Toon Knapen wrote: > Greg Lindahl wrote: >> >> In real life (i.e. not HPC), everyone uses message passing between >> nodes. So I don't see what you're getting at. >> > Many on this list suggest that using multiple MPI-processes on one and > the same node is superior to MT approaches IIUC.
I'm not sure where this conclusion came from. > However I have the > impression that almost the whole industry is looking into MT to benefit > from multi-core without even considering message-passing. Why is that so? > > toon These are developers working on NUMA and SMA, not network distributed parallel processing. Different problem, different tool. If an application is going to be using only shared memory, I have no doubt the consensus here is to use native threads or OpenMP. If the application is going to be working over a network, MPI (or PVM) is the way to go. Don't misconstrue any strategies and opinions on this list to be generalizable to all types of parallel computing. This list is here to discuss the engineering of Beowulf style systems, so opinions (unless qualified) will generally apply to Beowulf computers as well. -- Geoffrey D. Jacobs To have no errors would be life without meaning No struggle, no joy _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
