
李冰博士
首都师范大学交叉科学研究院 副研究员
Email: bing.li@cnu.edu.cn
个人简介
李冰博士,首都师范大学交叉科学研究院副研究员,美国杜克大学电子与计算机工程系博士后,中国科学院计算技术研究所博士。
主要研究方向是计算机体系结构及集成电路设计,具体关注新兴算法的加速器芯片设计和高能效深度学习算法优化,包括存算融合的高能效计算技术,如算法设计、体系结构,以及自动化设计(EDA),在计算系统结构及集成电路的可靠性问题和安全问题有多年的研究。
以第一作者及通讯作者身份在TCAD、DAC、ICCAD、DATE等在内的计算机体系结构及芯片设计自动化领域的顶级/权威会议及期刊发表论文40余篇,授权中美发明专利6项。荣获2018年美国科学院博士后奖学金,IEEE GLSVLSI'21最佳论文奖第二名(近几年大陆唯一获奖),2022年北京市高端人才项目。
现为IEEE会员、CCF会员以及CCF集成电路设计和CCF容错专委执行委员,北京科委电子与信息学部专家,中国能源研究会电力传感和智能分析专委,Frontiers in Computational Neuroscience客座主编。担任DAC22/21、DATE18、ASPDAC20/22/23国际学术会议的程序委员委员、DAC'22、ICCAD'21、ASPDAC'20/18在内的多个体系结构及集成电路领域国际会议会议主席(Session Chair)。TCAD、TCAS-I、TACO、TODAES, TNNLS、JETC等期刊审稿人。
研究领域
存算融合架构的软硬件设计
深度学习模型轻量化
加速器的可靠性及安全
教育经历
2017.09-2019.09 美国,杜克大学,电子与计算机工程系,进化智能研究中心,博士后研究员
导师: 李海教授Helen Li (ACM&IEEE Fellow, Duke ECE Chair电子与计算机工程系系主任)
2010.09-2016.06 北京,中国科学院大学,计算技术研究所国家重点实验室,工学博士
导师:胡瑜研究员
2006.09-2010.06 北京,中央民族大学(985, 211), 计算机科学与技术专业, 工学学士
工作经历
2019.10至今 中国,北京,首都师范大学,交叉科学研究院,副研究员
2016.09-2017.07 北京,中国联合通信有限公司研究院,工程师研究员
主持或参加科研项目
1)[主持] 国家自然科学基金青年科学基金项目,61872251,面向移动终端的忆阻器存内计算加速器设计方法和关键技术研究,2023/01-2025/12,30万元,在研。
2)[主持] 某深度学习项目子课题,存储计算资源管理技术研究,2020/05-2021/4,45万元,已结题。
代表性会议论文
[1] Yintao He, Songyun Qu, Ying Wang, BING LI, Huawei Li, and Xiaowei Li. 2022. InfoX: an energy-efficient ReRAM accelerator design with information-lossless low-bit ADCs. In Proceedings of the 59th ACM/IEEE Design Automation Conference (DAC '22). Association for Computing Machinery, New York, NY, USA, 97–102. https://doi.org/10.1145/3489517.3530396 (CCF A)
[2] Songyun Qu*, BING LI*, Ying Wang, Lei Zhang. ASBP: Automatic Structured Bit-Pruning for RRAM-based NN Accelerator. in 2021 58th ACM/IEEE Design Automation Conference (DAC). (CCF A)
[3] Songyun Qu*, BING LI*, Ying Wang, Dawen Xu, Xiandong Zhao, and Lei Zhang, RaQu: An Automatic High-utilization CNN Quantization and Mapping Framework for General-purpose RRAM Accelerator, in 2020 57th ACM/IEEE Design Automation Conference (DAC), Jul. 2020, pp. 1–6, doi: 10.1109/DAC18072.2020.9218724. (CCF A)
[4] Mengdi Wang*, BING LI*, Ying Wang, Huawei Li, and Xiaowei Li. MT-DLA: An Efficient Multi-Task Deep Learning Accelerator Design. In Proceedings of the 2021 on Great Lakes Symposium on VLSI (GLSVLSI '21). DOI:https://doi.org/10.1145/3453688.3461514 最佳论文(EI, CCF C)
[5] Chengsi Gao*, BING LI*, Ying Wang, Weiwei Chen, Lei Zhang. Tenet: A Neural Network Model Extraction Attack in Multicore Architecture. In Proceedings of the 2021 on Great Lakes Symposium on VLSI (GLSVLSI '21). DOI:https://doi.org/10.1145/3453688.3461512 (EI, CCF C)
[6] Hao Lv*, BING LI*, Ying Wang, Cheng Liu, Lei Zhang. VADER: Leveraging the Natural Variation of Hardware to Enhance Adversarial Attack, in 26th Asia and South Pacific Design Automation Conference (ASP-DAC), (pp. 487-492). 2021. (EI, CCF C)
[7] BING LI, Ying Wang, Yiran Chen. HitM: High-Throughput ReRAM-based PIM for Multi-Modal Neural Networks, in Proceedings of the 39th International Conference on Computer-Aided Design (ICCAD '20), DOI:https://doi.org/10.1145/3400302.3415663. (CCF B)
[8] BING LI Bonan Yan, Hai Helen Li. An Overview of In-memory Processing with Emerging Non-volatile Memory for Data-intensive Applications, In Proceedings of the 2019 on Great Lakes Symposium on VLSI (GLSVLSI '19). ACM, New York, NY, USA, 381-386. DOI: https://doi.org/10.1145/3299874.3319452 (EI, CCF C)
[9] BING LI, Bonan Yan, Chenchen Liu, Hai Helen Li. Build Reliable and Efficient Neuromorphic Design with Memristor Technology, in Proceedings of the 24th Asia and South Pacific Design Automation Conference (ASPDAC '19), pp. 224-229, DOI: https://doi.org/10.1145/3287624.3288744. (EI, CCF C)
[10]BING LI, Linghao Song, Fan Chen, Xuehai Qian, Yiran Chen, Hai Helen Li. ReRAM-based accelerator for deep learning, in Design, Automation & Test in Europe Conference & Exhibition (DATE), 2018, pp 815-820, doi: 10.23919/DATE.2018.8342118. (EI, CCF B)
代表性会议论文
[1] Hao Lv, BING LI*(共同一作), Lei Zhang, Cheng Liu, Ying Wang, Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (CCF A)
[2] BING LI* WU Kangjun, WANG Jing, LI Sen, GAO Lan, ZHANG Weigong, NI Tianming. A Sparsity Optimized Resistive Random Access Memory Based Accelerator for Graph Convolutional Network[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT211435 (ESCI, EI)
[3] Zhao Yinglin, Yang Jianlei, BING LI#(通讯作者), Cheng Xingzhou, Ye Xucheng, Wang Xueyan, Jia Xiaotao, Wang Zhaohao, Zhang Youguang, ZHAO Weisheng, NAND-SPIN-Based Processing-in-MRAM Architecture for Convolutional Neural Network Acceleration, In Journal of SCIENCE CHINA Information Sciences, 2022, ISSN 1674-733X, https://doi.org/10.1007/s11432-021-3472-9. (SCI JCR Q1)
[4] BING LI, Songyun Qu, Ying Wang. An Automated Quantization Framework for High-utilization RRAM-based PIM. in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, no. 3, pp. 583-596, March 2022, doi: 10.1109/TCAD.2021.3061521. (CCF A)
[5] Ziru Li, BING LI*, Zichen Fan, and Hai Li. RED: an ReRAM-based Efficient Accelerator for Deconvolutional Computation. in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), vol. 39, no. 12, pp. 4736-4747,doi: 10.1109/TCAD.2020.2981055. (CCF A)
[6] BING LI, Janardhan Rao Doppa, Partha Pratim Pande, Krishnendu Chakrabarty, Hai Li. 3D-ReG: A 3D ReRAM-based Heterogeneous Architecture for Training Deep Neural Networks, ACM Journal on Emerging Technologies in Computing Systems (JETC). 16 (2), 1-24, 2020. DOI:https://doi.org/10.1145/3375699 (SCI)
发明专利
已授权
[1] 一种基于忆阻器的DNN加速器的资源分配方法及装置. (授权号:202011539621.9)
[2] 一种相变存储器写加速方法及其系统. (授权号: 201410064466)
[3] 一种消息式内存模组的访存方法和装置. (授权号: 201310330220 .6)
[4] 一种内存访问的方法、设备及系统 . (授权号: 201310345355 .X)
[5] Memory access method and apparatus for message-type memory module. (美国专利:US9,811,416)
[6] Memory access method, device, and system. (美国专利: US9,772,891)
已申请
[1] 一种文本识别方法及系统. (申请号:202210661118.3)
[2] 一种忆阻器交叉阵列.(申请号:202110044218.7)
[3] 一种缓解忆阻加速器非理想因素的方法及装置.(申请号:202110506629.3)
[4] 一种卷积神经网络系统、忆阻器阵列和卷积神经网络. (申请号:2021032278.4)
[5] 一种相变存储器写加速方法及其系统. (授权号: 201410064466)
[6] 一种消息式内存模组的访存方法和装置. (授权号: 201310330220 .6)
[7] 一种内存访问的方法、设备及系统 . (授权号: 201310345355 .X)
美国授权专利
[8] Memory access method and apparatus for message-type memory module. (美国专利:US9,811,416)
[9] Memory access method, device, and system. (美国专利: US9,772,891)
教学
2020年春 《数字图像处理II》研究生方向课 选修
2021年秋 《深度学习应用与实践》研究生方向课 选修
2022年秋 《高级程序设计-Python与深度学习》 研究生基础课
学术服务
ITC-Asia、GLSVLSI 2020 & GLSVLSI 2021、23th & 25th ASP-DAC,China DA 2021 Session Chair
2021 京区青年学者“后摩尔时期的计算形态与设计自动化” 论坛发起人
DAC 2021 & 2022 、CCF CFTC 2019 & CCF CFTC 2021等程序委会成员
CCF DAC 2021论坛主席、CCF CHIP 2022 出版主席
TCAD、TCAS-I、TACO、TODAES, TNNLS、JETC等期刊审稿人。