@inproceedings{b1b12bcfb807431981f2632971d1856c,
title = "The Pangeo Ecosystem: Interactive Computing Tools for the Geosciences: Benchmarking on HPC",
abstract = "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 different HPC systems. Four different geoscience operations were considered in this benchmarking study with varying chunk sizes and chunking schemes. Both strong and weak scaling analyses were performed. Chunk sizes between 64 MB to 512 MB were considered, with the best scalability obtained for 512 MB. Compared to certain manual chunking schemes, the auto chunking scheme scaled well.",
keywords = "Benchmarking, Cloud, Dask, HPC, Interactive computing, Pangeo, Xarray",
author = "Odaka, \{Tina Erica\} and Anderson Banihirwe and Guillaume Eynard-Bontemps and Aurelien Ponte and Guillaume Maze and Kevin Paul and Jared Baker and Ryan Abernathey",
note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 6th Annual Workshop on HPC User Support Tools, HUST 2019, International Workshop on Software Engineering for HPC-Enabled Research, SE-HER 2019, and 3rd Workshop on Interactive High-Performance Computing, WIHPC 2019, held in conjunction with the International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2019 ; Conference date: 17-11-2019 Through 18-11-2019",
year = "2020",
doi = "10.1007/978-3-030-44728-1\_12",
language = "English",
isbn = "9783030447274",
series = "Communications in Computer and Information Science",
publisher = "Springer",
pages = "190--204",
editor = "Guido Juckeland and Sunita Chandrasekaran",
booktitle = "Tools and Techniques for High Performance Computing - Selected Workshops, HUST, SE-HER and WIHPC, held in Conjunction with SC 2019, Revised Selected Papers",
address = "Germany",
}