Dear Deal.II community, I 'm going to solve a 3D problem using MPI and I want to determine the number of processors before running my code. In deal.II document(specifically the glossary part about parallel scaling), I know it's better to make the number of dofs each process handles remain at more than 40000.
So my problem is how to consider the number of dofs to determine the number of processors when the program is running step by step. For example, I create two dof_handlers(dof_handler_1 and dof_handler_2). My solution consists of solution_1, solution_2 and solution_3, these solution components are initialized by solution_1.reinit(dof_handler_1), solution_2.reinit(dof_handler_1) and solution_3.reinit(dof_handler_2), respectively. If these three solutions are solved in one step, it's clear that the number of dofs should be just 2*dof_handler_1.n_dofs() plus dof_handler_2.n_dofs(). But what if solution_1 is solved in step one then solution_2 and solution_3 are solved in step two. In this case, how to determine the number of dofs and then determine the number of processors? Any advice or suggestions will be appreciated! Thank you. Best, Toddy -- The deal.II project is located at http://www.dealii.org/ For mailing list/forum options, see https://groups.google.com/d/forum/dealii?hl=en --- You received this message because you are subscribed to the Google Groups "deal.II User Group" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/dealii/8cb753f3-7c74-4c1a-9138-1253093c19fen%40googlegroups.com.
