ensure_gradedness uses a full MPI_allreduce
tommy-engels opened this issue · comments
Thomas Engels commented
The current version of ensure_gradedness uses a full MPI_ALLREDUCE:
call MPI_Allreduce(my_refine_change, refine_change, lgt_n, MPI_INTEGER1, MPI_MAX, WABBIT_COMM, ierr)
this can be extremely expensive if params%number_blocks becomes large and should be replaced b the more recent code using
subroutine synchronize_lgt_data( params, lgt_block, refinement_status_only )
Thomas Engels commented
closed for some time actually