EPJ

2024 Impact factor 4.8
EPJ C - Particles and Fields
Particles and Fields

EPJ B Colloquium: Large scale simulations on GPU clusters

Details
Published on 15 June 2015
Optimal partitioning for 1024 processors of an irregular domain representing a full coronary tree

Graphics Processing Units (GPU) are currently used as a cost-effective platform for computer simulations and big-data processing. Large scale applications require that multiple GPUs work together, but the efficiency obtained with cluster of GPUs is, at times, suboptimal because the GPU features are not exploited at their best.

In this EPJ B Colloquium, Massimo Bernaschi and colleagues describe how it is possible to achieve an excellent efficiency for applications in statistical mechanics, particle dynamics and networks analysis by using suitable memory access patterns and mechanisms like CUDA streams, profiling tools, etc. Similar concepts and techniques may be applied also to other problems like the solution of Partial Differential Equations.

Massimo Bernaschi, Mauro Bisson, and Massimiliano Fatica (2015),
Colloquium: Large scale simulations on GPU clusters,
European Physical Journal B, DOI: 10.1140/epjb/e2015-60180-8

All news

Editors-in-Chief
E. Dudas, M. Elsing, F. Forti, J. Monroe, D.J. Schwarz and G. Zanderighi

Submit your Paper
We thank you and the Editorial Office for the editorial work during the submission and revision of the manuscripts. We are particularly grateful to the Referee for his/her valuable work which has contributed improving the scientific content of the manuscripts.

Claudio Cremaschini and Massimo Tessarotto, Silesian University in Opava, Czech Republic

More testimonials
ISSN: 1434-6052 (Electronic Edition)

© Società Italiana di Fisica and
Springer-Verlag

Conference announcements