2025 to 2026 expected
Edinburgh
University of Edinburgh
MSc High Performance Computing with Data Science
Resume
Profile
MSc student in High Performance Computing with Data Science at the University of Edinburgh, with project experience across parallel computing, distributed execution, performance analysis, and machine learning systems.
My interests sit at the intersection of high performance computing, performance optimisation, and reliable system design for computationally demanding workloads.
Resume
Education
2023 to 2025
First Class Honours
University of Liverpool
BSc Computer Science
2021 to 2023
XJTLU
Xi'an Jiaotong-Liverpool University
Information and Computing Science
Resume
Skills
Languages
C/C++, Python, SQL
Parallel and HPC
MPI, OpenMP, PETSc, Slurm, ARCHER2
Tools
Linux, Git, VS Code, Linaro MAP
Resume
Projects
PETSc
Performance analysis
PETSc Benchmark and Performance Analysis Suite
- Developed a reproducible benchmarking framework for PETSc linear solvers.
- Designed Slurm job pipelines for strong scaling and hybrid MPI plus OpenMP experiments on ARCHER2.
- Built Python tools to transform runtime logs into CSV datasets and efficiency visualisations.
MPI and OpenMP
In progress
HPC Mini Applications
- Implemented mini-applications including heat diffusion, matrix multiplication, and N-body simulation.
- Designed MPI-based domain decomposition and halo exchange for distributed-memory parallelism.
- Evaluated hybrid execution for parallel efficiency, load balance, and memory behaviour.
MARL
PyTorch and ePyMARL
Value Function Factorisation in Multi-Agent Actor-Critic Methods
- Investigated VDN and QMIX-style critic designs within MAPPO-style learning.
- Implemented experimental variants using Python and PyTorch on top of PyMARL and ePyMARL.
- Analysed coordination and convergence in Matrix Game and Predator-Prey environments.
Resume
Research
Summer Undergraduate Research Programme, June 2024 to August 2024.
String Art Generator Based on Radon Transform
- Developed an algorithmic pipeline that converts images into string-based artwork.
- Implemented preprocessing and contrast enhancement to improve feature extraction.
- Designed a parameter control interface for interactive artistic generation.
Resume
Publication
CNN-based Medical Image Analysis
Li, Leyan (2024), presented at the International Conference on Engineering Management, Information Technology and Intelligence (EMITI 2024).