To the issue of optimizing cloud computing based on their cost
The paper offers an approach to the architectural settings of parallel computing on the cloud platform, which allows in semi-automatic mode to perform optimization of a parallel program with the goal function of minimum cost of computations. To solve the optimization problem, it is proposed to use l...
Збережено в:
| Дата: | 2021 |
|---|---|
| Автори: | , |
| Формат: | Стаття |
| Мова: | Ukrainian |
| Опубліковано: |
Інститут програмних систем НАН України
2021
|
| Теми: | |
| Онлайн доступ: | https://pp.isofts.kiev.ua/index.php/ojs1/article/view/435 |
| Теги: |
Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|
| Назва журналу: | Problems in programming |
| Завантажити файл: |  |
Репозитарії
Problems in programming| Резюме: | The paper offers an approach to the architectural settings of parallel computing on the cloud platform, which allows in semi-automatic mode to perform optimization of a parallel program with the goal function of minimum cost of computations. To solve the optimization problem, it is proposed to use linear programming and an available software solver, which with the help of the method of branches and boundaries in semi-automatic mode selects the value of the architecture parameters of the program configuration which significantly affect the cost of calculations. Therefore, the method of auto-tuning developed by the authors earlier is generalized and spread to the complex of services performed on the cloud platform. An analytical test was conducted on the model of cloud multiprocessor cluster, which presents the possibility of significantly reducing the cost of cloud computing due to the optimizations carried out.Prombles in programming 2020; 4: 14-21 |
|---|