Hello Pearl, > So, does > > dof_handler.distribute_dofs (fe); > > now take care of mesh partitioning?
Yes, that is all you need to do. The mesh is already partitioned in the distributed::Triangulation and each cell has a subdomain_id (identified with the processor id). The degrees of freedom are sorted per subdomain automatically in distribute_dofs(), so each processor has a continuous range of indices. If you have a block system, like in step-32, you can renumber them with component_wise(), if you want. -- Timo Heister http://num.math.uni-goettingen.de/~heister _______________________________________________ dealii mailing list http://poisson.dealii.org/mailman/listinfo/dealii
