Hi Patricia,<br><br>When you run paraview(in 2.x) or pvserver(2.x or 3.x) though MPI, the servermanager makes sure that when your reader is instantiated, one copy is started for every processor in the MPI group. The portion of the data that each copy is responsible for reading is a function of its process rank. The way that is done is to look at the request information to find what pieces/extents it is needs to produce.
<br><br>Looking at VTK/Parallel/vtkPDataSetReader.cxx may be helpful.<br><br>cheers<br>Dave DeMarle<br><br><div><span class="gmail_quote">On 8/1/07, <b class="gmail_sendername">Patrícia Sato</b> <<a href="mailto:psato1@gmail.com">
psato1@gmail.com</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Hi everybody<br><br>I have a question about distributed and parallel processing at ParaView: when we create a new filter/reader, how is it repassed to the different machines so that the distributed processing can occur?
<br>
<br>Thanks<br>Patricia Sato <br>
<br>_______________________________________________<br>ParaView mailing list<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:ParaView@paraview.org">ParaView@paraview.org</a><br><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.paraview.org/mailman/listinfo/paraview" target="_blank">
http://www.paraview.org/mailman/listinfo/paraview</a><br><br></blockquote></div><br>