我有一个MPI笛卡尔拓扑，并希望通过MPI_Neighbor_alltoall将每个节点等级发送给它们的邻居。我无法弄清楚，错误在哪里，我也实现了我自己的MPI_Neighbor_alltoall，它不起作用。我将我的代码最小化为（希望）易于理解的代码片段。
alltoall.c
#include <mpi.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
int main(int argc, char** argv) {
// MPI_Cart variables
MPI_Comm cart_comm;
MPI_Comm mycomm;
int ndims=2;
int periods[2]={0,0};
int coord[2];
int dims[2]={3,3};
int xdim = dims[0];
int ydim = dims[1];
int comm_size = xdim*ydim;
// Initialize the MPI environment and pass the arguments to all the processes.
MPI_Init(&argc, &argv);
// Get the rank and number of the process
int rank, size;
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
// output: dimensions
if(rank==0){
printf("dims: [%i] [%i]\n", xdim, ydim);
}
// enough nodes
if(comm_size<=size){
// Communicator count has to match nodecount in dims
// so we create a new Communicator with matching nodecount
int color;
int graphnode;
if(rank<comm_size){
//printf("%d<%d\n",rank,comm_size);
color=0;
graphnode=1;
} else {
//printf("%d>=%d\n",rank,comm_size);
// not used nodes
color=1;
graphnode=0;
}
MPI_Comm_split(MPI_COMM_WORLD, color, rank, &mycomm);
MPI_Comm_rank(mycomm, &rank);
MPI_Comm_size(mycomm, &size);
// ***GRAPHNODE-SECTION***
if(graphnode){
// Create Dimensions
MPI_Dims_create(size, ndims, dims);
// Create Cartesian
MPI_Cart_create(mycomm, ndims, dims, periods, 1, &cart_comm);
// Get the name of the processor
char processor_name[MPI_MAX_PROCESSOR_NAME];
int len;
MPI_Get_processor_name(processor_name, &len);
// Get coordinates
MPI_Cart_coords(cart_comm, rank, ndims, coord);
// sending
int *sendrank = &rank;
int recvrank[4];
MPI_Neighbor_alltoall(sendrank , 1, MPI_INT, recvrank, 1, MPI_INT, cart_comm);
printf("my rank: %i, received ranks: %i %i %i %i\n", rank, recvrank[0], recvrank[1], recvrank[2], recvrank[3]);
} else {
// *** SPARE NODES SECTION ***
}
} else {
// not enough nodes reserved
if(rank==0)
printf("not enough nodes\n");
}
// Finalize the MPI environment.
MPI_Finalize();
}
因此，此代码创建了一个3x3笛卡尔拓扑。如果节点太多，如果没有足够的节点并且让备用节点什么都不做，那么它最终确定。虽然这应该很容易，但我仍然做错了，因为输出缺少一些数据。
输出
$ mpicc alltoall.c
$ mpirun -np 9 a.out
dims: [3] [3]
my rank: 2, received ranks: -813779952 5 0 32621
my rank: 1, received ranks: 1415889936 4 0 21
my rank: 5, received ranks: 9 8 0 32590
my rank: 3, received ranks: 9 6 -266534912 21
my rank: 7, received ranks: 9 32652 0 21
my rank: 8, received ranks: 9 32635 0 32635
my rank: 6, received ranks: 9 32520 1372057600 21
my rank: 0, received ranks: -1815116784 3 -1803923456 21
my rank: 4, received ranks: 9 7 0 21
正如你在输出中看到的那样，没有人将节点1,2作为邻居，21来自哪里？等级4应该是唯一的节点，有4个邻居，但那应该是{1,3,5,7}对吗？我真的不知道我的错误在哪里。
坐标应如下所示：
[0,0] [1,0] [2,0]
[0,1] [1,1] [2,1]
[0,2] [1,2] [2,2]
并且排名如下：
0 3 6
1 4 7
2 5 8
答案 0 :(得分：0)
您正在访问大量未初始化的数据（包括sendrank和recvrank）
这是一个适合我的测试程序的重写版本
#include <mpi.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
int main(int argc, char** argv) {
// MPI_Cart variables
MPI_Comm cart_comm;
MPI_Comm mycomm;
int ndims=2;
int periods[2]={0,0};
int coord[2];
int dims[2]={3,3};
int xdim = dims[0];
int ydim = dims[1];
int comm_size = xdim*ydim;
// Initialize the MPI environment and pass the arguments to all the processes.
MPI_Init(&argc, &argv);
// Get the rank and number of the process
int rank, size;
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
MPI_Comm_size(MPI_COMM_WORLD, &size);
// output: dimensions
if(rank==0){
printf("dims: [%i] [%i]\n", xdim, ydim);
}
// enough nodes
if(comm_size<=size){
// Communicator count has to match nodecount in dims
// so we create a new Communicator with matching nodecount
int color;
int graphnode;
if(rank<comm_size){
//printf("%d<%d\n",rank,comm_size);
color=0;
graphnode=1;
} else {
//printf("%d>=%d\n",rank,comm_size);
// not used nodes
color=1;
graphnode=0;
}
MPI_Comm_split(MPI_COMM_WORLD, color, rank, &mycomm);
MPI_Comm_rank(mycomm, &rank);
MPI_Comm_size(mycomm, &size);
// ***GRAPHNODE-SECTION***
if(graphnode){
// Create Dimensions
MPI_Dims_create(size, ndims, dims);
// Create Cartesian
MPI_Cart_create(mycomm, ndims, dims, periods, 1, &cart_comm);
// Get the name of the processor
char processor_name[MPI_MAX_PROCESSOR_NAME];
int len;
MPI_Get_processor_name(processor_name, &len);
// Get coordinates
MPI_Cart_coords(cart_comm, rank, ndims, coord);
// sending
int sendrank[4];
int recvrank[4];
int i;
char * neighbors[4];
for (i=0; i<4; i++) {
sendrank[i] = rank;
recvrank[i] = -1;
}
MPI_Neighbor_alltoall(sendrank , 1, MPI_INT, recvrank, 1, MPI_INT, cart_comm);
for (i=0; i<4; i++) {
if (-1 != recvrank[i]) {
asprintf(&neighbors[i], "%d ", recvrank[i]);
} else {
neighbors[i] = "";
}
}
printf("my rank: %i, received ranks: %s%s%s%s\n", rank, neighbors[0], neighbors[1], neighbors[2], neighbors[3]);
} else {
// *** SPARE NODES SECTION ***
}
} else {
// not enough nodes reserved
if(rank==0)
printf("not enough nodes\n");
}
// Finalize the MPI environment.
MPI_Finalize();
}