On-the-fly memory compression for multibody algorithms

Eckhardt, W.; Glas, R.; Korzh, D.; Wallner, S.; Weinzierl, T.

Abstract

Memory and bandwidth demands challenge developers of particle-based codes that have to scale on new architectures, as the growth of concurrency outperforms improvements in memory access facilities, as the memory per core tends to stagnate, and as communication networks cannot increase bandwidth arbitrary. We propose to analyse each particle of such a code to find out whether a hierarchical data representation storing data with reduced precision caps the memory demands without exceeding given error bounds. For admissible candidates, we perform this compression and thus reduce the pressure on the memory subsystem, lower the total memory footprint and reduce the data to be exchanged via MPI. Notably, our analysis and transformation changes the data compression dynamically, i.e. the choice of data format follows the solution characteristics, and it does not require us to alter the core simulation code.

Citation

Eckhardt, W., Glas, R., Korzh, D., Wallner, S., & Weinzierl, T. (2015, September). On-the-fly memory compression for multibody algorithms. Presented at International Conference on Parallel Computing (ParCo) 2015, Edinburgh, Scotland

• Presentation Conference Type: Conference Paper (published)
• Conference Name: International Conference on Parallel Computing (ParCo) 2015
• Start Date: Sep 1, 2015
• End Date: Sep 4, 2015
• Acceptance Date: Sep 29, 2015
• Publication Date: Apr 1, 2016
• Deposit Date: Oct 1, 2015
• Publicly Available Date: Nov 9, 2015
• Pages: 421-430
• Series Title: Advances in parallel computing
• Series Number: 27
• Series ISSN: 0927-5452
• Book Title: Parallel computing : on the road to exascale.
• ISBN: 9781614996200
• DOI: https://doi.org/10.3233/978-1-61499-621-7-421
• Public URL: https://durham-repository.worktribe.com/output/1152898
• Publisher URL: http://ebooks.iospress.nl/volumearticle/42680
• Additional Information: Conference dates: 1-4 September 2015