diff options
Diffstat (limited to 'openmp/runtime/src/kmp_gsupport.c')
| -rw-r--r-- | openmp/runtime/src/kmp_gsupport.c | 92 |
1 files changed, 81 insertions, 11 deletions
diff --git a/openmp/runtime/src/kmp_gsupport.c b/openmp/runtime/src/kmp_gsupport.c index 9397e6fd988..42d58e50532 100644 --- a/openmp/runtime/src/kmp_gsupport.c +++ b/openmp/runtime/src/kmp_gsupport.c @@ -407,7 +407,8 @@ __kmp_GOMP_serialized_parallel(ident_t *loc, kmp_int32 gtid, void (*task)(void * int team_size = 1; ompt_callbacks.ompt_callback(ompt_event_parallel_begin)( ompt_task_id, ompt_frame, ompt_parallel_id, - team_size, (void *) task); + team_size, (void *) task, + OMPT_INVOKER(fork_context_gnu)); } // set up lightweight task @@ -488,8 +489,10 @@ xexpand(KMP_API_NAME_GOMP_PARALLEL_END)(void) ompt_team_info_t *team_info = __ompt_get_teaminfo(0, NULL); parallel_id = team_info->parallel_id; + // Record that we re-entered the runtime system in the implicit + // task frame representing the parallel region. ompt_frame = __ompt_get_task_frame_internal(0); - ompt_frame->exit_runtime_frame = __builtin_frame_address(0); + ompt_frame->reenter_runtime_frame = __builtin_frame_address(0); #if OMPT_TRACE if ((ompt_status == ompt_status_track_callback) && @@ -503,7 +506,19 @@ xexpand(KMP_API_NAME_GOMP_PARALLEL_END)(void) // unlink if necessary. no-op if there is not a lightweight task. ompt_lw_taskteam_t *lwt = __ompt_lw_taskteam_unlink(thr); // GOMP allocates/frees lwt since it can't be kept on the stack - if (lwt) __kmp_free(lwt); + if (lwt) { + __kmp_free(lwt); + +#if OMPT_SUPPORT + if (ompt_status & ompt_status_track) { + // Since a lightweight task was destroyed, make sure that the + // remaining deepest task knows the stack frame where the runtime + // was reentered. + ompt_frame = __ompt_get_task_frame_internal(0); + ompt_frame->reenter_runtime_frame = __builtin_frame_address(0); + } +#endif + } } #endif @@ -511,26 +526,48 @@ xexpand(KMP_API_NAME_GOMP_PARALLEL_END)(void) kmp_info_t *thr = __kmp_threads[gtid]; __kmp_run_after_invoked_task(gtid, __kmp_tid_from_gtid(gtid), thr, thr->th.th_team); - __kmp_join_call(&loc, gtid); + +#if OMPT_SUPPORT + if (ompt_status & ompt_status_track) { + // Set reenter frame in parent task, which will become current task + // in the midst of join. This is needed before the end_parallel callback. + ompt_frame = __ompt_get_task_frame_internal(1); + ompt_frame->reenter_runtime_frame = __builtin_frame_address(0); + } +#endif + + __kmp_join_call(&loc, gtid, fork_context_gnu); + +#if OMPT_SUPPORT + if (ompt_status & ompt_status_track) { + ompt_frame->reenter_runtime_frame = NULL; + } +#endif } else { __kmpc_end_serialized_parallel(&loc, gtid); #if OMPT_SUPPORT if (ompt_status & ompt_status_track) { + // Record that we re-entered the runtime system in the frame that + // created the parallel region. + ompt_frame->reenter_runtime_frame = __builtin_frame_address(0); + if ((ompt_status == ompt_status_track_callback) && ompt_callbacks.ompt_callback(ompt_event_parallel_end)) { ompt_task_info_t *task_info = __ompt_get_taskinfo(0); ompt_callbacks.ompt_callback(ompt_event_parallel_end)( - parallel_id, task_info->task_id); + parallel_id, task_info->task_id, + OMPT_INVOKER(fork_context_gnu)); } + ompt_frame->reenter_runtime_frame = NULL; + thr->th.ompt_thread_info.state = (((thr->th.th_team)->t.t_serialized) ? ompt_state_work_serial : ompt_state_work_parallel); } #endif - } } @@ -817,7 +854,7 @@ LOOP_NEXT_ULL(xexpand(KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT), \ // There are no ull versions (yet). // -#define PARALLEL_LOOP_START(func, schedule) \ +#define PARALLEL_LOOP_START(func, schedule, ompt_pre, ompt_post) \ void func (void (*task) (void *), void *data, unsigned num_threads, \ long lb, long ub, long str, long chunk_sz) \ { \ @@ -826,6 +863,8 @@ LOOP_NEXT_ULL(xexpand(KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT), \ KA_TRACE(20, ( #func ": T#%d, lb 0x%lx, ub 0x%lx, str 0x%lx, chunk_sz 0x%lx\n", \ gtid, lb, ub, str, chunk_sz )); \ \ + ompt_pre(); \ + \ if (__kmpc_ok_to_fork(&loc) && (num_threads != 1)) { \ if (num_threads != 0) { \ __kmp_push_num_threads(&loc, gtid, num_threads); \ @@ -843,14 +882,45 @@ LOOP_NEXT_ULL(xexpand(KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT), \ (str > 0) ? (ub - 1) : (ub + 1), str, chunk_sz, \ (schedule) != kmp_sch_static); \ \ + ompt_post(); \ + \ KA_TRACE(20, ( #func " exit: T#%d\n", gtid)); \ } -PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_STATIC_START), kmp_sch_static) -PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_DYNAMIC_START), kmp_sch_dynamic_chunked) -PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_GUIDED_START), kmp_sch_guided_chunked) -PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_RUNTIME_START), kmp_sch_runtime) + +#if OMPT_SUPPORT + +#define OMPT_LOOP_PRE() \ + ompt_frame_t *parent_frame; \ + if (ompt_status & ompt_status_track) { \ + parent_frame = __ompt_get_task_frame_internal(0); \ + parent_frame->reenter_runtime_frame = __builtin_frame_address(0); \ + } + + +#define OMPT_LOOP_POST() \ + if (ompt_status & ompt_status_track) { \ + parent_frame->reenter_runtime_frame = NULL; \ + } + +#else + +#define OMPT_LOOP_PRE() + +#define OMPT_LOOP_POST() + +#endif + + +PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_STATIC_START), + kmp_sch_static, OMPT_LOOP_PRE, OMPT_LOOP_POST) +PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_DYNAMIC_START), + kmp_sch_dynamic_chunked, OMPT_LOOP_PRE, OMPT_LOOP_POST) +PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_GUIDED_START), + kmp_sch_guided_chunked, OMPT_LOOP_PRE, OMPT_LOOP_POST) +PARALLEL_LOOP_START(xexpand(KMP_API_NAME_GOMP_PARALLEL_LOOP_RUNTIME_START), + kmp_sch_runtime, OMPT_LOOP_PRE, OMPT_LOOP_POST) // |
