主要从事高性能智能计算芯片的设计研究，重点包括以下方向：

1. AI加速器与数字集成电路芯片设计：

    面向人工智能领域，基于eDRAM和SRAM构建高性能、高能效的专用加速器芯片；

2. 低温CMOS计算芯片设计：

    探索低温环境下CMOS芯片的设计与优化，研究基于eDRAM的低温高性能存储与存内计算芯片；

3. 高能效FPGA电路与系统设计：

    聚焦可重构计算，定制设计FPGA关键核心模块及其IP核。

代表性期刊/会议论文 (Google Scholar):

[ICAS' 24] Yuhao Shu, Bin Ning, Yifei Li, Zhaodong Lyu, Jincheng Wang, Lintao Lan, Yuxin Zhou, Mengru Zhang, Hongtu Zhang, Yajun Ha, Overview of Cryogenic CMOS Based Computing Systems, Integrated Circuits and Systems, 2024

[JSSC' 24] Yuhao Shu, Hongtu Zhang, Qi Deng, Hao Sun, Zhaodong Lv, Yifei Li, Yajun Ha, eCIMC: A 603.1-TOPS/W eDRAM-Based Cryogenic In-Memory Computing Accelerator Supporting Boolean/Convolutional Operations, IEEE Journal of Solid-State Circuits, 2024 

[TCAS-I' 23] Hongtu Zhang*, Yuhao Shu*, Qi Deng, Hao Sun, Wenfeng Zhao, Yajun Ha, WDVR-RAM: A 0.25-1.2 V, 2.6-76 POPS/W Charge-Domain In-Memory-Computing Binarized CNN Accelerator for Dynamic AIoT Workloads, IEEE Transactions on Circuits and Systems I: Regular Papers, 2023 

[CICC' 23] Yuhao Shu, Hongtu Zhang, Qi Deng, Hao Sun, Yajun Ha, CIMC: A 603TOPS/W In-Memory-Computing C3T Macro with Boolean/Convolutional Operation for Cryogenic Computing, IEEE Custom Integrated Circuits Conference (CICC), 2023 

[ISCAS' 23] Yuhao Shu, Hongtu Zhang, Hao Sun, Qi Deng, Yajun Ha, CSDB-eDRAM: A 16Kb Energy-Efficient 4T CSDB Gain Cell eDRAM with over 16.6s Retention Time and 49.23uW/Kb at 4.2K for Cryogenic Computing, IEEE International Symposium on Circuits and Systems (ISCAS), 2023 

[TCAS-II' 21] Hongtu Zhang*, Yuhao Shu*, Weixiong Jiang, Zihan Yin, Wenfeng Zhao, Yajun Ha, A 55nm, 0.4V 5526-TOPS/W Compute-in-Memory Binarized CNN Accelerator for AIoT Applications, IEEE Transactions on Circuits and Systems II: Express Briefs, 2021 (ISCAS' 21 Invited Paper)