THE USE OF HETEROGENEOUS COMPUTING NODES IN GRID SYSTEMS IN SOLVING COMBINATORIAL PROBLEMS
Abstract
The main goal of this work is to create a parallel application that performs computations using a multithreaded execution model, optimized to make the best utilization of all available hardware resources. One of the main implementation requirements is to optimize application per-formance on different computer architectures, and to enable parallel execution of the application on various computing devices that are part of a heterogeneous computing system. The possibility of applying various methods of software and algorithmic optimization on multiprocessor architec-tures of different generations was investigated as well as the effectiveness of their use for highly loaded multithreaded applications was estimated. The problem of quasi-optimal dynamic distribu-tion of computational tasks among all currently available computing devices of a heterogeneous computing system was also solved. Currently, not only multiprocessor computing systems are used to solve large computational problems, but also various types of distributed systems. Distributed computing systems have a number of features: possible failures of nodes and communication channels, unstable operating time of nodes, possible errors in calculations, heterogeneity of com-puting nodes. By heterogeneity of computing nodes, we will understand not only the different com-puting capacity and different architectures of central processors, but also the presence of other devices on the node capable of performing calculations. Such devices include video cards and mathematical coprocessors. A node of a distributed computing system will be called heterogene-ous if, in addition to one or more central processing units, it contains additional computing devic-es. When solving a computational problem on a distributed system, it is necessary to maximize the utilization of all available computing resources. To do this, it is necessary not only to distribute computing subtasks to nodes in accordance with their computing capacity, but also to take into account the features of additional computing devices. This work is devoted to the study of methods for maximizing the resources utilization of heterogeneous nodes.
References
1. Anderson D.P. BOINC: A platform for volunteer computing, Journal of Grid Computing, 2020, Vol. 18, No. 1, pp. 99-122.
2. Wang L., Jie W., Chen J. Grid computing: infrastructure, service, and applications. CRC Press, 2018.
3. Braun T.D. et al. A comparison of eleven static heuristics for mapping a class of independent tasks onto heterogeneous distributed computing systems, Journal of Parallel and Distributed computing, 2001, Vol. 61, No. 6, pp. 810-837.
4. Cirne W. et al. Grid computing for bag of tasks applications, In Proc. of the 3rd IFIP Confer-ence on E-Commerce, E-Business and EGovernment, 2003.
5. Posypkin M., Semenov A., Zaikin O. Using BOINC desktop grid to solve large scale SAT prob-lems, Computer Science, 2012, Vol. 13, No. 1, pp. 25.
6. Yang C.T. et al. Performance benchmarking of deep learning framework on Intel Xeon Phi, The Journal of Supercomputing, 2021, Vol. 77, No. 3, pp. 2486-2510.
7. Jennett C. et al. Motivations, learning and creativity in online citizen science, Journal of Sci-ence Communication, 2016, Vol. 15, No 3.
8. Foster I., Kesselman C. (ed.). The Grid 2: Blueprint for a new computing infrastructure. Else-vier, 2003.
9. Amalarethinam D.I.G., Josphin A.M. Dynamic task scheduling methods in heterogeneous sys-tems: a survey, International Journal of Computer Applications, 2015, Vol. 110, No. 6.
10. Choi S.J. et al. Volunteer availability based fault tolerant scheduling mechanism in desktop grid computing environment, Third IEEE International Symposium on Network Computing and Applications, 2004.(NCA 2004). Proceedings. IEEE, 2004, pp. 366-371.
11. Vatutin E., Nikitina N., Belyshev A., Manzyuk M. On polynomial reduction of problems based on diagonal Latin squares to the exact cover problem, ICCS-DE, 2020, Vol. 2638, pp. 289-297. DOI: 10.47350/ICCS-DE.2020.26.
12. Brown J.W., Cherry F., Most L., Most M., Parker E.T., Wallis W.D. Completion of the spec-trum of orthogonal diagonal Latin squares, Lecture notes in pure and applied mathematics, 1992, Vol. 139, pp. 43-49. DOI: 10.1201/9780203719916.
13. Intel Xeon Phi Coprocessor System Software Developers Guide. Intel Corporation, 2014, 164 p.
14. Al'bert'yan A.M., Kurochkin I.I. Ispol'zovanie soprotsessorov Intel Xeon Phi v grid-sistemakh iz personal'nykh komp'yuterov [The use of Intel Xeon Phi coprocessors in grid systems from personal computers], CEUR-Proceedings: Selected Papers of the II Intern. Sci. Conf." Con-vergent Cognitive Information Technologies", Moscow, Russia, 2017, Vol. 2064, pp. 196-201.
15. Vatutin E., Belyshev A., Nikitina N., Manzuk M. Evaluation of Efficiency of Using Simple Transformations When Searching for Orthogonal Diagonal Latin Squares of Order 10, Com-munications in Computer and Information Science, Vol. 1304. Springer, 2020, pp. 127-146. DOI: 10.1007/978-3-030-66895-2_9.
16. James Jeffers, James Reinders Intel Xeon Phi Processor High Performance Programming. Morgan Kaufmann, 2013, 432 p. ISBN: 978-0-12-410414-3.
17. De Ravé E.G. et al. Using general-purpose computing on graphics processing units (GPGPU) to accelerate the ordinary kriging algorithm, Computers & Geosciences, 2014, Vol. 64, pp. 1-6.
18. Nobile M.S. et al. Graphics processing units in bioinformatics, computational biology and systems biology, Briefings in bioinformatics, 2017, Vol. 18, No. 5, pp. 870-885.
19. Morrison D.R. et al. Branch-and-bound algorithms: A survey of recent advances in searching, branching, and pruning, Discrete Optimization, 2016, Vol. 19, pp. 79-102.
20. Hill M.D. et al. On the Spectre and Meltdown processor security vulnerabilities, IEEE Micro, 2019, Vol. 39, No. 2, pp. 9-19.
