1. CSN
  2. All Volumes and Issues
  3. Number 905, 2018
  4. Software implementation of mathematical models, methods and algorithms for estimating the time of execution of complex software complexes in multiprocessor computer systems

Software implementation of mathematical models, methods and algorithms for estimating the time of execution of complex software complexes in multiprocessor computer systems

CSN.
2018;
, Number 905
: pp. 73 - 81
https://doi.org/10.23939/csn2018.905.073
Authors:
  1. Yurii Klushyn
1
Lviv Polytechnic National University, Computer Engineering Department

To solve the forecasting problem, a software package has been developed in full, which is based on mathematical models, methods and algorithms of direct stochastic modeling and tiered stochastic modeling, which are used to estimate the execution time of folding software systems in multiprocessor computer systems. The given software package calculates the average value and the distribution function of the execution time of a set of interrelated tasks on homogeneous resources of a parallel computing system.

parallel computing systems
complex of interconnected works
direct stochastic modeling
Markov process
function of distribution of random variable
  1. Chu W. W., Leung K.K. Module replication and assignment for real-time distributed processing system. // “Proc IEEE”. 1987. 75. N5. pp. 547–562.
  2. Khritankov A. S. Mathematical model of performance characteristics of distributed computing systems. Computer science, management, economics. WORKS OF MIPT. – 2010. – Volume 2, No. 1 (5), p. 110–115.
  3. Ivutin A. N., Larkin E. V. Prediction of the execution time of the algorithm. Magazine. News of TSU. Technical science. Issue number 3/2013 C. 301–315.
  4. Bocharov P. L., Ignatushchenko V. V. Mathematical models and methods for evaluating the effectiveness of parallel computing systems on complexes of interrelated works // Tez. report international conf, “High-Performance Computing Systems in Management and Scientific Research,” Alma-Ata, 1991, p. 6.
  5. Margalitashvili, A. L., Ambartsumian, A. L., Teplyakov, A. V., Preidunov, Yu, V., Graph models of complexes of interrelated works, M *, 1990, – Dep. in VINITI 31,01,90, No. 587–B90.
  6. Margalitashvili A. L, Investigation of the effectiveness of the functioning of parallel computing resources on given complexes of interrelated works, Abstract of Cand. dis. M .: In-t prbblem management, 1990.
  7. Bocharov P. L., Preydunov Yu. V., Estimation of the execution time of a complex of works on a parallel computational system // System analysis and computer science. Sat scientific papers, M.: Publishing house DN, 1991. C 29–41.
  8. Ingatushchenko V. V. Organization of structures for controlling multiprocessor computing systems. Moscow: Energoatomizdat, 1984.
  9. Ivanov N.N. Mathematical prediction of reliable execution of sets of tasks with symmetric runtime distributions. Journal of Open Education, Issue No. 2–2 / 2011, p. 52–55.
  10. Ignatushchenko V. V., Klushin Y. S. Prediction of the implementation of complex software systems on parallel computers: direct stochastic modeling // Automation and Remote Control. 1994. N12, p. 142–157.
  11. Klushin, Y. S. Prediction of the implementation of complex software systems on parallel computers // Proc. Report Second Ukrainian Conference on Automatic Control “Automation – 95”, Lviv, 1995, vol. 2, p. 100.
  12. Ignatushchenko V. V., Klushin Yu. S. Forecasting the implementation of complex software systems on control parallel computers: exact methods // Scientific works of the International Symposium “Automated Control Systems”, Tbilisi: ed. Intellect, 1996, p. 23–28.
  13. N. N. Ivanov, V. V. Ignatushchenko, A. Y. Mikhailov, Static prediction of the execution time of complexes of interrelated works in multiprocessor computing systems, Avtomat. and Telemekh., 2005, issue 6, 89–103.
  14. Klushin Y. S. Evaluation of the effectiveness of various dispatching disciplines for reducing the time to perform complex software systems on parallel computing systems / Bulletin of National University "Lviv Polytechnic" No413. Computer engineering and information technology. – Lviv: NU “LP”, 2000. – p. 19–23.
  15. Gross, D., Miller, D., Transition Markov processes // Operations Research. 1984. Vol. 32. No 4. P. 334–361.
  16. Reibman A. L., Trivedi K. S. Numerical transient analysis of Markov models // Computers and Operations Research. 1988. V. 15. No. 1. P. 19–36.
  17. Klushin, Y. S. Improving the accuracy of estimating the execution time of folding software systems in multiprocessor computer systems for belt stochastic modeling. Bulletin of NU “Lviv Polytechnic” No881. Computer systems and networks. – Lviv: NU “LP”, 2017.
  18. Preidunov Y. V. Development of mathematical models and methods for predicting the implementation of complex software systems on parallel computing systems. Cand. course work. M .: Inst. Of Problems of Management RAS, 1992.
  19. Klushin Y. S. reducing the number of states of the Markov process when executing complex software systems on parallel computers. Scientific Bulletin of Chernivtsi University. Computer systems and components. 2016. T. 7. Vol. 2, pp. 53–62.