6103184e81
* Makefile.am (libgomp_la_SOURCES): Add atomic.c, icv.c, icv-device.c. * Makefile.in. Regenerate. * configure.ac [nvptx*-*-*] (libgomp_use_pthreads): Set and use it... (LIBGOMP_USE_PTHREADS): ...here; new define. * configure: Regenerate. * config.h.in: Likewise. * config/posix/affinity.c: Move to... * affinity.c: ...here (new file). Guard use of Pthreads-specific interface by LIBGOMP_USE_PTHREADS. * critical.c: Split out GOMP_atomic_{start,end} into... * atomic.c: ...here (new file). * env.c: Split out ICV definitions into... * icv.c: ...here (new file) and... * icv-device.c: ...here. New file. * config/linux/lock.c (gomp_init_lock_30): Move to generic lock.c. (gomp_destroy_lock_30): Ditto. (gomp_set_lock_30): Ditto. (gomp_unset_lock_30): Ditto. (gomp_test_lock_30): Ditto. (gomp_init_nest_lock_30): Ditto. (gomp_destroy_nest_lock_30): Ditto. (gomp_set_nest_lock_30): Ditto. (gomp_unset_nest_lock_30): Ditto. (gomp_test_nest_lock_30): Ditto. * lock.c: New. * config/nvptx/lock.c: New. * config/nvptx/bar.c: New. * config/nvptx/bar.h: New. * config/nvptx/doacross.h: New. * config/nvptx/error.c: New. * config/nvptx/icv-device.c: New. * config/nvptx/mutex.h: New. * config/nvptx/pool.h: New. * config/nvptx/proc.c: New. * config/nvptx/ptrlock.h: New. * config/nvptx/sem.h: New. * config/nvptx/simple-bar.h: New. * config/nvptx/target.c: New. * config/nvptx/task.c: New. * config/nvptx/team.c: New. * config/nvptx/time.c: New. * config/posix/simple-bar.h: New. * libgomp.h: Guard pthread.h inclusion. Include simple-bar.h. (gomp_num_teams_var): Declare. (struct gomp_thread_pool): Change threads_dock member to gomp_simple_barrier_t. [__nvptx__] (gomp_thread): New implementation. (gomp_thread_attr): Guard by LIBGOMP_USE_PTHREADS. (gomp_thread_destructor): Ditto. (gomp_init_thread_affinity): Ditto. * team.c: Guard uses of Pthreads-specific interfaces by LIBGOMP_USE_PTHREADS. Adjust all uses of threads_dock. (gomp_free_thread) [__nvptx__]: Do not call 'free'. * config/nvptx/alloc.c: Delete. * config/nvptx/barrier.c: Ditto. * config/nvptx/fortran.c: Ditto. * config/nvptx/iter.c: Ditto. * config/nvptx/iter_ull.c: Ditto. * config/nvptx/loop.c: Ditto. * config/nvptx/loop_ull.c: Ditto. * config/nvptx/ordered.c: Ditto. * config/nvptx/parallel.c: Ditto. * config/nvptx/priority_queue.c: Ditto. * config/nvptx/sections.c: Ditto. * config/nvptx/single.c: Ditto. * config/nvptx/splay-tree.c: Ditto. * config/nvptx/work.c: Ditto. * testsuite/libgomp.fortran/fortran.exp (lang_link_flags): Pass -foffload=-lgfortran in addition to -lgfortran. * testsuite/libgomp.oacc-fortran/fortran.exp (lang_link_flags): Ditto. * plugin/plugin-nvptx.c: Include <limits.h>. (struct targ_fn_descriptor): Add new fields. (struct ptx_device): Ditto. Set them... (nvptx_open_device): ...here. (nvptx_adjust_launch_bounds): New. (nvptx_host2dev): Allow NULL 'nvthd'. (nvptx_dev2host): Ditto. (GOMP_OFFLOAD_get_caps): Add GOMP_OFFLOAD_CAP_OPENMP_400. (link_ptx): Adjust log sizes. (nvptx_host2dev): Allow NULL 'nvthd'. (nvptx_dev2host): Ditto. (nvptx_set_clocktick): New. Use it... (GOMP_OFFLOAD_load_image): ...here. Set new targ_fn_descriptor fields. (GOMP_OFFLOAD_dev2dev): New. (nvptx_adjust_launch_bounds): New. (nvptx_stacks_size): New. (nvptx_stacks_alloc): New. (nvptx_stacks_free): New. (GOMP_OFFLOAD_run): New. (GOMP_OFFLOAD_async_run): New (stub). Co-Authored-By: Dmitry Melnik <dm@ispras.ru> Co-Authored-By: Jakub Jelinek <jakub@redhat.com> From-SVN: r242789
167 lines
5.3 KiB
C
167 lines
5.3 KiB
C
/* Copyright (C) 2015-2016 Free Software Foundation, Inc.
|
|
Contributed by Alexander Monakov <amonakov@ispras.ru>
|
|
|
|
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 is an NVPTX specific implementation of a barrier synchronization
|
|
mechanism for libgomp. This type is private to the library. This
|
|
implementation uses atomic instructions and bar.sync instruction. */
|
|
|
|
#ifndef GOMP_BARRIER_H
|
|
#define GOMP_BARRIER_H 1
|
|
|
|
#include "mutex.h"
|
|
|
|
typedef struct
|
|
{
|
|
unsigned total;
|
|
unsigned generation;
|
|
unsigned awaited;
|
|
unsigned awaited_final;
|
|
} gomp_barrier_t;
|
|
|
|
typedef unsigned int gomp_barrier_state_t;
|
|
|
|
/* The generation field contains a counter in the high bits, with a few
|
|
low bits dedicated to flags. Note that TASK_PENDING and WAS_LAST can
|
|
share space because WAS_LAST is never stored back to generation. */
|
|
#define BAR_TASK_PENDING 1
|
|
#define BAR_WAS_LAST 1
|
|
#define BAR_WAITING_FOR_TASK 2
|
|
#define BAR_CANCELLED 4
|
|
#define BAR_INCR 8
|
|
|
|
static inline void gomp_barrier_init (gomp_barrier_t *bar, unsigned count)
|
|
{
|
|
bar->total = count;
|
|
bar->awaited = count;
|
|
bar->awaited_final = count;
|
|
bar->generation = 0;
|
|
}
|
|
|
|
static inline void gomp_barrier_reinit (gomp_barrier_t *bar, unsigned count)
|
|
{
|
|
__atomic_add_fetch (&bar->awaited, count - bar->total, MEMMODEL_ACQ_REL);
|
|
bar->total = count;
|
|
}
|
|
|
|
static inline void gomp_barrier_destroy (gomp_barrier_t *bar)
|
|
{
|
|
}
|
|
|
|
extern void gomp_barrier_wait (gomp_barrier_t *);
|
|
extern void gomp_barrier_wait_last (gomp_barrier_t *);
|
|
extern void gomp_barrier_wait_end (gomp_barrier_t *, gomp_barrier_state_t);
|
|
extern void gomp_team_barrier_wait (gomp_barrier_t *);
|
|
extern void gomp_team_barrier_wait_final (gomp_barrier_t *);
|
|
extern void gomp_team_barrier_wait_end (gomp_barrier_t *,
|
|
gomp_barrier_state_t);
|
|
extern bool gomp_team_barrier_wait_cancel (gomp_barrier_t *);
|
|
extern bool gomp_team_barrier_wait_cancel_end (gomp_barrier_t *,
|
|
gomp_barrier_state_t);
|
|
extern void gomp_team_barrier_wake (gomp_barrier_t *, int);
|
|
struct gomp_team;
|
|
extern void gomp_team_barrier_cancel (struct gomp_team *);
|
|
|
|
static inline gomp_barrier_state_t
|
|
gomp_barrier_wait_start (gomp_barrier_t *bar)
|
|
{
|
|
unsigned int ret = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
|
|
ret &= -BAR_INCR | BAR_CANCELLED;
|
|
/* A memory barrier is needed before exiting from the various forms
|
|
of gomp_barrier_wait, to satisfy OpenMP API version 3.1 section
|
|
2.8.6 flush Construct, which says there is an implicit flush during
|
|
a barrier region. This is a convenient place to add the barrier,
|
|
so we use MEMMODEL_ACQ_REL here rather than MEMMODEL_ACQUIRE. */
|
|
if (__atomic_add_fetch (&bar->awaited, -1, MEMMODEL_ACQ_REL) == 0)
|
|
ret |= BAR_WAS_LAST;
|
|
return ret;
|
|
}
|
|
|
|
static inline gomp_barrier_state_t
|
|
gomp_barrier_wait_cancel_start (gomp_barrier_t *bar)
|
|
{
|
|
return gomp_barrier_wait_start (bar);
|
|
}
|
|
|
|
/* This is like gomp_barrier_wait_start, except it decrements
|
|
bar->awaited_final rather than bar->awaited and should be used
|
|
for the gomp_team_end barrier only. */
|
|
static inline gomp_barrier_state_t
|
|
gomp_barrier_wait_final_start (gomp_barrier_t *bar)
|
|
{
|
|
unsigned int ret = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
|
|
ret &= -BAR_INCR | BAR_CANCELLED;
|
|
/* See above gomp_barrier_wait_start comment. */
|
|
if (__atomic_add_fetch (&bar->awaited_final, -1, MEMMODEL_ACQ_REL) == 0)
|
|
ret |= BAR_WAS_LAST;
|
|
return ret;
|
|
}
|
|
|
|
static inline bool
|
|
gomp_barrier_last_thread (gomp_barrier_state_t state)
|
|
{
|
|
return state & BAR_WAS_LAST;
|
|
}
|
|
|
|
/* All the inlines below must be called with team->task_lock
|
|
held. */
|
|
|
|
static inline void
|
|
gomp_team_barrier_set_task_pending (gomp_barrier_t *bar)
|
|
{
|
|
bar->generation |= BAR_TASK_PENDING;
|
|
}
|
|
|
|
static inline void
|
|
gomp_team_barrier_clear_task_pending (gomp_barrier_t *bar)
|
|
{
|
|
bar->generation &= ~BAR_TASK_PENDING;
|
|
}
|
|
|
|
static inline void
|
|
gomp_team_barrier_set_waiting_for_tasks (gomp_barrier_t *bar)
|
|
{
|
|
bar->generation |= BAR_WAITING_FOR_TASK;
|
|
}
|
|
|
|
static inline bool
|
|
gomp_team_barrier_waiting_for_tasks (gomp_barrier_t *bar)
|
|
{
|
|
return (bar->generation & BAR_WAITING_FOR_TASK) != 0;
|
|
}
|
|
|
|
static inline bool
|
|
gomp_team_barrier_cancelled (gomp_barrier_t *bar)
|
|
{
|
|
return __builtin_expect ((bar->generation & BAR_CANCELLED) != 0, 0);
|
|
}
|
|
|
|
static inline void
|
|
gomp_team_barrier_done (gomp_barrier_t *bar, gomp_barrier_state_t state)
|
|
{
|
|
bar->generation = (state & -BAR_INCR) + BAR_INCR;
|
|
}
|
|
|
|
#endif /* GOMP_BARRIER_H */
|