Stephen Herbein
I am a software engineer specializing in distributed systems and job scheduling. I am passionate about learning and making the world a better place.
Education
Degrees
Ph.D. in Computer Science
University of Delaware, 2018
4.0 GPA
M.S. in Computer Science
University of Delaware, 2016
4.0 GPA
B.S. in Computer Science
University of Delaware, 2014
3.932 GPA
Online Courses
Self-Driving Cars Specialization
Coursera, 2022
Experience
2022 - Present
2018 - 2022
- Flux: developed features, supported users, and readied code for future Exascale system - El Capitan
- HPC+Cloud: PI of $175K project to find gaps in LLNL’s converged computing capabilities
- Exaworks: created a portable, performant, and hardened workflow SDK
- ZFP: developed python bindings for this LLNL compression library
2012 - 2018
- 2014-2018: Created next-generation I/O-aware and hierarchical job schedulers for HPC clusters utilizing the Flux resource manager.
- 2014: Developed a suite of tools to profile, auto-tune, and optimize applications developed with the parallel I/O library ADIOS.
- 2013: Integrated in-transit analysis and staging into the scientific application QMCPack to improve I/O performance and scalability.
- 2012: Developed a crowdsourcing web application, ExSciTecH, to complement the volunteer computing project Docking@Home.
2014-2017
- 2017: Integrated my hierarchical scheduler with the Uncertainty Quantification Pipeline (UQP), resulting in a 37% improvement in workload runtime
- 2016: Added dynamicity to my hierarchical scheduler to eliminate resource fragmentation
- 2015: Developed an automatic job aggregator and hierarchical scheduler, resulting in a 4x speed up over the existing scheduler
- 2014: Developed a discrete-event simulator for the next-generation resource manager, Flux
2013
2012
- Optimized VolpexMPI library for use on large-scale clusters.