Flat combining and the synchronization-parallelism tradeoff

Danny Hendler, Itai Incze, Nir Shavit, Moran Tzafrir

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

220 Scopus citations

Abstract

Traditional data structure designs, whether lock-based or lock-free, provide parallelism via fine grained synchroniza- tion among threads. We introduce a new synchronization paradigm based on coarse locking, which we call flat combining. The cost of synchronization in flat combining is so low, that having a single thread holding a lock perform the combined access requests of all others, delivers, up to a certain non-negligible concurrency level, better performance than the most effective parallel finely synchronized implementations. We use flat-combining to devise, among other structures, new lin-earizable stack, queue, and priority queue algorithms that greatly outperform all prior algorithms.

Original languageEnglish
Title of host publicationSPAA'10 - Proceedings of the 22nd Annual Symposium on Parallelism in Algorithms and Architectures
Pages355-364
Number of pages10
DOIs
StatePublished - 30 Jul 2010
Event22nd ACM Symposium on Parallelism in Algorithms and Architectures, SPAA'10 - Thira, Santorini, Greece
Duration: 13 Jun 201015 Jun 2010

Publication series

NameAnnual ACM Symposium on Parallelism in Algorithms and Architectures

Conference

Conference22nd ACM Symposium on Parallelism in Algorithms and Architectures, SPAA'10
Country/TerritoryGreece
CityThira, Santorini
Period13/06/1015/06/10

Keywords

  • Concurrent data-structures
  • Multiprocessors
  • Synchronization

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'Flat combining and the synchronization-parallelism tradeoff'. Together they form a unique fingerprint.

Cite this