Aaron Black
HPC Software Architect Manager at Lawrence Livermore National Laboratory
Livermore, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAaron Black is an HPC software architect and manager with over a decade of experience modernizing large-scale, multi-physics simulation codes for world-class supercomputers at Lawrence Livermore National Laboratory. He leads cross-disciplinary teams of physicists, computer scientists, and applied mathematicians to refactor C/C++/Fortran codebases and optimize them for heterogeneous GPU-based architectures such as Sierra and the upcoming exascale El Capitan. His work spans performance engineering, profiling, and portability (OpenMP, CUDA, ROCm) as well as staff management and new-code development for high-order transport methods that map well to GPUs. Aaron has also improved build and test infrastructure in open-source finite element software (MFEM), demonstrating attention to reproducible testing and scalable CI for large scientific libraries. Based in Livermore, CA, he combines deep hands-on expertise with program-level leadership, and actively recruits and mentors students and early-career engineers to work on some of the fastest supercomputers in the world.
11 years of coding experience
8 years of employment as a software developer
California Polytechnic State University, San Luis ObispoMasters (incomplete), Computer Science, Masters (incomplete), Computer Science at CSU Sacramento
English, Spanish
Github Skills (6)
hpc10
parallel-computing10
makefile10
testing10
cicd9
python3
Programming languages (5)
Github contributions (5)
mfem/mfem
Mar 2017 - Sep 2017
Lightweight, general, scalable C++ library for finite element methods
Role in this project:
DevOps Engineer
DevOps EngineerContributions:57 commits, 23 PRs, 99 pushes in 6 months
Contributions summary:Aaron primarily focused on enhancing the build and testing infrastructure of the MFEM library. They modified configuration files (config/defaults.mk and config/test.mk) to allow for greater flexibility in MPI launcher selection and test error propagation. Several commits added features such as specifying the number of MPI tasks for tests and adjusting makeflags to improve test execution, demonstrating a focus on improving the testing and build processes.
c-plus-plusfinitefemamrc-library
LLNL/FGPU
Mar 2019 - Nov 2021
Contributions:123 commits, 4 PRs, 124 pushes in 2 years 8 months
cudafortrangpuopenmp
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.