Scripted HTML version of Foils prepared 29 December 1996

Foil 24 Cartesian Topology in MPI -- General

From CPS615-Linear Programming and Whirlwind Full Matrix Discussion Delivered Lectures of CPS615 Basic Simulation Track for Computational Science -- 5 Decemr 96. by Geoffrey C. Fox *
Secs 129.6
Under the new MPI cartesian topology, there are two functions which convert between the logical process coordinates, such as [i,j] in our 2D topology, to the (possibly new) 1D topolgy rank number required by the send and receive functions.
MPI_CART_COORDS(comm2d, myrank, 2, coords)
Takes a processor number myrank, in a 2 dim communicator called comm2d, and returns the 2 element vector cooresponding to the [i,j] position of this processor in the new system.
MPI_CART_RANK(comm2d, [i,j], myrank)
Takes a 2 element int array with logical process coordinates i and j and returns a 1D processor rank in the variable myrank.



© Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Thu Aug 14 1997