智能微纳系统设计与集成

环宇翔

环宇翔
职称:客座研究员
电子邮件:yhuan13@fudan.edu.cn
办公地点:复旦大学邯郸校区遗传学楼3楼

 

个人简介:

  • 环宇翔,广东省智能科学与技术研究院研究员,类脑计算架构与超大规模处理系统研究组组长。2018年于复旦大学取得微电子学与固体电子学博士学位,曾任复旦大学信息科学与工程学院任助理研究员、广东省智能科学与技术研究院副研究员。长期围绕领域专用处理架构(Domain-Specific Architecture, DSA)的芯片系统设计和领域应用开展研究,重点聚焦于从芯片到系统的分布式互联处理架构和设计方法的研究,包括可重构可扩展架构的领域专用处理器、复杂深度学习模型的高能效加速和分布式处理、神经拟态专用集成电路和类脑计算系统等,累计发表学术论文30余篇,申请发明专利15项。


研究方向:

  • 主要面向类脑计算的硬件处理架构和超大规模类脑计算系统设计展开研究,旨在借鉴人脑的信息处理机制,设计具有神经拟态特性的专用处理内核、大规模的芯片互联架构与方法、以及面向全脑尺度千亿神经元规模超级计算系统。课题组将主要聚焦:面向类脑计算的领域专用处理架构与芯片设计,超低延时和高可靠的片上网络互联,面向晶圆级集成芯片的新型片上分布式处理架构和任务调度方法。目标通过“算法-架构-电路”协同设计的方法,实现事件驱动的超大规模芯片计算网络,支持海量处理内核的局部数据共享、异步信息传递和分布式协同处理,最终支撑千亿神经元规模的类脑计算系统的设计构建。


代表论著:

  1. C. Ding#, Y. Huan#*, H. Jia, Y. Yan, F. Yang, L. Liu, M. Shen, Z. Zou and L.R. Zheng, "A Hybrid-Mode On-Chip Router for the Large-Scale FPGA-Based Neuromorphic Platform," in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 69, no. 5, pp. 1990-2001, 2022. (SCI, 共同一作,共同通信作者)
  2. B. Huang#, Y. Huan#*, H. Jia, C. Ding, Y. Yan, B. Huang, L.R. Zheng, and Z. Zou, "AIOC: An All-In-One-Card Hardware Design for Financial Market Trading System," in IEEE Transactions on Circuits and Systems II: Express Briefs, 2022. (SCI, 共同一作,共同通信作者)
  3. Y. Jin, B. Huang, Y. Yan; Y. Huan*, J. Xu, S. Li, P. Gope, L. Xu, Z. Zou, and L.R. Zheng, "Edge-based Collaborative Training System for Artificial Intelligence-of-Things," in IEEE Transactions on Industrial Informatics, 2022. (SCI,共同通信作者)
  4. B. Huang#, Y. Huan#*, H. Chu, J. Xu, L.R. Zheng, and Z. Zou, “IECA: An In-Execution Configuration CNN Accelerator With 30.55 GOPS/mm² Area Efficiency,” in IEEE Transactions on Circuits and Systems I: Regular Papers, 2021. (SCI, 共同一作,通信作者)
  5. J. Xu#, Y. Huan#, B. Huang, H. Chu, Y. Jin, L.R. Zheng, Z. Zou, “A Memory-Efficient CNN Accelerator Using Segmented Logarithmic Quantization and Multi-Cluster Architecture,” in IEEE Transactions on Circuits and Systems II: Express Briefs, 2020. (SCI, 共同一作)
  6. Y. Huan, N. Ma, J. Mao, S. Blixt, Z. Lu, Z. Zou and L. R. Zheng, “A 101.4 GOPS/W Reconfigurable and Scalable Control-Centric Embedded Processor for Domain-Specific Applications,” in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 63, no. 12, pp. 2245-2256, Dec. 2016. (SCI)
  7. Y. Jin, J. Cai, J. Xu, Y. Huan*, Y. Yan, B. Huang, Y. Guo, L.R. Zheng, Z. Zou, “Self-aware distributed deep learning framework for heterogeneous IoT edge devices,” Future Generation Computer Systems, Volume 125, 2021. (SCI, 通信作者)
  8. W. Li, H. Chu, B. Huang, Y. Huan*, L.R. Zheng, Z. Zou, “Enabling on-device classification of ECG with compressed learning for health IoT,” Microelectronics Journal, Volume 115, 2021. (SCI, 通信作者)
  9. J. Xu#, Y. Huan#, B. Huang, H. Chu, Y. Jin, L.R. Zheng, Z. Zou, “Base-Reconfigurable Segmented Logarithmic Quantization and Hardware Design for Deep Neural Networks,” in Journal of Signal Processing Systems, 2020. (SCI, 共同一作)
  10. Y. Huan, J. Xu, L. Zheng, H. Tenhunen and Z. Zou, “A 3D Tiled Low Power Accelerator for Convolutional Neural Network,” 2018 IEEE International Symposium on Circuits and Systems (ISCAS), Florence, Italy, 2018. (EI)

版权所有©复旦大学信息科学与工程学院微纳系统中心版权所有

地址:淞沪路2005号复旦大学江湾校区交叉学科二号楼7楼 电话:021-31242626