Home /Archive /2018, Volume 14 /14(6) /Deintelligent Parallel Computer with Intel Xeon Phi Processors of New Generation

Deintelligent Parallel Computer with Intel Xeon Phi Processors of New Generation

TitleDeintelligent Parallel Computer with Intel Xeon Phi Processors of New Generation
Publication TypeJournal Article
Year of Publication2018
AuthorsKhimich, OM, Mova, VI, Nikolaichuk, ОO, Popov, OV, Chistjakova, TV, Tulchinsky, VG
Short TitleSci. innov.
DOI10.15407/scine14.06.061
Volume14
Issue6
SectionResearch and Engineering Innovative Projects of the National Academy of Sciences of Ukraine
Pagination61-72
LanguageEnglish
Abstract

Introduction. Mathematical modeling with large volumes of data is an actual innovation problem in various spheres of human activity. For their effective computer research, it is necessary to use powerful computers and high-performance software.
Problem Statement. Models of processes studied on modern computers have approximate data, their mathematical properties are a priori unknown. However, the existing software does not take this into consideration. Modern parallel computers require high costs for production and use.
Purpose. To develop an intelligent personal computer based on Intel Xeon Phi processors of new generation and intelligent software for automatic research and solution of the main classes of problems of computational mathematics with approximate data.
Materials and Methods. The concept and methods for intellectualization of parallel computers of the Inparcom family, which are developed at the Glushkov Institute of Cybernetics of the NAS of Ukraine in cooperation with Electronmash. 
Results. Intelligent Parallel Computer Inparcom_xp with an Intel Xeon Phi 7210 processor, which makes computations (up to 3.5 TFlops) in the single-node format (test model, prototype). Intelligent software for automatic research and solution of problems in computational mathematics.
Conclusions. The Inparcom_xp guarantees a high reliability of computer solutions of problems, frees users from creating parallel algorithms and programs. The computer is made mainly for individual use, thereby raises the resource of personal computing for R&D calculations.
Keywordsapproximate data, computational mathematics, Intel Xeon Phi processor, mathematical modeling, parallel computer
References
1. TOP 500. 
URL: http://www.TOP500.org/ (Last accessed: 24.04 2018).
2. Wilkinson, J. H. (1963). Rounding Errors in Algebraic Processes. London: H.W. Staat. Off.
3. Wilkinson, J. H., Reinsh, K. (1976). Algorithm Reference in Algol. Linear algebra. Moskva: Mechanical engineering [in Russian].
4. Voevodin, V. V. (1969). Errors of rounding and stability in direct methods of linear algebra. Moskva: Izd. Computer Center of Moscow State University [in Russian].
5. Molchanov, I. N. (1987). Machinye metody reshenija prikladnyh sadach. Algebra, priblizhenie funkcij. Kyiv: Naukova dumka [in Russian].
6. Khimich, A. N. (1996). Оtsеnki vozmushchеnii dlja rеshеnija zаdаchi naimen'shikh kvadratov. Kibernetika i sistemnyi analiz, 3, 95–102 [in Russian].
7. Khimich, A. N. (2002). Оtsеnki pоlnоi pogreshnоsti reshеnija sistem lineinykh аlgebraichеskikh uravnenii dlja matrits proizvol'nogo ранга. Komp'jutеrnaja matematika, 2, 41–49 [in Russian].
8. Khimich, A. N., Voitsekhоvsky, С. А., Brusnikin, V. N. (2004). О dostovernosti lineinykh matematicheskikh modelei s priblizhonno sadannymi iskhodnymi dannymi. Matematicheskie mashiny i sistemy, 3, 54–62 [in Russian].
9. Forsyth, J., Malcolm, M., Mouler, K. (1980). Machine methods of mathematical calculations. Moskva: Mir [in Russian].
10. Chesbrough, H. (2007). Ореn Innovation: The New Imperative for Creating and Profiting from Technology. Moskva: Pokolenie [in Russian].
11. Tarnavsky, G. A., Aliev, A. V. (2007). Mathematical modeling: main segments, their features and problems. Computational methods and programming, 8, 297–310 [in Russian].
12. Ilyin, V. P. (2014). On sone "over-cloud" problems of mathematical modeling. Bulletin of the South Ural State University. Series "Computational Mathematics and Software Engineering", 3(1), 68-79 [in Russian].
https://doi.org/10.14529/cmse140106
13. Khimich, A. N., Molchanov, I. N., Mova, V. І., Nikolaichuk, О. O., Popov, A. V., Chistjakova, T. V., Jakovlev, M. F., Tulchinsky, V. G., Yushchenko, R. А. (2016). Intelligent Personal Supercomputer for Solving Scientific and Technical Problems. Sci. innov., 12(5), 17-31 [in Ukrainian].
https://doi.org/10.15407/scine12.05.015
14. IntelXeon Phi. 
URL: https://www.intel.com/content/wwilus/en/products/processors/xeon-phi/ 
(Last accessed: 20.04 2018).
15. Khimich, A. N., Molchanov, I. N., Mowa, V. I., Perevozchikova, O. L., Stryuchenko, V. A., Popov, A. V., Chistyakova, Т. V., Yakovlev, M. F., Gerasimova, T. A., Zubatenko, V. S., Gromovsky, A. V., Nesterenko, A. N., Polyanko, V. V., Rudich, O. V., Yushchenko, R. A., Nikolaychuk, A. A., Gorodetsky, A. S., Slobodian, Ya. E., Geraimovich, Yu. D. (2007). Chislennoe programmnoe obespechenie intellektual'nogo MIMD-komp'jutera Inparcom. Kyiv: Naukova dumka [in Russian].
16. Khimich, A. N., Popov, A. V., Chistyakova, T. V., Rudich, O. V., Chistyakov, A. V. (2017). The intelligente system for the investigating and solving of eigenvalue problem on parallel computers with processors Intel Xeon Phi. Scientific and theoretical journal «Artificial  intelligence», 2, 119–127 [in Ukrainian].
17. HC27.25.710–Knights–Landing–Sodani–Intel_copy.pdf.  
URL:https://www.hotchips.org/ (Last accessed: 22.04 2018).
18. Khimich, A. N., Molchanov, I. N., Popov, A. V., Chistjakova, T. V., Jakovlev, M. F. (2008). Parallel'nye algoritmy reshenija zadach vychislitel'noi matematiki. Kyiv: Naukova dumka  [in Russian].
19. Chistyakov, A. V. (2017, December). On the peculiarities of solving the algebraic problem of eigenvalues on parallel computers with Intel Xeon Phi processors. International Scientific Conference “Modern Computer Science: Problems, Achievements and Prospects of Development” devoted to the 60th anniversary of V.M. Glushkov Institute of Cybernetics of National Academy of Sciences of Ukraine, Кyiv [in Ukrainian].
20. Voevodin, V. V., Voevodin, Vl. V. (2002). Parallel computations. Sankt-Petersburg: BHV-Petersburg [in Russian].
21. OpenMP. V. 4.0. 
URL: http://www.openmp.org/mp-documents/OpenMP4.0.pdf/ (Last accessed: 24.04 2017).
22. Intel Math Kernel Library (MKL). Reference Manual. 
URL: https://software.intel.com/en-us/articles/mkl-reference-manual/ 
(Last accessed: 20.04 2017).
23. Gorodetsky, A. S., Evzerov, I. D. (2007). Computer models of constructions, Kyiv: FACT [in Russian].
24. Khimich, A. N., Poljanko, V. V., Popov, A. V., Rudich, O. V. (2008). Reshenie zadach rascheta prochnosti konstruktsii na MIMD-kompjutere. Iskusstvennyi intellekt, 3, 750–760.
25. Velikoivanenko, E. A., Milenin, A. S., Popov, A. V., Sidoruk, V. A., Khimich, A. N. (2014). Metody i tekhnologii paralel'nykh vychislenii dlja matematicheskogo modelirovanija naprjazhonno-deformirovannogo sostojanija konstruktsii s uchetom vjazkogo razrushenija. Problemy upravlenija i informatiki, Journal of Automation and Information Sciences, 6, 42–52 [in Russian].
26. Guz, A. N., Dekret, V. A. (2015). Model of short fibers in the theory of stability of composites.  Germany, Saarbrucken: LAP.
27. Decret, V. A., Zelensky, V. S., Bystrov, V. M. (2008). Numerical study of the stability of a laminated composite material under uniaxial compression of a filler. Kyiv: Naukova dumka [in Russian].
28. Khimich, A. N., Popov, A. V., Chistyakov, O. V. (2017). Hybrid algorithms for solving the algfebraic eigenvalue problem with sparse matrices. Cybernetics and Systems Analysis, 53(6), 132–146.
https://doi.org/10.1007/s10559-017-9996-5