关于 c :MPI 发送和接收的通信成本

Communication cost of MPI send and receive

我是 MPI 新手，想测量两个节点之间 MPI_Send 和 MPI_Recv 的通信成本。为此，我编写了以下代码：

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

/*==============================================================
* print_elapsed (prints timing statistics)
*==============================================================*/
void print_elapsed(const char* desc, struct timeval* start, struct timeval* end, int numiterations) {

struct timeval elapsed;
/* calculate elapsed time */
if(start->tv_usec > end->tv_usec) {

end->tv_usec += 1000000;
end->tv_sec--;
}
elapsed.tv_usec = end->tv_usec - start->tv_usec;
elapsed.tv_sec = end->tv_sec - start->tv_sec;

printf("\
%s total elapsed time = %ld (usec)\
",
desc, (elapsed.tv_sec*1000000 + elapsed.tv_usec)/numiterations );
}

int main(int argc, char **argv) {

int nprocs, nElements; /* command line args */

int my_id;

long double* buffer, *rec_buffer;
/* gettimeofday stuff */
struct timeval start, end; /* gettimeofday stuff */
struct timezone tzp;

MPI_Status status; /* Status variable for MPI operations */

MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &my_id); /* Getting the ID for this process */

/*---------------------------------------------------------
* Read Command Line
* - check usage and parse args
*---------------------------------------------------------*/

if(argc < 2) {

if(my_id == 0)
printf("Usage: %s [nElements]\
\
", argv[0]);

MPI_Finalize();
exit(1);
}

nElements = atoi(argv[1]);
int numiterations = 64;
MPI_Comm_size(MPI_COMM_WORLD, &nprocs); /* Get number of processors */

if(my_id == 0)
printf("\
Executing %s: numElements=%d \
",
argv[0], nElements);

buffer = (long double *) malloc(sizeof(long double)*nElements);
rec_buffer = (long double *) malloc(sizeof(long double)*nElements);

if(buffer == NULL) {
printf("Processor %d - unable to malloc()\
", my_id);
MPI_Finalize();
exit(1);
}

MPI_Barrier(MPI_COMM_WORLD);

if(my_id == 1)
gettimeofday(&start, &tzp);

for(int i = 0 ; i < numiterations ; ++i)
{
if(my_id == 0)
MPI_Send(buffer, nElements, MPI_LONG, 1, 0, MPI_COMM_WORLD);

if(my_id == 1)
MPI_Recv(rec_buffer, nElements, MPI_LONG, 0, 0, MPI_COMM_WORLD, &status);
}

if(my_id == 1) {
gettimeofday(&end,&tzp);
}

MPI_Barrier(MPI_COMM_WORLD);
if(my_id == 1) {
print_elapsed("Summation", &start, &end, numiterations);
}

free(buffer);

MPI_Finalize();

return 0;
} /* main() */

我重复发送和接收 numiteration 次，但我没有关于初始化成本和实际通信时间的信息。我想知道是否有更好的方法或工具可以更详细地衡量沟通成本。