Preview

«System analysis and applied information science»

Advanced search

COOPERATIVE MODEL FOR OPTIMIZATION OF EXECUTION OF THREADS ON MULTI-CORE SYSTEM

Abstract

The problem of the increase of efficiency of multi-thread applications on multi-core systems is investigated. The optimization cooperative model of threads execution has been proposed. It optimizes the execution order of the  computational operations and the operations of data exchange, decreases the overall time of the multithread application  execution by means of the reduction of the critical path in the concurrent algorithm graph, increases the application throughput at the growth of the number of threads, and excludes the competition among threads that is specific for preemptive multitasking...............................

About the Authors

A. A. Prihozhy
Belarusian National Technical University
Belarus


O. N. Karasik
Belarusian National Technical University
Belarus


References

1. Прихожий, А.А. Исследование методов реализации многопоточных приложений на многоядерных системах / А.А. Прихожий, О.Н. Карасик // Информатизация образования, 2014, № 1. − С. 43-62.

2. Ортега, Дж. Введение в параллельные и векторные методы решения линейных систем / Дж. Ортега // М.: Мир, 1991. − 367 c.

3. Рихтер, Дж. Windows для профессионалов. Создание эффективных WIN32-приложений с учетом специфики 64-разрядной версии Windows / Дж. Рихтер // Питер, РР, 2001. −752 с.

4. Probert, D. Inside Windows 7 User Mode Scheduler / D. Probert // Channel9 [Электронный ресурс]: – Режим доступа: http://channel9.msdn.com/shows/Going+Deep/Dave-Probert-Inside-Windows-7-User-Mode-Scheduler-UMS/. – Дата доступа: 30.12.2014


Review

For citations:


Prihozhy A.A., Karasik O.N. COOPERATIVE MODEL FOR OPTIMIZATION OF EXECUTION OF THREADS ON MULTI-CORE SYSTEM. «System analysis and applied information science». 2014;(4):13-20. (In Russ.)

Views: 3128


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 2309-4923 (Print)
ISSN 2414-0481 (Online)