It looks like you might be trying to mix versions of LAM (we changed
how the lamd is detected in several different versions, so if you mix
and match, it's common that something can't find the lamd)
From this output, it looks like "example1" was compiled with LAM 6.5.9
and then you tried to run it with LAM 7.0.x. You will need
*everything* to match in terms of LAM version for applications to run
successfully -- lamboot, mpirun, mpicc, etc. So try recompiling your
application with LAM 7.0.6; you should be able to run it then.
On Dec 27, 2004, at 7:19 PM, x z wrote:
> I am able to run ScaLAPACK on LAM 6.5.9 but not 7.0.6 on my Solaris 8
> workstations.
> For example, I tried the "example1.f" program provided in
> http://www.netlib.org/scalapack/examples/
> When I tried to run it with LAM 7.0.6 on 2 nodes, I got the following:
>
> hzmonte_at_living-document% which mpirun
> /home/messengr/LAMMPI/lam-7.0.6/bin/mpirun
>
> hzmonte_at_living-document% lamnodes
> n0 scalable-quality.xxx.edu:1:
> n1 living-document.xxx.edu:1:origin,this_node
>
> hzmonte_at_living-document% mpirun n0-1 example1
> -----------------------------------------------------------------------
> ------
> It seems that there is no lamd running on this host, which indicates
> that the LAM/MPI runtime environment is not operating. The LAM/MPI
> runtime environment is necessary for MPI programs to run (the MPI
> program tired to invoke the "MPI_Init" function).
>
> Please run the "lamboot" command the start the LAM/MPI runtime
> environment. See the LAM/MPI documentation for how to invoke
> "lamboot" across multiple machines.
> -----------------------------------------------------------------------
> ------
> -----------------------------------------------------------------------
> ------
> It seems that there is no lamd running on this host, which indicates
> that the LAM/MPI runtime environment is not operating. The LAM/MPI
> runtime environment is necessary for MPI programs to run (the MPI
> program tired to invoke the "MPI_Init" function).
>
> Please run the "lamboot" command the start the LAM/MPI runtime
> environment. See the LAM/MPI documentation for how to invoke
> "lamboot" across multiple machines.
> -----------------------------------------------------------------------
> ------
> -----------------------------------------------------------------------
> ------
> It seems that [at least] one of the processes that was started with
> mpirun did not invoke MPI_INIT before quitting (it is possible that
> more than one process did not invoke MPI_INIT -- mpirun was only
> notified of the first one, which was on node n0).
>
> mpirun can *only* be used with MPI programs (i.e., programs that
> invoke MPI_INIT and MPI_FINALIZE). You can use the "lamexec" program
> to run non-MPI programs over the lambooted nodes.
> -----------------------------------------------------------------------
> --
>
> I tried lamexec instead of mpirun but it does not help. Thanks.
>
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
--
{+} Jeff Squyres
{+} jsquyres_at_[hidden]
{+} http://www.lam-mpi.org/
|
