Active Knowledge Base Construction for Numerical Simulation of Relativistic Hydrodynamic Flows Based on RHydroBox3D Code
DOI:
https://doi.org/10.14529/cmse260304Keywords:
active knowledge concept, active knowledge base, LuNA system, automatic construction of parallel programs, high performance computing, relativistic hydrodynamicsAbstract
This paper considers the p’blem of automatic construction of efficient parallel programs based on the active knowledge concept for the case study of numerical simulation of relativistic hydrodynamic flows. Development of efficient parallel programs is a challenging task, as it requires specific expertise in system programming. Automatic construction of parallel programs aims to simplify the development of parallel programs with reasonable efficiency. The problem of automatic construction of efficient parallel programs in its general form is algorithmically hard; therefore, it is addressed in specialized ways for various subject areas. The active knowledge concept is a methodology for automatic construction of parallel programs, which enables the construction of efficient parallel programs in particular subject areas. This is achieved by constructing active knowledge bases for the subject areas. Active knowledge base is a partial formal description of a subject area, which can be used by an active knowledge system (e.g. LuNA system) to construct programs. This paper presents the development of an active knowledge base for numerical simulation of relativistic hydrodynamic flows. Based on the analysis of existing implementations that was conducted, the active knowledge base is constructed. It includes operations, variables and specific information, all of which allow solving the problem using 1D domain decomposition with variable number of domains on various configurations of computing systems. The active knowledge base was implemented in the LuNA system. A comparison of the efficiency was carried out between the automatically constructed program and existing implementations, in particular, the original implementation using Fortran. The automatically constructed program appeared to be of no worse quality than the Fortran implementation.
References
Kale L.V., Bhatele A. Parallel Science and Engineering Applications: The Charm++ Approach. CRC Press, 2016. 314 p. DOI: 10.1201/b16251.
Abramov S.M., Adamovich A.I., Kovalenko M.R. T-system: programming framework with support for automatic dynamic parallelization of programs. Case study of implementing a ray tracing algorithm for image rendering. Programming. 1999. Vol. 25, no. 2. P. 100–107. (in Russian).
Bosilca G., Bouteiller A., Danalis A., et al. PaRSEC: Exploiting Heterogeneity to Enhance Scalability. Computing in Science & Engineering. 2013. Vol. 15, no. 6. P. 36–45. DOI: 10.1109/MCSE.2013.98.
Bosilca G., Bouteiller A., Danalis A., et al. Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA. 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum, Anchorage, AK, USA, May 16–20, 2011. Proceedings. 2011. P. 1432–1441. DOI: 10.1109/IPDPS.2011.299.
Bauer M., Treichler S., Slaughter E., Aiken A. Legion: Expressing locality and independence with logical regions. SC ’12: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, Salt Lake City, UT, USA, November 10–16, 2012. Proceedings. 2012. P. 1–11. DOI: 10.1109/SC.2012.71.
Slaughter E., Lee W., Treichler S., et al. Regent: a high-productivity programming language for HPC with logical regions. Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Austin Texas, November 15–20, 2015. Proceedings. Austin, Texas: Association for Computing Machinery, 2015. Article 81. SC ’15. DOI: 10.1145/2807591.2807629.
Malyshkin V. Active Knowledge, LuNA and Literacy for Oncoming Centuries. Programming Languages with Applications to Biology and Security: Essays Dedicated to Pierpaolo Degano on the Occasion of His 65th Birthday / ed. by C. Bodei, G. Ferrari, C. Priami. Cham: Springer International Publishing, 2015. P. 292–303. DOI: 10.1007/978-3-319-25527-9_19.
Malyshkin V.E., Perepelkin V.A. Construction of active knowledge bases for automation of parallel programs construction based on LuNA system. Parallel Computational Technologies (PCT’2024): Proceedings of the International Scientific Conference, Chelyabinsk, Russia, April 2–4, 2024. Chelyabinsk: Publishing of the South Ural State University, 2024. P. 126–136. (in Russian) DOI: 10.14529/pct2024.
Valkovsky V.A., Malyshkin V.E. Synthesis of parallel programs and systems based on computational models. Novosibirsk: Nauka. Siberian branch, 1988. 126 p. (in Russian).
Kulikov I. A new code for the numerical simulation of relativistic flows on supercomputers by means of a low-dissipation scheme. Computer Physics Communications. 2020. Vol. 257. P. 107532. DOI: 10.1016/j.cpc.2020.107532.
Achikanath Chirakkara R., Federrath C., Seta A. AHKASH: a new Hybrid particle-in-cell code for simulations of astrophysical collisionless plasma. Monthly Notices of the Royal Astronomical Society. 2024. Vol. 534, no. 4. P. 3761–3782. DOI: 10.1093/mnras/stae2188.
Yuan Y., Chen A.Y., Luepker M. Physics of pair-producing gaps in black hole magnetospheres: Two-dimensional general relativistic particle-in-cell simulations. The Astrophysical Journal. 2025. Vol. 985, no. 2. P. 159. DOI: 10.3847/1538-4357/adce79.
Sun X., Bai X.-N. The magnetohydrodynamic-particle-in-cell module in Athena++: implementation and code tests. Monthly Notices of the Royal Astronomical Society. 2023. Vol. 523, no. 3. P. 3328–3347. DOI: 10.1093/mnras/stad1548.
Surmin I.A., Bastrakov S.I., Efimenko E.S., et al. Particle-in-Cell laser-plasma simulation on Xeon Phi coprocessors. Computer Physics Communications. 2016. Vol. 202. P. 204–210. DOI: 10.1016/j.cpc.2016.02.004.
Gruber T.R. Toward principles for the design of ontologies used for knowledge sharing? International Journal of Human-Computer Studies. 1995. Vol. 43, no. 5. P. 907–928. DOI: 10.1006/ijhc.1995.1081.
Cecconi B., Debisschop L., Derrière S., et al. OntoPortal-Astro, a semantic artefact catalogue for astronomy. Astronomy and Computing. 2025. Vol. 53. P. 100991. DOI: 10.1016/j.ascom.2025.100991.
Salayandia L., Roach S., Gates A.Q. Program synthesis from Workflow-Driven Ontologies. NAFIPS 2008 - 2008 Annual Meeting of the North American Fuzzy Information Processing Society, New York, NY, USA, May 19–22, 2008. Proceedings. 2008. P. 1–6. DOI: 10.1109/NAFIPS.2008.4531306.
Jackson P. Introduction to expert systems. Harlow, England: Addison-Wesley, 1998. 560 p.
Sapetina A., Kulikov I., Zagorulko G., Glinskiy B. Constructing an Expert System for Solving Astrophysical Problems Based on the Ontological Approach. Parallel Computational Technologies, Dubna, Russia, March 29–31, 2022, Revised Selected Papers / ed. by L. Sokolinsky, M. Zymbler. Cham: Springer International Publishing, 2022. P. 30–42. DOI: 10.1007/978-3-031-11623-0_3.
Malyshkin V.E., Perepelkin V.A. LuNA Fragmented Programming System, Main Functions and Peculiarities of Run-Time Subsystem. Parallel Computing Technologies, Kazan, Russia, September 19–23, 2011. Proceedings / ed. by V. Malyshkin. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. P. 53–61. DOI: 10.1007/978-3-642-23178-0_5.
Malyshkin V., Schukin G. Didal: Distributed Data Library for Development of Parallel Fragmented Programs. Parallel Computing Technologies, Astana, Kazakhstan, August 21–25, 2023. Proceedings. Vol. 14098 / ed. by V. Malyshkin. Cham: Springer Nature Switzerland, 2023. P. 30–41. DOI: 10.1007/978-3-031-41673-6_3.
Numrich R.W., Reid J. Co-array Fortran for parallel programming. SIGPLAN Fortran Forum. 1998. Vol. 17, no. 2. P. 1–31. DOI: 10.1145/289918.289920.
Schukin G., Perepelkin V., Malyshkin V. Parallelization of a Scientific Application Using Didal Distributed Data Library. Parallel Computing Technologies, Almaty, Kazakhstan, October 6–10, 2025. Proceedings / ed. by V. Malyshkin. Cham: Springer Nature Switzerland, 2026. P. 124–139. DOI: 10.1007/978-3-032-06751-7_9.
Information and Computing Center of Novosibirsk State University. URL: http://nusc.nsu.ru/wiki/doku.php/doc/index (accessed: 01.02.2026) (in Russian).
