Changes between Version 30 and Version 31 of ParaView
- Timestamp:
- 05/03/17 12:01:13 (7 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
ParaView
v30 v31 24 24 There are other more advanced configurations that can be used for Remote Visualization or separation of services (Data, Rendering, and User Interface). \\ 25 25 Each mode separates the three main components (User Interface, Computation, Rendering) in different ways.\\ 26 More details on possible !ParaView scenarios can be found [wiki:ParaView/Jureca here] .26 More details on possible !ParaView scenarios can be found [wiki:ParaView/Jureca here] or [https://daac.hpc.mil/software/ParaView/ParaView_on_Multiple_Processors.html here]. 27 27 28 28 ---- … … 42 42 43 43 === Parallel !ParaView 44 * [http://www.paraview.org/Wiki/ParaView/ParaView_Readers_and_Parallel_Data_Distribution ParaView Readers] 44 If your dataset is large you might be limited by the size of the memory or the cpu performance of a single node. \\ 45 Executing filters on your data in !ParaView might be slow and takes too long or even fails because of memory limitations. \\ 46 One possible solution can be to run !ParaView im parallel across multiple nodes. 45 47 46 ==== Parallel Data Management 47 Data must be distributed across parallel processes to take advantage of resources 48 ==== How to start !ParaView in parallel 49 First of all, __parallel__ !ParaView is only available on vis-compute nodes (not on vis-login nodes).\\ 50 We recommend the following: 51 * Start a VNC session on multiple vis-compute nodes using the login tool 'Strudel' [wiki:vnc3d (more details)]. 52 * Start !ParaViews 'pvserver' with MPI multiple times on the nodes. 53 * click the icon 'start PVServers' on the VNC desktop (profile vis). 54 * Start !ParaView and connect to the pvservers (localhost:11111). 55 56 ==== How to read data to !ParaView in parallel 57 Just starting !ParaView in parallel __does not__ result necessarily in using the compute resources (cpu and memory) of more than one node or using them on the allocated nodes equaly. 58 59 Two main issues must be considered: 60 * Parallel Data Management - the data must be distributed across parallel processes to take advantage of resources 61 * Parallel Work Managemnet - the work must be distributed across parallel processes to take advantage of 62 63 ===== Parallel Data Management 64 Data must be distributed across parallel processes to take advantage of resources.\\ 65 48 66 49 67 * Some !ParaView readers import in parallel