Guanpeng Li

I am an assistant professor in the Computer Science Department at the University of Iowa since 2020. Broadly speaking, my research focuses on building dependable high-performance computer systems. In the past, my students and/or I have won the Best Paper Awards (or finalists) at SC, DSN, and ISSRE conferences in 2022, 2021, 2020 and 2018, and IEEE Top Picks in Test and Reliability in 2023. I am also on the DSN Hall of Fame.

Educational Background

• Postdoc, University of Illinois Urbana-Champaign (2020)

• PhD, University of British Columbia (2019)

• BASc, University of British Columbia (2014)

Research Interests

• HPC Fault Tolerance

• Lossy Compression for HPC Data Reduction

• Safety of Automonous Driving Systems

• Machine Learning Dependability

• Approximate Computing

News

• 04/2024 [Service]: Serve as PC on DSN'25, ISSRE'24, QRS'24, PRDC'24, and HiPC'24. Serve as publicity co-chair at ISSRE'24.

• 03/2024 [Paper]: One paper accepted at DSN'24. Congratulations, Zhengyang!

• 03/2024 [Paper]: One paper accepted at MSST'24. Congratulations, Hasan!

• 02/2024 [Paper]: Our paper on DNN resilience accepeted at STVR journal.

• 12/2023 [Paper]: Two papers accepted at IPDPS'24.

• 11/2023 [Paper]: One paper accepted at AsiaCCS'24.

• 09/2023 [Paper]: Our paper about DNN resilience has been selected by 2023 IEEE Top Picks in Test and Reliability.

• 08/2023 [Student]: Welcome our new PhD students Abdullah, Ali, AKM, and Bohan to join our group!

• 08/2023 [Funding]: Our proposal on scalable and resilient modeling for federated-learning-based complex workflows has been funded by the Department of Energy, with a total of $4.35 million.

• 07/2023 [Paper]: One paper accepted at ISSRE'23.

• 06/2023 [Service]: Serve as PC on DSN'24 and ACM/SIGAPP SAC'24.

• 06/2023 [Paper]: Two papers accepted at SC'23. Congratulations to Yafan and Zhengyang!

• 05/2023 [Service]: Serve as PC on QRS'23, PRDC'23, and ISSRE'23. I am also serving as workshop co-chair at ISSRE this year.

• 01/2023 [Paper]: One paper accepted at CCGrid'23.

• 11/2022 [Service]: Serve as PC on HPDC'23.

• 11/2022 [Paper]: Our paper about feature-driven fixed-ratio lossy compression is accepted at ICDE'23. Congratulations, Hasan!

• More ...

Selected Publications (Full List)

HPC Fault Tolerance

• [IPDPS'24] DRUTO: Upper-Bounding Silent Data Corruption Vulnerability in GPU Applications
  Md Hasanur Rahman, Sheng Di, Shengjian Guo, Xiaoyi Lu, Guanpeng Li, and Franck Cappello
  

• [SC'23] Demystifying and Mitigating Cross-Layer Deficiencies of Soft Error Protection in Instruction Duplication
  Zhengyang He, Yafan Huang, Hui Xu, Dingwen Tao, and Guanpeng Li
  

• [SC'22] Mitigating Silent Data Corruptions in HPC Applications across Multiple Program Inputs
  Yafan Huang, Shengjian Guo, Sheng Di, Guanpeng Li, Franck Cappello
  Best Paper Award Finalist
  Best Student Paper Award Finalist

• [SC'21] Peppa-X: Finding Program Test Inputs to Bound Silent Data Corruption Vulnerability in HPC Applications
  Md Hasanur Rahman, Aabid Shamji, Shengjian Guo, Guanpeng Li

• [SC'20] GPU-TRIDENT: Efficient Modeling of Error Propagation in GPU Programs
  Abdul Rehman Anwer, Guanpeng Li, Karthik Pattabiraman, Michael Sullivan, Timothy Tsai and Siva Hari

• [DSN'18] Modeling Soft-Error Propagation in Programs
  Guanpeng Li, Karthik Pattabiraman, Siva Hari, Mike Sullivan, and Timothy Tsai
  Best Paper Award Runner-Up

Lossy Compression

• [MSST'24] A Generic and Efficient Framework for Estimating Lossy Compressibility of Scientific Data
  Md Hasanur Rahman, Sheng Di, Guanpeng Li, Franck Cappello

• [SC'23] cuSZp: An Ultra-Fast GPU Error-Bounded Lossy Compression Framework with Optimized End-to-End Performance
  Yafan Huang, Sheng Di, Xiaodong Yu, Guanpeng Li, and Franck Cappello

• [ICDE'23] A Feature-Driven Fixed-Ratio Lossy Compression Framework for Real-World Scientific Datasets
  Md Hasanur Rahman, Sheng Di, Kai Zhao, Robert Underwood, Guanpeng Li, Franck Cappello

• [VLDB'22] COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
  Sian Jin, Chengming Zhang, Jiannan Tian, Yunhe Feng, Hui Guan, Guanpeng Li, Shuaiwen Leon Song, Dingwen Tao

Safety of Autonomous Driving Systems

• [AsiaCCS'24] Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks
  Pritam Dash, Guanpeng Li, Mehdi Karimibiuki, Karthik Pattabiraman
  

• [DSN'21] PID-Piper: Recovering Robotic Vehicles from Physical Attacks
  Pritam Dash, Guanpeng Li, Zitao Chen, Mehdi Karimibiuki, and Karthik Pattabiraman
  Best Paper Award

• [ISSRE'20] AV-Fuzzer: Finding Safety Violations in Autonomous Driving Systems.
  Guanpeng Li, Yiran Li, Saurabh Jha, Tim Tsai, Mike Sullivan, Siva Hari, Zbigniew Kalbarczyk and Ravi Iyer
  Best Paper Award

Machine Learning Dependability

• [DSN'21] A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction
  Zitao Chen, Guanpeng Li, and Karthik Pattabiraman
  Best Paper Award Runner-Up
  Adopted by Intel OpenVINO [details]
  

• [SC'19] BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems
  Zitao Chen, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben
  

• [SC'17] Understanding Error Propagation in Deep-Learning Neural Network (DNN) Accelerators and Applications
  Guanpeng Li, Siva Hari, Mike Sullivan, Tim Tsai, Karthik Pattabiraman, Joel Emer, and Steve Keckler
  IEEE Top Picks in Test and Reliability (2023)

Contact

Email: guanpeng-li@uiowa.edu