The Great and Terrible implementation of MPI-2

function index


Reduces values on all processes to a single value
int MPI_Reduce(
  void *sendbuf,
  void *recvbuf,
  int count,
  MPI_Datatype datatype,
  MPI_Op op,
  int root,
  MPI_Comm comm


[in] address of send buffer (choice)
[out] address of receive buffer (choice, significant only at root)
[in] number of elements in send buffer (integer)
[in] data type of elements of send buffer (handle)
[in] reduce operation (handle)
[in] rank of root process (integer)
[in] communicator (handle)


MPI_REDUCE combines the elements provided in the input buffer of each process in the group, using the operation op, and returns the combined value in the output buffer of the process with rank root. The input buffer is defined by the arguments sendbuf, count and datatype; the output buffer is defined by the arguments recvbuf, count and datatype; both have the same number of elements, with the same type. The routine is called by all group members using the same arguments for count, datatype, op, root and comm. Thus, all processes provide input buffers and output buffers of the same length, with elements of the same type. Each process can provide one element, or a sequence of elements, in which case the combine operation is executed element-wise on each entry of the sequence. For example, if the operation is MPI_MAX and the send buffer contains two elements that are floating point numbers ( count = 2 and datatype = MPI_FLOAT), then and .

The operation op is always assumed to be associative. All predefined operations are also assumed to be commutative. Users may define operations that are assumed to be associative, but not commutative. The "canonical" evaluation order of a reduction is determined by the ranks of the processes in the group. However, the implementation can take advantage of associativity, or associativity and commutativity in order to change the order of evaluation. This may change the result of the reduction for operations that are not strictly associative and commutative, such as floating point addition.

Thread and Interrupt Safety

This routine is thread-safe. This means that this routine may be safely used by multiple threads without the need for any user-provided thread locks. However, the routine is not interrupt safe. Typically, this is due to the use of memory allocation routines such as malloc or other non-MPICH runtime routines that are themselves not interrupt-safe.

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, for example, MPI_ERRORS_RETURN, then no error may be indicated.

The reason for this is the performance problems in ensuring that all collective routines return the same error value.


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. Before the value is returned, the current MPI error handler is called. By default, this error handler aborts the MPI job. The error handler may be changed with MPI_Comm_set_errhandler (for communicators), MPI_File_set_errhandler (for files), and MPI_Win_set_errhandler (for RMA windows). The MPI-1 routine MPI_Errhandler_set may be used but its use is deprecated. The predefined error handler MPI_ERRORS_RETURN may be used to cause error values to be returned. Note that MPI does not guarentee that an MPI program can continue past an error; however, MPI implementations will attempt to continue whenever possible.

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).
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).

Example Code

The following sample code illustrates MPI_Reduce.

#include "mpi.h"
#include <stdio.h>
#include <stdlib.h>
/* A simple test of Reduce with all choices of root process */
int main( int argc, char *argv[] )
    int errs = 0;
    int rank, size, root;
int *sendbuf, *recvbuf, i;
    int minsize = 2, count;
    MPI_Comm comm;
    MPI_Init( &argc, &argv );
    comm = MPI_COMM_WORLD;
    /* Determine the sender and receiver */
    MPI_Comm_rank( comm, &rank );
    MPI_Comm_size( comm, &size );
    for (count = 1; count < 130000; count = count * 2) {
        sendbuf = (
int *)malloc( count * sizeof(int) );
        recvbuf = (
int *)malloc( count * sizeof(int) );
        for (root = 0; root < size; root ++) {
for (i=0; i<count; i++) sendbuf[i] = i;
            for (i=0; i<count; i++) recvbuf[i] = -1;
            MPI_Reduce( sendbuf, recvbuf, count, MPI_INT, MPI_SUM, root, comm );
            if (rank == root) {
                for (i=0; i<count; i++) {
                    if (recvbuf[i] != i * size) {
        free( sendbuf );
        free( recvbuf );
return errs;