A New Parallel Intel Xeon Phi Hydrodynamics Code for Massively Parallel Supercomputers

被引：11
作者：
Kulikov I.M. [1 ]
Chernykh I.G. [1 ]
Tutukov A.V. [2 ]
机构：
[1] Institute of Computational Mathematics and Mathematical Geophysics, Siberian Branch of the Russian Academy of Sciences, pr. Akademika Lavrent’eva 6, Novosibirsk
[2] Institute of Astronomy, Russian Academy of Sciences, ul. Pyatnitskaya 48, Moscow
来源：
Lobachevskii Journal of Mathematics | 2018年 / 39卷 / 9期
基金：
俄罗斯科学基金会;
关键词：
Computational astrophysics; high performance computing; Intel Xeon Phi;
D O I：
10.1134/S1995080218090135
中图分类号：
学科分类号：
摘要：
In this paper, a new hydrodynamics code called gooPhi to simulate astrophysical flows on modern Intel Xeon Phi processors with KNL architecture is presented. A new vector numerical method implemented in the form of a program code for massively parallel architectures is proposed. A detailed description is given and a parallel implementation of the code is made. A performance of 173 gigaflops and 48 speedup are obtained on a single Intel Xeon Phi processor. A 97 per cent scalability is reached with 16 processors. © 2018, Pleiades Publishing, Ltd.
引用
收藏
页码：1207 / 1216
页数：9
相关论文
共 31 条
  • [1] Kulikov I.M., Chernykh I.G., Snytnikov A.V., Glinskiy B.M., Tutukov A.V., AstroPhi: a code for complex simulation of dynamics of astrophysical objects using hybrid supercomputers, Comput. Phys. Commun., 186, pp. 71-80, (2015)
  • [2] Kulikov I., Chernykh I., Tutukov A., A new hydrodynamic model for numerical simulation of interacting galaxies on Intel Xeon Phi supercomputers, J. Phys.: Conf. Ser, 719, (2016)
  • [3] Glinsky B., Kulikov I., Chernykh I., Et al., The Co-design of Astrophysical Code for Massively Parallel Supercomputers, Lect. NotesComput. Sci., 10049, pp. 342-353, (2017)
  • [4] Kulikov I.M., Chernykh I.G., Glinskiy B.M., Protasov V.A., An efficient optimization of HLL method for the second generation of Intel Xeon Phi processor, Lobachevskii J. Math., 39, pp. 543-551, (2018)
  • [5] Pearcea F.R., Couchman H.M.P., Hydra: a parallel adaptive grid code, New Astron., 2, pp. 411-427, (1997)
  • [6] Wadsley J.W., Stadel J., Quinn T., Gasoline: a flexible, parallel implementation of TreeSPH, New Astron., 9, pp. 137-158, (2004)
  • [7] Matthias S., GRAPESPH: cosmological smoothed particle hydrodynamics simulations with the specialpurpose hardware GRAPE, Mon. Not. R. Astron. Soc., 278, pp. 1005-1017, (1996)
  • [8] Springel V., The cosmological simulation codeGADGET-2, Not. R. Astron. Soc., 364, pp. 1105-1134, (2005)
  • [9] Ziegler U., Self-gravitational adaptive mesh magnetohydrodynamics with the NIRVANA code, Astron. Astrophys., 435, pp. 385-395, (2005)
  • [10] Mignone A., Plewa T., Bodo G., The piecewise parabolic method for multidimensional relativistic fluid dynamics, Astrophys. J., 160, pp. 199-219, (2005)
1234