07dd3bcda1
OpenMP 5.1 adds env vars and functions to set and query new ICVs used
as fallback if thread_limit or num_teams clauses aren't specified on
teams construct.
The following patch implements those, though further work will be needed:
1) OpenMP 5.1 also changed the num_teams clause, so that it can specify
both lower and upper limit for how many teams should be created and
changed the meaning when only one expression is provided, instead of
num_teams(expr) in 5.0 meaning num_teams(1:expr) in 5.1, it now means
num_teams(expr:expr), i.e. while previously we could create 1 to expr
teams, in 5.1 we have some low limit by default equal to the single
expression provided and may not create fewer teams.
For host teams (which we don't currently implement efficiently for
NUMA hosts) we trivially satisfy it now by always honoring what the
user asked for, but for the offloading teams I think we'll need to
rethink the APIs; currently teams construct is just a call that returns
and possibly lowers the number of teams; and whenever possible we try
to evaluate num_teams/thread_limit already on the target construct
and the GOMP_teams call just sets the number of teams to the minimum
of provided and requested teams; for some cases e.g. where target
is not combined with teams and num_teams expression calls some functions
etc., we need to call those functions in the target region and so it is
late to figure number of teams, but also hw could just limit what it
is willing to create; in that case I'm afraid we need to run the target
body multiple times and arrange for omp_get_team_num () returning the
right values
2) we need to finally implement the NUMA handling for GOMP_teams_reg
3) I now realize I haven't added some testcase coverage, will do that
incrementally
4) libgomp.texi needs updates for these new APIs, but also others like
the allocator
2021-10-11 Jakub Jelinek <jakub@redhat.com>
gcc/
* omp-low.c (omp_runtime_api_call): Handle omp_get_max_teams,
omp_[sg]et_teams_thread_limit and omp_set_num_teams.
libgomp/
* omp.h.in (omp_set_num_teams, omp_get_max_teams,
omp_set_teams_thread_limit, omp_get_teams_thread_limit): Declare.
* omp_lib.f90.in (omp_set_num_teams, omp_get_max_teams,
omp_set_teams_thread_limit, omp_get_teams_thread_limit): Declare.
* omp_lib.h.in (omp_set_num_teams, omp_get_max_teams,
omp_set_teams_thread_limit, omp_get_teams_thread_limit): Declare.
* libgomp.h (gomp_nteams_var, gomp_teams_thread_limit_var): Declare.
* libgomp.map (OMP_5.1): Export omp_get_max_teams{,_},
omp_get_teams_thread_limit{,_}, omp_set_num_teams{,_,_8_} and
omp_set_teams_thread_limit{,_,_8_}.
* icv.c (omp_set_num_teams, omp_get_max_teams,
omp_set_teams_thread_limit, omp_get_teams_thread_limit): New
functions.
* env.c (gomp_nteams_var, gomp_teams_thread_limit_var): Define.
(omp_display_env): Print OMP_NUM_TEAMS and OMP_TEAMS_THREAD_LIMIT.
(initialize_env): Handle OMP_NUM_TEAMS and OMP_TEAMS_THREAD_LIMIT env
vars.
* teams.c (GOMP_teams_reg): If thread_limit is not specified, use
gomp_teams_thread_limit_var as fallback if not zero. If num_teams
is not specified, use gomp_nteams_var.
* fortran.c (omp_set_num_teams, omp_get_max_teams,
omp_set_teams_thread_limit, omp_get_teams_thread_limit): Add
ialias_redirect.
(omp_set_num_teams_, omp_set_num_teams_8_, omp_get_max_teams_,
omp_set_teams_thread_limit_, omp_set_teams_thread_limit_8_,
omp_get_teams_thread_limit_): New functions.
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>
|
|
|
|
static unsigned gomp_num_teams = 1, gomp_team_num = 0;
|
|
|
|
void
|
|
GOMP_teams_reg (void (*fn) (void *), void *data, unsigned int num_teams,
|
|
unsigned int thread_limit, unsigned int flags)
|
|
{
|
|
(void) flags;
|
|
(void) num_teams;
|
|
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;
|
|
gomp_num_teams = num_teams;
|
|
for (gomp_team_num = 0; gomp_team_num < num_teams; gomp_team_num++)
|
|
fn (data);
|
|
gomp_num_teams = 1;
|
|
gomp_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)
|
|
{
|
|
return gomp_num_teams;
|
|
}
|
|
|
|
int
|
|
omp_get_team_num (void)
|
|
{
|
|
return gomp_team_num;
|
|
}
|
|
|
|
ialias (omp_get_num_teams)
|
|
ialias (omp_get_team_num)
|