Hmm, for DMDA and DMStag is should not have a limit (certain ranges of values are better optimized than others but more optimizations may be done).
For DMPLEX in theory again it should be what ever you like (again larger values may require more optimization in our code to get really great performance) Barry > On Dec 5, 2019, at 9:50 AM, Yann Jobic <yann.jo...@univ-amu.fr> wrote: > > Hello, > I read in the email archive (from 2016) that, at that time, the number of > synchronized dof (in MPI/ghost cells sense) is 3 or 4. > Is that still the case ? I would like to use PETSc for solving the Boltzmann > equation (via Discreet velocity method, which means a lot of dof per node). > Is it the same for DMPlex ? > Thanks, > best regards, > Yann