Andrey Prokopenko
Research Scientist at Oak Ridge National Laboratory
Knoxville, Tennessee United States
Summary
🤩
Rockstar🎓
Top SchoolAndrey Prokopenko is a research scientist and computational software engineer with 13 years of experience building and hardening scientific tooling and performance-portable libraries. He holds advanced mathematics training from MSU and a PhD from the University of Houston, and applies that rigor to backend development and build engineering for high-performance computing projects. Andrey is an active open-source contributor to prominent projects like Spack and Kokkos, where he improved compiler support, build variants, and core correctness checks to ease scientific software deployment and GPU-parallel code reliability. Based in Knoxville, TN, he blends deep numerical insight with practical build-system expertise—often tackling the subtle infrastructure details (e.g., pic flags, package variants, static assertions) that make large-scale scientific workflows reproducible and portable.
13 years of coding experience
PhD, Mathematics, PhD, Mathematics at University of HoustonLomonosov Moscow State University
English, Russian
Github Skills (20)
programming-language10
c-language10
package-management10
python10
cluster-computing10
abstraction10
parallel-computing10
package10
build-automation10
build-tools10
cprogramming-language10
compiler-flags10
scientific-computing10
k10
cuda9
Programming languages (15)
Github contributions (5)
spack/spack
Nov 2016 - Oct 2022
A flexible package manager that supports multiple versions, configurations, platforms, and compilers.
Role in this project:
Back-end Developer & Build Engineer
Back-end Developer & Build EngineerContributions:56 reviews, 32 commits, 45 PRs in 6 years
Contributions summary:Andrey contributed to the Spack package manager by implementing new features, fixing bugs, and improving the build process for scientific software. They added functionality to support various compilers, including adding a `pic_flag` property to different compilers, thus improving the ability to build position-independent code. Furthermore, the user modified package definitions for specific software, such as netcdf, adding variants and features to control build options and dependencies. Their work involved modifying build scripts (package.py files), and adding and managing dependencies for various scientific computing libraries, reflecting their contribution to the core functionality of the package manager.
compilerspythonradiussplatformslinux
kokkos/kokkos
Nov 2015 - Apr 2020
Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction
Role in this project:Back-end Developer
Back-end DeveloperContributions:152 reviews, 8 commits, 22 PRs in 4 years 6 months
Contributions summary:Andrey contributed to the Kokkos project by addressing shadow warnings in Cuda parallel code and implementing features within the core components. They added static assertions to the `Device` type to ensure proper execution and memory spaces. Additionally, the user added a `rowConst()` function to `StaticCrsGraph` for viewing a graph row, along with adding tests for the functionality.
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.