ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
5 files

Malleable parallelism with minimal effort for maximal throughput and maximal hardware load.

preprint
revised on 05.02.2019, 15:09 and posted on 05.02.2019, 19:44 by Florian Spenke, Karsten Balzer, Sascha Frick, Bernd Hartke, Johannes M. Dieterich
A new parallel high-performance computing setup, which can use every little bit of computing resources left over by traditional scheduling, regardless how small or big it may be. This enables HPC providers to achieve 100 percent load on their machines at all times, and it enables HPC users to get substantial computing time on HPC systems that are "full" with traditional jobs.

Funding

DFG Ha2498/16-1

History

Email Address of Submitting Author

hartke@pctc.uni-kiel.de

Institution

Christian-Albrechts-University Kiel

Country

Germany

ORCID For Submitting Author

0000-0001-8480-0862

Declaration of Conflict of Interest

no conflict of interest

Exports