H Edwards
Distinguished Engineer at NVIDIA
Campbell, California, United States
Summary
🤩
Rockstar🎓
Top SchoolH Edwards is a Distinguished Engineer based in Campbell, California with 18 years of professional software and systems engineering experience and a multi-decade career in high-performance computing and applied mathematics. He holds a PhD in Computational and Applied Mathematics from UT Austin and brings deep domain expertise from long tenures at Sandia National Laboratories and NVIDIA, advancing system software and CUDA back-ends. His contributions to the Kokkos performance-portability ecosystem showcase hands-on mastery of low-level C++ and CUDA optimizations, memory management, and concurrency correctness for widely used HPC tooling. Known for translating mathematical rigor into production-quality parallel code, he balances research-grade algorithms with pragmatic engineering and performance tuning. Colleagues rely on him for architecting scalable device-host interactions and eliminating subtle race conditions that impact large-scale simulations. Outside obvious titles, he combines aerospace engineering roots with decades of systems software to solve cross-disciplinary performance challenges.
18 years of coding experience
41 years of employment as a software developer
Doctor of Philosophy (PhD) Computational and Applied Mathematics, Doctor of Philosophy (PhD) Computational and Applied Mathematics at The University of Texas at Austin
Github Skills (14)
cuda10
memory-management10
c-language10
cpp10
cprogramming-language10
performance-optimization10
parallel-execution9
parallel-computing9
parallel9
parallel-processing9
cluster-computing8
accelerated-computing8
scientific-computing8
high-performance8
Programming languages (4)
Github contributions (5)
kokkos/kokkos
Apr 2015 - Mar 2018
Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction
Role in this project:
Back-end Developer
Back-end DeveloperContributions:487 commits, 185 PRs, 287 pushes in 2 years 11 months
Contributions summary:H contributed to the Kokkos library by implementing and improving low-level features related to subview handling and task management within the CUDA back-end. Their work involved modifying data structures and algorithms for both the host and device, improving performance through optimizations like inlining, and addressing memory management and access issues to prevent race conditions. They also updated the codebase to utilize new C++11 and CUDA features, expanding the functionality and capabilities of the library.
memorympic-plus-plusmulti-threadingkokkos
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.