59a994e8da
__ompt_get_task_info_internal is now able to determine the right value of the “thread_num” argument during the execution of an explicit task. During the execution of a while loop that iterates over the ancestor tasks hierarchy, the “prev_team” variable was always set to “team” variable at the beginning of each loop iteration. Assume that the program contains a parallel region which encloses an explicit task executed by the worker thread of the region. Also assume that the tool inquires the “thread_num” of a worker thread for the implicit task that corresponds to the region (task at “ancestor_level == 1”) and expects to receive the value of “thread_num > 0”. After the loop finishes, both “team” and “prev_team” variables are equal and point to the team information of the parallel region. The “thread_num” is set to “prev_team->t.t_master_tid”, that is equal to “team->t.t_master_tid”. In this case, “team->t.t_master_tid” is 0, since the master thread of the region is the initial master thread of the program. This leads to a contradiction. To prevent this, “prev_team” variable is set to “team” variable only at the time when the loop that has already encountered the implicit task (“taskdata” variable contains the information about an implicit task) continues iterating over the implicit task’s ancestors, if any. After the mentioned loop finishes, the “prev_team” variable might be equal to NULL. This means that the task at requested “ancestor_level” belongs to the innermost parallel region, so the “thread_num” will be determined by calling the “__kmp_get_tid”. To prove that this patch works, the test case “explicit_task_thread_num.c” is provided. It contains the example of the program explained earlier in the summary. Differential Revision: https://reviews.llvm.org/D110473
69 lines
2.3 KiB
C
69 lines
2.3 KiB
C
// RUN: %libomp-compile-and-run | FileCheck %s
|
|
// REQUIRES: ompt
|
|
|
|
#include "callback.h"
|
|
#include <omp.h>
|
|
|
|
|
|
__attribute__ ((noinline)) // workaround for bug in icc
|
|
void print_task_info_at(int ancestor_level, int id)
|
|
{
|
|
#pragma omp critical
|
|
{
|
|
int task_type;
|
|
char buffer[2048];
|
|
ompt_data_t *parallel_data;
|
|
ompt_data_t *task_data;
|
|
int thread_num;
|
|
ompt_get_task_info(ancestor_level, &task_type, &task_data, NULL,
|
|
¶llel_data, &thread_num);
|
|
format_task_type(task_type, buffer);
|
|
printf("%" PRIu64 ": ancestor_level=%d id=%d task_type=%s=%d "
|
|
"parallel_id=%" PRIu64 " task_id=%" PRIu64
|
|
" thread_num=%d\n",
|
|
ompt_get_thread_data()->value, ancestor_level, id, buffer,
|
|
task_type, parallel_data->value, task_data->value, thread_num);
|
|
}
|
|
};
|
|
|
|
int main()
|
|
{
|
|
|
|
#pragma omp parallel num_threads(2)
|
|
{
|
|
|
|
if (omp_get_thread_num() == 1) {
|
|
// To assert that task is executed by the worker thread,
|
|
// if(0) is used in order to ensure that the task is immediately
|
|
// executed after its creation.
|
|
#pragma omp task if(0)
|
|
{
|
|
// thread_num should be equal to 1 for both explicit and implicit task
|
|
print_task_info_at(0, 1);
|
|
print_task_info_at(1, 0);
|
|
};
|
|
}
|
|
}
|
|
|
|
// Check if libomp supports the callbacks for this test.
|
|
// CHECK-NOT: {{^}}0: Could not register callback 'ompt_event_parallel_begin'
|
|
// CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_task_create'
|
|
// CHECK-NOT: {{^}}0: Could not register callback 'ompt_callback_implicit_task'
|
|
|
|
// CHECK: {{^}}0: NULL_POINTER=[[NULL:.*$]]
|
|
// CHECK: {{^}}[[MASTER_ID:[0-9]+]]: ompt_event_initial_task_begin
|
|
|
|
// parallel region used only to determine worker thread id
|
|
// CHECK: {{^}}[[MASTER_ID]]: ompt_event_parallel_begin
|
|
// CHECK-DAG: {{^}}[[MASTER_ID]]: ompt_event_implicit_task_begin
|
|
// CHECK-DAG: {{^}}[[WORKER_ID:[0-9]+]]: ompt_event_implicit_task_begin
|
|
|
|
// thread_num must be equal to 1 for both explicit and the implicit tasks
|
|
// CHECK: {{^}}[[WORKER_ID]]: ancestor_level=0 id=1 task_type=ompt_task_explicit
|
|
// CHECK-SAME: thread_num=1
|
|
// CHECK: {{^}}[[WORKER_ID]]: ancestor_level=1 id=0 task_type=ompt_task_implicit
|
|
// CHECK-SAME: thread_num=1
|
|
|
|
return 0;
|
|
}
|