An O(1)-Barriers optimal RMRs mutual exclusion algorithm

Hagit Attiya, Danny Hendler, Smadar Levy

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

8 Scopus citations

Abstract

Mutual exclusion is a fundamental coordination problem. Over the last 20 years, shared-memory mutual exclusion research focuses on local-spin algorithms and uses the remote memory references (RMRs) metric. To ensure the correctness of concurrent algorithms in general, and mutual exclusion algorithms in particular, it is often required to prohibit certain re-orderings of memory instructions that may compromise correctness, by inserting memory barrier instructions. Memory barriers incur non-negligible overhead and may significantly increase the algorithm's time complexity. This paper presents the first read/write mutual exclusion algorithm with asymptotically optimal complexity under both the RMRs and barriers metrics: each passage through the critical section incurs O(log n) RMRs and a constant number of barriers. The algorithm works in the popular Total Store Ordering model.

Original languageEnglish
Title of host publicationPODC 2013 - Proceedings of the 2013 ACM Symposium on Principles of Distributed Computing
Pages220-229
Number of pages10
DOIs
StatePublished - 11 Sep 2013
Event2013 ACM Symposium on Principles of Distributed Computing, PODC 2013 - Montreal, QC, Canada
Duration: 22 Jul 201324 Jul 2013

Publication series

NameProceedings of the Annual ACM Symposium on Principles of Distributed Computing

Conference

Conference2013 ACM Symposium on Principles of Distributed Computing, PODC 2013
Country/TerritoryCanada
CityMontreal, QC
Period22/07/1324/07/13

Keywords

  • Mutual exclusion
  • Shared memory
  • Total store ordering

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'An O(1)-Barriers optimal RMRs mutual exclusion algorithm'. Together they form a unique fingerprint.

Cite this