Greg Mackey is a Lead Analytics Engineer with 10 years of experience and a two-decade engineering background that includes a long tenure as Principal Member of Technical Staff at Sandia National Laboratories. Based in Lindsay, Oklahoma, he blends systems-level C++ performance engineering with analytics leadership, driving production analytics at Rocketgraph since 2017. His open-source contributions to the widely used Kokkos performance portability library demonstrate deep expertise in low-level memory management, thread safety, and CUDA optimization—skills that translate to high-performance analytics pipelines. Greg holds an MS in Computer Science from UIUC and a BS in Computer Science, bringing both research-grade rigor and practical delivery to complex, cross-platform compute problems. He is equally comfortable optimizing HPC kernels and architecting data products, often surfacing subtle performance wins through careful testing and execution-space integration.
10 years of coding experience
12 years of employment as a software developer
High School Diploma, High School Diploma at Oklahoma School of Science and Mathematics
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Oklahoma Baptist University
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Illinois Urbana-Champaign
Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction
Role in this project:
Back-end Developer & Performance Engineer
Contributions:69 commits, 17 PRs, 5 pushes in 1 year 2 months
Contributions summary:Greg's contributions centered on enhancing the performance and functionality of the Kokkos library, a C++ performance portability framework. Their work involved modifying the memory pool implementation, optimizing its thread safety, and adding a bitset version for improved CUDA performance. Furthermore, the user focused on adding and refining unit tests to validate the memory pool and its integration with different execution spaces, including OpenMP and CUDA. This highlights a focus on both core library development and ensuring its efficient utilization across diverse hardware architectures.
Contributions:115 pushes, 11 branches in 1 year 2 months
kokkos
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.