Homepage Program Systems: Theory and Applications Русская версия
ISSN 2079-3316 Bilingual online scientific Online scientific journal of the Ailamazyan Program System Institute of the Ailamazyan PSI of PSI of Russian Academy of Science of RAS 12+ 
Volume 16 (2025) . Issue 4 (67) . Paper No. 3 (450)

Artificial intelligence and machine learning

Research Article
DOIDigital Object Identifier 10.25209/2079-3316-2025-16-4-51-79

Forward propagation algorithm in the dataflow paradigm

Dmitry Nikolayevich Zmejev1Correspondent author, Nikolay Nikolayevich Levchenko2Correspondent author, Arkady Valentinovich Klimov3Correspondent author

National Research Center „Kurchatov Institute“, Moscow, Russia
1 Dmitry Nikolayevich Zmejev — Correspondent author zmejevdn@list.ru
2 Nikolay Nikolayevich Levchenko — Correspondent author nick@burcom.ru
3 Arkady Valentinovich Klimov — Correspondent author arkady.klimov@gmail.com

Abstract. The article discusses the issue of developing and implementing the forward propagation algorithm in the dataflow paradigm. The principles of dataflow computing differ significantly from traditional control-flow computing, just as the dataflow programming paradigm differs from the imperative one. Programs created in the dataflow paradigm are initially parallel. The article provides a detailed description of the forward propagation dataflow algorithm and the program that runs on the parallel dataflow computing system "Buran". The dataflow program is compact and versatile in its code. It automatically scales to the entire system, and its program code does not contain references to library functions and is based solely on basic arithmetic operations such as addition, multiplication, and comparison.

The program is capable of processing perceptrons of any dimension without modification and recompilation of the program code. The size and structure of the processed perceptron is determined by the initial data. The experimental part of the article demonstrates the high adaptability of the dataflow program to processing large amounts of continuously incoming data. An assessment of the applicability of the dataflow computing model for solving neural network problems is given. (In Russian).

Keywords: forward propagation, parallel programming, dataflow computing model, dataflow programming paradigm, parallel dataflow computing system

MSC-20202020 Mathematics Subject Classification 68Q09; 68T01, 68W10MSC-2020 68-XX: Computer science MSC-2020 68Qxx: Theory of computing MSC-2020 68Q09: Other nonclassical models of computation MSC-2020 68Txx: Artificial intelligence MSC-2020 68T01: General topics in artificial intelligence MSC-2020 68Wxx: Algorithms in computer science MSC-2020 68W10: Parallel algorithms in computer science

Acknowledgments: The work was carried out within the state assignment of NRC «Kurchatov institute»

For citation: Dmitry N. Zmejev, Nikolay N. Levchenko, Arkady V. Klimov. Forward propagation algorithm in the dataflow paradigm. Program Systems: Theory and Applications, 2025, 16:4, pp. 51–79. (In Russ.). https://psta.psiras.ru/2025/4_51-79.

Full text of article (PDF): https://psta.psiras.ru/read/psta2025_4_51-79.pdf.

The article was submitted 15.07.2025; approved after reviewing 25.08.2025; accepted for publication 25.08.2025; published online 04.09.2025.

© Zmejev D. N., Levchenko N. N., Klimov A. V.
2025
Editorial address: Ailamazyan Program Systems Institute of the Russian Academy of Sciences, Peter the First Street 4«a», Veskovo village, Pereslavl area, Yaroslavl region, 152021 Russia;   Website:  http://psta.psiras.ru Phone: +7(4852) 695-228;   E-mail: ;   License: CC-BY-4.0License text on the Creative Commons site
© Ailamazyan Program System Institute of Russian Academy of Science (site design) 2010–2025