int MPI_Reduce(void *sbuf, void* rbuf, int count,
MPI_Datatype dtype, MPI_Op op, int root,
- - address of send buffer (choice)
- - number of elements in send buffer (integer)
- - data type of elements of send buffer (handle)
- - reduce operation (handle)
- - rank of root process (integer)
- communicator (handle)
- address of receive buffer (choice,
significant only at
USAGE WITH IMPI EXTENSIONS
This function has had the IMPI extensions implemented. It is legal to call this function on IMPI communicators.
If there are 4 or less ranks involved, the root loops over receiving from each rank, and then performs the final reduction locally.
If there are more than 4 ranks involved, a tree-based algorithm is used to collate the reduced data at the root (the data is reduced at each parent in the tree so that the reduction operations are actaully distributed).
NOTES FOR FORTRAN
All MPI routines in Fortran (except for MPI_WTIME and MPI_WTICK ) have an additional argument ierr at the end of the argument list. ierr is an integer and has the same meaning as the return value of the routine in C. In Fortran, MPI routines are subroutines, and are invoked with the call statement.
All MPI objects (e.g., MPI_Datatype , MPI_Comm ) are of type INTEGER in Fortran.
NOTES ON COLLECTIVE OPERATIONS
The reduction functions ( MPI_Op ) do not return an error value. As a result, if the functions detect an error, all they can do is either call MPI_Abort or silently skip the problem. Thus, if you change the error handler from MPI_ERRORS_ARE_FATAL to something else (e.g., MPI_ERRORS_RETURN ), then no error may be indicated.
The reason for this is the performance problems that arise in ensuring that all collective routines return the same error value.
If an error occurs in an MPI function, the current MPI error handler is called to handle it. By default, this error handler aborts the MPI job. The error handler may be changed with MPI_Errhandler_set ; the predefined error handler MPI_ERRORS_RETURN may be used to cause error values to be returned (in C and Fortran; this error handler is less useful in with the C++ MPI bindings. The predefined error handler MPI::ERRORS_THROW_EXCEPTIONS should be used in C++ if the error value needs to be recovered). Note that MPI does not guarantee that an MPI program can continue past an error.
All MPI routines (except MPI_Wtime and MPI_Wtick ) return an error value; C routines as the value of the function and Fortran routines in the last argument. The C++ bindings for MPI do not return error values; instead, error values are communicated by throwing exceptions of type MPI::Exception (but not by default). Exceptions are only thrown if the error value is not MPI::SUCCESS .
Note that if the MPI::ERRORS_RETURN handler is set in C++, while MPI functions will return upon an error, there will be no way to recover what the actual error value was.
- - No error; MPI routine completed successfully.
- - Invalid communicator. A common error is to use a null communicator in a call (not even allowed in MPI_Comm_rank ).
- - A collective implementation was not able to be located at run-time for this communicator.
- - Invalid count argument. Count arguments must be non-negative; a count of zero is often valid.
- - Invalid datatype argument. May be an uncommitted MPI_Datatype (see MPI_Type_commit ).
- - Invalid buffer pointer. Usually a null buffer where one is not valid.
- - This error class is associcated with an error code that indicates that two buffer arguments are aliased ; that is, the describe overlapping storage (often the exact same storage). This is prohibited in MPI (because it is prohibited by the Fortran standard, and rather than have a separate case for C and Fortran, the MPI Forum adopted the more restrictive requirements of Fortran).
- Invalid root. The root must be specified as a rank
in the communicator. Ranks must be between zero and the size of the
communicator minus one.
For more information, please see the official MPI Forum web site, which contains the text of both the MPI-1 and MPI-2 standards. These documents contain detailed information about each MPI function (most of which is not duplicated in these man pages).
The LAM Team would like the thank the MPICH Team for the handy program to generate man pages ("doctext" from ftp://ftp.mcs.anl.gov/pub/sowing/sowing.tar.gz ), the initial formatting, and some initial text for most of the MPI-1 man pages.