Siu Chan

Principal Member Of Technical Staff at AMD

Markham, Ontario, Canada
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Siu Chan is a Principal Member of Technical Staff with 12 years of experience building compilers and tooling for heterogeneous and high-performance compute, currently focused on AMD’s ROCm/HCC ecosystem in Markham, Ontario. He has deep expertise in backend compiler development, device-side intrinsics, automatic vectorization and GPU acceleration, gained across roles at AMD and IBM and rooted in a Master’s in Electrical Engineering from McGill. Notable open-source contributions include work on ROCm/hip—improving warp shuffle, atomic operations and builtin mappings—showing a knack for low-level correctness that directly impacts GPU kernel portability. Siu blends research-grade rigor from academic work in shared-reality labs with production-driven performance engineering, often surfacing subtle device-side math and memory fixes that other teams miss.
code12 years of coding experience
job13 years of employment as a software developer
bookMaster, Electrical Engineering, Master, Electrical Engineering at McGill University
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (8)

cuda10
kernel10
hip10
gpu-programming10
c-language10
cprogramming-language10
atomics9
atomic9

Programming languages (7)

C++ShellCLLVMAssemblyPythonCuda

Github contributions (5)

github-logo-circle
ROCm/hip

Feb 2016 - Jan 2023

HIP: C++ Heterogeneous-Compute Interface for Portability
Role in this project:
userBack-end Developer
Contributions:3 reviews, 96 commits, 65 PRs in 7 years
Contributions summary:Siu primarily contributed to the development of the HIP (Heterogeneous-Compute Interface for Portability) project, focusing on adding and modifying device-side intrinsics, particularly related to warp shuffle operations and atomic operations. They fixed builtins mapping for IDs and Dims related to kernel launching. The user also addressed a number of device-side math functions and memory operations.
cudaheterogeneousgpuportabilityhip-runtime
scchan/llvm-project

Nov 2019 - Dec 2024

This is the canonical git mirror of the LLVM subversion repository. The repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
Contributions:12 pushes, 20 branches in 5 years 1 month
subversionclanglibgit2submitgit-mirror
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.
Request Free Trial