[petsc-users] Unstructured mesh

Mark Adams mfadams at lbl.gov
Mon Dec 13 08:02:44 CST 2021

> It is not. The number of processes is specified independently using
> 'mpiexec -n <p>' or when using the test system NP=<p>.
>> (i)     Say I start with -cells 1,1,1 -max_conv its 7; that would
>> eventually leave all refinement on level 7 running on 1 MPI process?
> I don't understand

> (ii)    Say I start with -cells 2,2,1 -max_conv its n; is it recommended
>> to run on 4 MPI processes?
> Yes!

> No, those options do not influence the number of processes.

Correct, but you are not answering the question that he asked!

The coupling of the two is not enforced in the code, but to get good load
balancing you want i*j*k == NP. (there is more flexibility than this, but
this is the place to start.)

>> I am running ex56 on gpu; I am looking at KSPSolve (or any other event)
>> but no gpu flops are recorded in the -log_view?
> I do not think you are running on the GPU then. Mark can comment, but we
> usually specify GPU execution using the Vec and Mat types
> through -dm_vec_type and -dm_mat_type.

This test has a ex56_ prefix.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20211213/315b2136/attachment.html>

More information about the petsc-users mailing list