Ruiling Song is a compiler engineer with 8+ years of experience building and optimizing LLVM-based backends for GPUs and media encoders. Currently at AMD, she focuses on LLVM toolchain improvements for AMD GPU codegen, having contributed nuanced fixes like DominatorTree handling in coroutines and SSA phi insertion optimizations in the upstream llvm-project. Her prior roles at Intel involved x86 SSE/AVX tuning for AV1 encoders and OpenCL/LLVM backend development, and earlier work spans OpenGL ES drivers and 3D engine programming. She brings a rare combination of low-level compiler theory and hands-on performance engineering across CPU and GPU toolchains. Based in Shanghai, she holds a master’s in mechatronics from Shanghai Jiao Tong University and often surfaces test-driven improvements in high-profile open-source projects.
8 years of coding experience
12 years of employment as a software developer
Master, mechatronics, Master, mechatronics at Shanghai Jiao Tong University
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:
Back-end Developer
Contributions:71 reviews, 38 PRs, 45 pushes in 4 years 8 months
Contributions summary:Ruiling focused on compiler and toolchain technologies, specifically contributing to the LLVM project. Their work included removing DominatorTree constructions in Coroutines and passing the DominatorTree in Loads for better dominance checks. Furthermore, the user added a test case to the AMDGPU code generation tests and optimized phi insertion during ssa reconstruction.
Contributions:61 pushes, 39 branches in 3 years 3 months
compilercompilerspipelinellvm
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.