FlowVision Scalability on Supercomputers with Angara Interconnect
- 4 Downloads
Scalability of computations in the FlowVision CFD software on the Angara-C1 cluster equipped with the Angara interconnect is studied. Different test problems with 260 thousand, 5.5 million and 26.8 million computational cells are considered. Computations in FlowVision are performed using a new solver of linear systems based on the algebraic multigrid (AMG) method. It is shown that the the special FlowVision’s Dynamic balancing technology significantly improves performance of computations if features of the problem lead to the non-uniform loading of CPUs. The Angara-C1 cluster demonstrates excellent performance and scalability characteristics comparable with its analogues based on the 4X FDR Infiniband interconnect.
Keywords and phrasesscalability FlowVision CFD gas dynamics cluster supercomputer interconnect Angara
Unable to display preview. Download preview PDF.
- 3.S. Derradji, “The BXI interconnect architecture,” HPC hardware efficiency for quantum and classicalmolecular dynamics,” in Proceedings of the 23rd Annual Symposium on High-Performance Interconnects HOTI (IEEE, Santa Clara, CA, 2015).Google Scholar
- 4.H. Fröning, “The on achieving high message rates,” in Proceedings of the 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, Delft, The Netherlands (IEEE, 2013).Google Scholar
- 5.A. S. Simonov, D. V. Makagon, I. A. Zhabin, A. N. Shcherbak, E. L. Syromyatnikov, and D. A. Polyakov, “The first generation of high-speed Angara interconnect,” Naukoemk. Tekhnol. 15 (1), 21–28 (2014).Google Scholar
- 6.A. I. Slutskin, A. S. Simonov, I. A. Zhabin, D. V. Makagon, and E. L. Syromyatnikov, “Development of the ES8430 Angara interconnect for future Russian supercomputers,” Usp. Sovrem. Radioelektron. 1, 6–10 (2012).Google Scholar
- 8.A. A. Agarkov, T. F. Ismagilov, D. V. Makagon, A. S. Semenov, and A. S. Simonov, “Evaluation testing results of the domestic high-speed Angara interconnect,” in Proceedings of the International Conference on Supercomputer Days in Russia, Moscow, Sept. 26–27, 2016 (Mosk. Gos. Univ., Moscow, 2016), pp. 626–639.Google Scholar
- 9.FlowVision—User’s Guide of version 3. 09. 05, Official site FlowVision CFD. https://doi.org/flowvision.ru/webhelp/fven_30905/. Accessed 2017.
- 10.G. B. Sushko and S. A. Kharchenko, “Experimental research on Chebyshev SKIF MSU of combined MPI+threads implementation of the algorithm for solving systems of linear equations arising in FlowVision during the simulation of computational hydrodynamics problems,” in Proceedings of the International Conference on Parallel Computational Technologies PaVT’2009, Nizh. Novgorod, March 30–Apr. 3, 2009 (Yuzh. Ural. Gos. Univ., Chelyabinsk, 2009), pp. 316–324.Google Scholar
- 11.M. J. de C. Henshaw, “M219 cavity case,” in Verification and Validation Data for Computational Unsteady Aerodynamics, Tech. Rep. RTO-TR-26, AC/323(AVT)TP/19 (QinetiQ, UK, 2002), pp. 453–472.Google Scholar
- 13.D. C. Wilcox, Turbulence Modeling for CFD (DCW Industries, 1994).Google Scholar
- 14.S. V. Zhluktov and A. A. Aksenov, “Wall functions for high-reynolds calculations in FlowVision software,” Comput. Res. Modeling 7, 1221–1239 (2015).Google Scholar