MPI_Reduce_scatter(3)
MPI_Reduce_scatter - Combines values and scatters the results
As shipped in IRIX 6.5.30. Last changed in IRIX 6.5.22.
NAME MPI_Reduce_scatter - Combines values and scatters the results SYNOPSIS C: #include <mpi.h> int MPI_Reduce_scatter ( sendbuf, recvbuf, recvcounts, datatype, op, comm ) void *sendbuf; void *recvbuf; int *recvcounts; MPI_Datatype datatype; MPI_Op op; MPI_Comm comm; C++: #include <mpi.h> void Intracomm::Reduce_scatter( const void* sendbuf, void* recvbuf, int recvcounts[], const Datatype& datatype, const Op& op) const Fortran: INCLUDE "mpif.h" (or USE MPI) <type> SENDBUF(*), RECVBUF(*) INTEGER recvcounts(*), datatype, op, comm, ierror CALL MPI_REDUCE_SCATTER(sendbuf, recvbuf, recvcounts(*), datatype, op, comm, ierror) STANDARDS This release implements the MPI 1.2 standard, as documented by the MPI Forum in the spring 1997 release of MPI: A Message Passing Interface Standard. The MPI_IN_PLACE option as defined in the MPI 2.0 standard is also supported in this implementation. DESCRIPTION The MPI_Reduce_scatter routine combines values and scatters the results. This routine accepts the following parameters: sendbuf Specifies the starting address of the send buffer (choice). You may also pass in the argument MPI_IN_PLACE for the value of sendbuf at all processes. In this case, the input data is taken from the top of the receive buffer. Note that the area occupied by the input data may be either longer or shorter than that filled by the output data, and that Fortran bindings for recvbuf that include INTENT should mark it as INOUT, not OUT. recvcounts Specifies the integer array that specifies the number of elements in the result that is distributed to each process. The array must be identical on all calling processes. datatype Specifies the data type of elements of the input buffer (handle) op Specifies the operation (handle) comm Specifies the communicator (handle) recvbuf Returns the starting address of the receive buffer (choice) ierror Specifies the return code value for successful completion, which is in MPI_SUCCESS. MPI_SUCCESS is defined in the mpif.h file.