是的,可以根據MPI standard一次執行多個非阻塞集體操作。特別是在第197頁的5.12節中。非阻塞共同操作:
多個非阻塞共同操作可以在優秀的單一傳播者。如果非阻塞調用導致某些系統資源耗盡,那麼它將失敗並生成MPI異常。 MPI的質量實施應確保 僅在病理情況下才會發生。 也就是說,一個MPI實現應該能夠支持大量未決的非阻塞操作,即 。
儘管如此,確保不同request
被用於連續調用MPI_Iscatterv()
。函數MPI_Waitall()
對於檢查多個非阻塞操作的完成很有用。
MPI_Request requests[2];
MPI_Iscatterv(...,&requests[0]);
MPI_Iscatterv(...,&requests[1]);
MPI_Waitall(2,requests,...);
一個示例代碼展示它是如何做:
#include <stdio.h>
#include <stdlib.h>
#include "mpi.h"
#include <math.h>
int main(int argc, char *argv[]) {
MPI_Request requests[42];
MPI_Init(&argc,&argv);
int size,rank;
MPI_Comm_size(MPI_COMM_WORLD,&size);
MPI_Comm_rank(MPI_COMM_WORLD,&rank);
int version,subversion;
MPI_Get_version(&version, &subversion);
if(rank==0){printf("MPI version %d.%d\n",version,subversion);}
//dimensions
int nbscatter=5;
int nlocal=2;
double* array=NULL;
int i,j,k;
//build a 2D array of nbscatter lines and nlocal*size columns on root process
if(rank==0){
array=malloc(nlocal*nbscatter*size*sizeof(double));
if(array==NULL){printf("malloc failure\n");}
for(i=0;i<nbscatter;i++){
for(j=0;j<size*nlocal;j++){
array[i*size*nlocal+j]=j+0.01*i;
printf("%lf ",array[i*size*nlocal+j]);
}
printf("\n");
}
}
//on each process, a 2D array of nbscatter lines and nlocal columns
double* arrayloc=malloc(nlocal*nbscatter*sizeof(double));
if(arrayloc==NULL){printf("malloc failure2\n");}
//counts and displacements
int* displs;
int* scounts;
displs = malloc(nbscatter*size*sizeof(int));
if(displs==NULL){printf("malloc failure\n");}
scounts = malloc(nbscatter*size*sizeof(int));
if(scounts==NULL){printf("malloc failure\n");}
for(i=0;i<nbscatter;i++){
for(j=0;j<size;j++){
displs[i*size+j]=j*nlocal;
scounts[i*size+j]=nlocal;
}
// scatter the lines
if(rank==0){
MPI_Iscatterv(&array[i*nlocal*size], &scounts[i*size], &displs[i*size],MPI_DOUBLE,&arrayloc[i*nlocal], nlocal,MPI_DOUBLE, 0, MPI_COMM_WORLD, &requests[i]);
}else{
MPI_Iscatterv(NULL, &scounts[i*size], &displs[i*size],MPI_DOUBLE,&arrayloc[i*nlocal], nlocal,MPI_DOUBLE, 0, MPI_COMM_WORLD, &requests[i]);
}
}
MPI_Status status[nbscatter];
if(MPI_Waitall(nbscatter,requests,status)!=MPI_SUCCESS){
printf("MPI_Waitall() failed\n");
}
if(rank==0){
free(array);
}
free(displs);
free(scounts);
//print the local array, containing the scattered columns
for(k=0;k<size;k++){
if(rank==k){
printf("on rank %d\n",k);
for(i=0;i<nbscatter;i++){
for(j=0;j<nlocal;j++){
printf("%lf ",arrayloc[i*nlocal+j]);
}
printf("\n");
}
}
MPI_Barrier(MPI_COMM_WORLD);
}
free(arrayloc);
MPI_Finalize();
return 0;
}
要通過mpicc main.c -o main -Wall
編譯和mpirun -np 4 main
跑