ADVANCED PRODUCTION OUTPUT ENGINE FOR IMPLEMENTING PARALLEL COMPUTING
Abstract
Relevance. The paper discusses a theoretical approach to organizing parallel computing based on a
production model of data flow control. The production paradigm of parallel computing has the necessary
conditions for building new architectures and organizing high-performance parallel computing. We consider
production (mathematical) systems that control sets of left-hand sides of productions (samples). The
goal is to increase the efficiency of parallel inference of solutions by reducing unproductive time spent
searching through possible alternatives in the inference graph space. The research is based on the creation
of an extended symbolic computation machine for implementing parallel steps. A symbolic computing
machine is an abstract system that systematizes production output as a sequence of four computational
and search stages. The inference engine defines the general appearance of a homogeneous computing
system. The main difference is the decomposition of the base of production rules into separate subsets
based on the algebra of production and the structuring of relations between products. Instead of a single
“flat” structure, it is proposed to decompose the product base into parts - to introduce a system of independent
subsets of products. Parallel inference is implemented for individual subsets without loss of generality,
while the search for possible alternatives is reduced. Each subset of productions has a special
marker word, the value of which activates only one subset of productions. It is loaded into the operating
part of a homogeneous computing system for parallel execution. Results. It is shown that quantitative
estimates of the reduction in output time depend on the total number of productions, the number of subsets
formed and their size. Simulation has shown that even the simplest decomposition into two subsets (one subset consists of 2 productions) gives a time gain of (1.07-1.52) times, proportional to the total number of
productions. Conclusions. The created extended symbolic computing machine is the basis for the subsequent
creation of the architecture of a homogeneous computing system with a combination of centralized
and local control. This property allows computational units of a homogeneous operating part to work in
parallel without excessive access to shared memory.
References
and methods in parallel processes]. Moscow: Nauka, 1986, 296 p.
2. Guzik V.F., Kalyaea I.A., Levin I.I. Rekonfiguriruemye vychislitel'nye sistemy: ucheb. posobie [Reconfigurable
computing systems: textbook: manual]. Taganrog: Izd-vo YuFU, 2016, 472 p.
3. Bulyga F.S., Kureychik V.M. Sravnitel'nyy analiz metodov vektorizatsii tekstovykh dannykh bol'shoy
razmernosti [Comparative analysis of methods for vectorizing high-dimensional text data], Izvestiya YuFU.
Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2023, No. 2 (232), pp. 212-226.
4. Titenko E.A., Emel'yanov S.G., Zerin I.S. Odnorodnye vychislitel'nye struktury dlya parallel'nykh
simvol'nykh vychisleniy [Homogeneous computational structures for parallel symbolic computations],
Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta [News of the South-West State University],
2011, No. 6 (39), Part 2, pp. 77-82.
5. Lothaire M. Algebraic Combinatorics on Words. Cambridge: Cambridge University Press; 2002.
(In Eng). – DOI: https:// doi.org/10.1017/CBO9781107326019.
6. Lothaire M. Applied Combinatorics on Words. In: Encyclopedia of Mathematics and its Applications.
Cambridge: Cambridge University Press, 2005.
7. Lyuger Dzh.F. Iskusstvennyy intellekt: strategii i metody resheniya slozhnykh problem [Artificial
intelligence: strategies and techniques for solving complex problems]. Moscow: Izdatel'skiy dom
«Vil'yams», 2003, 864 p.
8. Ognev I.V., Borisov V.V., Sutula N.A. Assotsiativnye pamyat', sredy, sistemy [Associative memory,
environments, systems], Moscow: Goryachaya liniya – Telekom, 2016, 420 p.
9. Gladkov L.A., Kureychik V.V., Kureychik V.M., Sorokoletov P.V. Bioinspirirovannye metody v
optimizatsii [Bioinspired optimization methods]. Moscow: Fizmatlit, 2009, 384 p.
10. Adamov A.A., Eysymont L.K. Varianty arkhitekturnykh resheniy EKB dlya sistem iskusstvennogo
intellekta [Options for ECB architectural solutions for artificial intelligence systems], Proektirovanie
budushchego. Problemy tsifrovoy real'nosti: Tr. 3-y Mezhdunarodnoy konferentsii [Designing the future.
Problems of digital reality: proceedings of the 3rd International Conference]. Moscow: IPM im.
M.V. Keldysha, 2020, pp. 112-131.
11. Va B.U., Louray M.B., Gotsze Li. EVM dlya obrabotki simvol'noy informatsii [Computer for processing
symbolic information], TIIER [TIIER], 1989, Vol. 77, No. 4, pp. 5-40.
12. Dobritsa V.P., Titenko E.A., KHalin Yu.A., Kiselev A.V. Sistemy iskusstvennogo intellekta [Artificial
intelligence systems]. Kursk: ZAO «Universitetskaya kniga», 2023, 143 p.
13. Eysymont L.K., Molyakov A.S., Zaborovskiy V.S., Fedorov S.A. Simvol'naya obrabotka: epizody
otechestvennoy istorii i perspektivy [Symbolic processing: episodes of Russian history and prospects],
Mater. 2-y Vserossiyskoy nauchno-tekhnicheskoy konferentsii «Superkomp'yuternye tekhnologii (CKT-
2012)» [Materials of the 2nd All-Russian Scientific and Technical Conference “Supercomputer Technologies
(SKT-2012)”]. Divnomorskoe, 2012, pp. 202-206.
14. Burtsev V.S. Parallelizm vychislitel'nykh protsessov i razvitie arkhitektur superEVM: Sb. statey [Parallelism
of computing processes and development of supercomputer architectures: collection of articles:
Articles]. Moscow: TORUS PRESS, 2006, 416 p.
15. Wichert A. Artificial intelligence and a universal quantum computer, AI Communications, 2016,
Vol. 29. Issue 4, pp. 537-543.
16. Bova V.V., Kravchenko Yu.A., Rodzin S.I. Metody i algoritmy klasterizatsii tekstovykh dannykh
(obzor) [Methods and algorithms for clustering text data (review)], Izvestiya YuFU. Tekhnicheskie
nauki [Izvestiya SFedU. Engineering Sciences], 2022, No. 4 (228), pp. 122-143.
17. Rybina G.V. Osnovy postroeniya intellektual'nykh system [Fundamentals of building intelligent systems].
Moscow: Finansy i statistika. 2010, 430 p.
18. Popov E.V. Staticheskie i dinamicheskie ekspertnye sistemy [Static and dynamic expert systems].
Moscow: Finansy i statistika. 1996, 211 p.
19. Dovgal' V.M. Metody modifikatsii formal'nykh sistem obrabotki simvol'noy informatsii [Methods for
modifying formal systems for processing symbolic information]. Kursk: Izd-vo Kursk. gos. tekhn. unt,
1996, 115 p.
20. Titenko E.A. Produktsionnaya model' i abstraktnaya mashina dlya realizatsii raspredelennykh
parallel'nykh vychisleniy [Production model and abstract machine for implementing distributed parallel
computing], Telekommunikatsii [Telecommunications], 2012, No. 6, pp. 7-11.
21. Tipikin A.P., Titenko E.A. Modifikatsiya tsikla raboty mashiny vyvoda dlya parallel'nykh
vychislitel'nykh ustroystv [Modification of the output machine operation cycle for parallel computing
devices], Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta [News of the South-West State
University], 2011, No. 6-2 (39), pp. 92-96.
22. Tutov E.B., Titenko E.A., Atakishchev A.O., TSukanov K.S. Primenenie kontekstno-svobodnykh grammatik
dlya obrabotki tekstov na estestvennom yazyke [Application of context-free grammars for processing
texts in natural language], Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya:
Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie [News of the South-
Western State University. Series: Management, computer technology, computer science. Medical instrumentation],
2012, No. 2-1, pp. 97-101.
23. Dovgal' V.M., Titenko E.A. Parallel'nye strategii vyvodov dlya sistem podderzhki prinyatiya resheniya
[Parallel inference strategies for decision support systems], Vestnik novykh meditsinskikh tekhnologiy
[Bulletin of new medical technologies], 2006, Vol. 13, No. 1, pp. 143-144.
24. Dobritsa V.P., Titenko E.A., Khalin Yu.A., Katykhin A.I. Modeli predstavleniya i obrabotki znaniy v
informatsionno-analiticheskikh sistemakh [Models of representation and processing of knowledge in
information and analytical systems]. Kursk: ZAO «Universitetskaya kniga», 2023, 172 p.
25. Karri Kh.B. Osnovaniya matematicheskoy logiki [Foundations of mathematical logic]: transl. from
english. Moscow: Mir, 1969, 568 p.
