| Issue |
EPJ Web Conf.
Volume 302, 2024
Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo (SNA + MC 2024)
|
|
|---|---|---|
| Article Number | 02009 | |
| Number of page(s) | 11 | |
| Section | Deterministic Transport Codes: Algorithms, HPC & GPU | |
| DOI | https://doi.org/10.1051/epjconf/202430202009 | |
| Published online | 15 October 2024 | |
https://doi.org/10.1051/epjconf/202430202009
Efficient sweep kernels on shared-memory architectures for the discrete ordinates neutron transport equation on Cartesian and hexagonal geometries
1 Université Paris-Saclay, CEA, Service d’Études des Réacteurs et de Mathématiques Appliquées, F-91191, Gif-sur-Yvette, France
2 Université Paris-Saclay, CEA, Service de Génie Logiciel pour la Simulation, F-91191, Gif-sur-Yvette, France
3 CEA, DES, IRESNE, DTN, Cadarache, F-13108 Saint-Paul-Lez-Durance, France
4 INRIA / AVALON / LIP - ENS Lyon
* e-mail: gabriel.suau@cea.fr
Published online: 15 October 2024
This paper describes the implementation of DONUT, a small multi-group SN-DG transport solver that aims at providing efficient and portable sweep kernels on shared-memory architectures for Cartesian and hexagonal geometries. DONUT heavily relies on the Kokkos C++ library for portability and genericity. First encouraging performance results are presented for multicore CPU architectures.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.