[Paraview] How to run paraview in parallel

[Cally K]

Thanks... I just wanted to make sure I was doing the right thing.. the timer
log showed there were some differences

On 5/19/08, Moreland, Kenneth <kmorel at sandia.gov> wrote:
>
>  Is there anything to suggest that something is wrong?  Nothing you are
> doing strikes me as an error.
>
>
>
> There really isn't any difference between the two approaches except that in
> approach B you save the data.  If you don't really want to read that data in
> again, then the save step is unnecessary.  If you do want to read the data
> in, then you may want to consider saving the data after running D3 so that
> you don't have to process it with D3 the next time you load the data.
>
>
>
> The difference between saving data in serial and parallel is the file
> formats offered.  In parallel, you can only use a file format that supports
> writing in parallel.  I think all the current parallel writers create a
> separate file per process and a metafile to point to them all.
>
>
>
> -Ken
>
>
>   ------------------------------
>
> *From:* paraview-bounces at paraview.org [mailto:
> paraview-bounces at paraview.org] *On Behalf Of *Cally K
> *Sent:* Monday, May 19, 2008 3:57 AM
> *To:* ParaView
> *Subject:* [Paraview] How to run paraview in parallel
>
>
>
> hi again
>
> I just want to make sure that I am doing the right thing, I followed some
> manual online to run my data on paraview ( built on a cluster )
>
> I did using 2 approaches
>
> My data is in a XML Polydata format
>
> Approach A
>
> 1) Load the data
>
> 2) Run the D3 filer
>
> 3) And then run Process ID scalar to show the difference
>
>
>
> Approach B
>
> 1) Load the data
>
> 2) save the data -- I read the below notes from paraview wiki
>
> What does "Save Data" entry in the file menu do when you are running more
> than one process ?
>
> When running one process, "Save Data" creates a file from the current data
> set in ParaView. When running more than one process, save data creates
> spatially distributed files. Each process writes its own data in a file. A
> single meta-file pointing to these pieces is also created.
>
> 3) Run the D3 filer
>
> 4) And then run Process ID scalar to show the difference
>
>
>
> What am I doing wrong.. which approach should I follow...? Thanks.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.paraview.org/pipermail/paraview/attachments/20080520/c7f6f3ee/attachment.htm>