The Pangeo Ecosystem: Interactive Computing Tools for the Geosciences: Benchmarking on HPC

The Pangeo ecosystem is an interactive computing software stack for HPC and public cloud infrastructures. In this paper, we show benchmarking results of the Pangeo platform on two di erent HPC sys- tems. Four di erent geoscience operations were considered in this bench- marking study with varying chunk sizes and chunking schemes. Both strong and weak scaling analyses were performed. Chunk sizes between 64MB to 512MB were considered, with the best scalability obtained for 512MB. Compared to certain manual chunking schemes, the auto chunk- ing scheme scaled well.

Keyword(s)

Pangeo, interactive computing, HPC, cloud, benchmarking, Dask, Xarray

Full Text

FilePagesSizeAccess
Author's final draft
148 Mo
Diaporama
2421 Mo
Publisher's official version
15307 Ko
How to cite
Odaka Tina, Banihirwe Anderson, Eynard-Bontemps Guillaume, Ponte Aurelien, Maze Guillaume, Paul Kevin, Baker Jared, Abernathey Ryan (2019). The Pangeo Ecosystem: Interactive Computing Tools for the Geosciences: Benchmarking on HPC. Juckeland G., Chandrasekaran S. (eds) Tools and Techniques for High Performance Computing. HUST 2019, SE-HER 2019, WIHPC 2019. Communications in Computer and Information Science, vol 1190. Springer, Cham. Print ISBN 978-3-030-44727-4 Online ISBN 978-3-030-44728-1. https://doi.org/10.1007/978-3-030-44728-1_12. pp.190-204 .. https://doi.org/10.1007/978-3-030-44728-1_12, https://archimer.ifremer.fr/doc/00597/70946/

Copy this text