On Mon, Feb 20, 2012 at 3:21 PM, Sean Farley <span dir="ltr"><<a href="mailto:sean@mcs.anl.gov">sean@mcs.anl.gov</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="gmail_quote"><div class="im"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">This hangs for me in the METIS ordering stage (src/ksp/ksp/examples/tutorials/ex2):<br>
<br>mpirun -np 1 ./ex2 -n 100 -m 100 -ksp_type preonly -pc_type lu -pc_factor_mat_solver_package mumps -mat_mumps_icntl_7 5 -info</blockquote>
<div><br></div></div><div>Thanks, I'll look into this. </div></div>
</blockquote></div><br>It seems to be a problem with metis' interpretation of the vertex weights. If you set the vwgt=0x0 in a debugger when stopped at metis_nodend_ it completes successfully. Also, if you set the weights to 1 inside dmumps_part2.F like:<br>
<br> DO I=1,NCMP<br> FILS(I) = 1<br> ENDDO<br><br>it also runs fine. I think having zero vertex weights is probably wrong anyways.<br><br>Regards,<br>John<br><br>