Stuart Midgley wrote: > Molecular dynamics is a good area to look at.
I've spent the last month using Gromacs, which is a free MD program, and it is definitely NOT an appropriate tool for learning about MPI and Beowulf's in general. In short, the scaling in the current version is not very good. Also MD programs are pretty arcane and prone to bizarre problems that a naive user would never expect. Example: couple protein and solvent together to the same temperature bath in Gromacs and the two sets of atoms will be driven to very different temperatures. For just learning to use MPI etc. it would probably be best to start with a problem that is known to scale well. Heat flow might be good, since at least there you could run problems that can be solved completely, so that there is a known solution to check the results against. Regards, David Mathog [EMAIL PROTECTED] Manager, Sequence Analysis Facility, Biology Division, Caltech _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
