Log In | Users | Register
Edit | Attach | New | Raw | Diff | Print | | Tools
You are here: COSMO » RcmProjects » ProjPOMPA

Performance on Massively Parallel Architectures (POMPA)

POMPA is a COSMO Priority Project which has started in September 2010 and is currently planned to run until September 2013. Its goal is to prepare the COSMO model for emerging and/or future high performance computing (HPC) architectures. The contect of these POMPA COSMO pages can be modified by everybody and serve the purpose of easily exchanging information and documents.

Note: information posted here is world-readable and -writeable. In case you want to post sensitive information (e.g. publications) please contact me so that we can setup permissions accordingly

If you're interested, you can ask for more information or join the project!

Information & Links

Task pages

  • Task 1 Performance analysis and documentation
  • Task 2 Redesign memory layout and data structures
  • Task 3 Improve current parallelization
  • Task 4 Parallel I/O
  • Task 5 Redesign implementation of dynamical core
  • Task 6 Explore GPU acceleration
  • Task 7 Implementation documentation


  • Doc Useful documents about OpenAcc
  • Errors Tricky errors with OpenAcc and their causes
This site is managed by the Center for Climate Systems Modeling (C2SM).
This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors. Ideas, requests, problems? Send feedback!