[Paraview] Ensight

[Randall Hand]

I've read some of the other points, and I can easily see one huge
bottleneck.

You've fed STructured Data to Ensight, but processed it (to remove blank
cells) into unstructured for Paraview.  Then, because of this, you have to
run a CellToPoints filter for each isosurface.  The way VTK does
CellToPoints is with a nice cell averaging routine, which gives you great
results but at a huge performance penalty.  For a more-balanced test, you
should have written out per-point data during the conversion process, to
eliminate this reprocessing during the Paraview run.

If I've misunderstood you and you actually are using Per-Cell data, then
perhaps an Isosurface isn't exactly what you want, but rather a Thresholding
(only keep data within a narrow range of your target value).

On 3/21/06, Terry Jordan <tejj at hotmail.com> wrote:
>
> 1) What are you animating? Single Isovalue for multiple
> timesteps?  Multiple
> isovalues?
>
> Single IsoValue for multiple timesteps.
>
>
> 2) What data type are you using?  Native VTK, Native Ensight, or a 3rd
> party.  Each of the first two give a somewhat unfair advantage to one
> product, if you're going for a truly even comparison.
>
> 3rd party cfd data.  We have written readers for paraview and ensight for
> this data.
>
> 3) What data format are you using? Structured, unstructured?  2d, 3d?
> For ensight it is structured, and in paraview we are using unstructured.
>
> 4) What pipeline/viz tools are you using?
> I'm not sure what you are asking here.  But I will guess you mean vtk
> pipeline in paraview.
> In paraview it's Reader->CellToPoint->Contour.
> and in ensight it is just Reader->IsoSurface.
>
> 5) What exactly are you counting time for?  Data load, or just
> computation?
> I bet you're just timing the actual time to generate all the isosurfaces,
> and Ensight gets a big win because it preloads all the data at once where
> Paraview loads it as it goes.
> We are counting the time it takes to generate all of the isosurfaces.
>
> Another problem could be that the data is taken as a structured grid in
> ensight and an unstructured grid in paraview.
>
> ----Original Message Follows----
> From: "Randall Hand" <randall.hand at gmail.com>
> To: "Terry Jordan" <tejj at hotmail.com>
> CC: paraview at paraview.org
> Subject: Re: [Paraview] Ensight
> Date: Tue, 21 Mar 2006 10:21:08 -0600
>
> Lots of information missing here.
> 1) What are you animating? Single Isovalue for multiple
> timesteps?  Multiple
> isovalues?
> 2) What data type are you using?  Native VTK, Native Ensight, or a 3rd
> party.  Each of the first two give a somewhat unfair advantage to one
> product, if you're going for a truly even comparison.
> 3) What data format are you using? Structured, unstructured?  2d, 3d?
> 4) What pipeline/viz tools are you using?
> 5) What exactly are you counting time for?  Data load, or just
> computation?
> I bet you're just timing the actual time to generate all the isosurfaces,
> and Ensight gets a big win because it preloads all the data at once where
> Paraview loads it as it goes.
>
>
> On 3/21/06, Terry Jordan <tejj at hotmail.com> wrote:
> >
> > We are running some test of the performance of ensight versus
> > paraview.  In
> > the test we use the same data set and create an iso surface
> > (contour).  Then
> > we animate the transient data set.  We are seeing about 1 order of
> > magnitude
> > increase in performance over paraview (about 2.5 mins to 29 mins).  Does
> > anyone know if ensight is doing something to speed up the performance
> such
> > as decimation or are their algorithms that much faster?
> >
> > Thanks in advance.
> >
> >
> > _______________________________________________
> > ParaView mailing list
> > ParaView at paraview.org
> > http://www.paraview.org/mailman/listinfo/paraview
> >
>
>
>
> --
> Randall Hand
> Visualization Scientist,
> ERDC-MSRC Vicksburg, MS
> Homepage: http://www.yeraze.com
>
>
> _______________________________________________
> ParaView mailing list
> ParaView at paraview.org
> http://www.paraview.org/mailman/listinfo/paraview
>
>
>


--
Randall Hand
Visualization Scientist,
ERDC-MSRC Vicksburg, MS
Homepage: http://www.yeraze.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://public.kitware.com/pipermail/paraview/attachments/20060321/beffb568/attachment.html