e460634820
gcc/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> * omp-low.c (lower_omp_ordered): Add argument to GOMP_SMD_ORDERED_* internal calls - 0 if ordered simd and 1 for ordered threads simd. * tree-vectorizer.c (adjust_simduid_builtins): If GOMP_SIMD_ORDERED_* argument is 1, replace it with GOMP_ordered_* call instead of removing it. gcc/c/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> * c-typeck.c (c_finish_omp_clauses): Don't mark GOMP_MAP_FIRSTPRIVATE_POINTER decls addressable. gcc/cp/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> * semantics.c (finish_omp_clauses): Don't mark GOMP_MAP_FIRSTPRIVATE_POINTER decls addressable. libgomp/ 2015-11-14 Jakub Jelinek <jakub@redhat.com> Aldy Hernandez <aldyh@redhat.com> Ilya Verbin <ilya.verbin@intel.com> * ordered.c (gomp_doacross_init, GOMP_doacross_post, GOMP_doacross_wait, gomp_doacross_ull_init, GOMP_doacross_ull_post, GOMP_doacross_ull_wait): For GFS_GUIDED don't divide number of iterators or IV by chunk size. * parallel.c (gomp_resolve_num_threads): Don't assume that if thr->ts.team is non-NULL, then pool must be non-NULL. * libgomp-plugin.h (GOMP_PLUGIN_target_task_completion): Declare. * libgomp.map (GOMP_PLUGIN_1.1): New symbol version, export GOMP_PLUGIN_target_task_completion. * Makefile.am (libgomp_la_SOURCES): Add priority_queue.c. * Makefile.in: Regenerate. * libgomp.h: Shuffle prototypes and forward definitions around so priority queues can be defined. (enum gomp_task_kind): Add GOMP_TASK_ASYNC_RUNNING. (enum gomp_target_task_state): New enum. (struct gomp_target_task): Add state, tgt, task and team fields. (gomp_create_target_task): Change return type to bool, add state argument. (gomp_target_task_fn): Change return type to bool. (struct gomp_device_descr): Add async_run_func. (struct gomp_task): Remove children, next_child, prev_child, next_queue, prev_queue, next_taskgroup, prev_taskgroup. Add pnode field. (struct gomp_taskgroup): Remove children. Add taskgroup_queue. (struct gomp_team): Change task_queue type to a priority queue. (splay_compare): Define inline. (priority_queue_offset): New. (priority_node_to_task): New. (task_to_priority_node): New. * oacc-mem.c: Do not include splay-tree.h. * priority_queue.c: New file. * priority_queue.h: New file. * splay-tree.c: Do not include splay-tree.h. (splay_tree_foreach_internal): New. (splay_tree_foreach): New. * splay-tree.h: Become re-entrant if splay_tree_prefix is defined. (splay_tree_callback): Define typedef. * target.c (splay_compare): Move to libgomp.h. (GOMP_target): Don't adjust *thr in any way around running offloaded task. (GOMP_target_ext): Likewise. Handle target nowait. (GOMP_target_update_ext, GOMP_target_enter_exit_data): Check return value from gomp_create_target_task, if false, fallthrough as if no dependencies exist. (gomp_target_task_fn): Change return type to bool, return true if the task should have another part scheduled later. Handle target nowait. (gomp_load_plugin_for_device): Initialize async_run. * task.c (gomp_init_task): Initialize children_queue. (gomp_clear_parent_in_list): New. (gomp_clear_parent_in_tree): New. (gomp_clear_parent): Handle priorities. (GOMP_task): Likewise. (priority_queue_move_task_first, gomp_target_task_completion, GOMP_PLUGIN_target_task_completion): New functions. (gomp_create_target_task): Use priority queues. Change return type to bool, add state argument, return false if for async {{enter,exit} data,update} constructs no dependencies need to be waited for, handle target nowait. Set task->fn to NULL instead of gomp_target_task_fn. (verify_children_queue): Remove. (priority_list_upgrade_task): New. (priority_queue_upgrade_task): New. (verify_task_queue): Remove. (priority_list_downgrade_task): New. (priority_queue_downgrade_task): New. (gomp_task_run_pre): Use priority queues. Abstract code out to priority_queue_downgrade_task. (gomp_task_run_post_handle_dependers): Use priority queues. (gomp_task_run_post_remove_parent): Likewise. (gomp_task_run_post_remove_taskgroup): Likewise. (gomp_barrier_handle_tasks): Likewise. Handle target nowait target tasks specially. (GOMP_taskwait): Likewise. (gomp_task_maybe_wait_for_dependencies): Likewise. Abstract code to priority-queue_upgrade_task. (GOMP_taskgroup_start): Use priority queues. (GOMP_taskgroup_end): Likewise. Handle target nowait target tasks specially. If taskgroup is NULL, and thr->ts.level is 0, act as a barrier. * taskloop.c (GOMP_taskloop): Handle priorities. * team.c (gomp_new_team): Call priority_queue_init. (free_team): Call priority_queue_free. (gomp_free_thread): Call gomp_team_end if thr->ts.team is artificial team created for target nowait in implicit parallel region. (gomp_team_start): For nested check, test thr->ts.level instead of thr->ts.team != NULL. * testsuite/libgomp.c/doacross-3.c: New test. * testsuite/libgomp.c/ordered-5.c: New test. * testsuite/libgomp.c/priority.c: New test. * testsuite/libgomp.c/target-31.c: New test. * testsuite/libgomp.c/target-32.c: New test. * testsuite/libgomp.c/target-33.c: New test. * testsuite/libgomp.c/target-34.c: New test. liboffloadmic/ 2015-11-14 Ilya Verbin <ilya.verbin@intel.com> * runtime/offload_host.cpp (task_completion_callback): New variable. (offload_proxy_task_completed_ooo): Call task_completion_callback. (__offload_register_task_callback): New function. * runtime/offload_host.h (__offload_register_task_callback): New declaration. * plugin/libgomp-plugin-intelmic.cpp (offload): Add async_data argument, handle async offloading. (register_main_image): Call register_main_image. (GOMP_OFFLOAD_init_device, get_target_table, GOMP_OFFLOAD_alloc, GOMP_OFFLOAD_free, GOMP_OFFLOAD_host2dev, GOMP_OFFLOAD_dev2host, GOMP_OFFLOAD_dev2dev) Adjust offload callers. (GOMP_OFFLOAD_async_run): New function. (GOMP_OFFLOAD_run): Implement using GOMP_OFFLOAD_async_run. From-SVN: r230381
415 lines
8.6 KiB
Plaintext
415 lines
8.6 KiB
Plaintext
OMP_1.0 {
|
|
global:
|
|
omp_set_num_threads;
|
|
omp_get_num_threads;
|
|
omp_get_max_threads;
|
|
omp_get_thread_num;
|
|
omp_get_num_procs;
|
|
omp_in_parallel;
|
|
omp_set_dynamic;
|
|
omp_get_dynamic;
|
|
omp_set_nested;
|
|
omp_get_nested;
|
|
#ifdef HAVE_SYMVER_SYMBOL_RENAMING_RUNTIME_SUPPORT
|
|
# If the assembler used lacks the .symver directive or the linker
|
|
# doesn't support GNU symbol versioning, we have the same symbol in
|
|
# two versions, which Sun ld chokes on.
|
|
omp_init_lock;
|
|
omp_init_nest_lock;
|
|
omp_destroy_lock;
|
|
omp_destroy_nest_lock;
|
|
omp_set_lock;
|
|
omp_set_nest_lock;
|
|
omp_unset_lock;
|
|
omp_unset_nest_lock;
|
|
omp_test_lock;
|
|
omp_test_nest_lock;
|
|
omp_destroy_lock_;
|
|
omp_destroy_nest_lock_;
|
|
omp_init_lock_;
|
|
omp_init_nest_lock_;
|
|
omp_set_lock_;
|
|
omp_set_nest_lock_;
|
|
omp_test_lock_;
|
|
omp_test_nest_lock_;
|
|
omp_unset_lock_;
|
|
omp_unset_nest_lock_;
|
|
#endif
|
|
omp_get_dynamic_;
|
|
omp_get_max_threads_;
|
|
omp_get_nested_;
|
|
omp_get_num_procs_;
|
|
omp_get_num_threads_;
|
|
omp_get_thread_num_;
|
|
omp_in_parallel_;
|
|
omp_set_dynamic_;
|
|
omp_set_dynamic_8_;
|
|
omp_set_nested_;
|
|
omp_set_nested_8_;
|
|
omp_set_num_threads_;
|
|
omp_set_num_threads_8_;
|
|
local:
|
|
*;
|
|
};
|
|
|
|
OMP_2.0 {
|
|
global:
|
|
omp_get_wtick;
|
|
omp_get_wtime;
|
|
omp_get_wtick_;
|
|
omp_get_wtime_;
|
|
} OMP_1.0;
|
|
|
|
OMP_3.0 {
|
|
global:
|
|
omp_set_schedule;
|
|
omp_set_schedule_;
|
|
omp_set_schedule_8_;
|
|
omp_get_schedule;
|
|
omp_get_schedule_;
|
|
omp_get_schedule_8_;
|
|
omp_get_thread_limit;
|
|
omp_get_thread_limit_;
|
|
omp_set_max_active_levels;
|
|
omp_set_max_active_levels_;
|
|
omp_set_max_active_levels_8_;
|
|
omp_get_max_active_levels;
|
|
omp_get_max_active_levels_;
|
|
omp_get_level;
|
|
omp_get_level_;
|
|
omp_get_ancestor_thread_num;
|
|
omp_get_ancestor_thread_num_;
|
|
omp_get_ancestor_thread_num_8_;
|
|
omp_get_team_size;
|
|
omp_get_team_size_;
|
|
omp_get_team_size_8_;
|
|
omp_get_active_level;
|
|
omp_get_active_level_;
|
|
omp_init_lock;
|
|
omp_init_nest_lock;
|
|
omp_destroy_lock;
|
|
omp_destroy_nest_lock;
|
|
omp_set_lock;
|
|
omp_set_nest_lock;
|
|
omp_unset_lock;
|
|
omp_unset_nest_lock;
|
|
omp_test_lock;
|
|
omp_test_nest_lock;
|
|
omp_destroy_lock_;
|
|
omp_destroy_nest_lock_;
|
|
omp_init_lock_;
|
|
omp_init_nest_lock_;
|
|
omp_set_lock_;
|
|
omp_set_nest_lock_;
|
|
omp_test_lock_;
|
|
omp_test_nest_lock_;
|
|
omp_unset_lock_;
|
|
omp_unset_nest_lock_;
|
|
} OMP_2.0;
|
|
|
|
OMP_3.1 {
|
|
global:
|
|
omp_in_final;
|
|
omp_in_final_;
|
|
} OMP_3.0;
|
|
|
|
OMP_4.0 {
|
|
global:
|
|
omp_get_cancellation;
|
|
omp_get_cancellation_;
|
|
omp_get_proc_bind;
|
|
omp_get_proc_bind_;
|
|
omp_set_default_device;
|
|
omp_set_default_device_;
|
|
omp_set_default_device_8_;
|
|
omp_get_default_device;
|
|
omp_get_default_device_;
|
|
omp_get_num_devices;
|
|
omp_get_num_devices_;
|
|
omp_get_num_teams;
|
|
omp_get_num_teams_;
|
|
omp_get_team_num;
|
|
omp_get_team_num_;
|
|
omp_is_initial_device;
|
|
omp_is_initial_device_;
|
|
} OMP_3.1;
|
|
|
|
OMP_4.5 {
|
|
global:
|
|
omp_get_max_task_priority;
|
|
omp_get_max_task_priority_;
|
|
omp_get_num_places;
|
|
omp_get_num_places_;
|
|
omp_get_place_num_procs;
|
|
omp_get_place_num_procs_;
|
|
omp_get_place_num_procs_8_;
|
|
omp_get_place_proc_ids;
|
|
omp_get_place_proc_ids_;
|
|
omp_get_place_proc_ids_8_;
|
|
omp_get_place_num;
|
|
omp_get_place_num_;
|
|
omp_get_partition_num_places;
|
|
omp_get_partition_num_places_;
|
|
omp_get_partition_place_nums;
|
|
omp_get_partition_place_nums_;
|
|
omp_get_partition_place_nums_8_;
|
|
omp_get_initial_device;
|
|
omp_get_initial_device_;
|
|
omp_target_alloc;
|
|
omp_target_free;
|
|
omp_target_is_present;
|
|
omp_target_memcpy;
|
|
omp_target_memcpy_rect;
|
|
omp_target_associate_ptr;
|
|
omp_target_disassociate_ptr;
|
|
} OMP_4.0;
|
|
|
|
GOMP_1.0 {
|
|
global:
|
|
GOMP_atomic_end;
|
|
GOMP_atomic_start;
|
|
GOMP_barrier;
|
|
GOMP_critical_end;
|
|
GOMP_critical_name_end;
|
|
GOMP_critical_name_start;
|
|
GOMP_critical_start;
|
|
GOMP_loop_dynamic_next;
|
|
GOMP_loop_dynamic_start;
|
|
GOMP_loop_end;
|
|
GOMP_loop_end_nowait;
|
|
GOMP_loop_guided_next;
|
|
GOMP_loop_guided_start;
|
|
GOMP_loop_ordered_dynamic_next;
|
|
GOMP_loop_ordered_dynamic_start;
|
|
GOMP_loop_ordered_guided_next;
|
|
GOMP_loop_ordered_guided_start;
|
|
GOMP_loop_ordered_runtime_next;
|
|
GOMP_loop_ordered_runtime_start;
|
|
GOMP_loop_ordered_static_next;
|
|
GOMP_loop_ordered_static_start;
|
|
GOMP_loop_runtime_next;
|
|
GOMP_loop_runtime_start;
|
|
GOMP_loop_static_next;
|
|
GOMP_loop_static_start;
|
|
GOMP_ordered_end;
|
|
GOMP_ordered_start;
|
|
GOMP_parallel_end;
|
|
GOMP_parallel_loop_dynamic_start;
|
|
GOMP_parallel_loop_guided_start;
|
|
GOMP_parallel_loop_runtime_start;
|
|
GOMP_parallel_loop_static_start;
|
|
GOMP_parallel_sections_start;
|
|
GOMP_parallel_start;
|
|
GOMP_sections_end;
|
|
GOMP_sections_end_nowait;
|
|
GOMP_sections_next;
|
|
GOMP_sections_start;
|
|
GOMP_single_copy_end;
|
|
GOMP_single_copy_start;
|
|
GOMP_single_start;
|
|
};
|
|
|
|
GOMP_2.0 {
|
|
global:
|
|
GOMP_task;
|
|
GOMP_taskwait;
|
|
GOMP_loop_ull_dynamic_next;
|
|
GOMP_loop_ull_dynamic_start;
|
|
GOMP_loop_ull_guided_next;
|
|
GOMP_loop_ull_guided_start;
|
|
GOMP_loop_ull_ordered_dynamic_next;
|
|
GOMP_loop_ull_ordered_dynamic_start;
|
|
GOMP_loop_ull_ordered_guided_next;
|
|
GOMP_loop_ull_ordered_guided_start;
|
|
GOMP_loop_ull_ordered_runtime_next;
|
|
GOMP_loop_ull_ordered_runtime_start;
|
|
GOMP_loop_ull_ordered_static_next;
|
|
GOMP_loop_ull_ordered_static_start;
|
|
GOMP_loop_ull_runtime_next;
|
|
GOMP_loop_ull_runtime_start;
|
|
GOMP_loop_ull_static_next;
|
|
GOMP_loop_ull_static_start;
|
|
} GOMP_1.0;
|
|
|
|
GOMP_3.0 {
|
|
global:
|
|
GOMP_taskyield;
|
|
} GOMP_2.0;
|
|
|
|
GOMP_4.0 {
|
|
global:
|
|
GOMP_barrier_cancel;
|
|
GOMP_cancel;
|
|
GOMP_cancellation_point;
|
|
GOMP_loop_end_cancel;
|
|
GOMP_parallel_loop_dynamic;
|
|
GOMP_parallel_loop_guided;
|
|
GOMP_parallel_loop_runtime;
|
|
GOMP_parallel_loop_static;
|
|
GOMP_parallel_sections;
|
|
GOMP_parallel;
|
|
GOMP_sections_end_cancel;
|
|
GOMP_taskgroup_start;
|
|
GOMP_taskgroup_end;
|
|
GOMP_target;
|
|
GOMP_target_data;
|
|
GOMP_target_end_data;
|
|
GOMP_target_update;
|
|
GOMP_teams;
|
|
} GOMP_3.0;
|
|
|
|
GOMP_4.0.1 {
|
|
global:
|
|
GOMP_offload_register;
|
|
GOMP_offload_unregister;
|
|
} GOMP_4.0;
|
|
|
|
GOMP_4.5 {
|
|
global:
|
|
GOMP_target_ext;
|
|
GOMP_target_data_ext;
|
|
GOMP_target_update_ext;
|
|
GOMP_target_enter_exit_data;
|
|
GOMP_taskloop;
|
|
GOMP_taskloop_ull;
|
|
GOMP_offload_register_ver;
|
|
GOMP_offload_unregister_ver;
|
|
GOMP_loop_doacross_dynamic_start;
|
|
GOMP_loop_doacross_guided_start;
|
|
GOMP_loop_doacross_runtime_start;
|
|
GOMP_loop_doacross_static_start;
|
|
GOMP_doacross_post;
|
|
GOMP_doacross_wait;
|
|
GOMP_loop_ull_doacross_dynamic_start;
|
|
GOMP_loop_ull_doacross_guided_start;
|
|
GOMP_loop_ull_doacross_runtime_start;
|
|
GOMP_loop_ull_doacross_static_start;
|
|
GOMP_doacross_ull_post;
|
|
GOMP_doacross_ull_wait;
|
|
GOMP_loop_nonmonotonic_dynamic_next;
|
|
GOMP_loop_nonmonotonic_dynamic_start;
|
|
GOMP_loop_nonmonotonic_guided_next;
|
|
GOMP_loop_nonmonotonic_guided_start;
|
|
GOMP_loop_ull_nonmonotonic_dynamic_next;
|
|
GOMP_loop_ull_nonmonotonic_dynamic_start;
|
|
GOMP_loop_ull_nonmonotonic_guided_next;
|
|
GOMP_loop_ull_nonmonotonic_guided_start;
|
|
GOMP_parallel_loop_nonmonotonic_dynamic;
|
|
GOMP_parallel_loop_nonmonotonic_guided;
|
|
} GOMP_4.0.1;
|
|
|
|
OACC_2.0 {
|
|
global:
|
|
acc_get_num_devices;
|
|
acc_get_num_devices_h_;
|
|
acc_set_device_type;
|
|
acc_set_device_type_h_;
|
|
acc_get_device_type;
|
|
acc_get_device_type_h_;
|
|
acc_set_device_num;
|
|
acc_set_device_num_h_;
|
|
acc_get_device_num;
|
|
acc_get_device_num_h_;
|
|
acc_async_test;
|
|
acc_async_test_h_;
|
|
acc_async_test_all;
|
|
acc_async_test_all_h_;
|
|
acc_wait;
|
|
acc_wait_h_;
|
|
acc_wait_async;
|
|
acc_wait_async_h_;
|
|
acc_wait_all;
|
|
acc_wait_all_h_;
|
|
acc_wait_all_async;
|
|
acc_wait_all_async_h_;
|
|
acc_init;
|
|
acc_init_h_;
|
|
acc_shutdown;
|
|
acc_shutdown_h_;
|
|
acc_on_device;
|
|
acc_on_device_h_;
|
|
acc_malloc;
|
|
acc_free;
|
|
acc_copyin;
|
|
acc_copyin_32_h_;
|
|
acc_copyin_64_h_;
|
|
acc_copyin_array_h_;
|
|
acc_present_or_copyin;
|
|
acc_present_or_copyin_32_h_;
|
|
acc_present_or_copyin_64_h_;
|
|
acc_present_or_copyin_array_h_;
|
|
acc_create;
|
|
acc_create_32_h_;
|
|
acc_create_64_h_;
|
|
acc_create_array_h_;
|
|
acc_present_or_create;
|
|
acc_present_or_create_32_h_;
|
|
acc_present_or_create_64_h_;
|
|
acc_present_or_create_array_h_;
|
|
acc_copyout;
|
|
acc_copyout_32_h_;
|
|
acc_copyout_64_h_;
|
|
acc_copyout_array_h_;
|
|
acc_delete;
|
|
acc_delete_32_h_;
|
|
acc_delete_64_h_;
|
|
acc_delete_array_h_;
|
|
acc_update_device;
|
|
acc_update_device_32_h_;
|
|
acc_update_device_64_h_;
|
|
acc_update_device_array_h_;
|
|
acc_update_self;
|
|
acc_update_self_32_h_;
|
|
acc_update_self_64_h_;
|
|
acc_update_self_array_h_;
|
|
acc_map_data;
|
|
acc_unmap_data;
|
|
acc_deviceptr;
|
|
acc_hostptr;
|
|
acc_is_present;
|
|
acc_is_present_32_h_;
|
|
acc_is_present_64_h_;
|
|
acc_is_present_array_h_;
|
|
acc_memcpy_to_device;
|
|
acc_memcpy_from_device;
|
|
acc_get_current_cuda_device;
|
|
acc_get_current_cuda_context;
|
|
acc_get_cuda_stream;
|
|
acc_set_cuda_stream;
|
|
};
|
|
|
|
GOACC_2.0 {
|
|
global:
|
|
GOACC_data_end;
|
|
GOACC_data_start;
|
|
GOACC_enter_exit_data;
|
|
GOACC_parallel;
|
|
GOACC_update;
|
|
GOACC_wait;
|
|
GOACC_get_thread_num;
|
|
GOACC_get_num_threads;
|
|
};
|
|
|
|
GOACC_2.0.1 {
|
|
global:
|
|
GOACC_declare;
|
|
GOACC_parallel_keyed;
|
|
} GOACC_2.0;
|
|
|
|
GOMP_PLUGIN_1.0 {
|
|
global:
|
|
GOMP_PLUGIN_malloc;
|
|
GOMP_PLUGIN_malloc_cleared;
|
|
GOMP_PLUGIN_realloc;
|
|
GOMP_PLUGIN_debug;
|
|
GOMP_PLUGIN_error;
|
|
GOMP_PLUGIN_fatal;
|
|
GOMP_PLUGIN_async_unmap_vars;
|
|
GOMP_PLUGIN_acc_thread;
|
|
};
|
|
|
|
GOMP_PLUGIN_1.1 {
|
|
global:
|
|
GOMP_PLUGIN_target_task_completion;
|
|
} GOMP_PLUGIN_1.0;
|