Richard Mills
Computational Scientist
Portland, Oregon, United States
Summary
👤
Senior🎓
Top SchoolRichard Mills is a computational scientist with 21 years of experience designing and optimizing large-scale, open-source scientific software that runs from laptops to leadership-class supercomputers. As a core PETSc developer and original author of PFLOTRAN, he blends first-principles simulation, machine learning, and performance engineering to tackle PDE-based modeling and earth-system problems. His career spans national labs, academia, and industry (including Intel), where he advised hardware design for HPC workloads and led exascale-ready algorithm and software development. Based in Portland, he mentors researchers and drives production-quality toolkits that enable reproducible, scalable science—often contributing subtle performance and API improvements that unlock real-world speedups on diverse architectures.
21 years of coding experience
16 years of employment as a software developer
B.A., College Scholars Program (emphasis in geology and physics), B.A., College Scholars Program (emphasis in geology and physics) at University of Tennessee, KnoxvillePh.D., Computer Science, with concentration in Computational Science, Ph.D., Computer Science, with concentration in Computational Science at William & Mary
Github Skills (6)
sparse-matrix10
performance-optimization10
linear-algebra10
cprogramming-language9
c-language9
code-documentation8
Programming languages (7)
Github contributions (5)
petsc/petsc
Mar 2005 - Nov 2022
Mirror of https://gitlab.com/petsc/petsc
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:446 commits in 17 years 11 months
Contributions summary:Richard made contributions to the PETSc library, specifically focusing on improving the performance and functionality of the MATAIJMKL matrix type. The contributions involved fixing typos in code and documentation, adding new features such as MatScale and functions to manage MKL matrix handles, and optimizing matrix multiplication routines with the goal of improved performance on a variety of platforms. The user also ensured the proper behavior of the MATAIJMKL code when being used as part of the larger PETSc system.
petscgitlab
jitendra-kumar/pflotran-dev_acme
Dec 2006 - Feb 2016
Contributions:303 commits in 9 years 3 months
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.