Question

此代码采样器用于学习MPI编程。我使用的MPI包是MPICH2 1.3.1。以下代码是我学习MPI_Isend()，MPI_Irecv()和MPI_Wait()的第一步。代码有一个主人和几个工人。 Master在工作人员向master发送数据时从工作人员接收数据。像往常一样，数据大小非常大，工作人员将数据分成中继并按顺序发送中继。发送中继时，我使用一些技巧来重叠计算和通信。该方法非常简单，只需保留两个缓冲区即可为每个发送周期保留两个中继。

int test_mpi_wait_2(int argc, char* argv[])
{
    int rank;
    int numprocs; 

    MPI_Init(&argc,&argv);
    MPI_Comm_size(MPI_COMM_WORLD,&numprocs);
    MPI_Comm_rank(MPI_COMM_WORLD,&rank);

    int trunk_num = 6;// assume there are six trunks
    int trunk_size = 10000;// assume each trunk has 10,000 data points
    if(rank == 0)
    {
        //allocate receiving buffer for all workers
        int** recv_buf = new int* [numprocs];
        for(int i=0;i<numprocs;i++)
            recv_buf[i] = new int [trunk_size];

        //collecting first trunk from all workers
        MPI_Request* requests = new MPI_Request[numprocs];
        for(int i=1;i<numprocs;i++)
            MPI_Irecv(recv_buf[i], trunk_size, MPI_INT, i, 0, MPI_COMM_WORLD, &requests[i]);

        //define send_buf counter used to record how many trunks have been collected
        vector<int> counter(numprocs);

        MPI_Status status;
        //assume therer are N-1 workers, then the total trunks will be collected is (N-1)*trunk_num
        for(int i=0;i<(numprocs-1)*trunk_num;i++)
        {         
            //wait until receive one trunk from any worker
            int active_index;
            MPI_Waitany(numprocs-1, requests+1, &active_index, &status);      

            int request_index = active_index + 1;
            int procs_index = active_index + 1;

            //check wheather all trunks from this worker have been collected
            if(++counter[procs_index] != trunk_num)
            {    
                //receive next trunk from this worker
                MPI_Irecv(recv_buf[procs_index], trunk_size, MPI_INT, procs_index, 0, MPI_COMM_WORLD, &requests[request_index]);
            }   
        }

        for(int i=0;i<numprocs;i++)
            delete [] recv_buf[i];
        delete [] recv_buf;
        delete [] requests;

        cout<<rank<<" done"<<endl;
    }
    else
    {  
        //for each worker, the worker first fill one trunk and send it to master
        //for efficiency, the computation of trunk and communication to master is overlapped.
        //two buffers are allocated to implement the overlapped computation

        int* send_buf[2];  
        send_buf[0] = new int [trunk_size];//Buffer A
        send_buf[1] = new int [trunk_size];//Buffer B

        MPI_Request requests[2];

        //file first trunk
        for(int i=0;i<trunk_size;i++)
            send_buf[0][i] = 0;
        //send this trunk
        MPI_Isend(send_buf[0], trunk_size, MPI_INT, 0, 0, MPI_COMM_WORLD, &requests[0]);

        if(trunk_num > 1)
        {
            //file second trunk
            for(int i=0;i<trunk_size;i++)
            send_buf[1][i] = i;
            //send this trunk
            MPI_Isend(send_buf[1], trunk_size, MPI_INT, 0, 0, MPI_COMM_WORLD, &requests[1]);
        }

        //for remained trunks, keep cycle until all trunks are sent
        for(int i=2;i<trunk_num;i+=2)
        {      
            //wait till trunk data at buffer A is sent
            MPI_Wait(&requests[0], MPI_STATUS_IGNORE);

            //fill buffer A with next trunk data
            for(int j=0;j<trunk_size;j++)
                send_buf[0][j] = j * i;

            //send buffer A
            MPI_Isend(send_buf[0], trunk_size, MPI_INT, 0, 0, MPI_COMM_WORLD, &requests[0]);

            //if more trunks are remained, fill buffer B and sent it
            if(i+ 1 < trunk_num)
            {
                MPI_Wait(&requests[1], MPI_STATUS_IGNORE);
                for(int j=0;j<trunk_size;j++)
                    send_buf[1][j] = j * (i + 1);
                MPI_Isend(send_buf[1], trunk_size, MPI_INT, 0, 0, MPI_COMM_WORLD, &requests[1]);
            }
        }

        //wait until last two trunks have been sent
        if(trunk_num == 1)
        {
            MPI_Wait(&requests[0], MPI_STATUS_IGNORE);
        }
        else
        {   
            MPI_Wait(&requests[0], MPI_STATUS_IGNORE);
            MPI_Wait(&requests[1], MPI_STATUS_IGNORE);       
        }

        delete [] send_buf[0];
        delete [] send_buf[1];

        cout<<rank<<" done"<<endl;
    }

    MPI_Finalize();

    return 0;
}

Answer 1

我看到几个明显的：一些 for 循环没有终止，一些 cout 语句没有终止等等。我相信代码格式不正确。 ..

Answer 2

答案不是很多但是这个编译并在我的MPI版本上运行，最多有4个处理器。代码似乎有点牵扯，但我也看不出它为什么不起作用的原因。

任何人都可以帮我识别此代码示例中的运行时MPI错误吗？

2 个答案: