Miroslav Stoyanov
Research Scientist at Oak Ridge National Laboratory
Knoxville Metropolitan Area United States
Summary
🤩
Rockstar🎓
Top SchoolMiroslav Stoyanov is a research scientist at Oak Ridge National Laboratory with eight years of experience applying advanced numerical methods and HPC tooling to scientific computing problems. He holds a Ph.D. in Mathematics from Virginia Tech and brings deep domain expertise in FFTs and parallel performance, exemplified by his integration of the heFFTe library into the widely used LAMMPS molecular dynamics code. His contributions to the Spack package manager—adding and updating TASMANIAN and HEFFTE packages with CUDA and ROCm support—showcase a practical focus on reproducible, portable HPC deployments. Based in the Knoxville area, he blends rigorous mathematical training with hands-on backend development to accelerate large-scale simulations. A less obvious strength is his ability to straddle research and engineering: translating algorithmic advances into maintainable, production-grade code that benefits the broader open-source HPC ecosystem.
8 years of coding experience
Ph.D., Mathematics, Ph.D., Mathematics at Virginia Tech
Github Skills (19)
fftw10
c-language10
molecular-simulation10
mpi10
hpc10
cmake10
dynamics10
fft10
molecular-dynamics-simulation10
build-tools10
package-manager10
cprogramming-language10
roc9
cuda9
scientific-computing8
Programming languages (7)
Github contributions (5)
spack/spack
Jul 2018 - Nov 2022
A flexible package manager that supports multiple versions, configurations, platforms, and compilers.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:41 reviews, 21 commits, 27 PRs in 4 years 4 months
Contributions summary:Miroslav primarily contributed to the `spack/spack` repository by developing package definitions, focusing on the integration of the TASMANIAN and HEFFTE libraries. Their work involved adding new versions of these packages, updating dependencies, improving conflict resolution, and adding support for CUDA, ROCm and other related dependencies. The contributions demonstrate a focus on expanding the package manager's capabilities to support scientific computing and high-performance computing (HPC) software.
compilerspythonradiussplatformslinux
lammps/lammps
Jul 2020 - Jan 2024
Public development project of the LAMMPS MD software package
Role in this project:Back-end Developer
Back-end DeveloperContributions:4 reviews, 4 PRs, 11 comments in 3 years 7 months
Contributions summary:Miroslav's contributions primarily involved integrating the heFFTe library for Fast Fourier Transforms (FFTs) within the LAMMPS molecular dynamics software. They enabled the use of heFFTe for the CPU backend, modifying the code to leverage heFFTe for distributed FFT computations. Further changes included updating variable names and documentation related to heFFTe integration. These modifications enhance the performance and scalability of LAMMPS, particularly for simulations requiring efficient FFT calculations.
lammpsmolecular-dynamicssimulationkokkos
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.