Matt Stack is a Solutions Architect at NVIDIA with eight years of experience building high-performance, GPU-accelerated systems and tooling. He combines hands-on C++ and CUDA expertise with architecture-level thinking, having contributed notable backend work to the widely used Kokkos performance portability library—improving CUDA memory management and asynchronous behavior. A University of Delaware computer science alumnus, he started by accelerating biology modeling on GPUs, a background that informs his practical approach to computational problems. Based in California, Matt bridges research and production, translating low-level performance tuning into scalable solutions for complex technical teams.
8 years of coding experience
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at University of Delaware
Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction
Role in this project:
Back-end Developer
Contributions:21 reviews, 23 commits, 11 PRs in 4 months
Contributions summary:Matt primarily contributed to the Kokkos library's CUDA integration. Their work focused on implementing and refining memory management for CUDA, including `cudaMallocAsync` and `cudaFreeAsync`, to improve performance. They added conditional compilation based on CUDA versions, addressing memory allocation issues, and added synchronization calls to prevent unintended asynchronous behavior. The user also made corrections to address compilation issues.
Contributions:2 PRs, 3 pushes, 3 branches in 2 years 9 months
python
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.