This is a read only copy of the old FEniCS QA forum. Please visit the new QA forum to ask questions

How is the mesh coordinate vector distributed among the processes in a parallel MPI run?

0 votes

I call

coords = dofmap.tabulate_all_coordinates(mesh).reshape(-1,gdim)

to get all coordinates ot the mesh. How is this vector distributed among the processes in a parallel MPI run? How can I scatter the coordinate vector to all processes?

asked Jun 22, 2015 by meipaff FEniCS Novice (320 points)

...