src/gmxlib/thread_mpi/barrier.c

   1 /*
   2 This source code file is part of thread_mpi.
   3 Written by Sander Pronk, Erik Lindahl, and possibly others.
   4
   5 Copyright (c) 2009, Sander Pronk, Erik Lindahl.
   6 All rights reserved.
   7
   8 Redistribution and use in source and binary forms, with or without
   9 modification, are permitted provided that the following conditions are met:
  10 1) Redistributions of source code must retain the above copyright
  11    notice, this list of conditions and the following disclaimer.
  12 2) Redistributions in binary form must reproduce the above copyright
  13    notice, this list of conditions and the following disclaimer in the
  14    documentation and/or other materials provided with the distribution.
  15 3) Neither the name of the copyright holders nor the
  16    names of its contributors may be used to endorse or promote products
  17    derived from this software without specific prior written permission.
  18
  19 THIS SOFTWARE IS PROVIDED BY US ''AS IS'' AND ANY
  20 EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
  21 WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
  22 DISCLAIMED. IN NO EVENT SHALL WE BE LIABLE FOR ANY
  23 DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
  24 (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  25 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
  26 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  27 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  28 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  29
  30 If you want to redistribute modifications, please consider that
  31 scientific software is very special. Version control is crucial -
  32 bugs must be traceable. We will be happy to consider code for
  33 inclusion in the official distribution, but derived work should not
  34 be called official thread_mpi. Details are found in the README & COPYING
  35 files.
  36 */
  37
  38 #ifdef HAVE_TMPI_CONFIG_H
  39 #include "tmpi_config.h"
  40 #endif
  41
  42 #ifdef HAVE_CONFIG_H
  43 #include "config.h"
  44 #endif
  45
  46 #ifdef HAVE_UNISTD_H
  47 #include <unistd.h>
  48 #endif
  49
  50 #include <errno.h>
  51 #include <stdlib.h>
  52 #include <stdio.h>
  53 #include <stdarg.h>
  54 #include <string.h>
  55
  56 #include "impl.h"
  57
  58
  59
  60 void tMPI_Spinlock_barrier_init(tMPI_Spinlock_barrier_t *barrier, int count)
  61 {
  62     barrier->threshold = count;
  63     barrier->cycle     = 0;
  64     tMPI_Atomic_set(&(barrier->count),count);
  65     TMPI_YIELD_WAIT_DATA_INIT(barrier);
  66 }
  67
  68
  69 int tMPI_Spinlock_barrier_wait(tMPI_Spinlock_barrier_t *barrier)
  70 {
  71     int    cycle;
  72     int    status;
  73     /*int    i;*/
  74
  75     /* We don't need to lock or use atomic ops here, since the cycle index
  76      * cannot change until after the last thread has performed the check
  77      * further down. Further, they cannot reach this point in the next
  78      * barrier iteration until all of them have been released, and that
  79      * happens after the cycle value has been updated.
  80      *
  81      * No synchronization == fast synchronization.
  82      */
  83     cycle = barrier->cycle;
  84
  85     /* Decrement the count atomically and check if it is zero.
  86      * This will only be true for the last thread calling us.
  87      */
  88     if( tMPI_Atomic_add_return( &(barrier->count), -1 ) <= 0)
  89     {
  90         tMPI_Atomic_set(&(barrier->count), barrier->threshold);
  91         barrier->cycle = !barrier->cycle;
  92
  93         status = -1;
  94     }
  95     else
  96     {
  97         /* Wait until the last thread changes the cycle index.
  98          * We are both using a memory barrier, and explicit
  99          * volatile pointer cast to make sure the compiler
 100          * doesn't try to be smart and cache the contents.
 101          */
 102         do
 103         {
 104             TMPI_YIELD_WAIT(barrier);
 105             tMPI_Atomic_memory_barrier();
 106         }
 107         while( *(volatile int *)(&(barrier->cycle)) == cycle);
 108
 109         status = 0;
 110     }
 111     return status;
 112 }
 113
 114