Systems and Means of Informatics
2019, Volume 29, Issue 2, pp 135-147
EVALUATION OF RELIABILITY OF THE HYBRID HIGH-PERFORMANCE COMPUTING COMPLEX IN SOLUTION OF SCIENTIFIC PROBLEMS
- A. A. Zatsarinny
- A. I. Garanin
- V.A. Kondrashev
- K. I. Volovich
- S. I. Malkovsky
Abstract
The necessity of using hybrid solutions in creation of high-performance computing systems is substantiated. A brief description of the hybrid high- performance computing complex (HHPCC) of FRC CSC RAS is given and its enlarged block diagram is presented. The paper offers the methodical approach to estimation of reliability of HHPCC on the basis of which calculations of reliability of the allocated functional subsystems are carried out. Separately, reliability of the "computing infrastructure" of HHPCC (without peripheral elements) was evaluated. Recommendations for improving reliability of functional subsystems are given.
[+] References (8)
- Shan, A. 2006. Heterogeneous processing: A strategy for augmenting Moore's law. Linux J. Available at: https://www.linuxjournal.com/article/8368 (accessed April 4, 2019).
- Sokolov, I. A., A. A. Zatsarinnyy, A.I. Diveev, V.N. Zakharov, M.A. Posypkin, and K. K. Abgarjan. 2018. Gibridnyy vysokoproizvoditel'nyy vychislitel'nyy kom pleks (GVVK) [Hybrid high-performance computing system (HHPCC)]. Available at: http://www.frccsc.ru/hhpcc (accessed April 4, 2019).
- GOST 24.701-86. 1986. Edinaya sistema standartov avtomatizirovannykh sis- tem upravleniya. Nadyozhnost' avtomatizirovannykh sistem upravleniya. Osnovnye polozheniya [State Standard "An uniform system of standards for automated control systems. Reliability of automated control systems. Fundamentals"]. Available at: http://docs.cntd.ru/document/1200022035 (accessed April 4, 2019).
- Kashtanov, V. A., and A. I. Medvedev. 2010. Teoriya nadezhnosti slozhnykh sistem [The reliability theory for complex systems]. Moscow: Fizmatlit. 608 p.
- Zatsarinnyy, A. A., A.I. Garanin, and S.V. Kozlov. 2017. Nauchno-prakticheskie aspecty obespecheniya nadezhnosti informatsionno-telekommunikatsionnykh setey [Scientific and practical aspects of ensuring reliability of information and telecommunication networks]. Moscow: FIC IU RAN. 246 p.
- Gnedenko, B.V., Y. K. Belyaev, and A. D. Soloviev. 1965. Matematicheskie metody v teorii nadezhnosti [Mathematical methods in the theory of reliability]. Moscow: Nauka. 524 p.
- Kozlov, B. A., and I. A. Ushakov. 1975. Spravochnik po raschetu nadezhnosti apparatury radioelektroniki i avtomatiki [Handbook on calculation of reliability of radioelectronics and automation equipment]. Moscow: Sovetskoe Radio. 462 p.
- Belyaev, Yu.K., V.A. Bogatyrev, V.V. Bolotin, et al. 1985. Nadezhnost' tekh- nicheskikh sistem: Spravochnik [Reliability of technical systems: Handbook]. Ed.
I. A. Ushakov. Moscow: Radio i svyaz'. 608 p.
[+] About this article
Title
EVALUATION OF RELIABILITY OF THE HYBRID HIGH-PERFORMANCE COMPUTING COMPLEX IN SOLUTION OF SCIENTIFIC PROBLEMS
Journal
Systems and Means of Informatics
Volume 29, Issue 2, pp 135-147
Cover Date
2019-05-30
DOI
10.14357/08696527190212
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
hybrid high-performance computing system; reliability; functional subsystems; failure; equivalent circuit for reliability calculation
Authors
A. A. Zatsarinny  , A. I. Garanin , V.A. Kondrashev , K. I. Volovich , and S. I. Malkovsky 
Author Affiliations
Institute of Informatics Problems, Federal Research Center "Computer Science and Control", Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
Computing Center, Far Eastern Branch of the Russian Academy of Sciences, 65 Kim U Chen Str., Khabarovsk 680000, Russian Federation
|