Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers

I. M. Kulikov, I. G. Chernykh, E. I. Vorobyov, A. V. Snytnikov, D. V. Weins, A. A. Moskovsky, A. B. Shmelev, V. A. Protasov, A. A. Serenko, V. E. Nenashev, V. A. Vshivkov, A. S. Rodionov, B. M. Glinsky, A. V. Tutukov

Research output: Contribution to journalConference articlepeer-review

Abstract

In this paper we present the AstroPhi code for numerical simulation of astrophysical flows at Intel Xeon Phi supercomputers. The co-design of a computational astrophysics model is described. The parallel implementation and scalability tests of the AstroPhi code are presented. The results of simulation of interaction between intergalactic wind and a disk galaxy are provided. For AstroPhi code a 134x speed-up with one Intel Xeon Phi accelerator and 75% weak scaling efficiency on 224x Intel Xeon Phi accelerators was obtained. We obtained the peak performance on a 7168 × 1024 × 1024 mesh size using 53760 RSC PetaStream threads.

Original languageEnglish
Pages (from-to)205-220
Number of pages16
JournalCEUR Workshop Proceedings
Volume1576
Publication statusPublished - 2016
Event10th Annual International Scientific Conference on Parallel Computing Technologies, PCT 2016 - Arkhangelsk, Russian Federation
Duration: 29 Mar 201631 Mar 2016

Keywords

  • High performance computing
  • Intel Xeon Phi accelerators
  • Numerical astrophysics

Fingerprint Dive into the research topics of 'Numerical hydrodynamics simulation of astrophysical flows at Intel Xeon Phi supercomputers'. Together they form a unique fingerprint.

Cite this