<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=utf-8">
<META content="MSHTML 6.00.6000.16945" name=GENERATOR></HEAD>
<BODY style="MARGIN: 4px 4px 1px; FONT: 10pt Tahoma">I began looking through the documentation again for this issue. From the samples I am able to conceptualize the distributed data filter implementation. But my question remains, is there a more simplistic way to partition data (mesh included) into 4 pieces without the use of MPI or the distributed data filter. Or possible a way to use the distributed data filter without MPI?<BR><BR>>>> "Berk Geveci" <berk.geveci@kitware.com> 12/29/2009 4:51 PM >>><BR>Oooooooo. Normally, you shouldn't have to run with MPI. Since you are<BR>setting the start and the end piece on the writer, the writer should<BR>stream 4 pieces. However, the distributed data filter is a parallel<BR>filter that can't stream so yes, you will have to run with MPI if you<BR>want to use the distributed data filter.<BR><BR>-berk<BR><BR>On Tue, Dec 29, 2009 at 2:14 PM, Terry Jordan <Terry.Jordan@netl.doe.gov> wrote:<BR>> No it creates 1 pvtu and 4 vtus but each vtu is approximately if not exactly<BR>> the same size and contains the entire mesh. To be clear I am not running<BR>> this with MPI. Do I have to? And that is pretty much my entire pipeline.<BR>> How does the distributed data filter know how to break up the mesh? Am I<BR>> missing a call?<BR>><BR>>>>> "Berk Geveci" <berk.geveci@kitware.com> 12/29/2009 1:03 PM >>><BR>> That should work (in theory). It is not?<BR>><BR>> On Tue, Dec 29, 2009 at 1:00 PM, Terry Jordan <Terry.Jordan@netl.doe.gov><BR>> wrote:<BR>>> I am trying this:<BR>>><BR>>> vtkDistributedDataFilter *dataFilter = vtkDistributedDataFilter::New();<BR>>> dataFilter->SetInput(filteredGrid);<BR>>> dataFilter->SetBoundaryMode( 0 );<BR>>><BR>>> vtkXMLPUnstructuredGridWriter *writer =<BR>>> vtkXMLPUnstructuredGridWriter::New();<BR>>> writer->SetInput( dataFilter );<BR>>> writer->SetFileName(vtkFilename);<BR>>> writer->SetNumberOfPieces( 4 );<BR>>> writer->SetStartPiece(0);<BR>>> writer->SetEndPiece(3);<BR>>> writer->Write();<BR>>><BR>>> Do I have to use MPI?<BR>>><BR>>>>>> "Berk Geveci" <berk.geveci@kitware.com> 12/29/2009 12:55 PM >>><BR>>> Inserting a distributed data filter between the reader and the writer<BR>>> should theoretically work. Of course, you can easily run a ParaView<BR>>> (pvbatch) script with 4 processes to do the same thing.<BR>>><BR>>> On Tue, Dec 29, 2009 at 9:07 AM, Terry Jordan <Terry.Jordan@netl.doe.gov><BR>>> wrote:<BR>>>> Yes, I want to break the mesh down. I want to partition the entire data<BR>>>> set<BR>>>> into 4 chunks. Does anyone have a link to sample code? I tried to use<BR>>>> the<BR>>>> distributed data filter, but was unsuccessful in its implementation. I<BR>>>> assume the file format would still be a pvtu and 4 vtus.<BR>>>><BR>>>>>>> "Berk Geveci" <berk.geveci@kitware.com> 12/28/2009 10:18 PM >>><BR>>>> or the distributed data filter in VTK.<BR>>>><BR>>>> On Mon, Dec 28, 2009 at 5:57 PM, Dominik Szczerba <dominik@itis.ethz.ch><BR>>>> wrote:<BR>>>>> -----BEGIN PGP SIGNED MESSAGE-----<BR>>>>> Hash: SHA1<BR>>>>><BR>>>>> I don't think this is intended to partition your mesh, or at least I<BR>>>>> would be highly (if positively) surprised.<BR>>>>><BR>>>>> Do you not mean to partition a mesh for e.g. domain decomposition<BR>>>>> purposes or other parallel applications? Then metis or chaco is what you<BR>>>>> need here.<BR>>>>><BR>>>>> Dominik<BR>>>>><BR>>>>> Terry Jordan wrote:<BR>>>>>><BR>>>>>> I am trying to partition a unstructured grid into 4 evenly sized<BR>>>>>> pieces. Currently I am doing the following:<BR>>>>>><BR>>>>>> vtkXMLPUnstructuredGridWriter *writer =<BR>>>>>> vtkXMLPUnstructuredGridWriter::New();<BR>>>>>> writer->SetInput( filteredGrid );<BR>>>>>> writer->SetFileName(vtkFilename);<BR>>>>>> writer->SetNumberOfPieces( 4 );<BR>>>>>> writer->SetStartPiece(0);<BR>>>>>> writer->SetEndPiece(3);<BR>>>>>> writer->Write();<BR>>>>>><BR>>>>>> filteredGrid is a vtkUnstructuredGrid<BR>>>>>><BR>>>>>> The result of this code is 4 copies of the data (1 pvtu and 4 vtu).<BR>>>>>> Each is identical to the original data. What am I missing? I am<BR>>>>>> running this code on a single cpu without the use of MPI. Do I have to<BR>>>>>> use MPI?<BR>>>>>><BR>>>>>> Thanks in advance.<BR>>>>>><BR>>>>>><BR>>>>>><BR>>>>>> ------------------------------------------------------------------------<BR>>>>>><BR>>>>>> _______________________________________________<BR>>>>>> Powered by www.kitware.com<BR>>>>>><BR>>>>>> Visit other Kitware open-source projects at<BR>>>>>> <A href="http://www.kitware.com/opensource/opensource.html">http://www.kitware.com/opensource/opensource.html</A><BR>>>>>><BR>>>>>> Please keep messages on-topic and check the VTK FAQ at:<BR>>>>>> <A href="http://www.vtk.org/Wiki/VTK_FAQ">http://www.vtk.org/Wiki/VTK_FAQ</A><BR>>>>>><BR>>>>>> Follow this link to subscribe/unsubscribe:<BR>>>>>> <A href="http://www.vtk.org/mailman/listinfo/vtkusers">http://www.vtk.org/mailman/listinfo/vtkusers</A><BR>>>>><BR>>>>> -----BEGIN PGP SIGNATURE-----<BR>>>>> Version: GnuPG v1.4.9 (GNU/Linux)<BR>>>>><BR>>>>> iEYEARECAAYFAks5N84ACgkQ/EBMh9bUuzL60wCg45gdE2GhJbZT9zztDLMJMRiX<BR>>>>> RGoAoNjFFwEpY9IfusrMv2YWiOj/mrEg<BR>>>>> =Rjc+<BR>>>>> -----END PGP SIGNATURE-----<BR>>>>> _______________________________________________<BR>>>>> Powered by www.kitware.com<BR>>>>><BR>>>>> Visit other Kitware open-source projects at<BR>>>>> <A href="http://www.kitware.com/opensource/opensource.html">http://www.kitware.com/opensource/opensource.html</A><BR>>>>><BR>>>>> Please keep messages on-topic and check the VTK FAQ at:<BR>>>>> <A href="http://www.vtk.org/Wiki/VTK_FAQ">http://www.vtk.org/Wiki/VTK_FAQ</A><BR>>>>><BR>>>>> Follow this link to subscribe/unsubscribe:<BR>>>>> <A href="http://www.vtk.org/mailman/listinfo/vtkusers">http://www.vtk.org/mailman/listinfo/vtkusers</A><BR>>>>><BR>>>><BR>>>><BR>>><BR>>><BR>><BR>><BR><BR></BODY></HTML>