【发布时间】:2017-10-12 01:22:32
【问题描述】:
我正在尝试使用 1、2、4 或 8 个处理器创建一个带有 MPI 的简单矩阵乘法程序。我的代码适用于 1(在这种情况下,它只进行正常的矩阵乘法,我的意思是,如果你只运行一个等级,就没有工作可以拆分)。它也适用于 2 和 4 处理器。但是,当我尝试使用 8 个处理器(即运行程序时在命令行上使用 -n 8)时,矩阵 c 中的所有位置都没有得到正确的值。
这里是例子:如果SIZE = 8(即a和b和c都是8x8矩阵),得到的矩阵如下:
8.00 8.00 8.00 8.00 8.00 8.00 8.00 8.00
8.00 8.00 8.00 8.00 8.00 8.00 8.00 8.00
8.00 8.00 8.00 8.00 8.00 8.00 8.00 8.00
8.00 8.00 8.00 8.00 8.00 8.00 8.00 8.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
0.00 0.00 16.00 16.00 16.00 16.00 16.00 16.00
如果 SIZE = 16:
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00 16.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
0.00 0.00 0.00 0.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00 32.00
如您所见,左下方会弹出零。 Rank 7 正在做的事情是导致这些坐标变为 0。
我现在一直盯着我的代码死,我觉得我只需要另一双眼睛盯着它们。据我所知,所有的发送和接收都正常工作,所有不同的任务都得到了他们应该得到的价值。根据我所做的测试,实际上没有任何任务将 c 矩阵中的任何位置的值设为 0。我不知道它为什么会发生、如何发生,或者我可以做些什么来修复它。
代码如下:
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
#define SIZE 16 /*assumption: SIZE a multiple of number of nodes*/
#define FROM_MASTER 1/*setting a message type*/
#define FROM_WORKER 2/*setting a message type*/
#define DEBUG 1/*1 = debug on, 0 = debug off*/
MPI_Status status;
static double a[SIZE][SIZE];
static double b[SIZE][SIZE];
static double c[SIZE][SIZE];
static double b_to_trans[SIZE][SIZE];
static void init_matrix(void)
{
int i, j;
for (i = 0; i < SIZE; i++)
{
for (j = 0; j < SIZE; j++) {
a[i][j] = 1.0;
if(i >= SIZE/2) a[i][j] = 2.0;
b_to_trans[i][j] = 1.0;
if(j >= SIZE/2) b[i][j] = 2.0;
// c[i][j] = 1.0;
}
}
}
static void print_matrix(void)
{
int i, j;
for(i = 0; i < SIZE; i++) {
for(j = 0; j < SIZE; j++) {
printf("%7.2f", c[i][j]);
}
printf("\n");
}
}
static void transpose_matrix()
{
int i, j;
for(i = 0; i<SIZE; i++)
for(j = 0; j<SIZE;j++)
b[i][j] = b_to_trans[j][i];
}
int main(int argc, char **argv)
{
int myrank, nproc;
int rows; /*amount of work per node (rows per worker)*/
int mtype; /*message type: send/recv between master and workers*/
int dest, src, offseta, offsetb;
int runthrough, runmod;
double start_time, end_time;
int i, j, k, l;
MPI_Init(&argc, &argv);
MPI_Comm_size(MPI_COMM_WORLD, &nproc);
MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
rows = SIZE/nproc;
mtype = FROM_MASTER;
if (myrank == 0) {
/*Initialization*/
printf("SIZE = %d, number of nodes = %d\n", SIZE, nproc);
init_matrix();
transpose_matrix();
start_time = MPI_Wtime();
if(nproc == 1) { /*In case we only run on one processor, the master will simply do a regular matrix-matrix multiplacation.*/
for(i = 0; i < SIZE; i++) {
for(j = 0; j < SIZE; j++) {
for(k = 0; k < SIZE; k++)
c[i][j] = c[i][j] + a[i][k]*b[j][k];
}
}
end_time = MPI_Wtime();
if(DEBUG) /*Prints the resulting matrix c*/
print_matrix();
printf("Execution time on %2d nodes: %f\n", nproc, end_time-start_time);
}
else {
for(l = 0; l < nproc; l++){
offsetb = rows*l;
offseta = rows;
mtype = FROM_MASTER;
for(dest = 1; dest < nproc; dest++){
MPI_Send(&offseta, 1, MPI_INT, dest, mtype, MPI_COMM_WORLD);
MPI_Send(&offsetb, 1, MPI_INT, dest, mtype, MPI_COMM_WORLD);
MPI_Send(&rows, 1, MPI_INT, dest, mtype, MPI_COMM_WORLD);
MPI_Send(&a[offseta][0], rows*SIZE, MPI_DOUBLE, dest, mtype, MPI_COMM_WORLD);
MPI_Send(&b[offsetb][0], rows*SIZE, MPI_DOUBLE, dest, mtype, MPI_COMM_WORLD);
offseta += rows;
offsetb = (offsetb+rows)%SIZE;
}
offseta = rows;
offsetb = rows*l;
//printf("Rank: %d, offseta: %d, offsetb: %d\n", myrank, offseta, offsetb);
//printf("Offseta: %d\n", offseta);
//printf("Offsetb: %d\n", offsetb);
for(i = 0; i < offseta; i++) {
for(j = offsetb; j < offsetb+rows; j++) {
for(k = 0; k < SIZE; k++){
c[i][j] = c[i][j] + a[i][k]*b[j][k];
}
}
}
mtype = FROM_WORKER;
for(src = 1; src < nproc; src++){
MPI_Recv(&offseta, 1, MPI_INT, src, mtype, MPI_COMM_WORLD, &status);
MPI_Recv(&offsetb, 1, MPI_INT, src, mtype, MPI_COMM_WORLD, &status);
MPI_Recv(&rows, 1, MPI_INT, src, mtype, MPI_COMM_WORLD, &status);
for(i = 0; i < rows; i++) {
MPI_Recv(&c[offseta+i][offsetb], offseta, MPI_DOUBLE, src, mtype, MPI_COMM_WORLD, &status); /*returns answer c(1,1)*/
}
}
}
end_time = MPI_Wtime();
if(DEBUG) /*Prints the resulting matrix c*/
print_matrix();
printf("Execution time on %2d nodes: %f\n", nproc, end_time-start_time);
}
}
else{
if(nproc > 1) {
for(l = 0; l < nproc; l++){
mtype = FROM_MASTER;
MPI_Recv(&offseta, 1, MPI_INT, 0, mtype, MPI_COMM_WORLD, &status);
MPI_Recv(&offsetb, 1, MPI_INT, 0, mtype, MPI_COMM_WORLD, &status);
MPI_Recv(&rows, 1, MPI_INT, 0, mtype, MPI_COMM_WORLD, &status);
MPI_Recv(&a[offseta][0], rows*SIZE, MPI_DOUBLE, 0, mtype, MPI_COMM_WORLD, &status);
MPI_Recv(&b[offsetb][0], rows*SIZE, MPI_DOUBLE, 0, mtype, MPI_COMM_WORLD, &status);
for(i = offseta; i < offseta+rows; i++) {
for(j = offsetb; j < offsetb+rows; j++) {
for(k = 0; k < SIZE; k++){
c[i][j] = c[i][j] + a[i][k]*b[j][k];
}
}
}
mtype = FROM_WORKER;
MPI_Send(&offseta, 1, MPI_INT, 0, mtype, MPI_COMM_WORLD);
MPI_Send(&offsetb, 1, MPI_INT, 0, mtype, MPI_COMM_WORLD);
MPI_Send(&rows, 1, MPI_INT, 0, mtype, MPI_COMM_WORLD);
for(i = 0; i < rows; i++){
MPI_Send(&c[offseta+i][offsetb], offseta, MPI_DOUBLE, 0, mtype, MPI_COMM_WORLD);
}
}
}
}
MPI_Finalize();
return 0;
}
任何建议都会有所帮助,在此先感谢您。
【问题讨论】:
-
詹斯,你也应该在这里添加你的代码,而不是把它放在 pastebin 上(我现在会为你做),这样你就不会得到封闭的投票
-
我不知道人们是否愿意将整个代码放在此处,或者他们是否会抱怨它会淹没页面。但无论哪种方式都非常感谢您。
-
嗨 Jens,好吧,所以我查看了您的代码,mpirun 肯定会产生问题,我将使用 cmets 重做一个矩阵乘法解决方案,而不是调试您的,(这是您的左下角没有整理)
-
我已经设法解决了这个问题,但是非常欢迎你试一试,如果没有别的办法,只能分享一个替代解决方案^^
标签: c mpi matrix-multiplication