Thank you for your reply . But I want to know whether the paraview can do the parallel with the ply data . And where it redistribute the data and send them to other process, and how it do this. In my experiment , I found that :(189 is the root process) 189::use_distributed_rendring::true 189::use_ordered_compositing::false 189::this->GetRenderWindow()->Render(); 190::use_distributed_rendring::true 190::use_ordered_compositing::false 190::this->GetRenderWindow()->Render(); we can see that it didn't use ordered_compositing, this to say ,it didn't need composite ,whether it say that it didn't need redistribute. Or It distribute data after IO? And 190 use its own window to render.It should use the 189's.I found 190::RenderEventPropagation::false . why this happen?
At 2015-04-17 14:07:47, "Favre Jean" <[email protected]> wrote: I have just a few days ago gotten to the same conclusion. Reading some large PLY files on our Cray nodes which only have 32Gb of memory, I would run out of memory and crash. Checking memory usage with the "Memory Inspector" will show that everything is loaded on rank 0. Using the D3 filter works and is able to re-distribute the data among all tasks. I suggest you try D3. Note also that ParaView is not able to animate through a time-dependent series of files, using the GUI. Never got any feedback on an earlier post (http://public.kitware.com/pipermail/paraview/2015-January/032999.html). I resorted to some python programming to run the animation. cheers ----------------- Jean/CSCS
_______________________________________________ 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 Search the list archives at: http://markmail.org/search/?q=ParaView Follow this link to subscribe/unsubscribe: http://public.kitware.com/mailman/listinfo/paraview
