[Paraview] Tiling configuration?

[Phillip Ezolt]

Berck,
	As you know, the MPI rank of each application instance is very
important when using paraview/ICE-T with a big display.  (If it is
wrong, the display can look like a mixed-up sliding block puzzle...) 

We are working on making HP's SVA/XC clusters work more smoothly with
Paraview, and I have some questions about how you currently use Paraview
with MPI on other types clusters. 

Questions: 
1) What MPI mechanism do you/your customers use when launching the job
to make sure that the proper nodes have proper ranks? 

(From the online examples that I've found
(http://www.cacr.caltech.edu/~slombey/asci/paraview/)  it looks as if
the "-machinefile" parameter to mpirun is used.)

2) Which versions of MPI do you/your customers use? From which vendors? 

...
I am trying to convince some of our developers to tweak things to make
it easier to launch paraview, so your answers would be greatly
appreciated. 

BTW.  If other people on the list are using MPI and would also like to
answer, I would also appreciate it. 

Thanks in advance,
--Phil

On Tue, 2005-05-24 at 15:24 -0400, Berk Geveci wrote:
> This is the first mpi implementation that does not use the same order
> the user specifies. As far as I know, this can't be done in the
> configuration file, sorry. I don't even know if Ice-T lets one do
> this. If it does, adding something to the configuration file wouldn't
> be too hard.

-- 
Phillip Ezolt <Phillip.Ezolt at hp.com>