OpenMP API5.0 Page7 Runtime Library Routines (continued) lprntepbcpartomvorlCvatheinemot place mums int omp_etiveevel(od integer function ompgetativelevel omp_in final uted in a final task region: e device b int omp_in_final (void): void_format(c char m omp_get_proc bind omp_get_thread_limit epni.omar*bfe int omp_get_thread_limit (void): omp proc_bind tomp get_proc_bind (void) hpe928ak2emt网 nteger tu p on using the void_(void) omp_display_affinity (const): integer function omp get supported active levels ( mo m ent in the olace时 int omp_get_num_places(void): void omp set max active levels (int max levels): a ent in the sodce int omp get max active levels (voidl: integer function omp get_max_active levels ( omp_get place proc_ids 盟eri论defa.device (m ntel th a2 int omp get level (void): int omp_get_default_device (void); integer function omp_get_level ( empnume2n2 thread num lint levei int omp_get_num_devices(id): integerfunction omp_get_place_mum( er function omp get num devices mp5eame20l2 m to which t remtte nt thread belo int get_patition_num places (void) int omp_getdevice_num (vid) m(in integer function omp_get_device_num() omp get team sire (even bers corres 2019 OpenMP ARB OMP0519-01-OMP© 2019 OpenMP ARB OMP0519-01-OMP5 OpenMP API 5.0 Page 7 Runtime Library Routines (continued) omp_get_schedule [3.2.13] [3.2.13] Returns the value of run-sched-var ICV, which is the schedule applied when runtime schedule is used. C/C++void omp_get_schedule ( omp_sched_t *kind, int *chunk_size); Forsubroutine omp_get_schedule (kind, chunk_size) integer (kind=omp_sched_kind) kind integer chunk_size kind for omp_set_schedule and omp_get_schedule is an implementation-defined schedule or: omp_sched_static omp_sched_dynamic omp_sched_guided omp_sched_auto Use + or | operators (C/C++) or the + operator (For) to combine the kinds with the modifier omp_sched_monotonic. omp_get_thread_limit [3.2.14] [3.2.14] Returns the value of the thread-limit-var ICV: the maximum number of OpenMP threads available in contention group. C/C++ int omp_get_thread_limit (void); For integer function omp_get_thread_limit () omp_get_supported_active_levels [3.2.15] Returns the number of active levels of parallelism supported. C/C++ void omp_get_supported_active_levels( void); For integer function omp_get_supported_active_levels () omp_set_max_active_levels [3.2.16] [3.2.15] Limits the number of nested active parallel regions, by setting max-active-levels-var ICV. C/C++ void omp_set_max_active_levels (int max_levels); For subroutine omp_set_max_active_levels (max_levels) integer max_levels omp_get_max_active_levels [3.2.17] [3.2.16] Returns the value of max-active-levels-var ICV, which determines the maximum number of nested active parallel regions. C/C++ int omp_get_max_active_levels (void); For integer function omp_get_max_active_levels () omp_get_level [3.2.18] [3.2.17] Returns the value of the levels-var ICV for the current device, which is the number of nested parallel regions on the device that enclose the task containing the call. C/C++ int omp_get_level (void); For integer function omp_get_level () omp_get_ancestor_thread_num [3.2.19] [3.2.18] Returns, for a given nested level of the current thread, the thread number of the ancestor of the current thread. C/C++ int omp_get_ancestor_thread_num (int level); For integer function omp_get_ancestor_thread_num (level) integer level omp_get_team_size [3.2.20] [3.2.19] Returns, for a given nested level of the current thread, the size of the thread team to which the ancestor or the current thread belongs. C/C++ int omp_get_team_size (int level); For integer function omp_get_team_size (level) integer level omp_get_active_level [3.2.21] [3.2.20] Returns the value of the active-level-vars ICV for the current device, which is the number of active, nested parallel regions on the device enclosing the task containing the call. C/C++ int omp_get_active_level (void); For integer function omp_get_active_level () omp_in_final [3.2.22] [3.2.21] Returns true if the routine is executed in a final task region; otherwise, it returns false. C/C++ int omp_in_final (void); For logical function omp_in_final () omp_get_proc_bind [3.2.23] [3.2.22] Returns the thread affinity policy to be used for the subsequent nested parallel regions that do not specify a proc_bind clause. C/C++ omp_proc_bind_t omp_get_proc_bind (void); For integer (kind=omp_proc_bind_kind) function omp_get_proc_bind () Valid return values include: omp_proc_bind_false omp_proc_bind_true omp_proc_bind_master omp_proc_bind_close omp_proc_bind_spread omp_get_num_places[3.2.24] [3.2.23] Returns the number of places available to the execution environment in the place list. C/C++ int omp_get_num_places (void); For integer function omp_get_num_places () omp_get_place_num_procs [3.2.25] [3.2.24] Returns the number of processors available to the execution environment in the specified place. C/C++ int omp_get_place_num_procs (int place_num); For integer function omp_get_place_num_procs (place_num) integer place_num omp_get_place_proc_ids [3.2.26] [3.2.25] Returns numerical identifiers of the processors available to the execution environment in the specified place. C/C++ void omp_get_place_proc_ids ( int place_num, int *ids); For subroutine omp_get_place_proc_ids(place_num, ids) integer place_num integer ids (*) omp_get_place_num [3.2.27] [3.2.26] Returns the place number of the place to which the encountering thread is bound. C/C++ int omp_get_place_num (void); For integer function omp_get_place_num () omp_get_partition_num_places [3.2.28] [3.2.27] Returns the number of places in the place-partition-var ICV of the innermost implicit task. C/C++ int omp_get_partition_num_places (void); For integer function omp_get_partition_num_places () omp_get_partition_place_nums [3.2.29] [3.2.28] Returns the list of place numbers corresponding to the places in the place-partition-var ICV of the innermost implicit task. C/C++ void omp_get_partition_place_nums ( int *place_nums); For subroutine omp_get_partition_place_nums( place_nums) integer place_nums (*) omp_set_affinity_format [3.2.30] Sets the affinity format to be used on the device by setting the value of the affinity-format-var ICV. C/C++ void omp_set_affinity_format (const char *format); For subroutine omp_set_affinity_format (format) character(len=*), intent(in) :: format omp_get_affinity_format [3.2.31] Returns the value of the affinity-format-var ICV on the device. C/C++ size_t omp_get_affinity_format (char *buffer, size_t size); For integer function omp_get_affinity_format (buffer) character(len=*), intent(out) :: buffer omp_display_affinity [3.2.32] Prints the OpenMP thread affinity information using the format specification provided. C/C++ void omp_display_affinity (const char *format); For subroutine omp_display_affinity (format) character(len=*), intent(in) :: format omp_capture_affinity [3.2.33] Prints the OpenMP thread affinity information into a buffer using the format specification provided. C/C++ size_t omp_capture_affinity (char *buffer, size_t size, const char *format) For integer function omp_capture_affinity (buffer, format) character(len=*), intent(out) :: buffer character(len=*), intent(in) :: format omp_set_default_device [3.2.34] [3.2.29] Assigns the value of the default-device-var ICV, which determines default target device. C/C++ void omp_set_default_device (int device_num); For subroutine omp_set_default_device (device_num) integer device_num omp_get_default_device [3.2.35] [3.2.30] Returns the value of the default-device-var ICV, which determines the default target device. C/C++ int omp_get_default_device (void); For integer function omp_get_default_device () omp_get_num_devices [3.2.36] [3.2.31] Returns the number of target devices. C/C++ int omp_get_num_devices (void); For integer function omp_get_num_devices () omp_get_device_num [3.2.37] Returns the device number of the device on which the calling thread is executing. C/C++ int omp_get_device_num (void); For integer function omp_get_device_num () Continued4 Continued4