| Presentation | 2021-09-10 Convolutional neural network implementations using Vitis AI Akihiko Ushiroyama, Nobuya Watanabe, Akira Nagoya, Minoru Watanabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, Xilinx provides an FPGA-based Vitis AI development environment which is one of deep learning frameworks to accelerate AI operations and to search a suitable neural network construction for a target application. In this paper, we've implemented three types of convolutional neural networks onto the Vitis AI development environment and evaluated the performance, power consumption, lines of code, and so on. As a result, we have confirmed the advantages of the Vitis AI. For example, the energy consumption of the FPGA platform is 5.06 times lower than that of a GPU. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Convolutional Neural Network (CNN) / FPGA / Vitis AI |
| Paper # | RECONF2021-19 |
| Date of Issue | 2021-09-03 (RECONF) |
| Conference Information | |
| Committee | RECONF |
|---|---|
| Conference Date | 2021/9/10(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Reconfigurable system, etc. |
| Chair | Kentaro Sano(RIKEN) |
| Vice Chair | Yoshiki Yamaguchi(Tsukuba Univ.) / Tomonori Izumi(Ritsumeikan Univ.) |
| Secretary | Yoshiki Yamaguchi(NEC) / Tomonori Izumi(Tokyo Inst. of Tech.) |
| Assistant | Yukitaka Takemura(INTEL) / Yasunori Osana(Ryukyu Univ.) |
| 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) | Convolutional neural network implementations using Vitis AI |
| Sub Title (in English) | |
| Keyword(1) | Convolutional Neural Network (CNN) |
| Keyword(2) | FPGA |
| Keyword(3) | Vitis AI |
| 1st Author's Name | Akihiko Ushiroyama |
| 1st Author's Affiliation | Okayama University(Okayama Univ.) |
| 2nd Author's Name | Nobuya Watanabe |
| 2nd Author's Affiliation | Okayama University(Okayama Univ.) |
| 3rd Author's Name | Akira Nagoya |
| 3rd Author's Affiliation | Okayama University(Okayama Univ.) |
| 4th Author's Name | Minoru Watanabe |
| 4th Author's Affiliation | Okayama University(Okayama Univ.) |
| Date | 2021-09-10 |
| Paper # | RECONF2021-19 |
| Volume (vol) | vol.121 |
| Number (no) | RECONF-175 |
| Page | pp.pp.13-18(RECONF), |
| #Pages | 6 |
| Date of Issue | 2021-09-03 (RECONF) |