Arvind --
Yes, this does sound like an Etnus problem, but keep us posted. Let us
know if there's anything we need to followup on.
Thanks!
On May 31, 2005, at 4:49 PM, Arvind Gopu wrote:
> Jeff et al-
>
> I believe this problem is in Etnus' domain, but still thought I should
> fwd
> my note to them, your way as well. Not very important...
>
> Cheers,-AG
>
>
> ---------- Forwarded message ----------
> Subject: Unable to laminate variable while running Totalview under LAM
>
> Hello (Peter et al.)-
>
> When I open Totalview using LAM's mpirun, I am unable to laminate a
> variable across multiple processes. I.e. within variable window, View
> ->
> Laminate -> Process does not show me variable values for all processes;
> Instead it gives me "Has No Matching call frame" as the value.
>
> This problem exists both in the older version (6.6) as well as the new
> version (6.8).
>
> If I compile with a -static flag, then variable values for all
> processes
> show up just fine. Also, I don't have the above problem if I run MPICH
> code though the problem of not being able to restart TV when an MPICH
> program completes (BUG REPORT: 7558 - MPI processes unable to restart
> under mpich and mpiexec.) still exists even in TV version 6.8.
>
> Any idea what might be going on?
>
> Here are some more details that may be relevant:
> RedHat Enterprise Linux Advanced Server 3,
> with kernel: 2.4.21-27.0.4.EL.050430
> LAM: lam-gm-7.1.1-intel (compiled with Intel compilers & to use
> Myrinet)
> Test code: Simple MPI program (nothing MPI 2'ish about it)
>
> Let me know if I can provide any more information. If there's no
> obvious
> solution, could file a bug report please? Thanks!
>
> Cheers,
> -Arvind
>
>
> _____________________________________________________________________
> Arvind Gopu | High Performance Computing Group| (UITS-RAC-HPC) @ IU
> HPC website: http://www.indiana.edu/~rac/hpc | Work: (812) 856-0187
> My website: http://cs.indiana.edu/~agopu | Cell: (812) 361-4054
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
--
{+} Jeff Squyres
{+} jsquyres_at_[hidden]
{+} http://www.lam-mpi.org/
|
