C++ 使用MPI_发送和MPI_接收而不是MPI_收集
我想比较MPI_Send和MPI_recv与MPI_Gather的性能差异;因此,我试图在没有MPI_聚集的情况下从这段代码中得到答案,但问题是root的缓冲区似乎没有更新。代码是:C++ 使用MPI_发送和MPI_接收而不是MPI_收集,c++,performance,parallel-processing,mpi,hpc,C++,Performance,Parallel Processing,Mpi,Hpc,我想比较MPI_Send和MPI_recv与MPI_Gather的性能差异;因此,我试图在没有MPI_聚集的情况下从这段代码中得到答案,但问题是root的缓冲区似乎没有更新。代码是: #include <fstream> #include <iostream> #include <vector> #include <string> #include "mpi.h" using namespace std; const int N
#include <fstream>
#include <iostream>
#include <vector>
#include <string>
#include "mpi.h"
using namespace std;
const int N = 2;
int main() {
MPI_Init(NULL, NULL);
int rank;
int size;
int root = 0;
vector<int> x(N);
vector<int> receive_data(N);
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
const int leng = size * N;
vector<int> single_arr(leng);
for (int i = 0; i < N;i++) {
x[i] = rank + i;
}
if (rank == 0) {
for (int i = 0; i < N; i++) {
single_arr[i] = x[i];
}
}
if (rank != root) {
MPI_Send(x.data(), N, MPI_INT, 0, 0, MPI_COMM_WORLD);
}
if (rank == root) {
for (int i = 1; i < size; i++) {
MPI_Recv(single_arr.data(), N, MPI_INT, rank + i, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
}
}
if (rank == root) {
for (int i = 0; i < single_arr.size();i++) {
cout << i << "\t" << single_arr[i] << endl;
}
}
MPI_Finalize();
}
但是,我想要这个:
0 0
1 1
2 1
3 2
4 2
5 3
6 3
7 4
有没有办法做到这一点?问题在于:
if (rank != root) {
MPI_Send(x.data(), N, MPI_INT, 0, 0, MPI_COMM_WORLD);
}
每个进程将向进程发送x
数组的N个元素=0
然后处理0:
if (rank == root) {
for (int i = 1; i < size; i++) {
MPI_Recv(single_arr.data(), N, MPI_INT, rank + i, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
}
}
打印最后一个进程(即3和4)的值,后跟零
要修复它,您必须执行以下操作:
if (rank == root) {
for (int i = 1; i < size; i++) {
MPI_Recv(&(single_arr.data()[N * i]), N, MPI_INT, rank + i, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
}
}
if(秩==根){
对于(int i=1;i
从位置[N*i]
到[N*i+N]
if (rank == root) {
for (int i = 0; i < single_arr.size();i++) {
cout << i << "\t" << single_arr[i] << endl;
}
}
if (rank == root) {
for (int i = 1; i < size; i++) {
MPI_Recv(&(single_arr.data()[N * i]), N, MPI_INT, rank + i, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
}
}