Massively Parallel Fitting of Gaussian Approximation Potentials

Autor:	Sascha Klawohn, James R Kermode, Albert P Bartók
Jazyk:	angličtina
Rok vydání:	2022
Předmět:	Human-Computer Interaction Condensed Matter - Materials Science Artificial Intelligence Materials Science (cond-mat.mtrl-sci) FOS: Physical sciences Computational Physics (physics.comp-ph) Physics - Computational Physics Software
Zdroj:	ArXiv.org
Popis:	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. 12 pages, 5 figures, 4 tables
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf7845fd33322f2d58d970026fa043a1 http://arxiv.org/abs/2207.03803 Zobrazit plný text záznamu