Home
Latest projects
-
ParMA (11/05/2011 02:45 pm)
Parallel unstructured simulations at extreme scale require that the mesh be distributed across a large number of processors with equal workload and minimum inter-part communications. The goal of ParMA it to dynamically partition unstructured meshes directly using the existing mesh adjacency information to account for multiple criteria. Results will demonstrate the ability of ParMA to dynamically rebalance large meshes (billions of mesh regions) on large core count machines (>100,000) accounting for multiple criteria. ...
- qacinaAdapt (10/20/2011 12:12 pm)
-
FASTMath (10/19/2011 10:58 am)
FASTMath Software Strategies
- Tensor Assembly (04/13/2011 07:20 pm)
- SVNSplitTool (04/13/2011 07:07 pm)