On Apr 22, 2007, at 8:46 PM, Mostyn Lewis wrote:
> More information.
>
> --mca mpi_paffinity_alone 0
Can you describe how you're verifying that the process is actually
bound?
> May I ask I question about the code, which I scanned.
>
> I see in ompi/runtime/ompi_mpi_params.c you do a:
>
> mca_base_param_reg_int_name("mpi", "paffinity_alone",
> "If nonzero, assume that this job
> is the only (set of) process(es) r
> unning on each node and bind processes to processors, starting with
> processor ID 0",
> false, false,
> (int) ompi_mpi_paffinity_alone,
> &value);
> ompi_mpi_paffinity_alone = OPAL_INT_TO_BOOL(value);
You're right that we're not checking the return value here, which is
bad. However, this is a pretty stable portion of the code -- I would
be surprised if it is failing.
Have you stepped through this with a debugger to verify if it is
actually failing or not?
--
Jeff Squyres
Cisco Systems
|
![[Flag]](../../../../../community/mirrors/flag-us.gif){kind=small}