Massively parallel fitting of Gaussian approximation potentials

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 imp...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Sascha Klawohn, James R Kermode, Albert P Bartók
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IOP Publishing 2023-01-01
Edice:	Machine Learning: Science and Technology
Témata:	Gaussian approximation potential machine learning interatomic potential high performance computing ScaLAPACK distributed linear algebra
On-line přístup:	https://doi.org/10.1088/2632-2153/aca743
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!