Shuo Ding
Compiler Engineer at Huawei
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolShuo Ding is a compiler engineer with nine years of experience specializing in compilers, computability, and complexity theory, currently based in Shanghai and working at Huawei. He holds a PhD in Computer Science from Georgia Tech and has bridged rigorous research and production engineering through roles including a PyTorch-focused compiler internship at Meta and applied security work at AWS. Shuo has made notable open-source contributions to PyTorch’s Inductor compiler, implementing and tuning the B2B-GEMM optimization to accelerate matrix-multiply workloads in a widely used ML framework. His background in mathematics and formal methods informs a methodical approach to performance engineering and correctness for AI compilers. Comfortable moving between research prototypes and production-grade optimizations, he brings both theoretical depth and practical impact to compiler and ML systems.
9 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Georgia Institute of TechnologyBachelor of Science - BS, Mathematics, Bachelor of Science - BS, Mathematics at Xi'an Jiaotong University
Chinese, English
Github Skills (11)
pytorch10
machine-learning10
deeplearning-ai10
deep-learning10
python10
induction10
gpu9
pattern-matching9
tensor9
triton8
autograd8
Programming languages (5)
Github contributions (5)
pytorch/pytorch
May 2024 - Aug 2024
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
ML Engineer
ML EngineerContributions:31 reviews, 7 PRs, 55 pushes in 2 months
Contributions summary:Shuo primarily contributed to optimizing and extending the Inductor compiler within the PyTorch project. Their work focused on implementing and refining the B2B-GEMM (back-to-back general matrix multiplication) pass, a critical optimization for improving the performance of matrix multiplication operations in the inductor compiler. This involved creating the initial implementation of the B2B-GEMM pass, as well as subsequent performance tuning and improvements to support pointwise intermediate nodes. These optimizations aimed to improve the efficiency of compiled PyTorch models.
pythongpu-accelerationdeep-learninggpunumpy
sdingcn/clocalc
May 2023 - Mar 2025
Contributions:314 pushes, 1 branch, 25 comments in 1 year 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.