In the MPI_Scatterv operation a root process distributes data
to every node. In addition to MPI_Scatter a displacement
and length can be given, which determine which data from the
root process' buffer is send to the other nodes. It is intersting to
see the extra costs compared to MPI_Scatter. We vary over the
number of nodes. The messages have the length of 256 Bytes (for each
node).
Pattern: Collective varied over number of nodes.
default values: 8 nodes, message length 256 units, max. / act. time for suite disabled/0.00 min.