| MPI_Scatterv(3) | Open MPI | MPI_Scatterv(3) |
MPI_Scatterv, MPI_Iscatterv - Scatters a buffer in parts to all tasks in a group.
#include <mpi.h> int MPI_Scatterv(const void *sendbuf, const int sendcounts[], const int displs[], MPI_Datatype sendtype, void *recvbuf, int recvcount, MPI_Datatype recvtype, int root, MPI_Comm comm) int MPI_Iscatterv(const void *sendbuf, const int sendcounts[], const int displs[], MPI_Datatype sendtype, void *recvbuf, int recvcount, MPI_Datatype recvtype, int root, MPI_Comm comm, MPI_Request *request)
USE MPI ! or the older form: INCLUDE 'mpif.h' MPI_SCATTERV(SENDBUF, SENDCOUNTS, DISPLS, SENDTYPE, RECVBUF, RECVCOUNT, RECVTYPE, ROOT, COMM, IERROR) <type> SENDBUF(*), RECVBUF(*) INTEGER SENDCOUNTS(*), DISPLS(*), SENDTYPE INTEGER RECVCOUNT, RECVTYPE, ROOT, COMM, IERROR MPI_ISCATTERV(SENDBUF, SENDCOUNTS, DISPLS, SENDTYPE, RECVBUF, RECVCOUNT, RECVTYPE, ROOT, COMM, REQUEST, IERROR) <type> SENDBUF(*), RECVBUF(*) INTEGER SENDCOUNTS(*), DISPLS(*), SENDTYPE INTEGER RECVCOUNT, RECVTYPE, ROOT, COMM, REQUEST, IERROR
USE mpi_f08 MPI_Scatterv(sendbuf, sendcounts, displs, sendtype, recvbuf, recvcount, recvtype, root, comm, ierror) TYPE(*), DIMENSION(..), INTENT(IN) :: sendbuf TYPE(*), DIMENSION(..) :: recvbuf INTEGER, INTENT(IN) :: sendcounts(*), displs(*), recvcount, root TYPE(MPI_Datatype), INTENT(IN) :: sendtype, recvtype TYPE(MPI_Comm), INTENT(IN) :: comm INTEGER, OPTIONAL, INTENT(OUT) :: ierror
MPI_Iscatterv(sendbuf, sendcounts, displs, sendtype, recvbuf, recvcount, recvtype, root, comm, request, ierror) TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf INTEGER, INTENT(IN), ASYNCHRONOUS :: sendcounts(*), displs(*) INTEGER, INTENT(IN) :: recvcount, root TYPE(MPI_Datatype), INTENT(IN) :: sendtype, recvtype TYPE(MPI_Comm), INTENT(IN) :: comm TYPE(MPI_Request), INTENT(OUT) :: request INTEGER, OPTIONAL, INTENT(OUT) :: ierror
#include <mpi.h> void MPI::Comm::Scatterv(const void* sendbuf, const int sendcounts[], const int displs[], const MPI::Datatype& sendtype, void* recvbuf, int recvcount, const MPI::Datatype& recvtype, int root) const
MPI_Scatterv is the inverse operation to MPI_Gatherv.
MPI_Scatterv extends the functionality of MPI_Scatter by allowing a varying count of data to be sent to each process, since sendcounts is now an array. It also allows more flexibility as to where the data is taken from on the root, by providing the new argument, displs.
The outcome is as if the root executed n send operations,
MPI_Send(sendbuf + displs[i] * extent(sendtype), \
sendcounts[i], sendtype, i, ...) and each process executed a receive,
MPI_Recv(recvbuf, recvcount, recvtype, root, ...) The send buffer is ignored for all nonroot processes.
The type signature implied by sendcount[i], sendtype at the root must be equal to the type signature implied by recvcount, recvtype at process i (however, the type maps may be different). This implies that the amount of data sent must be equal to the amount of data received, pairwise between each process and the root. Distinct type maps between sender and receiver are still allowed.
All arguments to the function are significant on process root, while on other processes, only arguments recvbuf, recvcount, recvtype, root, comm are significant. The arguments root and comm must have identical values on all processes.
The specification of counts, types, and displacements should not cause any location on the root to be read more than once.
Example 1: The reverse of Example 5 in the MPI_Gatherv manpage. We have a varying stride between blocks at sending (root) side, at the receiving side we receive 100 - i elements into the ith column of a 100 x 150 C array at process i.
MPI_Comm comm;
int gsize,recvarray[100][150],*rptr;
int root, *sendbuf, myrank, bufsize, *stride;
MPI_Datatype rtype;
int i, *displs, *scounts, offset;
...
MPI_Comm_size( comm, &gsize);
MPI_Comm_rank( comm, &myrank );
stride = (int *)malloc(gsize*sizeof(int));
...
/* stride[i] for i = 0 to gsize-1 is set somehow
* sendbuf comes from elsewhere
*/
...
displs = (int *)malloc(gsize*sizeof(int));
scounts = (int *)malloc(gsize*sizeof(int));
offset = 0;
for (i=0; i<gsize; ++i) {
displs[i] = offset;
offset += stride[i];
scounts[i] = 100 - i;
}
/* Create datatype for the column we are receiving
*/
MPI_Type_vector( 100-myrank, 1, 150, MPI_INT, &rtype);
MPI_Type_commit( &rtype );
rptr = &recvarray[0][myrank];
MPI_Scatterv(sendbuf, scounts, displs, MPI_INT,
rptr, 1, rtype, root, comm);
Example 2: The reverse of Example 1 in the MPI_Gather manpage. The root process scatters sets of 100 ints to the other processes, but the sets of 100 are stride ints apart in the sending buffer. Requires use of MPI_Scatterv, where stride >= 100.
MPI_Comm comm;
int gsize,*sendbuf;
int root, rbuf[100], i, *displs, *scounts;
...
MPI_Comm_size(comm, &gsize);
sendbuf = (int *)malloc(gsize*stride*sizeof(int));
...
displs = (int *)malloc(gsize*sizeof(int));
scounts = (int *)malloc(gsize*sizeof(int));
for (i=0; i<gsize; ++i) {
displs[i] = i*stride;
scounts[i] = 100;
}
MPI_Scatterv(sendbuf, scounts, displs, MPI_INT,
rbuf, 100, MPI_INT, root, comm);
When the communicator is an intracommunicator, you can perform a scatter operation in-place (the output buffer is used as the input buffer). Use the variable MPI_IN_PLACE as the value of the root process recvbuf. In this case, recvcount and recvtype are ignored, and the root process sends no data to itself.
Note that MPI_IN_PLACE is a special kind of value; it has the same restrictions on its use as MPI_BOTTOM.
Because the in-place option converts the receive buffer into a send-and-receive buffer, a Fortran binding that includes INTENT must mark these as INOUT, not OUT.
When the communicator is an inter-communicator, the root process in the first group sends data to all processes in the second group. The first group defines the root process. That process uses MPI_ROOT as the value of its root argument. The remaining processes use MPI_PROC_NULL as the value of their root argument. All processes in the second group use the rank of that root process in the first group as the value of their root argument. The receive buffer argument of the root process in the first group must be consistent with the receive buffer argument of the processes in the second group.
Almost all MPI routines return an error value; C routines as the value of the function and Fortran routines in the last argument. C++ functions do not return errors. If the default error handler is set to MPI::ERRORS_THROW_EXCEPTIONS, then on error the C++ exception mechanism will be used to throw an MPI::Exception object.
Before the error value is returned, the current MPI error handler is called. By default, this error handler aborts the MPI job, except for I/O function errors. The error handler may be changed with MPI_Comm_set_errhandler; the predefined error handler MPI_ERRORS_RETURN may be used to cause error values to be returned. Note that MPI does not guarantee that an MPI program can continue past an error.
MPI_Gather MPI_Gatherv MPI_Scatter
| October 29, 2018 | 3.1.3 |