[Beowulf] Using Autoparallel compilers or Multi-Threaded libraries
hahn at mcmaster.ca
Fri Nov 30 15:21:53 PST 2007
> IMHO the hybris approach (MPI+threads) is interesting in case every
> MPI-process has lots of local data.
yes. but does this happen a lot? the appealing case would be
threads that make lots of heavy use of some large data, _but_
without needing synchronization/locking. once you need locking
among the threads, message passing starts to catch up.
> latter is simpler because it only requires MPI-parallelism but if the code
> is memory-bound and every mpi-process has much of the same data, it will be
> better to share this common data with all processes on the same cpu and thus
> use threads intra-node.
what kind of applications behave like that? I agree that if your MPI
app is keeping huge amounts of (static) data replicated in each rank,
you should rethink your design.
thanks, mark hahn.
More information about the Beowulf