Question

我正在尝试使用MPI（即nxn矩阵与nx1向量相乘）实现矩阵向量乘法。

最初，我决定使用多个MPI_Bcast调用（在我注意到MPI_AllGather ...之前），我偶然发现了一些奇怪的行为。显然，无论传递给MPI_Bcast呼叫的等级如何，都可以接收数据。

所用代码的一部分（功能彼此后接，因此发送广播是在接收广播之前）。打印只是出于调试目的，我知道测试数据的长度为2：

class Processor
{
public:
    Processor(int rank, int communicatorSize);

private:
    void broadcastOwnVectorToOtherRanks();
    void receiveBroadcastsFromOtherRanks();
    //...

    int ownRank;
    int communicatorSize;
    std::vector<int> ownVectorPart;
    std::vector<int> totalVector;
    //...
};

void Processor::broadcastOwnVectorToOtherRanks()
{
    //ownVectorPart is correctly filled before this function call
    std::printf("Own data in vector %d %d\n", ownVectorPart[0], ownVectorPart[1]);
    MPI_Bcast(ownVectorPart.data(), ownVectorPart.size(), MPI_INT, ownRank, MPI_COMM_WORLD);
}

void Processor::receiveBroadcastsFromOtherCommunicators()
{
    for (int rank = 0; rank < communicatorSize; ++rank)
    {
        if (rank == ownRank)
        {
            totalVector.insert(totalVector.end(), ownVectorPart.begin(), ownVectorPart.end());
        }
        else
        {
            std::vector<int> buffer(ownVectorPart.size());
            MPI_Bcast(buffer.data(), ownVectorPart.size(), MPI_INT, rank, MPI_COMM_WORLD);
            std::printf("Received from process with rank %d: %d %d\n", rank, buffer[0], buffer[1]);
            totalVector.insert(totalVector.end(), buffer.begin(), buffer.end());
        }
    }
}

结果（按排名排序）：

[0] Own data in vector 0 1
[0] Received from communicator 1: 6 7
[0] Received from communicator 2: 4 5
[0] Received from communicator 3: 2 3
[1] Own data in vector 2 3
[1] Received from communicator 0: 0 1
[1] Received from communicator 2: 4 5
[1] Received from communicator 3: 6 7
[2] Own data in vector 4 5
[2] Received from communicator 0: 0 1
[2] Received from communicator 1: 2 3
[2] Received from communicator 3: 6 7
[3] Own data in vector 6 7
[3] Received from communicator 0: 4 5
[3] Received from communicator 1: 2 3
[3] Received from communicator 2: 0 1

您可以看到，在等级0和3的过程中，接收到的数据与发送的数据不同。例如，排名为0的进程接收到的排名为3的数据，即使它期望从进程1获得数据。

在我看来，当接收广播数据时，等级将被忽略，并且MPI会根据其来分配数据，无论它是否来自预期等级。

当作为参数传递的等级为MPI_Bcast时，为什么3从等级为1的进程接收数据？多次调用MPI_Bcast是一种不确定的行为吗？还是我的代码中有错误？

Answer 1

引用MPI 3.1标准（第5.12节）：

所有进程都必须调用集体操作（阻塞和非阻塞）每个沟通者的顺序相同。特别是一旦流程调用集体行动，沟通者的所有其他程序必须最终称为同一集体行动，没有两者之间使用同一通信器进行的其他集体操作。

将其与5.4节合并：

如果comm是内部通信者，则MPI_BCAST广播来自该过程本身是该组所有过程的基础包括在内。该组的所有成员都使用相同的名称 comm和root的参数。

我将这两部分解释为意味着您必须在所有进程上以相同的顺序调用MPI_Bcast和类似的集合通信函数，并使用相同的参数。用不同的根值调用无效。

我相信MPI_Allgather更适合您似乎想要的交流方式。它从所有进程收集相等数量的数据，并将其复制到每个进程。

多次调用MPI_Bcast是否错误？

1 个答案: