One model of parallel computing in heterogeneous distributed environments

O.P. Ignatenko, G.V. Parusimov, O.B. Sinetskyi

Abstract


This paper deals with model of parallel computing in heterogeneous multiprocessor system. We consider fluid model of computations to calculate the "ideal" finish, which gives the lower bound of possible real time. We propose game model of user’s interaction on the example of matrix multiplication problem. We use simulation environment GridSim to obtain experimental data and validate theoretical results.

References


Srinivasa Prasanna G.N., Musicus B. Generalized Multiprocessor Scheduling Using Optimal Control // Proc. SPAA. – 1991. – P. 216–228.

Grosu D., Chronopoulos A.T. Noncooperative load balancing in distributed systems // Journal of Parallel and Distributed Computing, 2005. – 65 (9). – P. 1022 – 1034.

Nazarathy Y., Weiss G. A Fluid Approach to Large Volume Job Shop Scheduling // Journal of Scheduling, 13(5). – 2010. P. 509–529.

Дорошенко А.Ю., Ігнатенко О.П., Іваненко П.А. Про одну модель оптимального розподілу ресурсів у багатопроцесорних середовищах // Проблеми програмування. – № 1. – 2011. – С. 21–28.

Андон Ф.И., Игнатенко А.П. Моделирование конфликтных процессов в сети Интернет // Кибернетика и системный анализ. – 2013. – № 4. – C. 153–162.

Ignatenko O., Synetskyi O. Evolutionary Game of N Competing AIMD Connections. In Information and Communication Technologies in Education, Research, and Industrial Applications. Springer International Publish-ing. – 2014. – P. 325–342.


Refbacks

  • There are currently no refbacks.