我正在尝试在属于超立方体组(快速排序项目)的进程之间分散值。根据进程的数量,我要么创建一个不包括过多进程的新通信器,要么复制 MPI_COMM_WORLD,如果它恰好适合任何超立方体(2 的幂)。
在这两种情况下,除 0 之外的进程都会收到它们的数据,但是: - 在第一种情况下,进程 0 会引发分段错误 11 - 在第二种情况下,没有任何错误,但进程 0 收到的值是乱码。
注意:如果我尝试常规 MPI_Scatter 一切正常。
//Input
vector<int> LoadFromFile();
int d; //dimension of hypercube
int p; //active processes
int idle; //idle processes
vector<int> values; //values loaded
int arraySize; //number of total values to distribute
int main(int argc, char* argv[])
{
int mpiWorldRank;
int mpiWorldSize;
int mpiRank;
int mpiSize;
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &mpiWorldRank);
MPI_Comm_size(MPI_COMM_WORLD, &mpiWorldSize);
MPI_Comm MPI_COMM_HYPERCUBE;
d = log2(mpiWorldSize);
p = pow(2, d); //Number of processes belonging to the hypercube
idle = mpiWorldSize - p; //number of processes in excess
int toExclude[idle]; //array of idle processes to exclude from communicator
int sendCounts[p]; //array of values sizes to be sent to processes
//
int i = 0;
while (i < idle)
{
toExclude[i] = mpiWorldSize - 1 - i;
++i;
}
//CREATING HYPERCUBE GROUP: Group of size of power of 2 -----------------
MPI_Group world_group;
MPI_Comm_group(MPI_COMM_WORLD, &world_group);
// Remove excessive processors if any from communicator
if (idle > 0)
{
MPI_Group newGroup;
MPI_Group_excl(world_group, 1, toExclude, &newGroup);
MPI_Comm_create(MPI_COMM_WORLD, newGroup, &MPI_COMM_HYPERCUBE);
//Abort any processor not part of the hypercube.
if (mpiWorldRank > p)
{
cout << "aborting: " << mpiWorldRank <<endl;
MPI_Finalize();
return 0;
}
}
else
{
MPI_Comm_dup(MPI_COMM_WORLD, &MPI_COMM_HYPERCUBE);
}
MPI_Comm_rank(MPI_COMM_HYPERCUBE, &mpiRank);
MPI_Comm_size(MPI_COMM_HYPERCUBE, &mpiSize);
//END OF: CREATING HYPERCUBE GROUP --------------------------
if (mpiRank == 0)
{
//STEP1: Read input
values = LoadFromFile();
arraySize = values.size();
}
//Transforming input vector into an array
int valuesArray[values.size()];
if(mpiRank == 0)
{
copy(values.begin(), values.end(), valuesArray);
}
//Broadcast input size to all processes
MPI_Bcast(&arraySize, 1, MPI_INT, 0, MPI_COMM_HYPERCUBE);
//MPI_Scatterv: determining size of arrays to be received and displacement
int nmin = arraySize / p;
int remainingData = arraySize % p;
int displs[p];
int recvCount;
int k = 0;
for (i=0; i<p; i++)
{
sendCounts[i] = i < remainingData
? nmin+1
: nmin;
displs[i] = k;
k += sendCounts[i];
}
recvCount = sendCounts[mpiRank];
int recvValues[recvCount];
//Following MPI_Scatter works well:
// MPI_Scatter(&valuesArray, 13, MPI_INT, recvValues , 13, MPI_INT, 0, MPI_COMM_HYPERCUBE);
MPI_Scatterv(&valuesArray, sendCounts, displs, MPI_INT, recvValues , recvCount, MPI_INT, 0, MPI_COMM_HYPERCUBE);
int j = 0;
while (j < recvCount)
{
cout << "rank " << mpiRank << " received: " << recvValues[j] << endl;
++j;
}
MPI_Finalize();
return 0;
}