DOI: https://doi.org/10.26089/NumMet.v26r439

Scalability study of parallel algorithm for numerical modeling of plasma confinement in open magnetic traps using simulation modeling methods

Authors

  • Igor G. Chernykh
  • Dmitry V. Vins
  • Vitaly A. Vshivkov
  • Marina A. Boronina

Keywords:

plasma physics
parallel algorithms
simulation modeling

Abstract

This article presents a methodology for evaluating the scalability of parallel algorithms. Instead of conducting costly experiments on supercomputers, we propose using a specialized simulation model. The methodology involves studying and developing the communication and computation scheme of the tested algorithm, creating a simulation model based on the actor model, configuring for a specific supercomputer architecture, and investigating its scalability. The article demonstrates the application of this methodology to a numerical modeling problem for plasma confinement in open magnetic traps. The results indicate 85% scaling efficiency of the algorithm for thousands of cores.


Downloads

Published

2025-12-22

Issue

Vol. 26 (2025): Issue 4.

Section

Parallel software tools and technologies

Authors

Igor G. Chernykh

Institute of Computational Mathematics and Mathematical Geophysics SB RAS (ICM&MG SB RAS)

• Head of Laboratory

Dmitry V. Vins

Institute of Computational Mathematics and Mathematical Geophysics SB RAS (ICM&MG SB RAS)

• Senior Researcher

Vitaly A. Vshivkov

Institute of Computational Mathematics and Mathematical Geophysics SB RAS (ICM&MG SB RAS)

• Chief Researcher

Marina A. Boronina

Institute of Computational Mathematics and Mathematical Geophysics SB RAS (ICM&MG SB RAS)

• Senior Researcher

References

  1. B. Glinskiy, I. Kulikov, I. Chernykh, A. Snytnikov, A. Sapetina, D. Weins, “The Integrated Approach to Solving Large-Size Physical Problems on Supercomputers,” in V. Voevodin, S. Sobolev (eds) Supercomputing, RuSCDays 2017, Moscow, Russia, September 25–26, 2017.(CCIS, Springer, Cham, 2017). Vol. 793, 278–289.
    doi 10.1007/978-3-319-71255-0_22
  2. S. S. Dosanjh, R. F. Barrett, D. W. Doerfler, et al., “Exascale design space exploration and co-design,” Future Generation Computer Systems. 30 (1), 46–58 (2014).
    doi 10.1016/j.future.2013.04.018
  3. P. Czarnul, J. Kuchta, P. Rosciszewski, J. Proficz, “Modeling energy consumption of parallel applications,” Proc. in M. Ganzha, L. Maciaszek, M. Paprzycki (eds) Federated Conference on Computer Science and Information Systems, Gdańsk, Poland, September 11–14, 2016.Annals of Computer Science and Information Systems, Vol. 8, 855–864.
    doi 10.15439/2016F308
  4. D. Shubhangi, S. Bushra, “Deploying Efficiently MapReduce Applications in Heterogeneous Computing Environments Using Novel Scheduling Algorithms,” International Journal of Scientific Engineering and Research (IJSER).5 (7), 61–71 (2017).
    doi 10.70729/IJSER171622
  5. M. Coelho, K. Ocaña, A. Pereira, et al., “Machine Learning Regression-Based Prediction for Improving Performance and Energy Consumption in HPC Platforms,” in Guerrero G., San Martín J., Meneses E., Barrios Hernández C.J., Osthoff C., Monsalve Diaz J.M. (eds) High Performance Computing, CARLA 2024.(CCIS, Springer, Cham, 2025). Vol. 2270, 186–200.
    doi 10.1007/978-3-031-80084-9_13
  6. H. Casanova, A. Legrand, and M. Quinson, “SimGrid: A Generic Framework for Large-Scale Distributed Experiments,” Proc. in Tenth International Conference on Computer Modeling and Simulation (uksim 2008), April 1–3, 2008.(Cambridge, UK, 2008). 126–131.
    doi 10.1109/UKSIM.2008.28
  7. M. Hsieh, R. Riesen, K. Thompson, W. Song, A. Rodrigues, “SST: A Scalable Parallel Framework for Architecture-Level Performance, Power, Area and Thermal Simulation,” Comput. J. 55 (2), 181–191 (2012).
    doi 10.1093/comjnl/bxr069
  8. D. Podkorytov, A. Rodionov, H. Choo, “Agent-based simulation system AGNES* for networks modeling: review and researching,” Proc. of the 6th Int. Conference on Ubiquitous Information Management and Communication (ACM ICUIMC 2012), Kuala Lumpur, Malaysia, February 20–22, 2012.(ACM, New York, NY, USA). Article No. 115, 1–4. doi 10.1145/2184751.2184883.
  9. D. V. Weins, B. M. Glinskiy, I. G. Chernykh, “Analysis of Means of Simulation Modeling of Parallel Algorithms,” in V. Voevodin, S. Sobolev (eds) Supercomputing, RuSCDays 2018, Moscow, Russia, September 24–25, 2018.(CCIS, Springer, Cham, 2019). Vol. 965, 29–39.
    doi 10.1007/978-3-030-05807-4_3
  10. F. Cesarini, S. Thompson, Erlang Programming(O’Reilly, 2009).
  11. Index - Erlang/OTP.
    http://www.erlang.org/ Cited December 18, 2025.
  12. D. D. Ryutov, “Open-ended traps,” Soviet Physics Uspekhi. 31 (4), 300 (1988).
    doi 10.1070/PU1988v031n04ABEH005747
  13. I. Chernykh, I. Kulikov, V. Vshivkov, E. Genrikh, D. Weins, G. Dudnikova, I. Chernoshtanov, M. Boronina, “Energy Efficiency of a New Parallel PIC Code for Numerical Simulation of Plasma Dynamics in Open Trap,” Mathematics. 10 (19), 3684 (2022).
    doi 10.3390/math10193684
  14. B. Glinsky, A. Rodionov, M. Marchenko, D. Podkorytov, D. Weins, “Scaling the Distributed Stochastic Simulation to Exaflop Supercomputers,” Proceedings of the 14th International Conference on High Performance Computing and Communication textsl&IEEE 9th International Conference on Embedded Software and Systems (HPCC–2012), Liverpool, UK, June 25–27, 2012, (Liverpool, UK, 2012). pp. 1131–1136.
    doi 10.1109/HPCC.2012.166
  15. D. A. Migov, D. V. Weins, “Parallel implementation and simulation of network reliability calculation by Monte Carlo method,” Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie vychislitelnaja tehnika i informatika [Tomsk State University Journal of Control and Computer Science]. 47, 66–74 (2019). [in Russian].
    doi 10.17223/19988605/47/8
  16. I. S. Chernoshtanov, I. G. Chernykh, G. I. Dudnikova, M. A. Boronina, T. V. Liseykina, and V. A. Vshivkov, “Effects Observed in Numerical Simulation of High-Beta Plasma with Hot Ions in an Axisymmetric Mirror Machine,” Journal of Plasma Physics, 90 (2), Article No. 905900211 (2024).
    doi 10.1017/S0022377824000333
  17. B. Glinskiy, A. Sapetina, V. Martynov, D. Weins, I. Chernykh, “The Hybrid-Cluster Multilevel Approach to Solving the Elastic Wave Propagation Problem,” in L. Sokolinsky, M. Zymbler (eds) Parallel Computational Technologies. PCT 2017.(CCIS, Springer, Cham, 2017). Vol. 753, 261–274.
    doi 10.1007/978-3-319-67035-5_19
  18. I. Kulikov, I. Chernykh, B. Glinskiy, D. Weins, and A. Shmelev, “Astrophysics simulation on RSC massively parallel architecture,” Proc. in 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid 2015, Shenzhen, China, May 4–7, 2015.pp. 1131–1134.
    doi 10.1109/CCGrid.2015.102
  19. M. A. Boronina, I. M. Kulikov, I. G. Chernikh, D. V. Vins, “Using a Combination of Roe and Rusanov Schemes for the Numerical Solution of the Equations of Magnetohydrodynamics in the Problems of Cosmic Plasma,” J. Appl. Ind. Math. 16 (4), 596–605 (2022).
    doi 10.1134/S1990478922040020
  20. D. Weins, V. Vorobyev, I. Chernykh, I. Logashenko, “Development of simulation model of HPC system for Super Charm-Tau factory,” Journal of Physics: Conference Series, 1336 (1), Article No. 012025 (2019).
    doi 10.1088/1742-6596/1336/1/012025
  21. Particle-in-Cell Method – WarpX 22.11 documentation.
    https://warpx.readthedocs.io/en/22.11/theory/picsar_theory.html Cited December 18, 2025.
  22. M. A. Boronina, I. S. Chernoshtanov, I. G. Chernykh, et al., “Three-Dimensional Model for Numerical Simulation of Beam-Plasma Dynamics in Open Magnetic Trap,” Lobachevskii J. Math. 45, 1–11 (2024).
    doi 10.1134/S1995080224010074
  23. R. W. Hockney, J. W. Eastwood, Computer Simulation Using Particles(Taylor & Francis Group, NY, USA, 1988).
    doi 10.1201/9780367806934
  24. S. E. Kireev, “Parallel Realization of the Particle-in-Cell Method for Simulating Gravitational Cosmodynamics Problems,” Avtometriya, No. 3. 3–35 (2006).
    https://sibran.ru/upload/iblock/d40/d4055c89a69fe12026b16920879c8ba6.pdf. [in Russian] Cited December 18, 2025.
    doi 10.1017/S0022377824000333
  25. Fix Performance Bottlenecks with Intel® VTune™ Profiler.
    https://www.intel.com/content/www/us/en/developer/tools/oneapi/vtune-profiler.html Cited December 18, 2025.

License

Copyright (c) 2025 И. Г. Черных, Д. В. Винс, В. А. Вшивков, М. А. Боронина

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.