Research Topics

Topic 1: Deep Neural Network Design Automation

In this project we will explore 1) DNN compression / acceleration and 2) DNN design space exploration.

approx-dnn 

Selected recent publications:

  • [C113] Qi Sun, Chen Bai, Hao Geng, Bei Yu, “Deep Neural Network Hardware Deployment Optimization via Advanced Active Learning”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Feb. 01–05, 2021.

  • [C92] Qi Sun, Tinghuan Chen, Jin Miao, Bei Yu, “Power-Driven DNN Dataflow Optimization on FPGA”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Westminster, CO, Nov. 4–7, 2019. (paper) (slides) (Invited Paper)

  • [C91] Yuzhe Ma, Ran Chen, Wei Li, Fanhua Shang, Wenjian Yu, Minsik Cho, Bei Yu, “A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks”, IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Portland, OR, Nov. 4–6, 2019. (arXiv) (slides) (Best Student Paper Award)



Topic 2: Deep Mask Learning

hotspots 

Selected recent publications:

  • [C104] Guojin Chen, Wanli Chen, Yuzhe Ma, Haoyu Yang, Bei Yu, “DAMO: Deep Agile Mask Optimization for Full Chip Scale”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Nov. 2–5, 2020. (paper) (slides) (whova)

  • [C57] Hang Zhang, Fengyuan Zhu, Haocheng Li, Evangeline F. Y. Young, Bei Yu, “Bilinear Lithography Hotspot Detection”, ACM International Symposium on Physical Design (ISPD), pp. 7–14, Portland, OR, Mar. 19–22, 2017. (paper) (Best Paper Award)



Topic 3: Learning on Chips

Machine learning is a powerful computer science technique which can derive knowledge from big data, and provides prediction and matching. Since nanometer VLSI CAD problems have extremely high complexity and gigantic data, there has been a surge recently in applying and adapting machine learning techniques in VLSI CAD.

hotspots 

Selected recent publications:

  • [C109] Wei Li, Yuxiao Qu, Gengjie Chen, Yuzhe Ma, Bei Yu, “TreeNet: Deep Point Cloud Embedding for Routing Tree Construction”, IEEE/ACM Asian and South Pacific Design Automation Conference (ASPDAC), Jan. 18–21, 2021.

  • [C101] Zhuolun He, Yuzhe Ma, Lu Zhang, Peiyu Liao, Ngai Wong, Bei Yu, Martin D. F. Wong, “Learn to Floorplan through Acquisition of Effective Local Search Heuristics”, IEEE International Conference on Computer Design (ICCD), Oct. 18–21, 2020.

  • [C98] Wei Li, Jialu Xia, Yuzhe Ma, Jialu Li, Yibo Lin, Bei Yu, “Adaptive Layout Decomposition with Graph Embedding Neural Networks”, ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, July 19–23, 2020. (paper) (slides)



Topic 4: Hardware Friendly Computer Vision

hardware-cv 



Topic 5: Combinatorial Algorithms in VLSI CAD

Many classical VLSI CAD problems can be extracted and formulated into challenging combinatorial optimization problems. We are heavily working to improve the state-of-the-art.

hotspots 

Selected recent publications are listed as follows:



Topic 6: Emerging Challenges

Cyber-physical system (CPS) addresses the close interactions and feedback loop between the cyber components such as sensing systems and the physical components such as varying environment and energy systems. Currently we are working on data regression and calibration in smart building environment. On ther other hand, we are also working on improving the security for hardware systems.

emerging topics 

Selected recent publications: