2021 Fiscal Year Annual Research Report
HDLRuby: a new high productivity hardware description language targeting next generation edge computing architectures for IoT
| Project/Area Number |
18K11284
|
|---|
| Research Institution | Ariake National College of Technology |
|---|
Principal Investigator |
Gauthier Lovic 有明工業高等専門学校, 創造工学科, 准教授 (90535717)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
石川 洋平 有明工業高等専門学校, 創造工学科, 准教授 (50435476)
白鳥 則郎 中央大学, 研究開発機構, 機構教授 (60111316)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Keywords | HDL / Edge Computing / FPGA / Design Exploration / Simulation / Ruby Language |
|---|
| Outline of Annual Research Achievements |
The goal of the research project was to design and promote HDLRuby, a new high productivity hardware description language targeting edge computing applications.
Toward that end, this language has been developed from a prototype to a full hardware design framework usable for designing digital circuits.
In details, We implemented several tools for processing HDLRuby descriptions including a compiler for generating synthesizable Verilog HDL and VHDL code and a hardware simulator. We also implemented a library of generic components including for instance generators for final state machines, decoders, and arbitrary functions, as well as extension for fixed point or linear algebra processing. These tools and the library have been validated with the design and implementation targeting IC or FPGA of several circuits, e.g., a processor or neural networks. The code of the HDLRuby framework is publicly available online as standard packages and as source code repository. The last year has been dedicated first to the increase of the performance of HDLRuby so that its compilation time becomes negligible compared to the whole synthesis time. Second, we deepened the evaluation of this framework by performing a design exploration of the implementation of a binarized neural network on various FPGA devices as well as its integration within a wireless environment.
|
-
-
-
-
-
-
[Journal Article] Federated Learning with Divided Data for BP2021
Author(s)
Hirofumi Miyajima, Noritaka Shigei, Hiromi Miyajima, Norio Shiratori
-
Journal Title
Proceedings of the International MultiConference of Engineers and Computer Scientists 2021
Volume: 28
Pages: 94 - 99
Peer Reviewed / Open Access / Int'l Joint Research
-
-
-
-
-
-
-
-
