Analysis and selection of the structure of a multiprocessor computing system according to the performance criterion
https://doi.org/10.32362/2500-316X-2024-12-6-20-25
EDN: PWDKPB
Abstract
Objectives. Analysis of the various architectures of computing systems (CSs) used in recent decades has allowed us to identify the most common structures. One of the key features is the use of mass-produced equipment to create data processing subsystems (for example, multicore processors and high-capacity semiconductor memory), as well as network equipment to build communication subsystems. This reduces hardware costs and allows typical or cluster configurations to be created, which is especially important for expensive CSs. The desire to achieve high computational speed and performance in such CSs requires minimizing the time to complete the task and balancing time delays both in data processing subsystems and in the communication subsystem which provides data transmission inside the CS. The aim of this work is to analyze computing modules (CMs) and structures on the basis of which the construction of cluster CSs is carried out.
Methods. The main results of the work were obtained using methods of mathematical analysis and modeling.
Results. The study considers the structure of modern multicore microprocessors as the basis for building CMs of cluster CSs. As the number of cores in the microprocessor structure increases, the communication network which unites them into a single structure becomes more complicated. It has been shown that in new developments of microprocessors, communication between cores is performed in the form of a network. The microprocessors themselves are MIMD structures in accordance with the well-known Flynn classification.
Conclusions. The proposed method of selecting an effective structure of a CS allows us to obtain the optimal structure of a CS according to the criterion of performance.
About the Authors
G. V. Petushkov
MIREA – Russian Technological University
Russian Federation
Russian Federation
Grigory V. Petushkov, Vice-Rector
78, Vernadskogo pr., Moscow, 119454
A. S. Sigov
https://www.researchgate.net/profile/A_Sigov
MIREA – Russian Technological University
Russian Federation
MIREA – Russian Technological University
Russian Federation
Alexander S. Sigov, Academician at the Russian Academy of Sciences, Dr. Sci. (Phys.–Math.), Professor,
President
78, Vernadskogo pr., Moscow, 119454
Scopus Author ID 35557510600;
ResearcherID L-4103-2017
References
1. Voevodin V.V., Voevodin Vl.V. Parallel’nye vychisleniya ( Parallel Computing). St. Petersburg: BHV-Petersburg; 2002. 608 p. (in Russ.).
2. Orlov S.A., Tsil’ker B.Ya. Organizatsiya EVM i system (Organization of Computers and Systems). St. Petersburg: Piter; 2016. 688 p. (in Russ.).
3. Henessey J.L., Patterson D.A. Komp’yuternaya arkhitektura. Kolichestvennyi podkhod ( Computer Architecture. A Quantitative Approach): transl. from Engl. 5th ed. Moscow: Tekhnosfera; 2016. 936 p. (in Russ.). [Henessey J.L., Patterson D.A. Computer Architecture. A Quantitative Approach. 5th ed. Morgan Kaufmann; 2011. 856 p.]
4. Kirk B., Sharad S., Stanley V. How to succeed in an economy of abundance of memory? Otkrytye sistemy = Open Systems. DBMS. 2016;2:25–32 (in Russ.).
5. Sugak E.V. Prikladnaya teoriya nadezhnosti. Praktikum (Applied Reliability Theory. The Workshop. Textbook). Moscow: Lan; 2023. 312 p. (in Russ.). ISBN 978-5-507-47014-3
6. Kovalenko S.M. Evaluation of the reliability of information management systems based on continuous models. Voprosy radioelektroniki = Questions of Radio Electronics. 2005;4(2):143–146 (in Russ.).
7. Polovko A.M., Gurov S.V. Osnovy teorii nadezhnosti (Fundamentals of Reliability Theory). St. Petersburg: BHV-Petersburg; 2006. 702 p. (in Russ.). ISBN 5-94157-541-6
8. Cherkesov G.N. Nadezhnost’ apparatno-programmnykh kompleksov ( Reliability of Hardware and Software Complexes). St. Petersburg: Piter; 2005. 479 p. (in Russ.). ISBN 5-469-00102-4
9. Kovalenko S.M., Platonova O.V. Analysis of the operational efficiency of complex automation systems and the calculation of their reliability on the basis of continuous models. Izvestiya vysshikh uchebnykh zavedenii. Mashinostroenie = BMSTU J. Mechanical Engineering. 2014;8(653):75–89 (in Russ.). http://doi.org/10.18698/0536-1044-2014-8-75-79
10. Podgorny Y.V., Antonovich A.N., Petrushin A.A., Sigov A.S., Vorotilov K.A. Effect of metal electrodes on the steady-state leakage current in PZT thin film capacitors. J. Electroceram. 2022;49:15–21. https://doi.org/10.1007/s10832-022-00288-5
11. Abdullaev D.A., Milovanov R.A., Volkov R.L., Borgardt N.I., Lantsev A.N., Vorotilov K.A., Sigov A.S. Ferroelectric memory: state-of-the-art manufacturing and research. Russ. Technol. J. 2020;8(5):44–67 (in Russ.). https://doi.org/10.32362/2500-316X-2020-8-5-44-67
12. Konyukhova O.V., Kravtsova E.A., Lukyanov P.V. Tekhnicheskoe i programmnoe obespechenie vychislitel’nykh mashin i system ( Technical and Software Support of Computers and Systems). Infra-Inzheneriya; 2023. 200 p. (in Russ.). ISBN 978-5-9729-1186-8
13. Zhuravlev A.A. Organizatsiya i arkhitektura EVM. Vychislitel’nye sistemy (Organization and Architecture of Computers. Computer Systems). Lan; 2022. 144 p. (in Russ.). ISBN 978-5-507-48089-0
14. Gelbukh C.A. Seti EVM i telekommunikatsii. Arkhitektura i organizatsiya (Computer Networks and Telecommunications. Architecture and Organization). Lan; 2019. 208 p. (in Russ.). ISBN 978-5-8114-3474-9
15. Andreev A.M., Mozharov G.P., Syuzev V.V. Mnogoprotsessornye vychislitel’nye sistemy. Teoreticheskii analiz, matematicheskie modeli i primenenie (Multiprocessor Computing Systems. Theoretical Analysis, Mathematical Models and Applications). Moscow: Bauman Press; 2011. 336 p. (in Russ.). ISBN 978-5-7038-3439-6
- The study considers the structure of modern multicore microprocessors as the basis for building computing modules of cluster computing systems (CSs). As the number of cores in the microprocessor structure increases, the communication network which unites them into a single structure becomes more complicated.
- It has been shown that in new developments of microprocessors, communication between cores is performed in the form of a network. The microprocessors themselves are MIMD structures in accordance with the well-known Flynn classification.
- The proposed method of selecting an effective structure of a CS allows us to obtain the optimal structure of a CS according to the criterion of performance.
Review
For citations:
Petushkov G.V., Sigov A.S. Analysis and selection of the structure of a multiprocessor computing system according to the performance criterion. Russian Technological Journal. 2024;12(6):20-25. https://doi.org/10.32362/2500-316X-2024-12-6-20-25. EDN: PWDKPB
Views:
251
Email this article 