Directions
Facebook
X
Instagram
YouTube
Japanese
Contact Us
TOP
Research
AI for Science Platform Division
Advanced AI Device Development Unit
Advanced AI Device Development Unit
Japanese
Unit Leader Kentaro Sano
kentaro.sano[at]riken.jp (Lab location: Kobe)- Please change [at] to @
- 2025
- Unit Leader, Next-Generation HPC Infrastructure System Development Unit, Next-Generation HPC Infrastructure Development Division, RIKEN R-CCS (-present)
- 2024
- Unit Leader, Advanced AI Device Development Unit, AI for Science Platform Division, R-CCS, RIKEN (-present)
- 2017
- Team Leader, Processor Research Team, AICS (renamed R-CCS in 2018), RIKEN (-present)
- 2006
- Visiting Researcher, Imperial College,London
- 2005
- Associate Professor, Graduate School of Information Sciences, Tohoku University
- 2001
- Assistant Professor, Graduate School of Information Sciences, Tohoku University
- 2000
- Assistant Professor, Graduate School of Engineering, Tohoku University
- 2000
- Graduated from Computer and Mathematical Sciences, Graduate School of Information Sciences, Tohoku University
Keyword
- Generative AI
- Next-generation foundation model
- Accelerator architecture for AI
Research summary
This unit researches and develops accelerator devices to improve the performance and efficiency of training and/or inference for the next-generation AIs such as generative AI. Especially, we focus on AI models and algorithms, new computer architectures and hardware designs, and system software such as compilers and frameworks for AI.
Representative papers
-
Emanuele Del Sozzo, Xinyuan Wang, Boma Adhi, Carlos Cortes, Jason Anderson, Kentaro Sano,
"Exploration of Trade-offs Between General-Purpose and Specialized Processing Elements in HPC-Oriented CGRA"
Proceedings of IEEE International Parallel & Distributed Processing Symposium (IPDPS), 2024. [Accepted] -
Boma Adhi, Carlos Cortes, Emanuele Del Sozzo, Tomohiro Ueno, Yiyu Tan, Takuya Kojima, Artur Podobas, Kentaro Sano,
"Less for More: Reducing Intra-CGRA Connectivity for Higher Performance and Efficiency in HPC"
Proceedings of CGRA4HPC Workshop IPDPS 2023, pp.452-459, 2023. -
Boma Adhi, Carlos Cortes, Yiyu Tan, Takuya Kojima, Artur Podobas, and Kentaro Sano,
"The Cost of Flexibility: Embedded versus Discrete Routers in CGRAs for HPC"
Proceedings of IEEE Cluster Conference (CLUSTER), pp.347-356, DOI: 10.1109/CLUSTER51413.2022.00046, Sep 6-9, 2022. -
Boma Adhi, Carlos Cortes, Yiyu Tan, Takuya Kojima, Artur Podobas, and Kentaro Sano,
"Exploration Framework for Synthesizable CGRAs Targeting HPC: Initial Design and Evaluation"
Proceedings of the First International Workshop on Coarse-Grained Reconfigurable Architectures for High-Performance Computing (CGRA4HPC), May 30, Lyon, 2022. Hybrid -
Tomohiro Ueno and Kentaro Sano,
"VCSN: Virtual Circuit-Switching Network for Flexible and Simple-to-Operate Communication in HPC FPGA Cluster"
ACM Transactions on Reconfigurable Technology and Systems (TRETS), Vol.16, Issue.2, Article No.25, pp.1-32, DOI: 10.1145/3579848, 2023.
