Isee, thank you! -- Rich On Feb 15, 2012, at 11:17 AM, David E DeMarle wrote:
> Other than look in the source code and see how each reader handles > UPDATE_EXTENT/UPDATE_PIECE_NUMBER* no. > > The default behavior for a reader which doesn't understand parallelism > is to have every node read the whole file and let the pipeline clip > out and deallocate everything owned by the other nodes just after the > reader. > > Readers that do understand parallelism vary in what specific strategy > they use to support it. Most have each node read a different file or > stripe of the same file and get just the local portion of the data. I > gather that some of the newer readers read larger portions on some > nodes and transmit over MPI the subportions that other nodes are > responsible (like the vtkTransmitX filters) for. > > This question has been asked twice recently so I'll see about > compiling a list and putting a description of the parallel strategy > that each reader uses into the XML and thus book and help. In the mean > time ask the list about any particular reader and someone will most > likely answer what that reader does. > > *see http://paraview.org/Wiki/Writing_ParaView_Readers > > David E DeMarle > Kitware, Inc. > R&D Engineer > 21 Corporate Drive > Clifton Park, NY 12065-8662 > Phone: 518-881-4909 > > > > On Wed, Feb 15, 2012 at 12:31 PM, Cook, Rich <[email protected]> wrote: >> Is there a way to determine if a reader works in parallel? I'm having a >> reader crash when run in parallel, and I'm not sure which are supposed to >> handle parallelism and which aren't, and if not, then is it supposed to >> crash or give an error or...? >> Thanks. >> -- >> ✐Richard Cook >> ✇ Lawrence Livermore National Laboratory >> Bldg-453 Rm-4024, Mail Stop L-557 >> 7000 East Avenue, Livermore, CA, 94550, USA >> ☎ (office) (925) 423-9605 >> ☎ (fax) (925) 423-6961 >> --- >> Information Management & Graphics Grp., Services & Development Div., >> Integrated Computing & Communications Dept. >> (opinions expressed herein are mine and not those of LLNL) >> >> >> >> _______________________________________________ >> 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 -- ✐Richard Cook ✇ Lawrence Livermore National Laboratory Bldg-453 Rm-4024, Mail Stop L-557 7000 East Avenue, Livermore, CA, 94550, USA ☎ (office) (925) 423-9605 ☎ (fax) (925) 423-6961 --- Information Management & Graphics Grp., Services & Development Div., Integrated Computing & Communications Dept. (opinions expressed herein are mine and not those of LLNL) _______________________________________________ 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
