MPI.在功能上运行mpi

Question

我想用mpi运行一些函数,main但我不知道它应该如何.看起来像:

#define MAXSIZE 100
int main (int argc, char **argv) {
  int i;
  float matrixA[MAXSIZE][MAXSIZE], matrixB[MAXSIZE][MAXSIZE], matrixC[MAXSIZE][MAXSIZE];
  for(i=0;i<10;i++){
    multiply(matrixA, matrixB, matrixC);
  }
}
void multiply(float matrixA[MAXSIZE][MAXSIZE], float matrixB[MAXSIZE][MAXSIZE], float matrixC[MAXSIZE][MAXSIZE]) {
  int rank; //process rank
  int size; //number of processes
  MPI_Init(&argc, &argv); //initialize MPI operations
  MPI_Comm_rank(MPI_COMM_WORLD, &rank); //get the rank
  MPI_Comm_size(MPI_COMM_WORLD, &size); //get number of processes

  ...someoperation...
  MPI_Finalize();
}

我知道如何在不使用其他功能的情况下运行基本MPI,但我需要这种结构.

Answer 1

在应用程序实例中,MPI最多可以初始化一次.所以你提供的代码结构不起作用.

您的程序的正确结构如下:

#define MAXSIZE 100
int main (int argc, char **argv) {
  int i;
  float matrixA[MAXSIZE][MAXSIZE], matrixB[MAXSIZE][MAXSIZE], matrixC[MAXSIZE][MAXSIZE];
  int rank; //process rank
  int size; //number of processes
  MPI_Init(&argc, &argv); //initialize MPI operations
  MPI_Comm_rank(MPI_COMM_WORLD, &rank); //get the rank
  MPI_Comm_size(MPI_COMM_WORLD, &size); //get number of processes
  for(i=0;i<10;i++){
    multiply(matrixA, matrixB, matrixC);
  }
  MPI_Finalize();
}
void multiply(float matrixA[MAXSIZE][MAXSIZE], float matrixB[MAXSIZE][MAXSIZE], float matrixC[MAXSIZE][MAXSIZE]) {    
  ...someoperation...
}