| Project/Area Number |
16K00170
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
High performance computing
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
Honda Hiroki 電気通信大学, 大学院情報理工学研究科, 教授 (20199574)
|
|---|
| Project Period (FY) |
2016-10-21 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
|
|---|
| Keywords | GPU / 並列処理 / 高性能コンピューティング / GPUコンピューティング / プログラム最適化 |
|---|
| Outline of Final Research Achievements |
In this study on optimization technique to realize the parallel GPU computing that was high efficiency, low consumption electricity, two next main result was provided.
- Optimization technique of the pattern matching processing including the condition divergence to cause degradation and consumption electricity increase in Network Intrusion Detection System using GPU
- Construction of the technique to acquire performance, consumption electricity properties of individual GPU in the most suitable task division, allotment in the parallel GPU environment
|
| Academic Significance and Societal Importance of the Research Achievements |
コンピュータに必要とされる性能が高くなっていく一方，コンピュータが消費する電力を少なくすることも求められている．GPUを複数搭載したコンピュータはそれを実現する方式として有望なものである．本研究成果はGPUにおけるアプリケーションプログラムの高性能・低消費電力な実行に不可欠な最適化のための重要項目を明らかにした点において意義がある．
|
