Research Interests
-
Numerical Program Analysis
- Floating-point error detection. Related publications: ASE 2023, TJSC 2023.
- Repairing numerical programs through expression rewriting: ISSTA 2024.
-
Deep Learning Systems
- Automated search for distributed parallelization strategies in LLM training.
- Compute-communication co-design.
Funding & Grants
-
Intelligent Compilation and Optimization Techniques for Supernode Parallelism Strategies
- Huawei Technologies (Agreement No. TC20241115006)
- Main participant
- ¥ 2,286,000
-
Research on Error Detection Methods for Floating-point Arithmetic Expressions
- Open Project of the State Key Laboratory of Mathematical Engineering and Advanced Computing (Grant No. 2023B02)
- Main participant
- ¥ 600,000
-
Deep Learning and Tensor Compilers based on the Polyhedral Model
- National Natural Science Foundation of China (Grant No. U20A20226)
- Participant
- ¥ 2,600,000 in total; ¥ 800,000 for the Information Engineering University
-
Elementary Mathematics Library System
- National major special project
- Participant
Honors and Awards
-
- Excellent MEng Dissertation Award (Information Engineering University)
-
- National Scholarship (Ministry of Education of China)
-
- First Class Academic Scholarship (Information Engineering University)
-
- Second Class Academic Scholarship (Information Engineering University)
-
- First Class Academic Scholarship (Information Engineering University)