[Paraview] Can I parallelize different input files?

[Adam Lyon]

Cool! Thanks - I'll try that.  I tried just loading a few vti files anyway
running the pvserver under mpirun on the multi-core machine. This machine
has no GPU and I got a lot of "swrast" errors (one per core). So I think I
don't have a good OpenGL on this machine. I tried building my own Mesa
OpenGL according to
http://www.paraview.org/Wiki/ParaView/ParaView_And_Mesa_3D, but got
compilation errors using the newest version of llvm. Then I had to move on
to other things.  Not sure if you've tried this - maybe you have some
ideas. Anyway, I hope to try this again sometime this week.  --- Adam

*------*

*Adam L. Lyon*
*Scientist; Associate Division Head for Systems for Scientific Applications*

Scientific Computing Division & Muon g-2 Experiment
Fermi National Accelerator Laboratory
630 840 5522 office
www.fnal.gov
lyon at fnal.gov

Connect with us!
Newsletter <http://www.fnal.gov/pub/today/>  |  Facebook
<https://www.facebook.com/Fermilab>  |  Twitter
<https://twitter.com/Fermilab>

On Sun, Jul 12, 2015 at 8:41 PM, Cory Quammen <cory.quammen at kitware.com>
wrote:

>  Hi Adam,
>
>  The PVTI file format should work perfectly for this application. The
> PVTI file is an XML file that specifies the different pieces in the whole
> image and points to the VTI images that contain the pieces. When loaded,
> each piece should land on a different CPU - if you are running 12 CPUs. The
> extents in your VTI files need to be defined in terms of the overall image
> extent - if they aren't you'll need to modify them so that they are.
>
>  I have attached an example PVTI file with four associated VTI files that
> you can use as a model to define your own PVTI file.
>
>  Please let us know if you have any trouble.
>
>  Thanks,
> Cory
>
>
> On Fri, Jul 10, 2015 at 9:34 AM, Adam Lyon <lyon at fnal.gov> wrote:
>
>> Hi - I have 12 fairly large vti files (each one is a simulation of part
>> of the magnetic field of my particle physics detector). Each file covers a
>> distinct part of the total volume, so that all 12 together covers the whole
>> thing. This would seem to be a perfect opportunity to try to parallelize
>> Paraview's handling of these files - one CPU per vti file.  I have a
>> machine with lots of cores at my disposal. Will Paraview recognize by
>> itself that it can parallelize its operations, one CPU per vti file, or do
>> I need to do something to make that happen? There's no overlap between the
>> files - will that be a problem? My plan is to run a pvserver on the
>> many-core CPU machine and connect to it via my Mac. Any advice would be
>> helpful and appreciated!  Thanks! -- Adam
>>       *-----*
>>
>>  *Adam L. Lyon*
>> *Scientist; Associate Division Head for Systems for Scientific
>> Applications*
>>
>>  Scientific Computing Division & Muon g-2 Experiment
>> Fermi National Accelerator Laboratory
>> 630 840 5522 office
>> www.fnal.gov
>> lyon at fnal.gov
>>
>>  Connect with us!
>> Newsletter <http://www.fnal.gov/pub/today/>  |  Facebook
>> <https://www.facebook.com/Fermilab>  |  Twitter
>> <https://twitter.com/Fermilab>
>>
>> _______________________________________________
>> 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
>>
>> Search the list archives at: http://markmail.org/search/?q=ParaView
>>
>> Follow this link to subscribe/unsubscribe:
>> http://public.kitware.com/mailman/listinfo/paraview
>>
>>
>
>
>  --
> Cory Quammen
> R&D Engineer
> Kitware, Inc.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/paraview/attachments/20150712/01b2ced5/attachment.html>