[SciPy-user] Parallel linear solver.

Adolph J. Vogel ajvogel@tuks.co...
Fri Jul 25 04:48:33 CDT 2008


Hi Frank, 

Im having trouble with using petcs4py. When trying to run the helloworld.py 
example, I get the following:

adolph@adolph-laptop:~/lib/petsc4py-0.7.5/tests/sandbox$ mpirun -np 2 python 
helloworld.py
[adolph-laptop:07785] mca: base: component_find: unable to open osc pt2pt: 
file not found (ignored)
libibverbs: Fatal: couldn't read uverbs ABI version.
--------------------------------------------------------------------------
[0,0,0]: OpenIB on host adolph-laptop was unable to find any HCAs.
Another transport will be used instead, although this may result in
lower performance.
--------------------------------------------------------------------------
Hello, World!! I am process 0 of 1
[adolph-laptop:07786] mca: base: component_find: unable to open osc pt2pt: 
file not found (ignored)
libibverbs: Fatal: couldn't read uverbs ABI version.
--------------------------------------------------------------------------
[0,0,0]: OpenIB on host adolph-laptop was unable to find any HCAs.
Another transport will be used instead, although this may result in
lower performance.
--------------------------------------------------------------------------
-----------------------------------------------------------------------------
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.
-----------------------------------------------------------------------------
[0]PETSC 
ERROR: ------------------------------------------------------------------------
[0]PETSC ERROR: Caught signal number 15 Terminate: Somet process (or the batch 
system) has told this process to end
[0]PETSC ERROR: Try option -start_in_debugger or -on_error_attach_debugger
[0]PETSC ERROR: or see 
http://www.mcs.anl.gov/petsc/petsc-as/documentation/troubleshooting.html#Signal[0]PETSC 
ERROR: or try http://valgrind.org on linux or man libgmalloc on Apple to find 
memory corruption errors
[0]PETSC ERROR: configure using --with-debugging=yes, recompile, link, and run
[0]PETSC ERROR: to get more information on the crash.
[adolph-laptop:07786] MPI_ABORT invoked on rank 0 in communicator 
MPI_COMM_WORLD with errorcode 59


The invocation I used, works with my mpi4py programs. However nothing from 
petcs4py seems to work. Any help would be greatly appreciated.

Adolph

On Thursday 24 July 2008 16:27:05 you wrote:
> Yes, there are.  What you are looking for is petsc4py.  PETSc is a very
> good, well-developed package for scalable scientific computing.  It is
> based on MPI and is very well-known and well-supported package (it is
> really amazing actually how good their support actually is!)
>
> Anyways, Lisandro Dalcin, a friend of mine, wrote petsc4py bindings that
> allow you to do anything you want in PETSc in python.  The bindings are
> very good, but not well documented.  It doesn't really matter however,
> because he is so accessible, and PETSc's documentation is so good that you
> can browse through it and guess what the correcponding syntax is in
> petsc4py.
>
> I highly recommend that you check it out.  Let me know how it goes or if
> you have any problems.
>
> -Frank
>
> On Thu, Jul 24, 2008 at 1:59 AM, Adolph J. Vogel <ajvogel@tuks.co.za> wrote:
> > Are there any bindings available for python to a Parallel linear solver
> > package like ScaLapack? I couldnt find anything conclusive on google.
> >
> > Thanx, Adolph
> > _______________________________________________
> > SciPy-user mailing list
> > SciPy-user@scipy.org
> > http://projects.scipy.org/mailman/listinfo/scipy-user



-- 
_/_/_/_/_/_/_/_/_/_/_/_/_/
Adolph J. Vogel
BEng(Mechanical)

University of Pretoria
Office: 012-420-2189
Email: ajvogel@tuks.co.za
Mobile: 072 592 5836
_/_/_/_/_/_/_/_/_/_/_/_/_/


More information about the SciPy-user mailing list