Olivier Giroux
Distinguished Engineer And Director Of GPU Architecture at Apple
California, United States
Summary
🤩
Rockstar🎓
Top SchoolOlivier Giroux is a Distinguished Engineer and Director of GPU Architecture based in California with 20+ years in GPU and systems design and 11 years of focused industry experience. He has led core GPU streaming-multiprocessor (SM) features and the architectural memory model across NVIDIA generations and now shapes GPU architecture strategy at Apple. A long-time ISO C++ contributor and chair on concurrency and parallelism, he founded and led NVIDIA’s ISO C++ delegation and contributes to the LLVM C++ Standard Library, influencing the programming model for parallel hardware. His hands-on work includes CUDA-level performance optimization and contributions to the widely referenced libcudacxx C++ library, reflecting deep expertise in parallel programming and build/test infrastructure. Known for bridging low-level microarchitecture with developer-facing programming models, he combines academic teaching experience with production-grade simulation, debugging, and performance verification.
11 years of coding experience
20 years of employment as a software developer
Master of Science (M.Sc.) Computer Software Engineering, Master of Science (M.Sc.) Computer Software Engineering at McGill University
French, English
Github Skills (5)
cuda10
c-language10
cprogramming-language10
gpu10
cpp9
Programming languages (5)
Github contributions (5)
NVIDIA/libcudacxx
Aug 2018 - Mar 2021
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
Role in this project:
Back-end Developer
Back-end DeveloperContributions:6 reviews, 141 commits, 7 PRs in 2 years 6 months
Contributions summary:Olivier's contributions primarily involved modifying and debugging CUDA code within the `libcudacxx` repository. They focused on implementing and testing CUDA code. The user also worked on building and testing the code, as evidenced by changes to build scripts and the addition of test files. The user's work is centered around using CUDA for parallel programming and optimizing performance.
c-plus-pluscxxcpp23cpp-librarynvidia-hpc-sdk
rapidsai/thirdparty-libcxx
Sep 2018 - Oct 2019
Mirror of official libcxx git repository located at http://llvm.org/git/libcxx. Updated every five minutes.
Contributions:110 commits in 1 year 1 month
git-repositoryversion-controlgit-clientmercuriallibgit2
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.