This routine allows the user to map processes to the
process grid in an arbitrary manner.
the process number of the process to be placed in
process grid. On most distributed systems, this process number is a
machine defined number between 0 ...
For PVM, these node numbers are the PVM TIDS (Task IDs). The
routine is intended for an experienced user. The
routine is much simpler.
simply performs a
where the first
nprow * npcol
processes are mapped into the current grid in a row-major natural
ordering. If you are an experienced user,
allows you to take advantage of your system's actual layout. That
is, you can map nodes that are physically connected to be neighbors
in the BLACS grid, etc. The
routine also opens the way for multigridding
: you can separate your nodes into
arbitrary grids, join them together at some later date, and then
re-split them into new grids.
also provides the ability to make arbitrary grids or subgrids (for
example, a "nearest neighbor" grid), which can greatly facilitate
operations among processes that do not fall on a row or column of
the main process grid.