Research on place and route method using deep learning
| Project/Area Number |
16K00081
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Computer system
|
|---|
| Research Institution | Hiroshima City University |
|---|
Principal Investigator |
Hironaka Tetsuo 広島市立大学, 情報科学研究科, 教授 (10253486)
|
|---|
| Project Period (FY) |
2016-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 配置配線 / ニューラルネットワーク / 再構成可能デバイス / SA法 / コスト関数 / 学習データの自動生成 / 深層学習 / 自己組織化マップ / リコンフィギャラブルシステム / 配置配線手法 |
|---|
| Outline of Final Research Achievements |
We revealed the method to apply a neural network as a cost function used in the SA method. If a neural network is simply applied, the placement and connection information will require an unrealistic number of input nodes. In this study, so we established a method to significantly reduce the number of input nodes without significantly losing the meaning of the input data by converting the placement and connection information to a map marked with placement position and the possibly routed area. Furthermore, we established a method to predict the better placement by comparing two placements generated from the same netlist by the neural network. Furthermore, it was also found that the placement performed by the conventional place and route methods can be improved by applying the SA method using the trained neural network as the cost function.
|
| Academic Significance and Societal Importance of the Research Achievements |
SA法のコスト関数は配線配置の可否を判定する数式モデルから作成している．そのため，性能向上を目指して再構成デバイスの構成を複雑にすると簡易な数式モデルで配線配置の可否を精度よく判定することが難しくなる．このコスト関数の精度が低下するとSA法を用いて生成される配置配線の品質が低下する．本研究では，深層学習を用いて訓練データである過去の配置配線結果から自動的にSA法のコスト関数を生成することの実現性を示した．これにより，精度の良い簡易な数式モデルが作成困難な場合においても，過去の配置配線結果を用いてより良いSA法のコスト関数を自動生成できる可能性を示した．
|
Report
(6 results)
Research Products
(13 results)
