Xinning Hui
5th-year Ph.D. student at
North Carolina State University
About Me
I am a Ph.D. student in the Department of Computer Science at the North Carolina State University, working with Dr. Xipeng Shen. I am broadly interested in improving the performance and efficiency of ML systems. My recent research focus on optimizing performance and effiency of the ML application on single- and multi-GPUs at cloud computing systems.
Interests
- AI Infrastructure
- Cloud Computing
- ML systems
Education
Ph.D. of Computer Science
North Carolina State University
MS of Computer Science
Tsinghua University
Publications
(2025).
FluidFaaS: A Dynamic Pipelined Solution for Serverless Computing with Strong Isolation-based GPU Sharing.
The 34rd International Symposium on High-Performance Parallel and Distributed Computing, HPDC25.
(2025).
Exploring Function Granularity for Serverless Machine Learning Application with GPU Sharing.
ACM SIGMETRICS 2025, SIGMETRICS25. (acceptance rate 15/113=13%).
(2025).
Reductive Analysis with Compiler-Guided Large Language Models for Input-Centric Code Optimizations.
2025 ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI25. (acceptance rate 90/316=28.5%).
(2024).
ESG: Pipeline-Conscious Efficient Scheduling of DNN Workflows on Serverless Platforms with Shareable GPUs.
The 33rd International Symposium on High-Performance Parallel and Distributed Computing, HPDC24. (acceptance rate 26/152=17%).
(2022).
Understanding and Reaching the Performance Limit of Schedule Tuning on Stable Synchronization Determinism.
The 31st International Conference on Parallel Architectures and Compilation Techniques, PACT22.