Jie Zhao

Position: Professor
Affiliation: College of Computer Science and Electronic Engineering, Hunan University
Contact: jiezhao AT hnu.edu.cn
Address: Lushan Road (S), Yuelu District, Changsha, 410082, China.

jiezhao-hpcchina2024.jpg

Jie Zhao is a Full Professor at the College of Computer Science and Electronic Engineering, Hunan University, where he leads the CYCLE Lab. He has established strong relationships with major technology companies, including Huawei Technologies, Alibaba Group, and ByteDance, as well as innovative startups like Stream Computing Co., Ltd. Jie Zhao earned his PhD under the supervision of Prof. Albert Cohen from PARKAS, a research group affiliated with the Département d’Informatique at École Normale Supérieure and INRIA Paris. Education & Experience details more about his academic and industrial careers. Jie Zhao’s research interests focus on building intelligent software systems, with an emphasis on machine learning systems, polyhedral compilers, numerical program analysis, and high-level synthesis. Research provides a comprehensive overview of his research topics, funding, honors, and awards. His scholarly contributions are listed under Publications, and his open-source work can be explored through Projects & Repositories. Jie Zhao also maintains a personal website in Chinese, which can be accessed at his homepage at Hunan University.

news

Oct 18, 2024 The website of our research group, the CYCLE Lab, which stands for Compiler Systems Yielding for Computational Languages and Execution Acceleration has been successfully established. One can access the laboratory homepage by visiting here.
Sep 07, 2024 The proposal titled “Design Automation of Integrated Circuits for Intelligent Chips” was approved by the National Natural Science Foundation of China (NSFC) under grant number T2422007 on August 27th, 2024. The project is scheduled to run from January 2025 to December 2027.
Jul 03, 2024 One paper titled “Arfa: An Agile Regime-based Floating-point Optimization Approach for Rounding Errors” was accepted by ISSTA 2024.

selected publications

  1. TOCS 2024
    Modeling the Interplay between Loop Tiling and Fusion in Optimizing Compilers Using Affine Relations
    Jie Zhao, Jinchen Xu, Peng Di, Wang Nie, Jiahui Hu, Yanzhi Yi, Sijia Yang, Zhen Geng, Renwei Zhang, Bojie Li, Zhiliang Gan, and Xuefeng Jin
    ACM Trans. Comput. Syst., Jan 2024
  2. OSDI 2023
    Effectively Scheduling Computational Graphs of Deep Neural Networks toward Their Domain-Specific Accelerators
    Jie Zhao, Siyuan Feng, Xiaoqiang Dan, Fei Liu, Chengke Wang, Sheng Yuan, Wenyuan Lv, and Qikai Xie
    In Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23), Jul 2023
  3. MLSys 2022
    Apollo: Automatic Partition-based Operator Fusion through Layer by Layer Optimization
    Jie Zhao, Xiong Gao, Ruijie Xia, Zhaochuang Zhang, Deshi Chen, Lei Chen, Renwei Zhang, Zhen Geng, Bin Cheng, and Xuefeng Jin
    In Proceedings of Machine Learning and Systems, Jul 2022
  4. PLDI 2021
    AKG: Automatic Kernel Generation for Neural Processing Units Using Polyhedral Transformations
    Jie Zhao, Bojie Li, Wang Nie, Zhen Geng, Renwei Zhang, Xiong Gao, Bin Cheng, Chen Wu, Yun Cheng, Zheng Li, Peng Di, Kun Zhang, and Xuefeng Jin
    In Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, Jul 2021
  5. MICRO 2020
    Optimizing the Memory Hierarchy by Compositing Automatic Transformations on Computations and Data
    Jie Zhao, and Peng Di
    In Proceedings of the 53rd IEEE/ACM International Symposium on Microarchitecture, Virtual Event, Athens, Greece, Jul 2020