Gordon Selley
Staff Software Engineer at AMD
Massachusetts, United States
Summary
🤩
RockstarGordon Selley is a Staff Software Engineer and Principal Member of Technical Staff based in Massachusetts with a decade of experience specializing in backend systems and performance engineering. He has deep expertise in GPU tooling—contributing to the well-known CodeXL project by implementing Vulkan presentation logic, adding API and GPU tracing, and optimizing trace-data handling within the graphics server. Gordon combines pragmatic bug fixing (frame capture and exit-detection issues) with thoughtful refactoring of shutdown mechanisms, showing a focus on reliability and maintainability in complex graphics pipelines. He brings a systems-minded approach to performance bottlenecks and a history of shipping low-level, high-impact improvements that bridge developer tooling and hardware-aware software.
10 years of coding experience
Github Skills (5)
vulkan10
c-language10
cprogramming-language10
performance-optimization10
multithreading9
Programming languages (1)
Github contributions (2)
GPUOpen-Archive/CodeXL
May 2016 - Sep 2016
CodeXL is a comprehensive tool suite that enables developers to harness the benefits of CPUs, GPUs and APUs.
Role in this project:
Backend Developer & Performance Engineer
Backend Developer & Performance EngineerContributions:48 commits, 37 pushes in 4 months
Contributions summary:Gordon primarily worked on improving the performance and functionality of the CodeXL tool suite, particularly focusing on Vulkan support within the graphics server. Their contributions included implementing Vulkan presentation logic, adding API tracing capabilities for both API and GPU traces, and optimizing the handling of trace data within the server. They also addressed bugs related to frame capture and application exit detection, alongside refactoring the shutdown mechanism for the server.
cppwindowsgpulinuxbenefits
GPUOpen-Tools/radeon_gpu_profiler
Jul 2017 - Jul 2017
Radeon GPU Profiler (RGP) is a tool from AMD that allows for deep inspection of GPU workloads.
Contributions:1 release, 5 commits, 4 pushes in 1 day
cudaamdinspectionworkloadsgpu
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.