Eur. Phys. J. B (2015) 88: 158
https://doi.org/10.1140/epjb/e2015-60180-8

Colloquium

Colloquium: Large scale simulations on GPU clusters

¹ Istituto per le Applicazioni del Calcolo, National Research Council of Italy, Via dei Taurini 19, 00185 Roma, Italy
² NVIDIA Corporation, 2701 San Tomas Expressway, Santa Clara, CA 95050, USA

^a e-mail: massimo.bernaschi@gmail.com

Received: 6 March 2015
Received in final form: 11 May 2015
Published online: 17 June 2015

Abstract

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, sub-optimal because the GPU features are not exploited at their best. We 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.