fa4fcb111a
When thinking about GOMP_teams3, I've realized that using global variables for the values returned by omp_get_num_teams()/omp_get_team_num() calls is incorrect even with our right now dumb way of implementing host teams. The problems are two, one is if host teams is used from multiple pthread_create created threads - the spec says that host teams can't be nested inside of explicit parallel or other teams constructs, but with pthread_create the standard says obviously nothing about it. Another more important thing is host fallback, right now we don't do anything for omp_get_num_teams() or omp_get_team_num() which was fine before host teams was introduced and the 5.1 requirement that num_teams clause specifies minimum of teams, but with the global vars it means inside of target teams num_teams (2) we happily return omp_get_num_teams() == 4 if the target teams is inside of host teams with num_teams(4). With target fallback being invoked from parallel regions global vars simply can't work right on the host. So, this patch moves them to struct gomp_thread and propagates those for parallel to child threads. For host fallback, the implicit zeroing of *thr results in us returning omp_get_num_teams () == 1 and omp_get_team_num () == 0 which is fine for target teams without num_teams clause, for target teams with num_teams clause something to work on and for target without teams nested in it I've asked on omp-lang what should be done. 2021-11-11 Jakub Jelinek <jakub@redhat.com> * libgomp.h (struct gomp_thread): Add num_teams and team_num members. * team.c (struct gomp_thread_start_data): Likewise. (gomp_thread_start): Initialize thr->num_teams and thr->team_num. (gomp_team_start): Initialize start_data->num_teams and start_data->team_num. Update nthr->num_teams and nthr->team_num. * teams.c (gomp_num_teams, gomp_team_num): Remove. (GOMP_teams_reg): Set and restore thr->num_teams and thr->team_num instead of gomp_num_teams and gomp_team_num. (omp_get_num_teams): Use thr->num_teams + 1 instead of gomp_num_teams. (omp_get_team_num): Use thr->team_num instead of gomp_team_num. * testsuite/libgomp.c/teams-4.c: New test.
77 lines
2.3 KiB
C
77 lines
2.3 KiB
C
/* Copyright (C) 2018-2021 Free Software Foundation, Inc.
|
|
Contributed by Jakub Jelinek <jakub@redhat.com>.
|
|
|
|
This file is part of the GNU Offloading and Multi Processing Library
|
|
(libgomp).
|
|
|
|
Libgomp is free software; you can redistribute it and/or modify it
|
|
under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; either version 3, or (at your option)
|
|
any later version.
|
|
|
|
Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY
|
|
WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
|
|
FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
more details.
|
|
|
|
Under Section 7 of GPL version 3, you are granted additional
|
|
permissions described in the GCC Runtime Library Exception, version
|
|
3.1, as published by the Free Software Foundation.
|
|
|
|
You should have received a copy of the GNU General Public License and
|
|
a copy of the GCC Runtime Library Exception along with this program;
|
|
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
/* This file handles the host TEAMS construct. */
|
|
|
|
#include "libgomp.h"
|
|
#include <limits.h>
|
|
|
|
void
|
|
GOMP_teams_reg (void (*fn) (void *), void *data, unsigned int num_teams,
|
|
unsigned int thread_limit, unsigned int flags)
|
|
{
|
|
struct gomp_thread *thr = gomp_thread ();
|
|
(void) flags;
|
|
unsigned old_thread_limit_var = 0;
|
|
if (thread_limit == 0)
|
|
thread_limit = gomp_teams_thread_limit_var;
|
|
if (thread_limit)
|
|
{
|
|
struct gomp_task_icv *icv = gomp_icv (true);
|
|
old_thread_limit_var = icv->thread_limit_var;
|
|
icv->thread_limit_var
|
|
= thread_limit > INT_MAX ? UINT_MAX : thread_limit;
|
|
}
|
|
if (num_teams == 0)
|
|
num_teams = gomp_nteams_var ? gomp_nteams_var : 3;
|
|
thr->num_teams = num_teams - 1;
|
|
for (thr->team_num = 0; thr->team_num < num_teams; thr->team_num++)
|
|
fn (data);
|
|
thr->num_teams = 0;
|
|
thr->team_num = 0;
|
|
if (thread_limit)
|
|
{
|
|
struct gomp_task_icv *icv = gomp_icv (true);
|
|
icv->thread_limit_var = old_thread_limit_var;
|
|
}
|
|
}
|
|
|
|
int
|
|
omp_get_num_teams (void)
|
|
{
|
|
struct gomp_thread *thr = gomp_thread ();
|
|
return thr->num_teams + 1;
|
|
}
|
|
|
|
int
|
|
omp_get_team_num (void)
|
|
{
|
|
struct gomp_thread *thr = gomp_thread ();
|
|
return thr->team_num;
|
|
}
|
|
|
|
ialias (omp_get_num_teams)
|
|
ialias (omp_get_team_num)
|