丁宸

助理工程师

Email: dingchen@@gdiist.cn

研究方向:

类脑与神经网络专用计算芯片设计

个人简介: 

2018年本科毕业于西安电子科技大学微电子学院微电子科学与工程专业,2024年于复旦大学取得电子信息专业工程博士学位。博士期间围绕以通信为中心的神经网络加速器架构的设计展开研究。博士期间参与了国家自然科学基金、上海市新一代人工智能市级重大专项等多项课题。其中具体研究内容包括基于混合模式路由的类脑计算系统设计、基于片上网络的高计算单元利用率神经网络专用计算芯片设计等。博士期间完成了百万神经元级类脑仿真计算平台的FPGA原型样机,以及基于片上网络的神经网络计算加速系统FPGA原型样机和ASIC芯片设计流片。相关研究成果共发表7篇学术论文,并申请发明专利2项。

1. C. Ding, H. Ji, B. Huang, Y. Huan, L. -R. Zheng and Z. Zou, "Communication-Aware and Resource-Efficient NoC-Based Architecture for CNN Acceleration," in IEEE Journal on Emerging and Selected Topics in Circuits and Systems, vol. 14, no. 3, pp. 440-454, Sept. 2024.

2. C. Ding, Y. Huan, H. Jia, Y. Yan, et al., “A Hybrid-Mode On-Chip Router for the Large-Scale FPGA-Based Neuromorphic Platform”. IEEE Transactions on Circuits and Systems I: Regular Papers (TCAS-I), vol. 69, no. 5, pp. 1990-2001, May 2022.

3. C. Ding, Y. Huan, H. Jia, et al., "An Ultra-Low Latency Multicast Router for Large-Scale Multi-Chip Neuromorphic Processing," 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS), Washington DC, DC, USA, 2021

4. C. Ding, Y. Huan, L. Zheng and Z. Zou, "Dynamic Precision Multiplier For Deep Neural Network Accelerators," 2020 IEEE 33rd International System-on-Chip Conference (SOCC), Las Vegas, NV, USA, pp. 180-184, 2020.

5. H. Jia, Y. Huan, C. Ding, Y. Yan, et al, "A Domain-Specific Accelerator for Ultra-low Latency Market Data Distribution System," in lEEE Transactions on industrial Informatics, vol. 19, no.4,pp.5465-5475,April 2023.

6. J. Xu, J. Fan, B. Nan, C. Ding, et al., "ASLog: An Area-Efficient CNN Accelerator for Per-Channel Logarithmic Post-Training Quantization," in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 70, no. 12, pp. 5380-5393, Dec. 2023.

7. B. Huang, Y. Huan, H. Jia, C. Ding, et al., "AIOC: An All-in-One-Card Hardware Design for Financial Market Trading System," in IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 9, pp. 3894-3898, Sept. 2022

8丁宸、环宇翔、梁龙飞、闫钰龙、邹卓、郑立荣, “一种用于大规模类脑计算网络的种群路由方法”,中国发明专利,CN112163673B,2020.(已授权)

9环字翔、邹卓、郑立荣、丁宸、贾浩、闫钰龙用于大规模类脑计算网络的种群聚类及种群路由方法”中国发明专利CN12149815B2020.(已授权)


类脑芯片联合实验室