UDC 004-027.21
PARALLELIZATION OF ALGORITHMS WITH USE THE SEMANTIC PETRI-MARKOV NETS
A. N. Ivutin, PhD (technical sciences), associated professor, Head of the Department of Computer Technology, TSU, Tula; This email address is being protected from spambots. You need JavaScript enabled to view it.
A. G. Troshina, PhD (technical sciences), assistant professor of the Department of Computer Technology, TSU, Tula; This email address is being protected from spambots. You need JavaScript enabled to view it.
D. O. Yesikov, post-graduate student, TSU, Tula; This email address is being protected from spambots. You need JavaScript enabled to view it.
The aim of this work is to create a unified mathematical apparatus and methods for solving the problems of optimal parallelization algorithms in practical situations where parallel processes are implemented in a computer system with known processing speed, memory volume, communication channels and the number of processors. The problem of the development and application of mathematical apparatus of se-mantic Petri-Markov nets to optimize the time computational complexity of algorithms by their parallelization taking into account contextual dependence of the operators is considered. For the first time we offer the notion of semantic Petri-Markov net (SPMN) for simulation of context-sensitive relations in the algorithms that will allow to make structural parallelization of computational process, preserving the logic of interaction of individual operators.
Key words: concurrent programming, Petri-Markov nets, semantic relations, semi-Markov process, simulation, transition function, paralleling technology, semantic net.