80 likes | 97 Views
Explore the integration of HDF5 I/O modules in Weather Research and Forecasting Model (WRF) to improve I/O performance, reduce file size, and enhance storage capabilities. This work, presented at WRF workshops and conferences, led to significant improvements in Parallel HDF5 implementation.
E N D
An HDF5-WRF module MuQun Yang, Robert E. McGrath, Mike Folk National Center for Supercomputing ApplicationsUniversity of Illinois, Urbana-Champaign
What is WRF? • Weather Research and Forecasting Model – Framework for Weather Model Community • Primarily uses sequential I/O with NetCDF
Goal • Provide an optional HDF5 IO module for WRF • Investigate IO performance of WRF
Results • Map WRF data model to HDF5 • Implemented two WRF IO modules • Sequential IO module with compression • Parallel IO module • Parallel IO module is include in WRF distribution • Performance studies • Presented to WRF workshop, conferences
Findings • Parallel HDF5-WRF module can greatly reduce wall clock time in some WRF applications. • Sequential HDF5-WRF module can greatly reduce the WRF file size with szip or shuffling and deflate compression algorithms. • Parallel HDF5 library needs to be improved for chunking storage.
Impact • Parallel HDF5 WRF I/O is available to modelling community • Included in WRF 2.0 source distribution (May 2004) • This investigation has led to improvements in Parallel HDF5
For more information • HDF5 WRF IO: http://hdf.ncsa.uiuc.edu/apps/WRF-ROMS • WRF: http://www.wrf-model.org/
Acknowledgements • This work is part of NSF-funded Modeling Environment for Atmospheric Discovery Expedition (MEAD) (http://www.ncsa.uiuc.edu/AboutUs/FocusAreas/MEADExpedition.html)