[Paraview] Paraview in batch and in parallel

[David E DeMarle]

Yes you generally still need MPI installed. You may also need to build
paraview yourself.

At Kitware we inconsistently include MPI in our binaries due to technical
difficulties regarding the range of OS's and versions we build for. Also,
the MPI we distribute is likely not compatible and almost certainly not
optimal on your hardware. Depending on your OS and distribution, there may
be paraview-MPI package you can simply pull.

And you are correct. Once you get paraview with mpi installed, run mpiexec
-n N pvbatch to run it in parallel.

See also: http://paraview.org/paraview/resources/webinars.html "Big Data
Analysis" and
http://extremecomputingtraining.anl.gov/files/2013/07/DOEPV.pdf for more
background knowledge.

On Jul 26, 2013 9:18 PM, "Nikolaos Beratlis" <nikos.beratlis at gmail.com>
wrote:

>
> I read in Paraview Wiki that as of Paraview 3.10 the MPI library is
packaged in the binary release. Do I still need to have an MPI version
installed on my computer to run Paraview in parallel in batch mode
(pvbatch)? If MPI is not required, then how do I run pvbatch in parallel.
Is there an argument to specify to use multi core on shared memory
clusters? Otherwise I assume that a MPI version is required and I'd run it
using "mpiexec -n Nprocs pvbatch python.py"
>
> Thank you,
>
> Nikos
>
> _______________________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
http://www.kitware.com/opensource/opensource.html
>
> Please keep messages on-topic and check the ParaView Wiki at:
http://paraview.org/Wiki/ParaView
>
> Follow this link to subscribe/unsubscribe:
> http://www.paraview.org/mailman/listinfo/paraview
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.paraview.org/pipermail/paraview/attachments/20130807/d8252b1e/attachment.htm>