The Library
Massively parallel fitting of Gaussian approximation potentials
Tools
Klawohn, Sascha, Kermode, James R. and Bartók, Albert P. (2023) Massively parallel fitting of Gaussian approximation potentials. Machine Learning: Science and Technology, 4 (1). 015020. doi:10.1088/2632-2153/aca743 ISSN 2632-2153.
|
PDF
WRAP-Massively-parallel-fitting-Gaussian-23.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (562Kb) | Preview |
Official URL: https://doi.org/10.1088/2632-2153/aca743
Abstract
We present a data-parallel software package for fitting Gaussian approximation potentials (GAPs) on multiple nodes using the ScaLAPACK library with MPI and OpenMP. Until now the maximum training set size for GAP models has been limited by the available memory on a single compute node. In our new implementation, descriptor evaluation is carried out in parallel with no communication requirement. The subsequent linear solve required to determine the model coefficients is parallelised with ScaLAPACK. Our approach scales to thousands of cores, lifting the memory limitation and also delivering substantial speedups. This development expands the applicability of the GAP approach to more complex systems as well as opening up opportunities for efficiently embedding GAP model fitting within higher-level workflows such as committee models or hyperparameter optimisation.
Item Type: | Journal Article | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics Q Science > QC Physics |
||||||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering Faculty of Science, Engineering and Medicine > Science > Physics |
||||||||||||
SWORD Depositor: | Library Publications Router | ||||||||||||
Library of Congress Subject Headings (LCSH): | Gaussian processes, Approximation theory, Potential theory (Mathematics), Machine learning, High performance computing, Algebras, Linear -- Data processing, Subroutines (Computer programs) | ||||||||||||
Journal or Publication Title: | Machine Learning: Science and Technology | ||||||||||||
Publisher: | IOP Publishing | ||||||||||||
ISSN: | 2632-2153 | ||||||||||||
Official Date: | 16 February 2023 | ||||||||||||
Dates: |
|
||||||||||||
Volume: | 4 | ||||||||||||
Number: | 1 | ||||||||||||
Article Number: | 015020 | ||||||||||||
DOI: | 10.1088/2632-2153/aca743 | ||||||||||||
Status: | Peer Reviewed | ||||||||||||
Publication Status: | Published | ||||||||||||
Reuse Statement (publisher, data, author rights): | ** From IOP Publishing via Jisc Publications Router ** History: received 19-10-2022; revised 15-11-2022; oa-requested 16-11-2022; accepted 29-11-2022; epub 16-02-2023; open-access 16-02-2023; ppub 01-03-2023. ** Licence for this article: http://creativecommons.org/licenses/by/4.0 | ||||||||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||
Copyright Holders: | © 2023 The Author(s). Published by IOP Publishing Ltd | ||||||||||||
Date of first compliant deposit: | 21 February 2023 | ||||||||||||
Date of first compliant Open Access: | 21 February 2023 | ||||||||||||
RIOXX Funder/Project Grant: |
|
||||||||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year