> You say there's no swapping.... but if it's spending system time, and it's
> the later insertions that are being slow.... AND it gets worse with 3D
> (which will probably have more DOFs)... it REALLY sounds like you're running
> out of memory....

PETSc needs to be told how many nonzeros will be present on each row of the
sparse matrix. The DofMap figures this out for you, but if you are doing
something unanticipated it could have it wrong.

The old PETSc command-line option was -log_info  and it will tell you
exactly how many allocations occurred in the matrix insertion phase.  You
should have 0. I think as of PETSc 2.3.3 the option may be -info.

In any case run with -help, it may tell you which is the current way to get
at the information you seek.

-Ben


-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/
_______________________________________________
Libmesh-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/libmesh-users

Reply via email to