[Paraview] 1 Parallel Paraview
A. Vidjinnagni
aryvidj at gmail.com
Wed Mar 4 12:51:07 EST 2009
When you work in parallel, paraview automatically subdivide your data in
many pieces according with the number of processors you have.
If not you need to do that yourself by using D3 filter by example. Each
processor has a copy of you code and work separately on the piece
of data he has. Paraview by IceT collect and diplay the output but the
result is still on each process.
If you want to have the result on the the root you can collect the data
yourself to the node0.
If anytime you want to see the different data each process has you can apply
ProcessId filter.
Arolde.
Hi!
I?m not sure if I understood well how Paraview is working in parallel mode:
I have started Paraview in client/server mode, i.e. with
mpirun -np 8 ./pvserver
and then I started the client and connected.
I?m not sure how this works with filters: I?ve written a few filters, and
when I run Paraview in parallel, is the filter parallelized as well,
automatically? That on every piece of data the filter is applied separately
and necessary data of other pieces is send there by mpi? Or is the filter
computed on a single node and I have to change something in order to make it
work parallel?
Applying the ProcessId-Filter on the output of my filter, it says that it
was computed separately on every piece of dataset, I?m just wondering,
because the filter uses the whole dataset to compute the desired output..
thx for explaining,
Natalie
2009/3/4 <paraview-request at paraview.org>
> Send ParaView mailing list submissions to
> paraview at paraview.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
> http://www.paraview.org/mailman/listinfo/paraview
> or, via email, send a message with subject or body 'help' to
> paraview-request at paraview.org
>
> You can reach the person managing the list at
> paraview-owner at paraview.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of ParaView digest..."
>
>
> Today's Topics:
>
> 1. Parallel Paraview (Natalie Happenhofer)
> 2. annotating in paraview? (Chris Goller)
> 3. Re: 64Bit Experiment (Sean McBride)
> 4. Re: Parallel Paraview (Moreland, Kenneth)
> 5. Re: 64Bit Experiment (Clinton Stimpson)
> 6. Re: Parallel Paraview (David E DeMarle)
> 7. Re: 64Bit Experiment (Sean McBride)
> 8. Re: 64Bit Experiment (Michael Jackson)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Wed, 4 Mar 2009 16:26:17 +0100
> From: Natalie Happenhofer <nataliehapp at hotmail.com>
> Subject: [Paraview] Parallel Paraview
> To: <paraview at paraview.org>
> Message-ID: <BAY122-W48BD4CBA39F991F21AF17ABCA70 at phx.gbl>
> Content-Type: text/plain; charset="iso-8859-1"
>
>
> Hi!
> I?m not sure if I understood well how Paraview is working in parallel mode:
> I have started Paraview in client/server mode, i.e. with
> mpirun -np 8 ./pvserver
> and then I started the client and connected.
>
> I?m not sure how this works with filters: I?ve written a few filters, and
> when I run Paraview in parallel, is the filter parallelized as well,
> automatically? That on every piece of data the filter is applied separately
> and necessary data of other pieces is send there by mpi? Or is the filter
> computed on a single node and I have to change something in order to make it
> work parallel?
> Applying the ProcessId-Filter on the output of my filter, it says that it
> was computed separately on every piece of dataset, I?m just wondering,
> because the filter uses the whole dataset to compute the desired output..
>
> thx for explaining,
> Natalie
>
>
> _________________________________________________________________
> ?Quieres cuidarte y estar bien? Conoce MSN Salud y Bienestar
> http://salud.latam.msn.com/
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://www.paraview.org/pipermail/paraview/attachments/20090304/ab6064bc/attachment-0001.htm
> >
>
> ------------------------------
>
> Message: 2
> Date: Wed, 4 Mar 2009 09:34:10 -0600
> From: Chris Goller <goller at gmail.com>
> Subject: [Paraview] annotating in paraview?
> To: paraview at paraview.org
> Message-ID:
> <b0cfaac60903040734w2c554374pd29903a93f29aa79 at mail.gmail.com>
> Content-Type: text/plain; charset="windows-1252"
>
> Hi-
>
> I'm trying to analyze data by looking at it an annotating it. I'd like to
> draw a box around anomalies and then write some information about it.
>
> Is that possible to do?
>
> Thanks,
>
> Chris
>
> --
> ?Like a poet has to write poetry, I wake up in the morning and I have to
> write a computer program.? -- Knuth
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://www.paraview.org/pipermail/paraview/attachments/20090304/70633fd5/attachment-0001.htm
> >
>
> ------------------------------
>
> Message: 3
> Date: Wed, 4 Mar 2009 10:37:03 -0500
> From: "Sean McBride" <sean at rogue-research.com>
> Subject: Re: [Paraview] 64Bit Experiment
> To: "Michael Jackson" <mike.jackson at bluequartz.net>, ParaView
> <ParaView at paraview.org>
> Message-ID: <20090304153703.2002231881 at kingu.local>
> Content-Type: text/plain; charset=ISO-8859-1
>
> On 3/4/09 8:30 AM, Michael Jackson said:
>
> > Who wants to try out the just released Qt 4.5 with Cocoa 64 bit
> >and ParaView 64 bit? Or maybe some already are trying it out? Any
> >complaints or other issues building ParaView CVS against Qt 4.5?
>
> See also:
> <http://public.kitware.com/Bug/view.php?id=7818>
>
> --
> ____________________________________________________________
> Sean McBride, B. Eng sean at rogue-research.com
> Rogue Research www.rogue-research.com
> Mac Software Developer Montr?al, Qu?bec, Canada
>
>
>
>
> ------------------------------
>
> Message: 4
> Date: Wed, 4 Mar 2009 08:43:50 -0700
> From: "Moreland, Kenneth" <kmorel at sandia.gov>
> Subject: Re: [Paraview] Parallel Paraview
> To: "Natalie Happenhofer" <nataliehapp at hotmail.com>,
> "paraview at paraview.org" <paraview at paraview.org>
> Message-ID: <C5D3EFC6.6851%kmorel at sandia.gov<C5D3EFC6.6851%25kmorel at sandia.gov>
> >
> Content-Type: text/plain; charset="iso-8859-1"
>
> In brief, the cells of the data are distributed amongst the processes, and
> each process runs your algorithm on its local piece. Algorithms that
> perform per-cell or per-point operations usually work without any
> communication (assuming the request and receive any necessary ghost cells).
>
> You can read more in Chapter 13 of the ParaView book or in the latest SC
> tutorial that is posted on the ParaView Wiki.
>
> -Ken
>
>
> On 3/4/09 8:26 AM, "Natalie Happenhofer" <nataliehapp at hotmail.com> wrote:
>
> Hi!
> I?m not sure if I understood well how Paraview is working in parallel mode:
> I have started Paraview in client/server mode, i.e. with
> mpirun -np 8 ./pvserver
> and then I started the client and connected.
>
> I?m not sure how this works with filters: I?ve written a few filters, and
> when I run Paraview in parallel, is the filter parallelized as well,
> automatically? That on every piece of data the filter is applied separately
> and necessary data of other pieces is send there by mpi? Or is the filter
> computed on a single node and I have to change something in order to make it
> work parallel?
> Applying the ProcessId-Filter on the output of my filter, it says that it
> was computed separately on every piece of dataset, I?m just wondering,
> because the filter uses the whole dataset to compute the desired output..
>
> thx for explaining,
> Natalie
>
>
> ________________________________
> Hay un nuevo Messenger que tienes que conocer... ?Mira las novedades! <
> http://www.nuevomessenger2009.com/>
>
>
> **** Kenneth Moreland
> *** Sandia National Laboratories
> ***********
> *** *** *** email: kmorel at sandia.gov
> ** *** ** phone: (505) 844-8919
> *** web: http://www.cs.unm.edu/~kmorel<http://www.cs.unm.edu/%7Ekmorel>
>
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://www.paraview.org/pipermail/paraview/attachments/20090304/1b8b4484/attachment-0001.htm
> >
>
> ------------------------------
>
> Message: 5
> Date: Wed, 04 Mar 2009 08:49:00 -0700
> From: Clinton Stimpson <clinton at elemtech.com>
> Subject: Re: [Paraview] 64Bit Experiment
> To: Michael Jackson <mike.jackson at bluequartz.net>
> Cc: ParaView <ParaView at paraview.org>
> Message-ID: <49AEA2EC.5080809 at elemtech.com>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
> Michael Jackson wrote:
> > Thanks, I'll try to take a look at it.
> >
> > Also reported issue http://public.kitware.com/Bug/view.php?id=8671
> > against the FindQt4.cmake file. Patch is attached to the bug.
> >
> > Synopsis: The Carbon framework is being added to the link line when it
> > should not when Qt4.5 built with Cocoa is found.
> >
>
> I didn't change that because qmake still adds the -framework Carbon
> compile flag for a Cocoa based Qt. At least that's what I saw in the
> beta and rc1.
> I'm not sure why it still does.
>
> Clint
>
>
>
> ------------------------------
>
> Message: 6
> Date: Wed, 4 Mar 2009 10:49:49 -0500
> From: David E DeMarle <dave.demarle at kitware.com>
> Subject: Re: [Paraview] Parallel Paraview
> To: Natalie Happenhofer <nataliehapp at hotmail.com>
> Cc: paraview at paraview.org
> Message-ID:
> <e85d6c9a0903040749he8661d8td473450424f3a9ba at mail.gmail.com>
> Content-Type: text/plain; charset=ISO-8859-1
>
> Slightly less briefly than what Ken said:
>
> In parallel, the end of the pipeline on each processor is told to
> process piece i out of j. Where i is the local processor's rank and j
> is the number of processors. See
> vtkStreamingDemandDrivenPipeline::SetUpdatePiece() and
> SetNumberOfPieces(). That information flows back through the pipeline
> in the RequestUpdateExtent pass. Here each filter along the pipeline
> looks as what it is asked to produce, and tells its inputs what they
> need to produce for it to do that. In your case if the algorithm
> requires the whole domain then filter is telling everything upstream
> to give it everything, and parallelism is only effective AFTER your
> filter. If the algorithm can be changed so that each processor needs
> only a portion of the domain (perhaps using ghostlevels to extent the
> boundaries a bit) then you will get better scalability. After
> RequestUpdateExtent, the RequestData pass happens in which each filter
> executes in turn. In this pass the filter's RequestData() method uses
> the input it is given to fill out the previously agreed extent and
> passes it onward.
>
> On Wed, Mar 4, 2009 at 10:26 AM, Natalie Happenhofer
> <nataliehapp at hotmail.com> wrote:
> > Hi!
> > I?m not sure if I understood well how Paraview is working in parallel
> mode:
> > I have started Paraview in client/server mode, i.e. with
> > mpirun -np 8 ./pvserver
> > and then I started the client and connected.
> >
> > I?m not sure how this works with filters: I?ve written a few filters, and
> > when I run Paraview in parallel, is the filter parallelized as well,
> > automatically? That on every piece of data the filter is applied
> separately
> > and necessary data of other pieces is send there by mpi? Or is the filter
> > computed on a single node and I have to change something in order to make
> it
> > work parallel?
> > Applying the ProcessId-Filter on the output of my filter, it says that it
> > was computed separately on every piece of dataset, I?m just wondering,
> > because the filter uses the whole dataset to compute the desired output..
> >
> > thx for explaining,
> > Natalie
> >
> >
> > ________________________________
> > Hay un nuevo Messenger que tienes que conocer... ?Mira las novedades!
> > _______________________________________________
> > 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
> >
> >
>
>
>
> --
> David E DeMarle
> Kitware, Inc.
> R&D Engineer
> 28 Corporate Drive
> Clifton Park, NY 12065-8662
> Phone: 518-371-3971 x109
>
>
> ------------------------------
>
> Message: 7
> Date: Wed, 4 Mar 2009 10:50:44 -0500
> From: "Sean McBride" <sean at rogue-research.com>
> Subject: Re: [Paraview] 64Bit Experiment
> To: "Clinton Stimpson" <clinton at elemtech.com>, "Michael Jackson"
> <mike.jackson at bluequartz.net>
> Cc: ParaView <ParaView at paraview.org>
> Message-ID: <20090304155044.683299720 at kingu.local>
> Content-Type: text/plain; charset=ISO-8859-1
>
> On 3/4/09 8:49 AM, Clinton Stimpson said:
>
> >> Thanks, I'll try to take a look at it.
> >>
> >> Also reported issue http://public.kitware.com/Bug/view.php?id=8671
> >> against the FindQt4.cmake file. Patch is attached to the bug.
> >>
> >> Synopsis: The Carbon framework is being added to the link line when it
> >> should not when Qt4.5 built with Cocoa is found.
> >
> >I didn't change that because qmake still adds the -framework Carbon
> >compile flag for a Cocoa based Qt. At least that's what I saw in the
> >beta and rc1.
> >I'm not sure why it still does.
>
> Not all of Carbon.framework is deprecated, and much of it is available
> in 64 bit too. Maybe they need parts of it even for their Cocoa version?
>
> --
> ____________________________________________________________
> Sean McBride, B. Eng sean at rogue-research.com
> Rogue Research www.rogue-research.com
> Mac Software Developer Montr?al, Qu?bec, Canada
>
>
>
>
> ------------------------------
>
> Message: 8
> Date: Wed, 4 Mar 2009 10:56:30 -0500
> From: Michael Jackson <mike.jackson at bluequartz.net>
> Subject: Re: [Paraview] 64Bit Experiment
> To: ParaView <ParaView at paraview.org>
> Message-ID: <6D0E27F7-469E-4D15-9904-DD092B9F99FF at bluequartz.net>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed; delsp=yes
>
> Um.. well I just put in a bug report the removes the Carbon framework
> from linker flags in the FindQt4.cmake file. Wonder if that was really
> necessary. I just assumed that if I want a true 64 bit build then
> Carbon would hold me back on that.
>
> I guess, how do we know if we get a true 64bit build of Qt4.5 and
> ParaView then? I guess if the compile succeeds that is the first step.
>
> I don't actually have a 64 bit machine (yet) but hopefully by the end
> of the month I'll have one of those swanky Core i7 Xeons that just got
> release on tuesday.
>
> _________________________________________________________
> Mike Jackson mike.jackson at bluequartz.net
> www.bluequartz.net
>
> On Mar 4, 2009, at 10:50 AM, Sean McBride wrote:
>
> > On 3/4/09 8:49 AM, Clinton Stimpson said:
> >
> >>> Thanks, I'll try to take a look at it.
> >>>
> >>> Also reported issue http://public.kitware.com/Bug/view.php?id=8671
> >>> against the FindQt4.cmake file. Patch is attached to the bug.
> >>>
> >>> Synopsis: The Carbon framework is being added to the link line
> >>> when it
> >>> should not when Qt4.5 built with Cocoa is found.
> >>
> >> I didn't change that because qmake still adds the -framework Carbon
> >> compile flag for a Cocoa based Qt. At least that's what I saw in the
> >> beta and rc1.
> >> I'm not sure why it still does.
> >
> > Not all of Carbon.framework is deprecated, and much of it is available
> > in 64 bit too. Maybe they need parts of it even for their Cocoa
> > version?
> >
> > --
> > ____________________________________________________________
> > Sean McBride, B. Eng sean at rogue-research.com
> > Rogue Research www.rogue-research.com
> > Mac Software Developer Montr?al, Qu?bec, Canada
> >
> >
>
>
>
> ------------------------------
>
> _______________________________________________
> 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
>
>
> End of ParaView Digest, Vol 59, Issue 7
> ***************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.paraview.org/pipermail/paraview/attachments/20090304/b00df9be/attachment-0001.htm>
More information about the ParaView
mailing list