Laurent Morichetti
Fellow at AMD
Greater Seattle Area United States
Summary
🤩
Rockstar🎓
Top SchoolLaurent Morichetti is a Fellow and software architect with over a decade of experience specializing in OpenCL, JVM internals, compilers, multi-threading, and performance analysis. Based in the Greater Seattle Area, he has driven stream computing and OpenCL architecture at AMD since 2008, evolving from Principal Member of Technical Staff to Fellow. His work spans deep runtime and compiler integration—most recently contributing backend support for CUDA/HIP in ROCm’s hip project, including HIP-Clang adaptations and code object v3 integration to improve portable heterogeneous compute. Earlier roles as a JVM architect at Hewlett-Packard and as SPEC’s OSG Java representative reflect longstanding expertise in virtual machines and benchmarking. Known for pragmatic, low-level problem solving, he blends systems-level mastery with a focus on cross-platform portability and measurable performance gains.
10 years of coding experience
16 years of employment as a software developer
ESME, école d'ingénieurs généraliste
Github Skills (7)
cuda10
hip10
c-language10
clangd10
cprogramming-language10
clang10
opencl8
Programming languages (3)
Github contributions (5)
ROCm/hip
Feb 2018 - May 2020
HIP: C++ Heterogeneous-Compute Interface for Portability
Role in this project:
Back-end Developer
Back-end DeveloperContributions:30 commits, 22 PRs, 3 pushes in 2 years 2 months
Contributions summary:Laurent primarily contributed to the implementation of CUDA and HIP support within the ROCm HIP project. Their work involved defining and adapting compiler directives, kernel launch mechanisms, and runtime APIs to support HIP-Clang, a key component for portability. They addressed build errors and refactored code to align with updated compiler flags and standards. The user also integrated code object v3 support, enhancing the project's ability to handle different binary formats.
cudaheterogeneousgpuportabilityhip-runtime
ROCm/ROCdbgapi
Dec 2019 - Nov 2022
The AMD Debugger API is a library that provides all the support necessary for a debugger and other tools to perform low level control of the execution and inspection of execution state of AMD's commercially available GPU architectures.
Contributions:14 releases, 469 commits, 1 PR in 2 years 11 months
architecturesamdapicppinspection
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.