DOI: https://doi.org/10.15407/pp2018.02.012

Transition systems as method of designing applications in GPGPU technology

S.L. Kryvyi, S.D. Pogorilyy, M.C. Slynko

Abstract


The method of researching systems with high-performance computing support, based on the transition systems apparatus (discrete computational model), is proposed. Two variants of synchronous product limitations of transition systems that model tha Nvidia CUDA approach are proposed. transition systems that represent two types of instructions, process of the warp instruction execution, and the process of warp scheduling were described. GPGPU application execution model was formalized and its correctness was proved. Two variants of the relevant Petri net which allowed automatic or semi-automatic detection of design errors were obtained.

Problems in programming 2018; 2-3: 012-020


Keywords


Nvidia CUDA; GPGPU; SAA; Petri net; transition system

Full Text:

PDF (Ukrainian)

References


POGORILYY S.D., VITEL D. Yu. & VERESCHINSKY O.A. (2012) Modern video adapter architectures. GPGPU technology. Part 1. Data registration, storage and processing. 14 (4).

POGORILYY S.D. & SHKULIPA I. Yu. (2009) A Conception for Creating a System of Parametric Design of Parallel Algorithms and their Software Implementations. Cybernetics and System Analysis, Volume 45, Issue 6 (November 2009) pages: 952 - 958. Springer Science and Business Media Inc. ISSN:1060-0396. https://doi.org/10.1007/s10559-009-9172-7

POGORILYY S.D., SLYNKO M.S. (2016) Research and development of Johnson’s algorithm parallel schemes in GPGPU technology. In 10-th international scientific programming conference UKRPROG’2016. Kyiv, pp. 105-112.

POGORILYY S.D., SLYNKO M.S. & RUSTAMOV Y.I. (2017) A formalized method of Johnson’s algorithm parallelization suitable for use in GPGPU technology. TWMS Journal of Pure and Applied Mathematics, V.8, N.1, 2017, pp. 12-21.

POGORILYY S.D., BOYKO Yu.V., TRYBRAT M.I., GRYAZNOV D.B. (2010) Analysis of the computer performance improvement methods using graphic processors and CUDA platform. Mathematical Machines and Systems, N.1, pp. 40-54.

BOYKO Yu.V., KRYVYI S.L., POGORILYY S.D. et al. (2016). Methods and latest approaches to the design, management and application of high-performance IT infrastructures. Publishing and printing center “Kyiv University”.

KRYVYI S.L. (2015). Linear Diophantine limits and their application. Chernivtsi: “Bukrek” Publishing House.




DOI: https://doi.org/10.15407/pp2018.02.012

Refbacks

  • There are currently no refbacks.