Researcher @ Huawei 2012 Network Technique Lab, Email: zhou.zhe@pku.edu.cn [CV] [Google Scholar] [GitHub]

About me

I obtained a PhD. degree in 2024 at Peking University under the supervision of Dr. Guangyu Sun.
Before that, I received the B.S. degree also from Peking University. My research interests primarily lie in the areas of computer architecture, near-data processing, domain-specific accelerators, deep learning systems, and interconnect techniques. I pay particular attention to addressing the Memory Wall and Communication Wall problems. Through my work, I have published as the first author in top-tier computer architecture/system conferences/journals including HPCA (Won the Best Paper Award), MICRO, USENIX ATC, DAC, PACT and TCAD.

Internship Opportunities

🌟 现招聘实习生 (Now Hiring Interns)
我们（华为中央研究院网络技术实验室）正在寻找对 ScaleUp 互联架构 感兴趣的优秀实习生！如果您对以下技术方向有研究兴趣或经验，欢迎联系我：
• Huawei Unified Bus (UB)
• CXL (Compute Express Link)
• NVIDIA NVLink
• 具有 计算机体系结构 背景的同学优先

We (Network Technology Lab, Huawei Central Research Institute) are actively seeking talented interns interested in ScaleUp Interconnect Architecture! If you have research interests or experience in the following areas, please feel free to contact me:
• Huawei Unified Bus (UB) interconnect technology
• CXL (Compute Express Link) protocol and applications
• NVIDIA NVLink high-speed interconnect
• Students with computer architecture background preferred

📧 Contact: zhou.zhe@pku.edu.cn

Research Interests

• ScaleUp Interconnect Architecture

• Domain-Specific Architecture

• Near-Data Processing

• Machine Learning System

News:

• Our UB-Mesh paper https://arxiv.org/abs/2503.20377 will be presented at HotChips 2025.

Selected Publications

• NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering.
  Zhe Zhou(1), Yiqi Chen(1), Tao Zhang, Yang Wang, Ran Shu, Shuotao Xu, Peng Cheng, Lei Qu, Jie Zhang Yongqiang Xiong, Guangyu Sun.
  MICRO 2024

• DIMM-Link: Enabling Efficient Inter-DIMM Communication for Near-Memory Processing.
  Zhe Zhou(1), Cong Li(1), Fan Yang, Guangyu Sun.
  International Symposium on High- Performance Computer Architecture (HPCA), 2023. (Best Paper Award!)

• PetS: A Unified Framework for Parameter-Efficient Transformers Serving.
  Zhe Zhou, Xuechao Wei, Jiejing Zhang, Guangyu Sun.
  USENIX Annual Technical Conference (USENIX ATC), 2022. Acceptance rate: 16%.

• GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processing.
  Zhe Zhou, Cong Li, XueChao Wei, Guangyu Sun.
  International Conference on Parallel Architectures and Compilation Techniques (PACT), 2022.

• Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention
  Zhe Zhou, Junlin Liu, Guangyu Sun, and Zhenyu Gu.
  IEEE Transactions on Computer Aided Design of Integrated Circuits & Systems (TCAD), 2022.

• BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices
  Zhe Zhou, Bizhao Shi, Zhe Zhang, Guangyu Sun, and Guojie Luo.
  Design Automation Conference , (DAC), 2021. Acceptance rate: 23%

• NMExplorer: An Efficient Exploration Framework for DIMM-based Near-Memory Tensor Reduction. (To Appear~)
  Cong Li, Zhe Zhou, Xingchen Li, Dimin Niu, Guangyu Sun.
  Design Automation Conference (DAC), 2023.

• PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization.
  Cong Li, Zhe Zhou, Yang Wang, Fan Yang, Ting Cao, Mao Yang, Yun Liang, Guangyu Sun.
  Accepted by ASPLOS 2024

• SpecPIM: SpecPIM: Accelerating Speculative Inference on PIM-Enabled System via Architecture-Dataflow Co-Exploration.
  Cong Li, Zhe Zhou, Size Zheng, Jiaxi Zhang, Yun Liang, Guangyu Sun.
  Accepted by ASPLOS 2024

• FD-CNN: A Frequency-Domain FPGA Acceleration Scheme for CNN-based Image Processing Applications.
  Xiaoyang wang (1), Zhe Zhou (1), Zhihang Yuan et al.
  ACM Transactions on Embedded Computing Systems (TECS), 2022.

• Hardware-Assistedservice Live Migration in Resource-Limited Edge Computing Systems.
  Zhe Zhou, Xintong Li, Xiaoyang Wang, Zheng Liang, Guangyu Sun, and Guojie Luo.
  Design Automation Conference , (DAC), 2020. Acceptance rate: 22%.

Honors and Awards

• 2025: Outstanding Doctoral Dissertation Award, ACM ChinaSys / ACM ChinaSys优博 (3 positions)

• 2024: Outstanding Doctoral Dissertation Award of Computer Department / 北京大学计算机学院优博 (10 positions)

• 2023: HPCA Best Paper Award / HPCA 最佳论文奖 (2 positions)

• 2023: President Award of Peking University / 北京大学校长奖学金 (top 2%)

• 2023: Award of Excellence, Stars of Tomorrow Intership Program / 微软亚研院“明日之星”优秀实习生奖 (top 10%)

• 2022: ByteDance Scholarship / 字节跳动奖学金 (10 students in China)

• 2022: China National Scholarship / 博士生国家奖学金 (top 2%)

• 2022: Academic Innovation Award of Peking University / 北京大学科研创新奖 (top 1%)

• 2021: Merit Student of Peking University / 北京大学三好学生

• 2016: Excellent Social Work Award of Peking University / 北京大学社会工作奖

Industrial Experience

• Huawei 2012 (Network Technique Lab)

  Researcher. July 2024-

• Microsoft Research Asia (Networking Research Group)

  Research Intern. Aug 2022- May 2023

• Alibaba DAMO Academy (Machine Intelligence Laboratory)

  Research Intern. May 2021-Jan 2022

• Alibaba DAMO Academy (T-HEAD Semiconductor)

  Research Intern. July 2020-January 2021

• Advanced Institute of Information Technology (Real-Time Computing Laboratory)

  Research Intern. April 2019-April 2020