The following predefined operations are supplied for MPI_REDUCE and related functions MPI_ALLREDUCE, MPI_REDUCE_SCATTER_BLOCK, MPI_REDUCE_SCATTER, MPI_SCAN, MPI_EXSCAN, all nonblocking variants of those (see Section Nonblocking Collective Operations), and MPI_REDUCE_LOCAL. These operations are invoked by placing the following in op.
The two operations MPI_MINLOC and MPI_MAXLOC are discussed separately in Section MINLOC and MAXLOC. For the other predefined operations, we enumerate below the allowed combinations of op and datatype arguments. First, define groups of MPI basic datatypes in the following way.
Now, the valid datatypes for each operation are specified below.
These operations together with all listed datatypes are valid in all supported programming languages, see also Reduce Operations in Section MPI Opaque Objects.
The following examples use intra-communicators.
Example
A routine that computes
the dot product of two vectors that are distributed across a
group of MPI processes and returns the answer at node zero.
Example
A routine that computes
the product of a vector and an array that are distributed across a
group of MPI processes and returns the answer at node zero.
