libgomp/config/linux/bar.c

/* Copyright (C) 2005-2013 Free Software Foundation, Inc.
   Contributed by Richard Henderson <rth@redhat.com>.

   This file is part of the GNU OpenMP 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 a Linux specific implementation of a barrier synchronization
   mechanism for libgomp.  This type is private to the library.  This 
   implementation uses atomic instructions and the futex syscall.  */

#include <limits.h>
#include "wait.h"


void
gomp_barrier_wait_end (gomp_barrier_t *bar, gomp_barrier_state_t state)
{
  if (__builtin_expect ((state & 1) != 0, 0))
    {
      /* Next time we'll be awaiting TOTAL threads again.  */
      bar->awaited = bar->total;
      __atomic_store_n (&bar->generation, bar->generation + 4,
			MEMMODEL_RELEASE);
      futex_wake ((int *) &bar->generation, INT_MAX);
    }
  else
    {
      do
	do_wait ((int *) &bar->generation, state);
      while (__atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE) == state);
    }
}

void
gomp_barrier_wait (gomp_barrier_t *bar)
{
  gomp_barrier_wait_end (bar, gomp_barrier_wait_start (bar));
}

/* Like gomp_barrier_wait, except that if the encountering thread
   is not the last one to hit the barrier, it returns immediately.
   The intended usage is that a thread which intends to gomp_barrier_destroy
   this barrier calls gomp_barrier_wait, while all other threads
   call gomp_barrier_wait_last.  When gomp_barrier_wait returns,
   the barrier can be safely destroyed.  */

void
gomp_barrier_wait_last (gomp_barrier_t *bar)
{
  gomp_barrier_state_t state = gomp_barrier_wait_start (bar);
  if (state & 1)
    gomp_barrier_wait_end (bar, state);
}

void
gomp_team_barrier_wake (gomp_barrier_t *bar, int count)
{
  futex_wake ((int *) &bar->generation, count == 0 ? INT_MAX : count);
}

void
gomp_team_barrier_wait_end (gomp_barrier_t *bar, gomp_barrier_state_t state)
{
  unsigned int generation, gen;

  if (__builtin_expect ((state & 1) != 0, 0))
    {
      /* Next time we'll be awaiting TOTAL threads again.  */
      struct gomp_thread *thr = gomp_thread ();
      struct gomp_team *team = thr->ts.team;

      bar->awaited = bar->total;
      if (__builtin_expect (team->task_count, 0))
	{
	  gomp_barrier_handle_tasks (state);
	  state &= ~1;
	}
      else
	{
	  __atomic_store_n (&bar->generation, state + 3, MEMMODEL_RELEASE);
	  futex_wake ((int *) &bar->generation, INT_MAX);
	  return;
	}
    }

  generation = state;
  do
    {
      do_wait ((int *) &bar->generation, generation);
      gen = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
      if (__builtin_expect (gen & 1, 0))
	{
	  gomp_barrier_handle_tasks (state);
	  gen = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
	}
      if ((gen & 2) != 0)
	generation |= 2;
    }
  while (gen != state + 4);
}

void
gomp_team_barrier_wait (gomp_barrier_t *bar)
{
  gomp_team_barrier_wait_end (bar, gomp_barrier_wait_start (bar));
}