Linux kernel co-scheduling for bulk synchronous parallel applications

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

This paper describes a kernel scheduling algorithm that is based on co-scheduling principles and that is intended for parallel applications running on 1000 cores or more where inter-node scalability is key. Experimental results for a Linux implementation on a Cray XT5 machine are presented. The results indicate that Linux is a suitable operating system for this new scheduling scheme, and that this design provides a dramatic improvement in scaling performance for synchronizing collective operations at scale.

Original languageEnglish
Title of host publicationProceedings of the 1st International Workshop on Runtime and Operating Systems for Supercomputers, ROSS 2011
Pages57-64
Number of pages8
DOIs
StatePublished - 2011
Event1st International Workshop on Runtime and Operating Systems for Supercomputers, ROSS 2011 - Tucson, AZ, United States
Duration: May 31 2011May 31 2011

Publication series

NameProceedings of the 1st International Workshop on Runtime and Operating Systems for Supercomputers, ROSS 2011

Conference

Conference1st International Workshop on Runtime and Operating Systems for Supercomputers, ROSS 2011
Country/TerritoryUnited States
CityTucson, AZ
Period05/31/1105/31/11

Keywords

  • co-scheduling
  • kernel scheduling
  • operating system interference
  • operating system noise

Fingerprint

Dive into the research topics of 'Linux kernel co-scheduling for bulk synchronous parallel applications'. Together they form a unique fingerprint.

Cite this