Presentation | 2020-05-29 Proposal of Reconfigurable Device Placement Algorithm Using Placement Quality Judgment Neural Network as Cost Function of SA Method Yuichi Natsume, Tokio Kamada, Kubota Atsushi, Kazuya Tanigawa, Tetsuo Hironaka, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The circuit performance of reconfigurable devices greatly depends on the place-and-route results, so optimal place-and-route is important. However, the SA method using the conventional cost function has a problem that an accurate cost value cannot be calculated, and thus it is difficult to perform optimal place-and-route. Therefore, we propose to use a neural network as a cost function. In this paper, by using the conventional cost function and neural network together, the wiring success rate and the average wire length can be significantly improved compared with using the conventional cost function alone. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Reconfigurable devices / Place-and-Route / Neural Network / Simulated Annealing |
Paper # | RECONF2020-13 |
Date of Issue | 2020-05-21 (RECONF) |
Conference Information | |
Committee | RECONF |
---|---|
Conference Date | 2020/5/28(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Meeting room on Web |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Reconfigurable system, etc. |
Chair | Yuichiro Shibata(Nagasaki Univ.) |
Vice Chair | Kentaro Sano(RIKEN) / Yoshiki Yamaguchi(Tsukuba Univ.) |
Secretary | Kentaro Sano(Hiroshima City Univ.) / Yoshiki Yamaguchi(e-trees.Japan) |
Assistant | Yuuki Kobayashi(NEC) / Hiroki Nakahara(Tokyo Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Reconfigurable Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Proposal of Reconfigurable Device Placement Algorithm Using Placement Quality Judgment Neural Network as Cost Function of SA Method |
Sub Title (in English) | |
Keyword(1) | Reconfigurable devices |
Keyword(2) | Place-and-Route |
Keyword(3) | Neural Network |
Keyword(4) | Simulated Annealing |
1st Author's Name | Yuichi Natsume |
1st Author's Affiliation | Hiroshima City University(Hiroshima City Univ.) |
2nd Author's Name | Tokio Kamada |
2nd Author's Affiliation | Hiroshima City University(Hiroshima City Univ.) |
3rd Author's Name | Kubota Atsushi |
3rd Author's Affiliation | Hiroshima City University(Hiroshima City Univ.) |
4th Author's Name | Kazuya Tanigawa |
4th Author's Affiliation | Hiroshima City University(Hiroshima City Univ.) |
5th Author's Name | Tetsuo Hironaka |
5th Author's Affiliation | Hiroshima City University(Hiroshima City Univ.) |
Date | 2020-05-29 |
Paper # | RECONF2020-13 |
Volume (vol) | vol.120 |
Number (no) | RECONF-36 |
Page | pp.pp.71-76(RECONF), |
#Pages | 6 |
Date of Issue | 2020-05-21 (RECONF) |