Cheng Li

Personal webpage

Follow me on GitHub

Welcome to Cheng Li’s Website

I am an associate professor at the School of Computer Science, University of Science and Technology of China, and the director of the Information Computing Platform of the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center. My scientific interests are mainly in parallel and distributed intelligent computing and storage systems, with a data-centric perspective, to understand the mechanism of full-cycle data organization, storage, reading, writing, transmission and other factors affecting the computational efficiency during intelligent computing processes such as large models, and to propose new system architectures and design ideas.

Before joining USTC, I was an associated researcher with my PhD supervisor Rodrigo Rodrigues at INESC-ID, Portugal, and a senior member of technical staff at Oracle Labs Swiss.

In 2016, I obtained my PhD degree from the Dependable Systems Group at the Max Planck Institute for Software Sytems (MPI-SWS) and Saarland University in Germany. Before studying at MPI-SWS, I obtained my bachelor’s degree from Nankai University in 2009.

News

  • [Nov-15-2024] Our paper “PolyBase: Adapting to Data Affinity Changes in Geo-Replicated Database via Row-Level Paxos-Group Affiliation Re-Assignment” has been accepted to VLDB 2025! Congratulations to Chaoyi Ruan!
  • [Oct-18-2024] Congratulations to Chaoyi Ruan for successfully defending his PhD dissertation! The title is “Design and Optimization of Resource Scaling and High Availability for Cloud-Native Databases”.
  • [Sept-20-2024] Our paper “VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models” has been accepted to the EMNLP 2024 Main Conference! Congratulations to Yifei Liu!
  • [July-8-2024] Our paper “Eliminating Data Processing Bottlenecks in GNN Training over Large Graphs via Two-level Feature Compression” has been accepted to VLDB 2024! Congratulations to Yuxin Ma and Ping Gong!
  • [Mar-22-2024] Our paper “Cuber: Constraint-Guided Parallelization Plan Generation for Deep Learning Training” has been accepted to OSDI 2024! Congratulations to Zhiqi Lin!

Publications

  • Eliminating Data Processing Bottlenecks in GNN Training over Large Graphs via Two-level Feature Compression [pdf]. Yuxin Ma, Ping Gong, Tianming Wu, Jiawei Yi, Chengru Yang, Cheng Li, Qirong Peng, Guiming Xie, Yongcheng Bao, Haifeng Liu, Yinlong Xu. In Proceedings of the VLDB Endowment, Volume 17, Issue 11 (VLDB 2024).
  • Noctua: Towards Automated and Practical Fine-grained Consistency Analysis [pdf]. Kai Ma, Cheng Li, Enzuo Zhu, Ruichuan Chen, Feng Yan, Kang Chen. In Proceedings of the Nineteenth European Conference on Computer Systems (EuroSys 2024).
  • nnScaler: Constraint-Guided Parallelization Plan Generation for Deep Learning Training [pdf]. Zhiqi Lin, Youshan Miao, Quanlu Zhang, Fan Yang, Yi Zhu, Cheng Li, Saeed Maleki, Xu Cao, Ning Shang, Yilei Yang, Weijiang Xu, Mao Yang, Lintao Zhang, Lidong Zhou. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2024).
  • Tessel: Boosting Distributed Execution of Large DNN Models via Flexible Schedule Search [pdf]. Zhiqi Lin, Youshan Miao, Guanbin Xu, Cheng Li, Olli Saarikivi, Saeed Maleki, Fan Yang. In Proceedings of the 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA 2024).
  • SPFresh: Incremental In-Place Update for Billion-Scale Vector Search [pdf]. Yuming Xu, Hengyu Liang, Jin Li, Shuotao Xu, Qi Chen, Qianxi Zhang, Cheng Li, Ziyue Yang, Fan Yang, Yuqing Yang, Peng Cheng, Mao Yang. In Proceedings of the 29th Symposium on Operating Systems Principles (SOSP 2023).
  • gsampler: General and efficient gpu-based graph sampling for graph learning [pdf]. Ping Gong, Renjie Liu, Zunyao Mao, Zhenkun Cai, Xiao Yan, Cheng Li, Minjie Wang, Zhuozhao Li. In Proceedings of the 29th Symposium on Operating Systems Principles (SOSP 2023).
  • Frozenhot cache: Rethinking cache management for modern hardware [pdf]. Ziyue Qiu, Juncheng Yang, Juncheng Zhang, Cheng Li, Xiaosong Ma, Qi Chen, Mao Yang, Yinlong Xu. In Proceedings of the Eighteenth European Conference on Computer Systems (EuroSys 2023).
  • Cfs: Scaling metadata service for distributed file system via pruned scope of critical sections [pdf]. Yiduo Wang, Yufei Wu, Cheng Li, Pengfei Zheng, Biao Cao, Yan Sun, Fei Zhou, Yinlong Xu, Yao Wang, Guangjun Xie. In Proceedings of the Eighteenth European Conference on Computer Systems (EuroSys 2023).
  • Persistent memory disaggregation for cloud-native relational databases [pdf]. Chaoyi Ruan, Yingqiang Zhang, Chao Bi, Xiaosong Ma, Hao Chen, Feifei Li, Xinjun Yang, Cheng Li, Ashraf Aboulnaga, Yinlong Xu, In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 (ASPLOS 2023).
  • Mpress: Democratizing billion-scale model training on multi-gpu servers via memory-saving inter-operator parallelism [pdf]. Quan Zhou, Haiquan Wang, Xiaoyan Yu, Cheng Li, Youhui Bai, Feng Yan, Yinlong Xu, In Proceedings of the 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA 2023).
  • Revitalizing the Forgotten On-Chip DMA to Expedite Data Movement in {NVM-based} Storage Systems [pdf]. Jingbo Su, Jiahao Li, Luofan Chen, Cheng Li, Kai Zhang, Liang Yang, Yinlong Xu, In Proceedings of the 21st USENIX Conference on File and Storage Technologies (FAST 2023).
  • Gradient compression supercharged high-performance data parallel dnn training [pdf]. Youhui Bai, Cheng Li, Quan Zhou, Jun Yi, Ping Gong, Feng Yan, Ruichuan Chen, Yinlong Xu, In Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles (SOSP 2021).
  • Towards Cost-Effective and Elastic Cloud Database Deployment via Memory Disaggregation [pdf]. Yingqiang Zhang, Chaoyi Ruan, Cheng Li, Xinjun Yang, Wei Cao, Feifei Li, Bo Wang, Jing Fang, Yuhui Wang, Jingze Huo, Chao Bi. In Proceedings of the VLDB Endowment, Volume 14, Issue 10 (VLDB 2021).
  • AutoGR: Automated Geo-Replication with Fast System Performance and Preserved Application Semantics [pdf]. Jiawei Wang, Cheng Li, Kai Ma, Jingze Huo, Feng Yan, Xinyu Feng, Yinlong Xu. In Proceedings of the VLDB Endowment, Volume 14, Issue 10 (VLDB 2021).
  • SpanDB: A Fast, Cost-Effective LSM-tree Based KV Store on Hybrid Storage [pdf]. Hao Chen, Chaoyi Ruan, Cheng Li, Xiaosong Ma, Yinlong Xu. In Proceedings of the 19th USENIX Conference on File and Storage Technologies (FAST 2021).

Sponsors

With joint funding from the Ministry of Science and Technology, the Ministry of Education, the National Natural Science Foundation of China, the Chinese Academy of Sciences, and Anhui Province, as well as collaborations with Huawei, Alibaba, Baidu, and other companies, we have ample research funding, averaging $500,000 per year for the last five years.

Open positions for prospective students

We have several open positions for PostDoc, PhD, and master students every year. The applicants we are looking for should have the following competencies:

  1. a passion for systems research and a willingness to work for it
  2. have an outgoing personality, a positive attitude, a strong will, will not give up because of difficulties, and will continue to move forward after several rejections
  3. strong programming and engineering skills
  4. good communication skills in both English and Chinese.

Professional activities (recent)

  • OSDI 2025 PC member
  • EuroSys 2024/2025 PC member
  • FAST 2024 PC member
  • SOSP 2021 PC member
  • 2nd ACM TURC SIGOPS/14th ChinaSys workshop Co-Program Chair (with Rong Chen)
  • ACM SOSP Poster Session Co-Chair 2017 (with Gernot Heiser)

Teaching