| Presentation | 2023-03-16 [Invited Talk] Social Applications of FPGA and Machine Learning Yuichiro Shibata, Taito Manabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A field programmable gate array (FPGA) is a programmable device that allows users to configure logic circuits at their hand. Since FPGAs can be flexibly programmed to configure highly efficient circuits tailored for each application, they can be used for application-specific integrated circuit (ASIC) prototyping and as power-efficient computing accelerators. Especially in the field of social applications of machine learning, FPGAs are attracting attention as an inference platform for edge systems, which have severe power constraints. Although dedicated hardware description languages were required for FPGA design, high-level synthesis design methods using ordinary programming languages such as C and C++ are now widely used. On the other hand, it is still difficult to fully exploit the advantages of FPGAs unless the characteristics of FPGAs are well understood before programming. In this talk, after overviewing the principle of hardware programmability that FPGAs offer, some typical application examples where a customized architecture can achieve high efficiency are demonstrated. Then, some implementation and optimization techniques often used for improving the efficiency of machine learning applications on FPGAs are introduced. Finally, the research projects that the authors have engaged in, which are related to social applications of machine learning on FPGAs, are introduced, discussing the findings and technical issues that have emerged in the process of the research activities. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | FPGA / High Level Synthesis / Machine Learning |
| Paper # | MSS2022-87,NLP2022-132 |
| Date of Issue | 2023-03-08 (MSS, NLP) |
| Conference Information | |
| Committee | NLP / MSS |
|---|---|
| Conference Date | 2023/3/15(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Akio Tsuneda(Kumamoto Univ.) / Atsuo Ozaki(Osaka Inst. of Tech.) |
| Vice Chair | Hiroyuki Torikai(Hosei Univ.) / Shingo Yamaguchi(Yamaguchi Univ.) |
| Secretary | Hiroyuki Torikai(Sojo Univ.) / Shingo Yamaguchi(Gifu Univ.) |
| Assistant | Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.) / Masato Shirai(Shimane Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems / Technical Committee on Mathematical Systems Science and its Applications |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] Social Applications of FPGA and Machine Learning |
| Sub Title (in English) | |
| Keyword(1) | FPGA |
| Keyword(2) | High Level Synthesis |
| Keyword(3) | Machine Learning |
| 1st Author's Name | Yuichiro Shibata |
| 1st Author's Affiliation | Nagasaki University(Nagasaki Univ.) |
| 2nd Author's Name | Taito Manabe |
| 2nd Author's Affiliation | Nagasaki University(Nagasaki Univ.) |
| Date | 2023-03-16 |
| Paper # | MSS2022-87,NLP2022-132 |
| Volume (vol) | vol.122 |
| Number (no) | MSS-435,NLP-436 |
| Page | pp.pp.121-121(MSS), pp.121-121(NLP), |
| #Pages | 1 |
| Date of Issue | 2023-03-08 (MSS, NLP) |