On Thu, 4 Apr 2013, Manav Bhatia wrote: > At this point, I do not have a need for off-processor element > data. So, the current status of ParallelMesh could be a good > thing. > > I did give it a go for my application, and so far it seems to be > working well. The memory footprint of each process has also come > down significantly (from ~4GB to ~0.8GB), which is great!
Excellent! > I noticed that the .xdr restart solutions are now written one per > mesh block. This seems to suggest that this can be read into a > ParallelMesh data structure for a restart, and not a SerialMesh. > Is this correct? Doing N-to-N reads into a ParallelMesh for a restart is the intention, yes. I don't know if anybody has thoroughly tested it yet, though; mostly we've been using Nemesis for distributed mesh I/O. It looks like you might even be able to read those N files into an N-processor SerialMesh code if it was partitioned in the exact same way. --- Roy ------------------------------------------------------------------------------ Minimize network downtime and maximize team effectiveness. Reduce network management and security costs.Learn how to hire the most talented Cisco Certified professionals. Visit the Employer Resources Portal http://www.cisco.com/web/learning/employer_resources/index.html _______________________________________________ Libmesh-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/libmesh-users
