A method for evaluating the performance of a real-time multiprocessor computing system : доклад, тезисы доклада | Научно-инновационный портал СФУ

A method for evaluating the performance of a real-time multiprocessor computing system : доклад, тезисы доклада

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: III International Conference on Advanced Technologies in Materials Science, Mechanical and Automation Engineering MIP: Engineering-III -2021; Krasnoyarsk; Krasnoyarsk

Год издания: 2021

Идентификатор DOI: 10.1063/5.0071527

Аннотация: The problem of constructing an analytical model of the performance of a multiprocessor computing complex for a real-time system is considered. A computing system consists of an arbitrary number of different types of processors, a single bus, and shared memory. The process of functioning of a computer system is represented by a closed system with a limited queue, where the streams of service requests from processors to shared memory are considered as independent of each other, and the integral flow of requests in the system is considered as the simplest Poisson one. The constructed analytical model can be used to evaluate the performance of multiprocessor computing systems at the design stage, which will reduce the cost of manufacturing prototypes of computing systems when they are created.

Ссылки на полный текст

Издание

Журнал: AIP Conference Proceedings

Выпуск журнала: Volume 2402

Номера страниц: 50015

Место издания: Melville, New York, United States of America

Издатель: AIP Publishing

Персоны

  • Efimov Sergey (Reshetnev Siberian State University of Science and Technology)
  • Terskov Vitalij (Reshetnev Siberian State University of Science and Technology)
  • Serikova Olesya (Irkutsk State University of Railway Engineering)
  • Popova Anastasiya (Reshetnev Siberian State University of Science and Technology)

Вхождение в базы данных

Информация о публикациях загружается с сайта службы поддержки публикационной активности СФУ. Сообщите, если заметили неточности.

Вы можете отметить интересные фрагменты текста, которые будут доступны по уникальной ссылке в адресной строке браузера.