Method of semantic application verification in GPGPU technology

Authors

DOI:

https://doi.org/10.20535/SRIT.2308-8893.2020.3.01

Keywords:

CUDA, graphical processing units (GPU), General Purpose Graphics Computing (GPGPU), transition system, Petri net, model design

Abstract

An application development and verification method for massively parallel systems using NVIDIA GPUs is proposed. The method allows creating models at different levels of abstraction using the apparatus of marked transition systems. The compositions (product) of such systems are transformed into a Petri net, which are then analyzed by appropriate means. The proposed method allows specifying model properties by temporal logic formulas. This allows studying the properties of massively parallel systems which is almost impossible to analyze manually, since the number of execution threads in the latest NVIDIA video adapter architectures (Pascal, Volta, Turing, Ampere) is measured in hundreds of thousands or millions.

Author Biographies

Serhii L. Kryvyi, Taras Shevchenko National University of Kyiv, Kyiv

Serhii Kryvyi,

Doctor of Physical and Mathematical Sciences, a professor at the Department of Intelligent Software Systems of Taras Shevchenko National University of Kyiv, Kyiv, Ukraine.

Sergiy D. Pogorilyy, Taras Shevchenko National University of Kyiv, Kyiv

Sergiy Pogorilyy,

a professor, Doctor of Technical Sciences, the Head of the Computer Engineering Department of Taras Shevchenko National University of Kyiv, Kyiv, Ukraine.

Maksym S. Slynko, Taras Shevchenko National University of Kyiv, Kyiv

Maksym Slynko,

a graduate student at Taras Shevchenko National University of Kyiv, Kyiv, Ukraine.

Artem A. Kramov, Taras Shevchenko National University of Kyiv, Kyiv

Artem Kramov,

a graduate student at Taras Shevchenko National University of Kyiv, Kyiv, Ukraine.

References

Nvidia Data Center – Nvidia, 2018. [Online]. Available: https://www.nvidia.com/ en-us/data-center/. Accessed on: 2019, March 14.

TOP500 Lists TOP500 Supercomputer Sites, 2018. [Online]. Available: https://www.top500.org/lists. Accessed on: 2019, March 14.

A.V. Anisimov, S.D. Pogorilyy, and D.Yu. Vitel, “About the Issue of Algorithms formalized Design for Parallel Computer Architectures”, Applied and Computational Mathematics, vol. 12, no. 2, pp.140–151, 2013.

A. Arnold, Finite Transition Systems: Semantics of Communicating Systems. Paris, France: Prentice Hall, 1994, 177 p.

T. Murata, “Petri nets: properties, analysis and applications”, in Proc. of the IEEE, 77:541.80, 1989.

M. Ben-Ari, Mathematical Logic for Computer Science. UK: Prentice Hall International Ltd, 1993, 305 p.

E.M. Clarke, Jr., O. Grumberg, and D.A. Peled, Model Checking. USA: MIT Press, 1999.

S.D. Pogorilyy, S.L. Kryvyi, and M.S. Slynko, “Model justification of GPU-based applications”, Control Systems and Computers, vol. 4, pp. 46–56, 2018.

S.L. Kryvyi, Linear Diophantine constraints and their applications. Chernivtsi: Bukrek Publishing House, 2015.

S.L. Kryvyi, S.D. Pogorilyy, and M.S. Slynko, “Transition systems as method of designing applications in GPGPU technology”, in Proc. 11-th international scientific and practical conference on programming UkrPROG’2018.

S.L. Kryvyi et al., “Design of Grid Structures on the Basis of Transition Systems with the Substantiation of the Correctness of Their Operation”, Cybernetics and Systems Analysis, vol. 53, no. 1, pp.105–114, New York, USA: Springer Science + Business Media, January 2017.

Downloads

Published

2020-12-07

Issue

Section

Progressive information technologies, high-efficiency computer systems