Study on Intelligent Network System for Dynamic Optimization Control in Distributed Computing Environment
| Project/Area Number |
15K00169
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
High performance computing
|
|---|
| Research Institution | Kyoto Institute of Technology |
|---|
Principal Investigator |
Nunome Atsushi 京都工芸繊維大学, 情報工学・人間科学系, 助教 (60335320)
|
|---|
| Research Collaborator |
ICHII Sekai
SHIMANO Shingo
SHOJI Yuki
TASHIRO Saki
DEJIMA Takashi
HAYASHI Shohei
HIRATA Hiroaki
FUJISAWA Kohei
YAMASAKI Hiroki
YOKOI Yuta
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 計算機システム / ハイパフォーマンスコンピューティング / 分散処理 / 動的負荷分散制御 / ハイパフォーマンス・コンピューティング |
|---|
| Outline of Final Research Achievements |
In a massively distributed computing environment, it is important to tune the system from both aspects of software and hardware to bring out potential performance to the maximum. In this study, we have proposed a scheme to perform dynamic optimization control for the heterogeneous environments where various types of node are mixed. It also considers differences in the effective performance which is occurred at run-time. Formerly, a high overhead is regarded as a problem because the information needed for such control must be collected at run-time. In our scheme, the overhead accompanied with the optimization control will be suppressed by appending the system management information onto ordinary packets by the network device. We have established one of a fundamental technology which is capable of applying even if the management information enlarges for more complex dynamic optimization control in the near future.
|
Report
(4 results)
Research Products
(20 results)
