Astrophysical particle simulations with large custom GPU clusters on three continents

  • Authors:

  • R. Spurzem;P. Berczik;I. Berentzen;K. Nitadori;T. Hamada;G. Marcus;A. Kugel;R. Männer;J. Fiestas;R. Banerjee;R. Klessen

  • Affiliations:

  • National Astronomical Observatories of China, Chinese Academy of Sciences, Beijing, China 100012 and Astronomisches Rechen-Institut (ZAH), University of Heidelberg, Heidelberg, Germany 69120;National Astronomical Observatories of China, Chinese Academy of Sciences, Beijing, China 100012 and Astronomisches Rechen-Institut (ZAH), University of Heidelberg, Heidelberg, Germany 69120 and M ...;Astronomisches Rechen-Institut (ZAH), University of Heidelberg, Heidelberg, Germany 69120 and Institut für Theor. Astrophysik (ZAH), University of Heidelberg, Heidelberg, Germany;Nagasaki Advanced Computing Center, University of Nagasaki, RIKEN Institute, Tokyo, Japan;Nagasaki Advanced Computing Center, University of Nagasaki, RIKEN Institute, Tokyo, Japan;Department of Computer Science V, Central Inst. of Computer Engineering, University of Heidelberg, Heidelberg, Germany;Department of Computer Science V, Central Inst. of Computer Engineering, University of Heidelberg, Heidelberg, Germany;Department of Computer Science V, Central Inst. of Computer Engineering, University of Heidelberg, Heidelberg, Germany;National Astronomical Observatories of China, Chinese Academy of Sciences, Beijing, China 100012 and Astronomisches Rechen-Institut (ZAH), University of Heidelberg, Heidelberg, Germany 69120;Institut für Theor. Astrophysik (ZAH), University of Heidelberg, Heidelberg, Germany;Institut für Theor. Astrophysik (ZAH), University of Heidelberg, Heidelberg, Germany

  • Venue:
  • Computer Science - Research and Development
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present direct astrophysical N-body simulations with up to six million bodies using our parallel MPI-CUDA code on large GPU clusters in Beijing, Berkeley, and Heidelberg, with different kinds of GPU hardware. The clusters are linked in the cooperation of ICCS (International Center for Computational Science). We reach about one third of the peak performance for this code, in a real application scenario with hierarchically block time-steps and a core-halo density structure of the stellar system. The code and hardware is used to simulate dense star clusters with many binaries and galactic nuclei with supermassive black holes, in which correlations between distant particles cannot be neglected.