The big problem is that you did not include the last arg ierr in the call to MPI_Gather. The doc said All MPI routines in Fortran (except for MPI_WTIME and MPI_WTICK) have an additional argument ierr at the end of the argument list. In addition to that, my advise is to always stick to good … Read more
The details of the Cube class aren’t relevant here: consider a simpler version #include <mpi.h> #include <cstdlib> using namespace std; int main(int argc, char *argv[]) { int size, rank; const int root = 0; int datasize = atoi(argv[1]); MPI_Init(&argc, &argv); MPI_Comm_size(MPI_COMM_WORLD, &size); MPI_Comm_rank(MPI_COMM_WORLD, &rank); if (rank != root) { int nodeDest = rank + 1; … Read more
MPI is designed to work with arrays of structures rather that with structures of arrays. The MPI_Hindexed that @suszterpatt proposed is a terrible hack. It will only allow you to send one element of the structure type and only the element that was used to define the MPI data type. For other variables of the … Read more
Thread-safety in MPI doesn’t work out of the box. First, you have to ensure that your implementation actually supports multiple threads making MPI calls at once. With some MPI implementations, for example Open MPI, this requires the library to be configured with special options at build time. Then you have to tell MPI to initialise … Read more
MPI_Publish_name is supplied with an MPI info object, which could have an Open MPI specific boolean key ompi_global_scope. If this key is set to true, then the name would be published to the global scope, i.e. to an already running instance of ompi-server. MPI_Lookup_name by default first does a global name lookup if the URI … Read more
So it’s not a good idea to write large amounts of data as text. It’s really, really, slow, it generates unnecessarily large files, and it’s a pain to deal with. Large amounts of data should be written as binary, with only summary data for humans written as text. Make the stuff the computer is going … Read more
So this is a little more subtle, and requires some understanding of how the Gather collective places complex types. If you look at most examples of MPI_Gather, they’re of 1-d arrays, and it’s fairly easy to interpret what should happen; you’re getting (say) 10 ints from each process, and Gather is smart enough to put … Read more
Yes; most MPI implementations, for the sake of performance, busy-wait on blocking operations. The assumption is that the MPI job is the only thing going on that we care about on the processor, and if the task is blocked waiting for communications, the best thing to do is to continually poll for that communication to … Read more
Here’s an algorithm that is built on mapping and reducing (folding). It expresses the sieve of Eratosthenes P = {3,5,7, …} \ U {{p2, p2+2p, p2+4p, …} | p in P} for the odd primes (i.e without the 2). The folding tree is indefinitely deepening to the right, like this: where each prime number … Read more
OpenMP Is this a question about OpenMP? Then all you have to do is compile with -fopenmp which you can do by appending it to CMAKE_C_FLAGS, for example: SET(CMAKE_C_FLAGS “${CMAKE_C_FLAGS} -fopenmp) MPI For MPI, you have to find mpi first find_package(MPI) #make it REQUIRED, if you want then add it’s header files to your search … Read more