{Interface}: @tab @code{subroutine acc_present_or_create(a, len)} | |
2895 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2896 | @item @tab @code{integer len} | |
2897 | @item @emph{Interface}: @tab @code{subroutine acc_pcreate(a)} | |
2898 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2899 | @item @emph{Interface}: @tab @code{subroutine acc_pcreate(a, len)} | |
2900 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2901 | @item @tab @code{integer len} | |
2902 | @end multitable | |
2903 | ||
2904 | @item @emph{Reference}: | |
e464fc90 TB |
2905 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2906 | 3.2.21. | |
cdf6119d JN |
2907 | @end table |
2908 | ||
2909 | ||
2910 | ||
2911 | @node acc_copyout | |
2912 | @section @code{acc_copyout} -- Copy device memory to host memory. | |
2913 | @table @asis | |
2914 | @item @emph{Description} | |
2915 | This function copies mapped device memory to host memory which is specified | |
2916 | by host address @var{a} for a length @var{len} bytes in C/C++. | |
2917 | ||
2918 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
2919 | a contiguous array section. The second form @var{a} specifies a variable or | |
2920 | array element and @var{len} specifies the length in bytes. | |
2921 | ||
2922 | @item @emph{C/C++}: | |
2923 | @multitable @columnfractions .20 .80 | |
2924 | @item @emph{Prototype}: @tab @code{acc_copyout(h_void *a, size_t len);} | |
e464fc90 TB |
2925 | @item @emph{Prototype}: @tab @code{acc_copyout_async(h_void *a, size_t len, int async);} |
2926 | @item @emph{Prototype}: @tab @code{acc_copyout_finalize(h_void *a, size_t len);} | |
2927 | @item @emph{Prototype}: @tab @code{acc_copyout_finalize_async(h_void *a, size_t len, int async);} | |
cdf6119d JN |
2928 | @end multitable |
2929 | ||
2930 | @item @emph{Fortran}: | |
2931 | @multitable @columnfractions .20 .80 | |
2932 | @item @emph{Interface}: @tab @code{subroutine acc_copyout(a)} | |
2933 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2934 | @item @emph{Interface}: @tab @code{subroutine acc_copyout(a, len)} | |
2935 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2936 | @item @tab @code{integer len} | |
e464fc90 TB |
2937 | @item @emph{Interface}: @tab @code{subroutine acc_copyout_async(a, async)} |
2938 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2939 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2940 | @item @emph{Interface}: @tab @code{subroutine acc_copyout_async(a, len, async)} | |
2941 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2942 | @item @tab @code{integer len} | |
2943 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2944 | @item @emph{Interface}: @tab @code{subroutine acc_copyout_finalize(a)} | |
2945 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2946 | @item @emph{Interface}: @tab @code{subroutine acc_copyout_finalize(a, len)} | |
2947 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2948 | @item @tab @code{integer len} | |
2949 | @item @emph{Interface}: @tab @code{subroutine acc_copyout_finalize_async(a, async)} | |
2950 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2951 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2952 | @item @emph{Interface}: @tab @code{subroutine acc_copyout_finalize_async(a, len, async)} | |
2953 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2954 | @item @tab @code{integer len} | |
2955 | @item @tab @code{integer(acc_handle_kind) :: async} | |
cdf6119d JN |
2956 | @end multitable |
2957 | ||
2958 | @item @emph{Reference}: | |
e464fc90 TB |
2959 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
2960 | 3.2.22. | |
cdf6119d JN |
2961 | @end table |
2962 | ||
2963 | ||
2964 | ||
2965 | @node acc_delete | |
2966 | @section @code{acc_delete} -- Free device memory. | |
2967 | @table @asis | |
2968 | @item @emph{Description} | |
2969 | This function frees previously allocated device memory specified by | |
2970 | the device address @var{a} and the length of @var{len} bytes. | |
2971 | ||
2972 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
2973 | a contiguous array section. The second form @var{a} specifies a variable or | |
2974 | array element and @var{len} specifies the length in bytes. | |
2975 | ||
2976 | @item @emph{C/C++}: | |
2977 | @multitable @columnfractions .20 .80 | |
2978 | @item @emph{Prototype}: @tab @code{acc_delete(h_void *a, size_t len);} | |
e464fc90 TB |
2979 | @item @emph{Prototype}: @tab @code{acc_delete_async(h_void *a, size_t len, int async);} |
2980 | @item @emph{Prototype}: @tab @code{acc_delete_finalize(h_void *a, size_t len);} | |
2981 | @item @emph{Prototype}: @tab @code{acc_delete_finalize_async(h_void *a, size_t len, int async);} | |
cdf6119d JN |
2982 | @end multitable |
2983 | ||
2984 | @item @emph{Fortran}: | |
2985 | @multitable @columnfractions .20 .80 | |
2986 | @item @emph{Interface}: @tab @code{subroutine acc_delete(a)} | |
2987 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2988 | @item @emph{Interface}: @tab @code{subroutine acc_delete(a, len)} | |
2989 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2990 | @item @tab @code{integer len} | |
e464fc90 TB |
2991 | @item @emph{Interface}: @tab @code{subroutine acc_delete_async(a, async)} |
2992 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2993 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2994 | @item @emph{Interface}: @tab @code{subroutine acc_delete_async(a, len, async)} | |
2995 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
2996 | @item @tab @code{integer len} | |
2997 | @item @tab @code{integer(acc_handle_kind) :: async} | |
2998 | @item @emph{Interface}: @tab @code{subroutine acc_delete_finalize(a)} | |
2999 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3000 | @item @emph{Interface}: @tab @code{subroutine acc_delete_finalize(a, len)} | |
3001 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3002 | @item @tab @code{integer len} | |
3003 | @item @emph{Interface}: @tab @code{subroutine acc_delete_async_finalize(a, async)} | |
3004 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3005 | @item @tab @code{integer(acc_handle_kind) :: async} | |
3006 | @item @emph{Interface}: @tab @code{subroutine acc_delete_async_finalize(a, len, async)} | |
3007 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3008 | @item @tab @code{integer len} | |
3009 | @item @tab @code{integer(acc_handle_kind) :: async} | |
cdf6119d JN |
3010 | @end multitable |
3011 | ||
3012 | @item @emph{Reference}: | |
e464fc90 TB |
3013 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3014 | 3.2.23. | |
cdf6119d JN |
3015 | @end table |
3016 | ||
3017 | ||
3018 | ||
3019 | @node acc_update_device | |
3020 | @section @code{acc_update_device} -- Update device memory from mapped host memory. | |
3021 | @table @asis | |
3022 | @item @emph{Description} | |
3023 | This function updates the device copy from the previously mapped host memory. | |
3024 | The host memory is specified with the host address @var{a} and a length of | |
3025 | @var{len} bytes. | |
3026 | ||
3027 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
3028 | a contiguous array section. The second form @var{a} specifies a variable or | |
3029 | array element and @var{len} specifies the length in bytes. | |
3030 | ||
3031 | @item @emph{C/C++}: | |
3032 | @multitable @columnfractions .20 .80 | |
3033 | @item @emph{Prototype}: @tab @code{acc_update_device(h_void *a, size_t len);} | |
e464fc90 | 3034 | @item @emph{Prototype}: @tab @code{acc_update_device(h_void *a, size_t len, async);} |
cdf6119d JN |
3035 | @end multitable |
3036 | ||
3037 | @item @emph{Fortran}: | |
3038 | @multitable @columnfractions .20 .80 | |
3039 | @item @emph{Interface}: @tab @code{subroutine acc_update_device(a)} | |
3040 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3041 | @item @emph{Interface}: @tab @code{subroutine acc_update_device(a, len)} | |
3042 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3043 | @item @tab @code{integer len} | |
e464fc90 TB |
3044 | @item @emph{Interface}: @tab @code{subroutine acc_update_device_async(a, async)} |
3045 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3046 | @item @tab @code{integer(acc_handle_kind) :: async} | |
3047 | @item @emph{Interface}: @tab @code{subroutine acc_update_device_async(a, len, async)} | |
3048 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3049 | @item @tab @code{integer len} | |
3050 | @item @tab @code{integer(acc_handle_kind) :: async} | |
cdf6119d JN |
3051 | @end multitable |
3052 | ||
3053 | @item @emph{Reference}: | |
e464fc90 TB |
3054 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3055 | 3.2.24. | |
cdf6119d JN |
3056 | @end table |
3057 | ||
3058 | ||
3059 | ||
3060 | @node acc_update_self | |
3061 | @section @code{acc_update_self} -- Update host memory from mapped device memory. | |
3062 | @table @asis | |
3063 | @item @emph{Description} | |
3064 | This function updates the host copy from the previously mapped device memory. | |
3065 | The host memory is specified with the host address @var{a} and a length of | |
3066 | @var{len} bytes. | |
3067 | ||
3068 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
3069 | a contiguous array section. The second form @var{a} specifies a variable or | |
3070 | array element and @var{len} specifies the length in bytes. | |
3071 | ||
3072 | @item @emph{C/C++}: | |
3073 | @multitable @columnfractions .20 .80 | |
3074 | @item @emph{Prototype}: @tab @code{acc_update_self(h_void *a, size_t len);} | |
e464fc90 | 3075 | @item @emph{Prototype}: @tab @code{acc_update_self_async(h_void *a, size_t len, int async);} |
cdf6119d JN |
3076 | @end multitable |
3077 | ||
3078 | @item @emph{Fortran}: | |
3079 | @multitable @columnfractions .20 .80 | |
3080 | @item @emph{Interface}: @tab @code{subroutine acc_update_self(a)} | |
3081 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3082 | @item @emph{Interface}: @tab @code{subroutine acc_update_self(a, len)} | |
3083 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3084 | @item @tab @code{integer len} | |
e464fc90 TB |
3085 | @item @emph{Interface}: @tab @code{subroutine acc_update_self_async(a, async)} |
3086 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3087 | @item @tab @code{integer(acc_handle_kind) :: async} | |
3088 | @item @emph{Interface}: @tab @code{subroutine acc_update_self_async(a, len, async)} | |
3089 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3090 | @item @tab @code{integer len} | |
3091 | @item @tab @code{integer(acc_handle_kind) :: async} | |
cdf6119d JN |
3092 | @end multitable |
3093 | ||
3094 | @item @emph{Reference}: | |
e464fc90 TB |
3095 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3096 | 3.2.25. | |
cdf6119d JN |
3097 | @end table |
3098 | ||
3099 | ||
3100 | ||
3101 | @node acc_map_data | |
3102 | @section @code{acc_map_data} -- Map previously allocated device memory to host memory. | |
3103 | @table @asis | |
3104 | @item @emph{Description} | |
3105 | This function maps previously allocated device and host memory. The device | |
3106 | memory is specified with the device address @var{d}. The host memory is | |
3107 | specified with the host address @var{h} and a length of @var{len}. | |
3108 | ||
3109 | @item @emph{C/C++}: | |
3110 | @multitable @columnfractions .20 .80 | |
3111 | @item @emph{Prototype}: @tab @code{acc_map_data(h_void *h, d_void *d, size_t len);} | |
3112 | @end multitable | |
3113 | ||
3114 | @item @emph{Reference}: | |
e464fc90 TB |
3115 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3116 | 3.2.26. | |
cdf6119d JN |
3117 | @end table |
3118 | ||
3119 | ||
3120 | ||
3121 | @node acc_unmap_data | |
3122 | @section @code{acc_unmap_data} -- Unmap device memory from host memory. | |
3123 | @table @asis | |
3124 | @item @emph{Description} | |
3125 | This function unmaps previously mapped device and host memory. The latter | |
3126 | specified by @var{h}. | |
3127 | ||
3128 | @item @emph{C/C++}: | |
3129 | @multitable @columnfractions .20 .80 | |
3130 | @item @emph{Prototype}: @tab @code{acc_unmap_data(h_void *h);} | |
3131 | @end multitable | |
3132 | ||
3133 | @item @emph{Reference}: | |
e464fc90 TB |
3134 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3135 | 3.2.27. | |
cdf6119d JN |
3136 | @end table |
3137 | ||
3138 | ||
3139 | ||
3140 | @node acc_deviceptr | |
3141 | @section @code{acc_deviceptr} -- Get device pointer associated with specific host address. | |
3142 | @table @asis | |
3143 | @item @emph{Description} | |
3144 | This function returns the device address that has been mapped to the | |
3145 | host address specified by @var{h}. | |
3146 | ||
3147 | @item @emph{C/C++}: | |
3148 | @multitable @columnfractions .20 .80 | |
3149 | @item @emph{Prototype}: @tab @code{void *acc_deviceptr(h_void *h);} | |
3150 | @end multitable | |
3151 | ||
3152 | @item @emph{Reference}: | |
e464fc90 TB |
3153 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3154 | 3.2.28. | |
cdf6119d JN |
3155 | @end table |
3156 | ||
3157 | ||
3158 | ||
3159 | @node acc_hostptr | |
3160 | @section @code{acc_hostptr} -- Get host pointer associated with specific device address. | |
3161 | @table @asis | |
3162 | @item @emph{Description} | |
3163 | This function returns the host address that has been mapped to the | |
3164 | device address specified by @var{d}. | |
3165 | ||
3166 | @item @emph{C/C++}: | |
3167 | @multitable @columnfractions .20 .80 | |
3168 | @item @emph{Prototype}: @tab @code{void *acc_hostptr(d_void *d);} | |
3169 | @end multitable | |
3170 | ||
3171 | @item @emph{Reference}: | |
e464fc90 TB |
3172 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3173 | 3.2.29. | |
cdf6119d JN |
3174 | @end table |
3175 | ||
3176 | ||
3177 | ||
3178 | @node acc_is_present | |
3179 | @section @code{acc_is_present} -- Indicate whether host variable / array is present on device. | |
3180 | @table @asis | |
3181 | @item @emph{Description} | |
3182 | This function indicates whether the specified host address in @var{a} and a | |
3183 | length of @var{len} bytes is present on the device. In C/C++, a non-zero | |
3184 | value is returned to indicate the presence of the mapped memory on the | |
3185 | device. A zero is returned to indicate the memory is not mapped on the | |
3186 | device. | |
3187 | ||
3188 | In Fortran, two (2) forms are supported. In the first form, @var{a} specifies | |
3189 | a contiguous array section. The second form @var{a} specifies a variable or | |
3190 | array element and @var{len} specifies the length in bytes. If the host | |
3191 | memory is mapped to device memory, then a @code{true} is returned. Otherwise, | |
3192 | a @code{false} is return to indicate the mapped memory is not present. | |
3193 | ||
3194 | @item @emph{C/C++}: | |
3195 | @multitable @columnfractions .20 .80 | |
3196 | @item @emph{Prototype}: @tab @code{int acc_is_present(h_void *a, size_t len);} | |
3197 | @end multitable | |
3198 | ||
3199 | @item @emph{Fortran}: | |
3200 | @multitable @columnfractions .20 .80 | |
3201 | @item @emph{Interface}: @tab @code{function acc_is_present(a)} | |
3202 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3203 | @item @tab @code{logical acc_is_present} | |
3204 | @item @emph{Interface}: @tab @code{function acc_is_present(a, len)} | |
3205 | @item @tab @code{type, dimension(:[,:]...) :: a} | |
3206 | @item @tab @code{integer len} | |
3207 | @item @tab @code{logical acc_is_present} | |
3208 | @end multitable | |
3209 | ||
3210 | @item @emph{Reference}: | |
e464fc90 TB |
3211 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3212 | 3.2.30. | |
cdf6119d JN |
3213 | @end table |
3214 | ||
3215 | ||
3216 | ||
3217 | @node acc_memcpy_to_device | |
3218 | @section @code{acc_memcpy_to_device} -- Copy host memory to device memory. | |
3219 | @table @asis | |
3220 | @item @emph{Description} | |
3221 | This function copies host memory specified by host address of @var{src} to | |
3222 | device memory specified by the device address @var{dest} for a length of | |
3223 | @var{bytes} bytes. | |
3224 | ||
3225 | @item @emph{C/C++}: | |
3226 | @multitable @columnfractions .20 .80 | |
3227 | @item @emph{Prototype}: @tab @code{acc_memcpy_to_device(d_void *dest, h_void *src, size_t bytes);} | |
3228 | @end multitable | |
3229 | ||
3230 | @item @emph{Reference}: | |
e464fc90 TB |
3231 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3232 | 3.2.31. | |
cdf6119d JN |
3233 | @end table |
3234 | ||
3235 | ||
3236 | ||
3237 | @node acc_memcpy_from_device | |
3238 | @section @code{acc_memcpy_from_device} -- Copy device memory to host memory. | |
3239 | @table @asis | |
3240 | @item @emph{Description} | |
3241 | This function copies host memory specified by host address of @var{src} from | |
3242 | device memory specified by the device address @var{dest} for a length of | |
3243 | @var{bytes} bytes. | |
3244 | ||
3245 | @item @emph{C/C++}: | |
3246 | @multitable @columnfractions .20 .80 | |
3247 | @item @emph{Prototype}: @tab @code{acc_memcpy_from_device(d_void *dest, h_void *src, size_t bytes);} | |
3248 | @end multitable | |
3249 | ||
3250 | @item @emph{Reference}: | |
e464fc90 TB |
3251 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
3252 | 3.2.32. | |
3253 | @end table | |
3254 | ||
3255 | ||
3256 | ||
3257 | @node acc_attach | |
3258 | @section @code{acc_attach} -- Let device pointer point to device-pointer target. | |
3259 | @table @asis | |
3260 | @item @emph{Description} | |
3261 | This function updates a pointer on the device from pointing to a host-pointer | |
3262 | address to pointing to the corresponding device data. | |
3263 | ||
3264 | @item @emph{C/C++}: | |
3265 | @multitable @columnfractions .20 .80 | |
3266 | @item @emph{Prototype}: @tab @code{acc_attach(h_void **ptr);} | |
3267 | @item @emph{Prototype}: @tab @code{acc_attach_async(h_void **ptr, int async);} | |
3268 | @end multitable | |
3269 | ||
3270 | @item @emph{Reference}: | |
3271 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3272 | 3.2.34. | |
3273 | @end table | |
3274 | ||
3275 | ||
3276 | ||
3277 | @node acc_detach | |
3278 | @section @code{acc_detach} -- Let device pointer point to host-pointer target. | |
3279 | @table @asis | |
3280 | @item @emph{Description} | |
3281 | This function updates a pointer on the device from pointing to a device-pointer | |
3282 | address to pointing to the corresponding host data. | |
3283 | ||
3284 | @item @emph{C/C++}: | |
3285 | @multitable @columnfractions .20 .80 | |
3286 | @item @emph{Prototype}: @tab @code{acc_detach(h_void **ptr);} | |
3287 | @item @emph{Prototype}: @tab @code{acc_detach_async(h_void **ptr, int async);} | |
3288 | @item @emph{Prototype}: @tab @code{acc_detach_finalize(h_void **ptr);} | |
3289 | @item @emph{Prototype}: @tab @code{acc_detach_finalize_async(h_void **ptr, int async);} | |
3290 | @end multitable | |
3291 | ||
3292 | @item @emph{Reference}: | |
3293 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3294 | 3.2.35. | |
cdf6119d JN |
3295 | @end table |
3296 | ||
3297 | ||
3298 | ||
3299 | @node acc_get_current_cuda_device | |
3300 | @section @code{acc_get_current_cuda_device} -- Get CUDA device handle. | |
3301 | @table @asis | |
3302 | @item @emph{Description} | |
3303 | This function returns the CUDA device handle. This handle is the same | |
3304 | as used by the CUDA Runtime or Driver API's. | |
3305 | ||
3306 | @item @emph{C/C++}: | |
3307 | @multitable @columnfractions .20 .80 | |
3308 | @item @emph{Prototype}: @tab @code{void *acc_get_current_cuda_device(void);} | |
3309 | @end multitable | |
3310 | ||
3311 | @item @emph{Reference}: | |
e464fc90 | 3312 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
3313 | A.2.1.1. |
3314 | @end table | |
3315 | ||
3316 | ||
3317 | ||
3318 | @node acc_get_current_cuda_context | |
3319 | @section @code{acc_get_current_cuda_context} -- Get CUDA context handle. | |
3320 | @table @asis | |
3321 | @item @emph{Description} | |
3322 | This function returns the CUDA context handle. This handle is the same | |
3323 | as used by the CUDA Runtime or Driver API's. | |
3324 | ||
3325 | @item @emph{C/C++}: | |
3326 | @multitable @columnfractions .20 .80 | |
18c247cc | 3327 | @item @emph{Prototype}: @tab @code{void *acc_get_current_cuda_context(void);} |
cdf6119d JN |
3328 | @end multitable |
3329 | ||
3330 | @item @emph{Reference}: | |
e464fc90 | 3331 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
3332 | A.2.1.2. |
3333 | @end table | |
3334 | ||
3335 | ||
3336 | ||
3337 | @node acc_get_cuda_stream | |
3338 | @section @code{acc_get_cuda_stream} -- Get CUDA stream handle. | |
3339 | @table @asis | |
3340 | @item @emph{Description} | |
18c247cc TS |
3341 | This function returns the CUDA stream handle for the queue @var{async}. |
3342 | This handle is the same as used by the CUDA Runtime or Driver API's. | |
cdf6119d JN |
3343 | |
3344 | @item @emph{C/C++}: | |
3345 | @multitable @columnfractions .20 .80 | |
18c247cc | 3346 | @item @emph{Prototype}: @tab @code{void *acc_get_cuda_stream(int async);} |
cdf6119d JN |
3347 | @end multitable |
3348 | ||
3349 | @item @emph{Reference}: | |
e464fc90 | 3350 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
3351 | A.2.1.3. |
3352 | @end table | |
3353 | ||
3354 | ||
3355 | ||
3356 | @node acc_set_cuda_stream | |
3357 | @section @code{acc_set_cuda_stream} -- Set CUDA stream handle. | |
3358 | @table @asis | |
3359 | @item @emph{Description} | |
3360 | This function associates the stream handle specified by @var{stream} with | |
18c247cc TS |
3361 | the queue @var{async}. |
3362 | ||
3363 | This cannot be used to change the stream handle associated with | |
3364 | @code{acc_async_sync}. | |
3365 | ||
3366 | The return value is not specified. | |
cdf6119d JN |
3367 | |
3368 | @item @emph{C/C++}: | |
3369 | @multitable @columnfractions .20 .80 | |
18c247cc | 3370 | @item @emph{Prototype}: @tab @code{int acc_set_cuda_stream(int async, void *stream);} |
cdf6119d JN |
3371 | @end multitable |
3372 | ||
3373 | @item @emph{Reference}: | |
e464fc90 | 3374 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
3375 | A.2.1.4. |
3376 | @end table | |
3377 | ||
3378 | ||
3379 | ||
5fae049d TS |
3380 | @node acc_prof_register |
3381 | @section @code{acc_prof_register} -- Register callbacks. | |
3382 | @table @asis | |
3383 | @item @emph{Description}: | |
3384 | This function registers callbacks. | |
3385 | ||
3386 | @item @emph{C/C++}: | |
3387 | @multitable @columnfractions .20 .80 | |
3388 | @item @emph{Prototype}: @tab @code{void acc_prof_register (acc_event_t, acc_prof_callback, acc_register_t);} | |
3389 | @end multitable | |
3390 | ||
3391 | @item @emph{See also}: | |
3392 | @ref{OpenACC Profiling Interface} | |
3393 | ||
3394 | @item @emph{Reference}: | |
3395 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3396 | 5.3. | |
3397 | @end table | |
3398 | ||
3399 | ||
3400 | ||
3401 | @node acc_prof_unregister | |
3402 | @section @code{acc_prof_unregister} -- Unregister callbacks. | |
3403 | @table @asis | |
3404 | @item @emph{Description}: | |
3405 | This function unregisters callbacks. | |
3406 | ||
3407 | @item @emph{C/C++}: | |
3408 | @multitable @columnfractions .20 .80 | |
3409 | @item @emph{Prototype}: @tab @code{void acc_prof_unregister (acc_event_t, acc_prof_callback, acc_register_t);} | |
3410 | @end multitable | |
3411 | ||
3412 | @item @emph{See also}: | |
3413 | @ref{OpenACC Profiling Interface} | |
3414 | ||
3415 | @item @emph{Reference}: | |
3416 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3417 | 5.3. | |
3418 | @end table | |
3419 | ||
3420 | ||
3421 | ||
3422 | @node acc_prof_lookup | |
3423 | @section @code{acc_prof_lookup} -- Obtain inquiry functions. | |
3424 | @table @asis | |
3425 | @item @emph{Description}: | |
3426 | Function to obtain inquiry functions. | |
3427 | ||
3428 | @item @emph{C/C++}: | |
3429 | @multitable @columnfractions .20 .80 | |
3430 | @item @emph{Prototype}: @tab @code{acc_query_fn acc_prof_lookup (const char *);} | |
3431 | @end multitable | |
3432 | ||
3433 | @item @emph{See also}: | |
3434 | @ref{OpenACC Profiling Interface} | |
3435 | ||
3436 | @item @emph{Reference}: | |
3437 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3438 | 5.3. | |
3439 | @end table | |
3440 | ||
3441 | ||
3442 | ||
3443 | @node acc_register_library | |
3444 | @section @code{acc_register_library} -- Library registration. | |
3445 | @table @asis | |
3446 | @item @emph{Description}: | |
3447 | Function for library registration. | |
3448 | ||
3449 | @item @emph{C/C++}: | |
3450 | @multitable @columnfractions .20 .80 | |
3451 | @item @emph{Prototype}: @tab @code{void acc_register_library (acc_prof_reg, acc_prof_reg, acc_prof_lookup_func);} | |
3452 | @end multitable | |
3453 | ||
3454 | @item @emph{See also}: | |
3455 | @ref{OpenACC Profiling Interface}, @ref{ACC_PROFLIB} | |
3456 | ||
3457 | @item @emph{Reference}: | |
3458 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3459 | 5.3. | |
3460 | @end table | |
3461 | ||
3462 | ||
3463 | ||
cdf6119d JN |
3464 | @c --------------------------------------------------------------------- |
3465 | @c OpenACC Environment Variables | |
3466 | @c --------------------------------------------------------------------- | |
3467 | ||
3468 | @node OpenACC Environment Variables | |
3469 | @chapter OpenACC Environment Variables | |
3470 | ||
3471 | The variables @env{ACC_DEVICE_TYPE} and @env{ACC_DEVICE_NUM} | |
3472 | are defined by section 4 of the OpenACC specification in version 2.0. | |
5fae049d TS |
3473 | The variable @env{ACC_PROFLIB} |
3474 | is defined by section 4 of the OpenACC specification in version 2.6. | |
cdf6119d JN |
3475 | The variable @env{GCC_ACC_NOTIFY} is used for diagnostic purposes. |
3476 | ||
3477 | @menu | |
3478 | * ACC_DEVICE_TYPE:: | |
3479 | * ACC_DEVICE_NUM:: | |
5fae049d | 3480 | * ACC_PROFLIB:: |
cdf6119d JN |
3481 | * GCC_ACC_NOTIFY:: |
3482 | @end menu | |
3483 | ||
3484 | ||
3485 | ||
3486 | @node ACC_DEVICE_TYPE | |
3487 | @section @code{ACC_DEVICE_TYPE} | |
3488 | @table @asis | |
3489 | @item @emph{Reference}: | |
e464fc90 | 3490 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
3491 | 4.1. |
3492 | @end table | |
3493 | ||
3494 | ||
3495 | ||
3496 | @node ACC_DEVICE_NUM | |
3497 | @section @code{ACC_DEVICE_NUM} | |
3498 | @table @asis | |
3499 | @item @emph{Reference}: | |
e464fc90 | 3500 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section |
cdf6119d JN |
3501 | 4.2. |
3502 | @end table | |
3503 | ||
3504 | ||
3505 | ||
5fae049d TS |
3506 | @node ACC_PROFLIB |
3507 | @section @code{ACC_PROFLIB} | |
3508 | @table @asis | |
3509 | @item @emph{See also}: | |
3510 | @ref{acc_register_library}, @ref{OpenACC Profiling Interface} | |
3511 | ||
3512 | @item @emph{Reference}: | |
3513 | @uref{https://www.openacc.org, OpenACC specification v2.6}, section | |
3514 | 4.3. | |
3515 | @end table | |
3516 | ||
3517 | ||
3518 | ||
cdf6119d JN |
3519 | @node GCC_ACC_NOTIFY |
3520 | @section @code{GCC_ACC_NOTIFY} | |
3521 | @table @asis | |
3522 | @item @emph{Description}: | |
3523 | Print debug information pertaining to the accelerator. | |
3524 | @end table | |
3525 | ||
3526 | ||
3527 | ||
3528 | @c --------------------------------------------------------------------- | |
3529 | @c CUDA Streams Usage | |
3530 | @c --------------------------------------------------------------------- | |
3531 | ||
3532 | @node CUDA Streams Usage | |
3533 | @chapter CUDA Streams Usage | |
3534 | ||
3535 | This applies to the @code{nvptx} plugin only. | |
3536 | ||
3537 | The library provides elements that perform asynchronous movement of | |
3538 | data and asynchronous operation of computing constructs. This | |
3539 | asynchronous functionality is implemented by making use of CUDA | |
3540 | streams@footnote{See "Stream Management" in "CUDA Driver API", | |
3541 | TRM-06703-001, Version 5.5, for additional information}. | |
3542 | ||
c1030b5c | 3543 | The primary means by that the asynchronous functionality is accessed |
cdf6119d JN |
3544 | is through the use of those OpenACC directives which make use of the |
3545 | @code{async} and @code{wait} clauses. When the @code{async} clause is | |
3546 | first used with a directive, it creates a CUDA stream. If an | |
3547 | @code{async-argument} is used with the @code{async} clause, then the | |
3548 | stream is associated with the specified @code{async-argument}. | |
3549 | ||
3550 | Following the creation of an association between a CUDA stream and the | |
3551 | @code{async-argument} of an @code{async} clause, both the @code{wait} | |
3552 | clause and the @code{wait} directive can be used. When either the | |
3553 | clause or directive is used after stream creation, it creates a | |
3554 | rendezvous point whereby execution waits until all operations | |
3555 | associated with the @code{async-argument}, that is, stream, have | |
3556 | completed. | |
3557 | ||
3558 | Normally, the management of the streams that are created as a result of | |
3559 | using the @code{async} clause, is done without any intervention by the | |
3560 | caller. This implies the association between the @code{async-argument} | |
3561 | and the CUDA stream will be maintained for the lifetime of the program. | |
3562 | However, this association can be changed through the use of the library | |
3563 | function @code{acc_set_cuda_stream}. When the function | |
3564 | @code{acc_set_cuda_stream} is called, the CUDA stream that was | |
3565 | originally associated with the @code{async} clause will be destroyed. | |
3566 | Caution should be taken when changing the association as subsequent | |
3567 | references to the @code{async-argument} refer to a different | |
3568 | CUDA stream. | |
3569 | ||
3570 | ||
3571 | ||
3572 | @c --------------------------------------------------------------------- | |
3573 | @c OpenACC Library Interoperability | |
3574 | @c --------------------------------------------------------------------- | |
3575 | ||
3576 | @node OpenACC Library Interoperability | |
3577 | @chapter OpenACC Library Interoperability | |
3578 | ||
3579 | @section Introduction | |
3580 | ||
3581 | The OpenACC library uses the CUDA Driver API, and may interact with | |
3582 | programs that use the Runtime library directly, or another library | |
3583 | based on the Runtime library, e.g., CUBLAS@footnote{See section 2.26, | |
3584 | "Interactions with the CUDA Driver API" in | |
3585 | "CUDA Runtime API", Version 5.5, and section 2.27, "VDPAU | |
3586 | Interoperability", in "CUDA Driver API", TRM-06703-001, Version 5.5, | |
3587 | for additional information on library interoperability.}. | |
3588 | This chapter describes the use cases and what changes are | |
3589 | required in order to use both the OpenACC library and the CUBLAS and Runtime | |
3590 | libraries within a program. | |
3591 | ||
3592 | @section First invocation: NVIDIA CUBLAS library API | |
3593 | ||
3594 | In this first use case (see below), a function in the CUBLAS library is called | |
3595 | prior to any of the functions in the OpenACC library. More specifically, the | |
3596 | function @code{cublasCreate()}. | |
3597 | ||
3598 | When invoked, the function initializes the library and allocates the | |
3599 | hardware resources on the host and the device on behalf of the caller. Once | |
3600 | the initialization and allocation has completed, a handle is returned to the | |
3601 | caller. The OpenACC library also requires initialization and allocation of | |
3602 | hardware resources. Since the CUBLAS library has already allocated the | |
3603 | hardware resources for the device, all that is left to do is to initialize | |
3604 | the OpenACC library and acquire the hardware resources on the host. | |
3605 | ||
3606 | Prior to calling the OpenACC function that initializes the library and | |
3607 | allocate the host hardware resources, you need to acquire the device number | |
3608 | that was allocated during the call to @code{cublasCreate()}. The invoking of the | |
3609 | runtime library function @code{cudaGetDevice()} accomplishes this. Once | |
3610 | acquired, the device number is passed along with the device type as | |
3611 | parameters to the OpenACC library function @code{acc_set_device_num()}. | |
3612 | ||
3613 | Once the call to @code{acc_set_device_num()} has completed, the OpenACC | |
3614 | library uses the context that was created during the call to | |
3615 | @code{cublasCreate()}. In other words, both libraries will be sharing the | |
3616 | same context. | |
3617 | ||
3618 | @smallexample | |
3619 | /* Create the handle */ | |
3620 | s = cublasCreate(&h); | |
3621 | if (s != CUBLAS_STATUS_SUCCESS) | |
3622 | @{ | |
3623 | fprintf(stderr, "cublasCreate failed %d\n", s); | |
3624 | exit(EXIT_FAILURE); | |
3625 | @} | |
3626 | ||
3627 | /* Get the device number */ | |
3628 | e = cudaGetDevice(&dev); | |
3629 | if (e != cudaSuccess) | |
3630 | @{ | |
3631 | fprintf(stderr, "cudaGetDevice failed %d\n", e); | |
3632 | exit(EXIT_FAILURE); | |
3633 | @} | |
3634 | ||
3635 | /* Initialize OpenACC library and use device 'dev' */ | |
3636 | acc_set_device_num(dev, acc_device_nvidia); | |
3637 | ||
3638 | @end smallexample | |
3639 | @center Use Case 1 | |
3640 | ||
3641 | @section First invocation: OpenACC library API | |
3642 | ||
3643 | In this second use case (see below), a function in the OpenACC library is | |
3644 | called prior to any of the functions in the CUBLAS library. More specificially, | |
3645 | the function @code{acc_set_device_num()}. | |
3646 | ||
3647 | In the use case presented here, the function @code{acc_set_device_num()} | |
3648 | is used to both initialize the OpenACC library and allocate the hardware | |
3649 | resources on the host and the device. In the call to the function, the | |
3650 | call parameters specify which device to use and what device | |
3651 | type to use, i.e., @code{acc_device_nvidia}. It should be noted that this | |
3652 | is but one method to initialize the OpenACC library and allocate the | |
3653 | appropriate hardware resources. Other methods are available through the | |
3654 | use of environment variables and these will be discussed in the next section. | |
3655 | ||
3656 | Once the call to @code{acc_set_device_num()} has completed, other OpenACC | |
3657 | functions can be called as seen with multiple calls being made to | |
3658 | @code{acc_copyin()}. In addition, calls can be made to functions in the | |
3659 | CUBLAS library. In the use case a call to @code{cublasCreate()} is made | |
3660 | subsequent to the calls to @code{acc_copyin()}. | |
3661 | As seen in the previous use case, a call to @code{cublasCreate()} | |
3662 | initializes the CUBLAS library and allocates the hardware resources on the | |
3663 | host and the device. However, since the device has already been allocated, | |
3664 | @code{cublasCreate()} will only initialize the CUBLAS library and allocate | |
3665 | the appropriate hardware resources on the host. The context that was created | |
3666 | as part of the OpenACC initialization is shared with the CUBLAS library, | |
3667 | similarly to the first use case. | |
3668 | ||
3669 | @smallexample | |
3670 | dev = 0; | |
3671 | ||
3672 | acc_set_device_num(dev, acc_device_nvidia); | |
3673 | ||
3674 | /* Copy the first set to the device */ | |
3675 | d_X = acc_copyin(&h_X[0], N * sizeof (float)); | |
3676 | if (d_X == NULL) | |
3677 | @{ | |
3678 | fprintf(stderr, "copyin error h_X\n"); | |
3679 | exit(EXIT_FAILURE); | |
3680 | @} | |
3681 | ||
3682 | /* Copy the second set to the device */ | |
3683 | d_Y = acc_copyin(&h_Y1[0], N * sizeof (float)); | |
3684 | if (d_Y == NULL) | |
3685 | @{ | |
3686 | fprintf(stderr, "copyin error h_Y1\n"); | |
3687 | exit(EXIT_FAILURE); | |
3688 | @} | |
3689 | ||
3690 | /* Create the handle */ | |
3691 | s = cublasCreate(&h); | |
3692 | if (s != CUBLAS_STATUS_SUCCESS) | |
3693 | @{ | |
3694 | fprintf(stderr, "cublasCreate failed %d\n", s); | |
3695 | exit(EXIT_FAILURE); | |
3696 | @} | |
3697 | ||
3698 | /* Perform saxpy using CUBLAS library function */ | |
3699 | s = cublasSaxpy(h, N, &alpha, d_X, 1, d_Y, 1); | |
3700 | if (s != CUBLAS_STATUS_SUCCESS) | |
3701 | @{ | |
3702 | fprintf(stderr, "cublasSaxpy failed %d\n", s); | |
3703 | exit(EXIT_FAILURE); | |
3704 | @} | |
3705 | ||
3706 | /* Copy the results from the device */ | |
3707 | acc_memcpy_from_device(&h_Y1[0], d_Y, N * sizeof (float)); | |
3708 | ||
3709 | @end smallexample | |
3710 | @center Use Case 2 | |
3711 | ||
3712 | @section OpenACC library and environment variables | |
3713 | ||
3714 | There are two environment variables associated with the OpenACC library | |
3715 | that may be used to control the device type and device number: | |
8d1a1cb1 TB |
3716 | @env{ACC_DEVICE_TYPE} and @env{ACC_DEVICE_NUM}, respectively. These two |
3717 | environment variables can be used as an alternative to calling | |
cdf6119d JN |
3718 | @code{acc_set_device_num()}. As seen in the second use case, the device |
3719 | type and device number were specified using @code{acc_set_device_num()}. | |
3720 | If however, the aforementioned environment variables were set, then the | |
3721 | call to @code{acc_set_device_num()} would not be required. | |
3722 | ||
3723 | ||
3724 | The use of the environment variables is only relevant when an OpenACC function | |
3725 | is called prior to a call to @code{cudaCreate()}. If @code{cudaCreate()} | |
3726 | is called prior to a call to an OpenACC function, then you must call | |
3727 | @code{acc_set_device_num()}@footnote{More complete information | |
3728 | about @env{ACC_DEVICE_TYPE} and @env{ACC_DEVICE_NUM} can be found in | |
9651fbaf | 3729 | sections 4.1 and 4.2 of the @uref{https://www.openacc.org, OpenACC} |
e464fc90 | 3730 | Application Programming Interface”, Version 2.6.} |
cdf6119d JN |
3731 | |
3732 | ||
3733 | ||
5fae049d TS |
3734 | @c --------------------------------------------------------------------- |
3735 | @c OpenACC Profiling Interface | |
3736 | @c --------------------------------------------------------------------- | |
3737 | ||
3738 | @node OpenACC Profiling Interface | |
3739 | @chapter OpenACC Profiling Interface | |
3740 | ||
3741 | @section Implementation Status and Implementation-Defined Behavior | |
3742 | ||
3743 | We're implementing the OpenACC Profiling Interface as defined by the | |
3744 | OpenACC 2.6 specification. We're clarifying some aspects here as | |
3745 | @emph{implementation-defined behavior}, while they're still under | |
3746 | discussion within the OpenACC Technical Committee. | |
3747 | ||
3748 | This implementation is tuned to keep the performance impact as low as | |
3749 | possible for the (very common) case that the Profiling Interface is | |
3750 | not enabled. This is relevant, as the Profiling Interface affects all | |
3751 | the @emph{hot} code paths (in the target code, not in the offloaded | |
3752 | code). Users of the OpenACC Profiling Interface can be expected to | |
3753 | understand that performance will be impacted to some degree once the | |
3754 | Profiling Interface has gotten enabled: for example, because of the | |
3755 | @emph{runtime} (libgomp) calling into a third-party @emph{library} for | |
3756 | every event that has been registered. | |
3757 | ||
3758 | We're not yet accounting for the fact that @cite{OpenACC events may | |
3759 | occur during event processing}. | |
b52643ab KCY |
3760 | We just handle one case specially, as required by CUDA 9.0 |
3761 | @command{nvprof}, that @code{acc_get_device_type} | |
3762 | (@ref{acc_get_device_type})) may be called from | |
3763 | @code{acc_ev_device_init_start}, @code{acc_ev_device_init_end} | |
3764 | callbacks. | |
5fae049d TS |
3765 | |
3766 | We're not yet implementing initialization via a | |
3767 | @code{acc_register_library} function that is either statically linked | |
3768 | in, or dynamically via @env{LD_PRELOAD}. | |
3769 | Initialization via @code{acc_register_library} functions dynamically | |
3770 | loaded via the @env{ACC_PROFLIB} environment variable does work, as | |
3771 | does directly calling @code{acc_prof_register}, | |
3772 | @code{acc_prof_unregister}, @code{acc_prof_lookup}. | |
3773 | ||
3774 | As currently there are no inquiry functions defined, calls to | |
3775 | @code{acc_prof_lookup} will always return @code{NULL}. | |
3776 | ||
3777 | There aren't separate @emph{start}, @emph{stop} events defined for the | |
3778 | event types @code{acc_ev_create}, @code{acc_ev_delete}, | |
3779 | @code{acc_ev_alloc}, @code{acc_ev_free}. It's not clear if these | |
3780 | should be triggered before or after the actual device-specific call is | |
3781 | made. We trigger them after. | |
3782 | ||
3783 | Remarks about data provided to callbacks: | |
3784 | ||
3785 | @table @asis | |
3786 | ||
3787 | @item @code{acc_prof_info.event_type} | |
3788 | It's not clear if for @emph{nested} event callbacks (for example, | |
3789 | @code{acc_ev_enqueue_launch_start} as part of a parent compute | |
3790 | construct), this should be set for the nested event | |
3791 | (@code{acc_ev_enqueue_launch_start}), or if the value of the parent | |
3792 | construct should remain (@code{acc_ev_compute_construct_start}). In | |
3793 | this implementation, the value will generally correspond to the | |
3794 | innermost nested event type. | |
3795 | ||
3796 | @item @code{acc_prof_info.device_type} | |
3797 | @itemize | |
3798 | ||
3799 | @item | |
3800 | For @code{acc_ev_compute_construct_start}, and in presence of an | |
3801 | @code{if} clause with @emph{false} argument, this will still refer to | |
3802 | the offloading device type. | |
3803 | It's not clear if that's the expected behavior. | |
3804 | ||
3805 | @item | |
3806 | Complementary to the item before, for | |
3807 | @code{acc_ev_compute_construct_end}, this is set to | |
3808 | @code{acc_device_host} in presence of an @code{if} clause with | |
3809 | @emph{false} argument. | |
3810 | It's not clear if that's the expected behavior. | |
3811 | ||
3812 | @end itemize | |
3813 | ||
3814 | @item @code{acc_prof_info.thread_id} | |
3815 | Always @code{-1}; not yet implemented. | |
3816 | ||
3817 | @item @code{acc_prof_info.async} | |
3818 | @itemize | |
3819 | ||
3820 | @item | |
3821 | Not yet implemented correctly for | |
3822 | @code{acc_ev_compute_construct_start}. | |
3823 | ||
3824 | @item | |
3825 | In a compute construct, for host-fallback | |
3826 | execution/@code{acc_device_host} it will always be | |
3827 | @code{acc_async_sync}. | |
3828 | It's not clear if that's the expected behavior. | |
3829 | ||
3830 | @item | |
3831 | For @code{acc_ev_device_init_start} and @code{acc_ev_device_init_end}, | |
3832 | it will always be @code{acc_async_sync}. | |
3833 | It's not clear if that's the expected behavior. | |
3834 | ||
3835 | @end itemize | |
3836 | ||
3837 | @item @code{acc_prof_info.async_queue} | |
3838 | There is no @cite{limited number of asynchronous queues} in libgomp. | |
3839 | This will always have the same value as @code{acc_prof_info.async}. | |
3840 | ||
3841 | @item @code{acc_prof_info.src_file} | |
3842 | Always @code{NULL}; not yet implemented. | |
3843 | ||
3844 | @item @code{acc_prof_info.func_name} | |
3845 | Always @code{NULL}; not yet implemented. | |
3846 | ||
3847 | @item @code{acc_prof_info.line_no} | |
3848 | Always @code{-1}; not yet implemented. | |
3849 | ||
3850 | @item @code{acc_prof_info.end_line_no} | |
3851 | Always @code{-1}; not yet implemented. | |
3852 | ||
3853 | @item @code{acc_prof_info.func_line_no} | |
3854 | Always @code{-1}; not yet implemented. | |
3855 | ||
3856 | @item @code{acc_prof_info.func_end_line_no} | |
3857 | Always @code{-1}; not yet implemented. | |
3858 | ||
3859 | @item @code{acc_event_info.event_type}, @code{acc_event_info.*.event_type} | |
3860 | Relating to @code{acc_prof_info.event_type} discussed above, in this | |
3861 | implementation, this will always be the same value as | |
3862 | @code{acc_prof_info.event_type}. | |
3863 | ||
3864 | @item @code{acc_event_info.*.parent_construct} | |
3865 | @itemize | |
3866 | ||
3867 | @item | |
3868 | Will be @code{acc_construct_parallel} for all OpenACC compute | |
3869 | constructs as well as many OpenACC Runtime API calls; should be the | |
3870 | one matching the actual construct, or | |
3871 | @code{acc_construct_runtime_api}, respectively. | |
3872 | ||
3873 | @item | |
3874 | Will be @code{acc_construct_enter_data} or | |
3875 | @code{acc_construct_exit_data} when processing variable mappings | |
3876 | specified in OpenACC @emph{declare} directives; should be | |
3877 | @code{acc_construct_declare}. | |
3878 | ||
3879 | @item | |
3880 | For implicit @code{acc_ev_device_init_start}, | |
3881 | @code{acc_ev_device_init_end}, and explicit as well as implicit | |
3882 | @code{acc_ev_alloc}, @code{acc_ev_free}, | |
3883 | @code{acc_ev_enqueue_upload_start}, @code{acc_ev_enqueue_upload_end}, | |
3884 | @code{acc_ev_enqueue_download_start}, and | |
3885 | @code{acc_ev_enqueue_download_end}, will be | |
3886 | @code{acc_construct_parallel}; should reflect the real parent | |
3887 | construct. | |
3888 | ||
3889 | @end itemize | |
3890 | ||
3891 | @item @code{acc_event_info.*.implicit} | |
3892 | For @code{acc_ev_alloc}, @code{acc_ev_free}, | |
3893 | @code{acc_ev_enqueue_upload_start}, @code{acc_ev_enqueue_upload_end}, | |
3894 | @code{acc_ev_enqueue_download_start}, and | |
3895 | @code{acc_ev_enqueue_download_end}, this currently will be @code{1} | |
3896 | also for explicit usage. | |
3897 | ||
3898 | @item @code{acc_event_info.data_event.var_name} | |
3899 | Always @code{NULL}; not yet implemented. | |
3900 | ||
3901 | @item @code{acc_event_info.data_event.host_ptr} | |
3902 | For @code{acc_ev_alloc}, and @code{acc_ev_free}, this is always | |
3903 | @code{NULL}. | |
3904 | ||
3905 | @item @code{typedef union acc_api_info} | |
3906 | @dots{} as printed in @cite{5.2.3. Third Argument: API-Specific | |
3907 | Information}. This should obviously be @code{typedef @emph{struct} | |
3908 | acc_api_info}. | |
3909 | ||
3910 | @item @code{acc_api_info.device_api} | |
3911 | Possibly not yet implemented correctly for | |
3912 | @code{acc_ev_compute_construct_start}, | |
3913 | @code{acc_ev_device_init_start}, @code{acc_ev_device_init_end}: | |
3914 | will always be @code{acc_device_api_none} for these event types. | |
3915 | For @code{acc_ev_enter_data_start}, it will be | |
3916 | @code{acc_device_api_none} in some cases. | |
3917 | ||
3918 | @item @code{acc_api_info.device_type} | |
3919 | Always the same as @code{acc_prof_info.device_type}. | |
3920 | ||
3921 | @item @code{acc_api_info.vendor} | |
3922 | Always @code{-1}; not yet implemented. | |
3923 | ||
3924 | @item @code{acc_api_info.device_handle} | |
3925 | Always @code{NULL}; not yet implemented. | |
3926 | ||
3927 | @item @code{acc_api_info.context_handle} | |
3928 | Always @code{NULL}; not yet implemented. | |
3929 | ||
3930 | @item @code{acc_api_info.async_handle} | |
3931 | Always @code{NULL}; not yet implemented. | |
3932 | ||
3933 | @end table | |
3934 | ||
3935 | Remarks about certain event types: | |
3936 | ||
3937 | @table @asis | |
3938 | ||
3939 | @item @code{acc_ev_device_init_start}, @code{acc_ev_device_init_end} | |
3940 | @itemize | |
3941 | ||
3942 | @item | |
3943 | @c See 'DEVICE_INIT_INSIDE_COMPUTE_CONSTRUCT' in | |
3944 | @c 'libgomp.oacc-c-c++-common/acc_prof-kernels-1.c', | |
3945 | @c 'libgomp.oacc-c-c++-common/acc_prof-parallel-1.c'. | |
ff7bc505 | 3946 | When a compute construct triggers implicit |
5fae049d TS |
3947 | @code{acc_ev_device_init_start} and @code{acc_ev_device_init_end} |
3948 | events, they currently aren't @emph{nested within} the corresponding | |
3949 | @code{acc_ev_compute_construct_start} and | |
3950 | @code{acc_ev_compute_construct_end}, but they're currently observed | |
3951 | @emph{before} @code{acc_ev_compute_construct_start}. | |
3952 | It's not clear what to do: the standard asks us provide a lot of | |
3953 | details to the @code{acc_ev_compute_construct_start} callback, without | |
3954 | (implicitly) initializing a device before? | |
3955 | ||
3956 | @item | |
3957 | Callbacks for these event types will not be invoked for calls to the | |
3958 | @code{acc_set_device_type} and @code{acc_set_device_num} functions. | |
3959 | It's not clear if they should be. | |
3960 | ||
3961 | @end itemize | |
3962 | ||
3963 | @item @code{acc_ev_enter_data_start}, @code{acc_ev_enter_data_end}, @code{acc_ev_exit_data_start}, @code{acc_ev_exit_data_end} | |
3964 | @itemize | |
3965 | ||
3966 | @item | |
3967 | Callbacks for these event types will also be invoked for OpenACC | |
3968 | @emph{host_data} constructs. | |
3969 | It's not clear if they should be. | |
3970 | ||
3971 | @item | |
3972 | Callbacks for these event types will also be invoked when processing | |
3973 | variable mappings specified in OpenACC @emph{declare} directives. | |
3974 | It's not clear if they should be. | |
3975 | ||
3976 | @end itemize | |
3977 | ||
3978 | @end table | |
3979 | ||
3980 | Callbacks for the following event types will be invoked, but dispatch | |
3981 | and information provided therein has not yet been thoroughly reviewed: | |
3982 | ||
3983 | @itemize | |
3984 | @item @code{acc_ev_alloc} | |
3985 | @item @code{acc_ev_free} | |
3986 | @item @code{acc_ev_update_start}, @code{acc_ev_update_end} | |
3987 | @item @code{acc_ev_enqueue_upload_start}, @code{acc_ev_enqueue_upload_end} | |
3988 | @item @code{acc_ev_enqueue_download_start}, @code{acc_ev_enqueue_download_end} | |
3989 | @end itemize | |
3990 | ||
3991 | During device initialization, and finalization, respectively, | |
3992 | callbacks for the following event types will not yet be invoked: | |
3993 | ||
3994 | @itemize | |
3995 | @item @code{acc_ev_alloc} | |
3996 | @item @code{acc_ev_free} | |
3997 | @end itemize | |
3998 | ||
3999 | Callbacks for the following event types have not yet been implemented, | |
4000 | so currently won't be invoked: | |
4001 | ||
4002 | @itemize | |
4003 | @item @code{acc_ev_device_shutdown_start}, @code{acc_ev_device_shutdown_end} | |
4004 | @item @code{acc_ev_runtime_shutdown} | |
4005 | @item @code{acc_ev_create}, @code{acc_ev_delete} | |
4006 | @item @code{acc_ev_wait_start}, @code{acc_ev_wait_end} | |
4007 | @end itemize | |
4008 | ||
4009 | For the following runtime library functions, not all expected | |
4010 | callbacks will be invoked (mostly concerning implicit device | |
4011 | initialization): | |
4012 | ||
4013 | @itemize | |
4014 | @item @code{acc_get_num_devices} | |
4015 | @item @code{acc_set_device_type} | |
4016 | @item @code{acc_get_device_type} | |
4017 | @item @code{acc_set_device_num} | |
4018 | @item @code{acc_get_device_num} | |
4019 | @item @code{acc_init} | |
4020 | @item @code{acc_shutdown} | |
4021 | @end itemize | |
4022 | ||
4023 | Aside from implicit device initialization, for the following runtime | |
4024 | library functions, no callbacks will be invoked for shared-memory | |
4025 | offloading devices (it's not clear if they should be): | |
4026 | ||
4027 | @itemize | |
4028 | @item @code{acc_malloc} | |
4029 | @item @code{acc_free} | |
4030 | @item @code{acc_copyin}, @code{acc_present_or_copyin}, @code{acc_copyin_async} | |
4031 | @item @code{acc_create}, @code{acc_present_or_create}, @code{acc_create_async} | |
4032 | @item @code{acc_copyout}, @code{acc_copyout_async}, @code{acc_copyout_finalize}, @code{acc_copyout_finalize_async} | |
4033 | @item @code{acc_delete}, @code{acc_delete_async}, @code{acc_delete_finalize}, @code{acc_delete_finalize_async} | |
4034 | @item @code{acc_update_device}, @code{acc_update_device_async} | |
4035 | @item @code{acc_update_self}, @code{acc_update_self_async} | |
4036 | @item @code{acc_map_data}, @code{acc_unmap_data} | |
4037 | @item @code{acc_memcpy_to_device}, @code{acc_memcpy_to_device_async} | |
4038 | @item @code{acc_memcpy_from_device}, @code{acc_memcpy_from_device_async} | |
4039 | @end itemize | |
4040 | ||
4041 | ||
4042 | ||
3721b9e1 DF |
4043 | @c --------------------------------------------------------------------- |
4044 | @c The libgomp ABI | |
4045 | @c --------------------------------------------------------------------- | |
4046 | ||
4047 | @node The libgomp ABI | |
4048 | @chapter The libgomp ABI | |
4049 | ||
4050 | The following sections present notes on the external ABI as | |
6a2ba183 | 4051 | presented by libgomp. Only maintainers should need them. |
3721b9e1 DF |
4052 | |
4053 | @menu | |
4054 | * Implementing MASTER construct:: | |
4055 | * Implementing CRITICAL construct:: | |
4056 | * Implementing ATOMIC construct:: | |
4057 | * Implementing FLUSH construct:: | |
4058 | * Implementing BARRIER construct:: | |
4059 | * Implementing THREADPRIVATE construct:: | |
4060 | * Implementing PRIVATE clause:: | |
4061 | * Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses:: | |
4062 | * Implementing REDUCTION clause:: | |
4063 | * Implementing PARALLEL construct:: | |
4064 | * Implementing FOR construct:: | |
4065 | * Implementing ORDERED construct:: | |
4066 | * Implementing SECTIONS construct:: | |
4067 | * Implementing SINGLE construct:: | |
cdf6119d | 4068 | * Implementing OpenACC's PARALLEL construct:: |
3721b9e1 DF |
4069 | @end menu |
4070 | ||
4071 | ||
4072 | @node Implementing MASTER construct | |
4073 | @section Implementing MASTER construct | |
4074 | ||
4075 | @smallexample | |
4076 | if (omp_get_thread_num () == 0) | |
4077 | block | |
4078 | @end smallexample | |
4079 | ||
4080 | Alternately, we generate two copies of the parallel subfunction | |
432de084 | 4081 | and only include this in the version run by the primary thread. |
6a2ba183 | 4082 | Surely this is not worthwhile though... |
3721b9e1 DF |
4083 | |
4084 | ||
4085 | ||
4086 | @node Implementing CRITICAL construct | |
4087 | @section Implementing CRITICAL construct | |
4088 | ||
4089 | Without a specified name, | |
4090 | ||
4091 | @smallexample | |
4092 | void GOMP_critical_start (void); | |
4093 | void GOMP_critical_end (void); | |
4094 | @end smallexample | |
4095 | ||
4096 | so that we don't get COPY relocations from libgomp to the main | |
4097 | application. | |
4098 | ||
4099 | With a specified name, use omp_set_lock and omp_unset_lock with | |
4100 | name being transformed into a variable declared like | |
4101 | ||
4102 | @smallexample | |
4103 | omp_lock_t gomp_critical_user_<name> __attribute__((common)) | |
4104 | @end smallexample | |
4105 | ||
4106 | Ideally the ABI would specify that all zero is a valid unlocked | |
6a2ba183 | 4107 | state, and so we wouldn't need to initialize this at |
3721b9e1 DF |
4108 | startup. |
4109 | ||
4110 | ||
4111 | ||
4112 | @node Implementing ATOMIC construct | |
4113 | @section Implementing ATOMIC construct | |
4114 | ||
4115 | The target should implement the @code{__sync} builtins. | |
4116 | ||
4117 | Failing that we could add | |
4118 | ||
4119 | @smallexample | |
4120 | void GOMP_atomic_enter (void) | |
4121 | void GOMP_atomic_exit (void) | |
4122 | @end smallexample | |
4123 | ||
4124 | which reuses the regular lock code, but with yet another lock | |
4125 | object private to the library. | |
4126 | ||
4127 | ||
4128 | ||
4129 | @node Implementing FLUSH construct | |
4130 | @section Implementing FLUSH construct | |
4131 | ||
4132 | Expands to the @code{__sync_synchronize} builtin. | |
4133 | ||
4134 | ||
4135 | ||
4136 | @node Implementing BARRIER construct | |
4137 | @section Implementing BARRIER construct | |
4138 | ||
4139 | @smallexample | |
4140 | void GOMP_barrier (void) | |
4141 | @end smallexample | |
4142 | ||
4143 | ||
4144 | @node Implementing THREADPRIVATE construct | |
4145 | @section Implementing THREADPRIVATE construct | |
4146 | ||
4147 | In _most_ cases we can map this directly to @code{__thread}. Except | |
4148 | that OMP allows constructors for C++ objects. We can either | |
4149 | refuse to support this (how often is it used?) or we can | |
4150 | implement something akin to .ctors. | |
4151 | ||
4152 | Even more ideally, this ctor feature is handled by extensions | |
4153 | to the main pthreads library. Failing that, we can have a set | |
4154 | of entry points to register ctor functions to be called. | |
4155 | ||
4156 | ||
4157 | ||
4158 | @node Implementing PRIVATE clause | |
4159 | @section Implementing PRIVATE clause | |
4160 | ||
4161 | In association with a PARALLEL, or within the lexical extent | |
4162 | of a PARALLEL block, the variable becomes a local variable in | |
4163 | the parallel subfunction. | |
4164 | ||
4165 | In association with FOR or SECTIONS blocks, create a new | |
4166 | automatic variable within the current function. This preserves | |
4167 | the semantic of new variable creation. | |
4168 | ||
4169 | ||
4170 | ||
4171 | @node Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses | |
4172 | @section Implementing FIRSTPRIVATE LASTPRIVATE COPYIN and COPYPRIVATE clauses | |
4173 | ||
6a2ba183 AH |
4174 | This seems simple enough for PARALLEL blocks. Create a private |
4175 | struct for communicating between the parent and subfunction. | |
3721b9e1 DF |
4176 | In the parent, copy in values for scalar and "small" structs; |
4177 | copy in addresses for others TREE_ADDRESSABLE types. In the | |
4178 | subfunction, copy the value into the local variable. | |
4179 | ||
6a2ba183 AH |
4180 | It is not clear what to do with bare FOR or SECTION blocks. |
4181 | The only thing I can figure is that we do something like: | |
3721b9e1 DF |
4182 | |
4183 | @smallexample | |
4184 | #pragma omp for firstprivate(x) lastprivate(y) | |
4185 | for (int i = 0; i < n; ++i) | |
4186 | body; | |
4187 | @end smallexample | |
4188 | ||
4189 | which becomes | |
4190 | ||
4191 | @smallexample | |
4192 | @{ | |
4193 | int x = x, y; | |
4194 | ||
4195 | // for stuff | |
4196 | ||
4197 | if (i == n) | |
4198 | y = y; | |
4199 | @} | |
4200 | @end smallexample | |
4201 | ||
4202 | where the "x=x" and "y=y" assignments actually have different | |
4203 | uids for the two variables, i.e. not something you could write | |
4204 | directly in C. Presumably this only makes sense if the "outer" | |
4205 | x and y are global variables. | |
4206 | ||
4207 | COPYPRIVATE would work the same way, except the structure | |
4208 | broadcast would have to happen via SINGLE machinery instead. | |
4209 | ||
4210 | ||
4211 | ||
4212 | @node Implementing REDUCTION clause | |
4213 | @section Implementing REDUCTION clause | |
4214 | ||
4215 | The private struct mentioned in the previous section should have | |
4216 | a pointer to an array of the type of the variable, indexed by the | |
4217 | thread's @var{team_id}. The thread stores its final value into the | |
432de084 | 4218 | array, and after the barrier, the primary thread iterates over the |
3721b9e1 DF |
4219 | array to collect the values. |
4220 | ||
4221 | ||
4222 | @node Implementing PARALLEL construct | |
4223 | @section Implementing PARALLEL construct | |
4224 | ||
4225 | @smallexample | |
4226 | #pragma omp parallel | |
4227 | @{ | |
4228 | body; | |
4229 | @} | |
4230 | @end smallexample | |
4231 | ||
4232 | becomes | |
4233 | ||
4234 | @smallexample | |
4235 | void subfunction (void *data) | |
4236 | @{ | |
4237 | use data; | |
4238 | body; | |
4239 | @} | |
4240 | ||
4241 | setup data; | |
4242 | GOMP_parallel_start (subfunction, &data, num_threads); | |
4243 | subfunction (&data); | |
4244 | GOMP_parallel_end (); | |
4245 | @end smallexample | |
4246 | ||
4247 | @smallexample | |
4248 | void GOMP_parallel_start (void (*fn)(void *), void *data, unsigned num_threads) | |
4249 | @end smallexample | |
4250 | ||
4251 | The @var{FN} argument is the subfunction to be run in parallel. | |
4252 | ||
4253 | The @var{DATA} argument is a pointer to a structure used to | |
4254 | communicate data in and out of the subfunction, as discussed | |
f1b0882e | 4255 | above with respect to FIRSTPRIVATE et al. |
3721b9e1 DF |
4256 | |
4257 | The @var{NUM_THREADS} argument is 1 if an IF clause is present | |
4258 | and false, or the value of the NUM_THREADS clause, if | |
4259 | present, or 0. | |
4260 | ||
4261 | The function needs to create the appropriate number of | |
4262 | threads and/or launch them from the dock. It needs to | |
4263 | create the team structure and assign team ids. | |
4264 | ||
4265 | @smallexample | |
4266 | void GOMP_parallel_end (void) | |
4267 | @end smallexample | |
4268 | ||
4269 | Tears down the team and returns us to the previous @code{omp_in_parallel()} state. | |
4270 | ||
4271 | ||
4272 | ||
4273 | @node Implementing FOR construct | |
4274 | @section Implementing FOR construct | |
4275 | ||
4276 | @smallexample | |
4277 | #pragma omp parallel for | |
4278 | for (i = lb; i <= ub; i++) | |
4279 | body; | |
4280 | @end smallexample | |
4281 | ||
4282 | becomes | |
4283 | ||
4284 | @smallexample | |
4285 | void subfunction (void *data) | |
4286 | @{ | |
4287 | long _s0, _e0; | |
4288 | while (GOMP_loop_static_next (&_s0, &_e0)) | |
4289 | @{ | |
4290 | long _e1 = _e0, i; | |
4291 | for (i = _s0; i < _e1; i++) | |
4292 | body; | |
4293 | @} | |
4294 | GOMP_loop_end_nowait (); | |
4295 | @} | |
4296 | ||
4297 | GOMP_parallel_loop_static (subfunction, NULL, 0, lb, ub+1, 1, 0); | |
4298 | subfunction (NULL); | |
4299 | GOMP_parallel_end (); | |
4300 | @end smallexample | |
4301 | ||
4302 | @smallexample | |
4303 | #pragma omp for schedule(runtime) | |
4304 | for (i = 0; i < n; i++) | |
4305 | body; | |
4306 | @end smallexample | |
4307 | ||
4308 | becomes | |
4309 | ||
4310 | @smallexample | |
4311 | @{ | |
4312 | long i, _s0, _e0; | |
4313 | if (GOMP_loop_runtime_start (0, n, 1, &_s0, &_e0)) | |
4314 | do @{ | |
4315 | long _e1 = _e0; | |
4316 | for (i = _s0, i < _e0; i++) | |
4317 | body; | |
4318 | @} while (GOMP_loop_runtime_next (&_s0, _&e0)); | |
4319 | GOMP_loop_end (); | |
4320 | @} | |
4321 | @end smallexample | |
4322 | ||
6a2ba183 | 4323 | Note that while it looks like there is trickiness to propagating |
3721b9e1 DF |
4324 | a non-constant STEP, there isn't really. We're explicitly allowed |
4325 | to evaluate it as many times as we want, and any variables involved | |
4326 | should automatically be handled as PRIVATE or SHARED like any other | |
4327 | variables. So the expression should remain evaluable in the | |
4328 | subfunction. We can also pull it into a local variable if we like, | |
4329 | but since its supposed to remain unchanged, we can also not if we like. | |
4330 | ||
4331 | If we have SCHEDULE(STATIC), and no ORDERED, then we ought to be | |
4332 | able to get away with no work-sharing context at all, since we can | |
4333 | simply perform the arithmetic directly in each thread to divide up | |
4334 | the iterations. Which would mean that we wouldn't need to call any | |
4335 | of these routines. | |
4336 | ||
4337 | There are separate routines for handling loops with an ORDERED | |
4338 | clause. Bookkeeping for that is non-trivial... | |
4339 | ||
4340 | ||
4341 | ||
4342 | @node Implementing ORDERED construct | |
4343 | @section Implementing ORDERED construct | |
4344 | ||
4345 | @smallexample | |
4346 | void GOMP_ordered_start (void) | |
4347 | void GOMP_ordered_end (void) | |
4348 | @end smallexample | |
4349 | ||
4350 | ||
4351 | ||
4352 | @node Implementing SECTIONS construct | |
4353 | @section Implementing SECTIONS construct | |
4354 | ||
4355 | A block as | |
4356 | ||
4357 | @smallexample | |
4358 | #pragma omp sections | |
4359 | @{ | |
4360 | #pragma omp section | |
4361 | stmt1; | |
4362 | #pragma omp section | |
4363 | stmt2; | |
4364 | #pragma omp section | |
4365 | stmt3; | |
4366 | @} | |
4367 | @end smallexample | |
4368 | ||
4369 | becomes | |
4370 | ||
4371 | @smallexample | |
4372 | for (i = GOMP_sections_start (3); i != 0; i = GOMP_sections_next ()) | |
4373 | switch (i) | |
4374 | @{ | |
4375 | case 1: | |
4376 | stmt1; | |
4377 | break; | |
4378 | case 2: | |
4379 | stmt2; | |
4380 | break; | |
4381 | case 3: | |
4382 | stmt3; | |
4383 | break; | |
4384 | @} | |
4385 | GOMP_barrier (); | |
4386 | @end smallexample | |
4387 | ||
4388 | ||
4389 | @node Implementing SINGLE construct | |
4390 | @section Implementing SINGLE construct | |
4391 | ||
4392 | A block like | |
4393 | ||
4394 | @smallexample | |
4395 | #pragma omp single | |
4396 | @{ | |
4397 | body; | |
4398 | @} | |
4399 | @end smallexample | |
4400 | ||
4401 | becomes | |
4402 | ||
4403 | @smallexample | |
4404 | if (GOMP_single_start ()) | |
4405 | body; | |
4406 | GOMP_barrier (); | |
4407 | @end smallexample | |
4408 | ||
4409 | while | |
4410 | ||
4411 | @smallexample | |
4412 | #pragma omp single copyprivate(x) | |
4413 | body; | |
4414 | @end smallexample | |
4415 | ||
4416 | becomes | |
4417 | ||
4418 | @smallexample | |
4419 | datap = GOMP_single_copy_start (); | |
4420 | if (datap == NULL) | |
4421 | @{ | |
4422 | body; | |
4423 | data.x = x; | |
4424 | GOMP_single_copy_end (&data); | |
4425 | @} | |
4426 | else | |
4427 | x = datap->x; | |
4428 | GOMP_barrier (); | |
4429 | @end smallexample | |
4430 | ||
4431 | ||
4432 | ||
cdf6119d JN |
4433 | @node Implementing OpenACC's PARALLEL construct |
4434 | @section Implementing OpenACC's PARALLEL construct | |
4435 | ||
4436 | @smallexample | |
4437 | void GOACC_parallel () | |
4438 | @end smallexample | |
4439 | ||
4440 | ||
4441 | ||
3721b9e1 | 4442 | @c --------------------------------------------------------------------- |
f1f3453e | 4443 | @c Reporting Bugs |
3721b9e1 DF |
4444 | @c --------------------------------------------------------------------- |
4445 | ||
4446 | @node Reporting Bugs | |
4447 | @chapter Reporting Bugs | |
4448 | ||
f1f3453e | 4449 | Bugs in the GNU Offloading and Multi Processing Runtime Library should |
c1030b5c | 4450 | be reported via @uref{https://gcc.gnu.org/bugzilla/, Bugzilla}. Please add |
41dbbb37 TS |
4451 | "openacc", or "openmp", or both to the keywords field in the bug |
4452 | report, as appropriate. | |
3721b9e1 DF |
4453 | |
4454 | ||
4455 | ||
4456 | @c --------------------------------------------------------------------- | |
4457 | @c GNU General Public License | |
4458 | @c --------------------------------------------------------------------- | |
4459 | ||
e6fdc918 | 4460 | @include gpl_v3.texi |
3721b9e1 DF |
4461 | |
4462 | ||
4463 | ||
4464 | @c --------------------------------------------------------------------- | |
4465 | @c GNU Free Documentation License | |
4466 | @c --------------------------------------------------------------------- | |
4467 | ||
4468 | @include fdl.texi | |
4469 | ||
4470 | ||
4471 | ||
4472 | @c --------------------------------------------------------------------- | |
4473 | @c Funding Free Software | |
4474 | @c --------------------------------------------------------------------- | |
4475 | ||
4476 | @include funding.texi | |
4477 | ||
4478 | @c --------------------------------------------------------------------- | |
4479 | @c Index | |
4480 | @c --------------------------------------------------------------------- | |
4481 | ||
3d3949df SL |
4482 | @node Library Index |
4483 | @unnumbered Library Index | |
3721b9e1 DF |
4484 | |
4485 | @printindex cp | |
4486 | ||
4487 | @bye |