Parallel Solution of Boundary Value Problems using OpenMP Technology
Authors: Martynenko S.I., Bakhtin V.A., Rumyantsev E.V., Tarasov G.A., Seredkin N.N., Boyarskikh K.A. | Published: 27.04.2022 |
Published in issue: #2(101)/2022 | |
DOI: 10.18698/1812-3368-2022-2-36-56 | |
Category: Mathematics and Mechanics | Chapter: Computational Mathematics | |
Keywords: parallel algorithms, boundary value problems, numerical methods, large-scale granularity |
Abstract
The paper introduces the results of the theoretical and experimental analysis of the Robust Multigrid Technique (RMT), a computational algorithm designed for the numerical solution of (initial-)boundary value problems for the equations of mathematical physics in black-box software. The purpose of the study was to develop robust, efficient and large-scale granulated algorithm for solving a wide class of nonlinear applied problems. The paper describes the algebraic and geometric parallelisms of the RMT and the multigrid cycle for solving nonlinear problems. The OpenMP technology was used to implement the parallel RMT. Computational experiments related to the solution of the Dirichlet problem for the Poisson equation in the unit cube were performed on a personal computer using 3, 9 and 27 threads (p = 3, 9, 27) and on a multiprocessor computer system with shared memory using 27 threads (p = 27). The highest achieved efficiency of the parallel RMT is E ≈ 0.95 at N > 106 and p = 3 and E ≈ 0.80 at N > 107 and p = 27. Findings of the research reveal that the determining factor affecting the efficiency of the parallel RMT is the limited memory performance of multicore computing systems. The complexity of the sequential iteration of the V-cycle and the parallel iteration of the RMT was theoretically analyzed. The study shows that the parallel iteration of the RMT, implemented on 27 threads, will be executed several times faster than the sequential iteration of the V-loop
Research work was carried out with the financial support of the Russian Science Foundation under agreement no. 21-72-20023 on the topic: "Supercomputer simulation of high-speed impacts on artificial space objects and the Earth"
Please cite this article in English as:
Martynenko S.I., Bakhtin V.A., Rumyantsev E.V., et al. Parallel solution of boundary value problems using OpenMP technology. Herald of the Bauman Moscow State Technical University, Series Natural Sciences, 2022, no. 2 (101), pp. 36--56 (in Russ.). DOI: https://doi.org/10.18698/1812-3368-2022-2-36-56
References
[1] Ilin V.P. Matematicheskoe modelirovanie. Ch. 1. Nepreryvnye i diskretnye modeli [Mathematical modeling. Part 1. Continuous and discrete models]. Novosibirsk, SB RAS Publ., 2017.
[2] Martynenko S.I. Posledovatel’noe programmnoe obespechenie dlya universal’noy mnogosetochnoy tekhnologii [Sequential software for the robust multigrid technique]. Moscow, Triumf Publ., 2020.
[3] Martynenko S.I. Parallel’noe programmnoe obespechenie dlya universal’noy mnogo-setochnoy tekhnologii [Parallel software for the robust multigrid technique]. Moscow, Triumf Publ., 2021.
[4] Martynenko S.I. Mnogosetochnaya tekhnologiya: teoriya i prilozheniya [Multigrid technology: theory and applications]. Moscow, FIZMATLIT Publ., 2015.
[5] Martynenko S.I. The robust multigrid technique. For black-box software. Berlin, De Gruyter, 2017.
[6] Samarskiy A.A. Uravneniya parabolicheskogo tipa i raznostnye metody ikh resheniya [Equations of parabolic type and difference methods for their solution]. Trudy Vsesoyuznogo soveshchaniya po differentsial’nym uravneniyam [Proc. of All-Union Meeting on Differential Equations]. Erevan, AN ArmSSR Publ., 1958, pp. 148--160 (in Russ.).
[7] Fedorenko R.P. A relaxation method for solving elliptic difference equations. USSR Comput. Math. Math. Phys., 1962, vol. 1, iss. 4, pp. 1092--1096. DOI: https://doi.org/10.1016/0041-5553(62)90031-9
[8] Vanka S.P. Block-implicit multigrid solution of Navier --- Stokes equations in primitive variables. J. Comput. Phys., 1986, vol. 65, iss. 1, pp. 138--158. DOI: https://doi.org/10.1016/0021-9991(86)90008-2
[9] Hackbusch W. Multi-grid methods and applications. Springer Series in Computational Mathematics. Berlin, Heidelberg, Springer, 1985. DOI: https://doi.org/10.1007/978-3-662-02427-0
[10] Frederickson P.O., McBryan O.A. Parallel superconvergent multigrid. In: Multigrid Methods. Theory, Applications and Supercomputing. New York, Marcel Dekker, 1988, pp. 195--210.
[11] Frederickson P.O., McBryan O.A. Recent developments for the PSMG multiscale method. In: Multigrid Methods III. Birkhauser, 1991, pp. 21--39.
[12] Antonov A.S. Parallel’noe programmirovanie s ispol’zovaniem tekhnologii OpenMP [Parallel programming using OpenMP technology]. Moscow, MSU Publ., 2009.
[13] Gergel V.P. Vysokoproizvoditel’nye vychisleniya dlya mnogoyadernykh mnogoprotsessornykh system [High-performance computations for multi-core multiprocessor systems]. Nizhny Novgorod, Lobachevskiy NNSU Publ., 2010.
[14] Xu J. The auxiliary space method and optimal multigrid preconditioning techniques for unstructured grids. Computing, 1996, vol. 56, no. 3, pp. 215--235. DOI: https://doi.org/10.1007/BF02238513
[15] Wesseling P. An introduction to multigrid methods. Wiley, 1992.
[16] Ortega J.M. Introduction to parallel and vector solution of linear systems. Frontiers of Computer Science. Boston, MA, Springer, 1988. DOI: https://doi.org/10.1007/978-1-4899-2112-3
[17] Trottenberg U., Oosterlee C.W., Schuuller A. Multigrid. Academic Press, 2000.