@inproceedings{eeb6e49e4d7444afb3eff544a46db98c,
title = "Node-Based Job Scheduling for Large Scale Simulations of Short Running Jobs",
abstract = "Diverse workloads such as interactive supercomputing, big data analysis, and large-scale AI algorithm development, requires a high-performance scheduler. This paper presents a novel node-based scheduling approach for large scale simulations of short running jobs on MIT SuperCloud systems, that allows the resources to be fully utilized for both long running batch jobs while simultaneously providing fast launch and release of large-scale short running jobs. The node-based scheduling approach has demonstrated up to 100 times faster scheduler performance that other state-of-The-Art systems.",
keywords = "cluster utilization, fast scheduling, job management, scheduling performance",
author = "Chansup Byun and William Arcand and David Bestor and Bill Bergeron and Vijay Gadepally and Michael Houle and Matthew Hubbell and Michael Jones and Anna Klein and Peter Michaleas and Lauren Milechin and Julie Mullen and Andrew Prout and Albert Reuther and Antonio Rosa and Siddharth Samsi and Charles Yee and Jeremy Kepner",
note = "Funding Information: This material is based upon work supported by the Assistant Secretary of Defense for Research and Engineering under Air Force Contract No. FA8721-05-C-0002 and/or FA8702-15-D-0001. Any opinions, findings, conclusions or recommendations expressed in this material are those of the author(s) and do not necessarily reflect the views of the Assistant Secretary of Defense for Research and Engineering. Publisher Copyright: {\textcopyright} 2021 IEEE.; null ; Conference date: 20-09-2021 Through 24-09-2021",
year = "2021",
doi = "10.1109/HPEC49654.2021.9622870",
language = "English",
series = "2021 IEEE High Performance Extreme Computing Conference, HPEC 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2021 IEEE High Performance Extreme Computing Conference, HPEC 2021",
}