1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
/* StarPU --- Runtime system for heterogeneous multicore architectures.
*
* Copyright (C) 2010 Université de Bordeaux 1
* Copyright (C) 2010, 2011, 2012 Centre National de la Recherche Scientifique
*
* StarPU is free software; you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published by
* the Free Software Foundation; either version 2.1 of the License, or (at
* your option) any later version.
*
* StarPU 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 Lesser General Public License in COPYING.LGPL for more details.
*/
#include <starpu_mpi.h>
#include "helper.h"
#define NITER 2048
unsigned token = 42;
starpu_data_handle_t token_handle;
#ifdef STARPU_USE_CUDA
extern void increment_cuda(void *descr[], __attribute__ ((unused)) void *_args);
#endif
void increment_cpu(void *descr[], __attribute__ ((unused)) void *_args)
{
unsigned *tokenptr = (unsigned *)STARPU_VECTOR_GET_PTR(descr[0]);
(*tokenptr)++;
}
static struct starpu_codelet increment_cl =
{
.where = STARPU_CPU|STARPU_CUDA,
#ifdef STARPU_USE_CUDA
.cuda_funcs = {increment_cuda, NULL},
#endif
.cpu_funcs = {increment_cpu, NULL},
.nbuffers = 1,
.modes = {STARPU_RW}
};
void increment_token(void)
{
struct starpu_task *task = starpu_task_create();
task->cl = &increment_cl;
task->handles[0] = token_handle;
int ret = starpu_task_submit(task);
STARPU_CHECK_RETURN_VALUE(ret, "starpu_task_submit");
}
int main(int argc, char **argv)
{
int ret, rank, size;
#if 0
MPI_Init(NULL, NULL);
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
#endif
ret = starpu_init(NULL);
STARPU_CHECK_RETURN_VALUE(ret, "starpu_init");
ret = starpu_mpi_initialize_extended(&rank, &size);
STARPU_CHECK_RETURN_VALUE(ret, "starpu_mpi_initialize_extended");
if (size < 2)
{
if (rank == 0)
FPRINTF(stderr, "We need at least 2 processes.\n");
MPI_Finalize();
return STARPU_TEST_SKIPPED;
}
starpu_vector_data_register(&token_handle, 0, (uintptr_t)&token, 1, sizeof(unsigned));
unsigned nloops = NITER;
unsigned loop;
unsigned last_loop = nloops - 1;
unsigned last_rank = size - 1;
for (loop = 0; loop < nloops; loop++)
{
int tag = loop*size + rank;
if (loop == 0 && rank == 0)
{
token = 0;
FPRINTF(stdout, "Start with token value %d\n", token);
}
else
{
starpu_mpi_irecv_detached(token_handle, (rank+size-1)%size, tag, MPI_COMM_WORLD, NULL, NULL);
}
increment_token();
if (loop == last_loop && rank == last_rank)
{
starpu_data_acquire(token_handle, STARPU_R);
FPRINTF(stdout, "Finished : token value %d\n", token);
starpu_data_release(token_handle);
}
else
{
starpu_mpi_isend_detached(token_handle, (rank+1)%size, tag+1, MPI_COMM_WORLD, NULL, NULL);
}
}
starpu_task_wait_for_all();
starpu_mpi_shutdown();
starpu_shutdown();
//MPI_Finalize();
if (rank == last_rank)
{
FPRINTF(stderr, "[%d] token = %d == %d * %d ?\n", rank, token, nloops, size);
STARPU_ASSERT(token == nloops*size);
}
return 0;
}
|
