Supporting lock-free composition of concurrent data objects
D. Cederman, and P. Tsigas. Proceedings of the 7th ACM international conference on Computing frontiers, page 53--62. New York, NY, USA, ACM, (2010)
DOI: 10.1145/1787275.1787286
Abstract
Lock-free data objects offer several advantages over their blocking counterparts, such as being immune to deadlocks and convoying and, more importantly, being highly concurrent. However, composing the operations they provide into larger atomic operations, while still guaranteeing efficiency and lock-freedom, is a challenging algorithmic task.</p> <p>We present a lock-free methodology for composing highly concurrent linearizable objects together by unifying their linearization points. This makes it possible to relatively easily introduce atomic lock-free move operations to a wide range of concurrent objects. Experimental evaluation has shown that the operations originally supported by the data objects keep their performance behavior under our methodology.
Description
Supporting lock-free composition of concurrent data objects
%0 Conference Paper
%1 Cederman:2010:SLC:1787275.1787286
%A Cederman, Daniel
%A Tsigas, Philippas
%B Proceedings of the 7th ACM international conference on Computing frontiers
%C New York, NY, USA
%D 2010
%I ACM
%K composition sharedmemory
%P 53--62
%R 10.1145/1787275.1787286
%T Supporting lock-free composition of concurrent data objects
%U http://doi.acm.org/10.1145/1787275.1787286
%X Lock-free data objects offer several advantages over their blocking counterparts, such as being immune to deadlocks and convoying and, more importantly, being highly concurrent. However, composing the operations they provide into larger atomic operations, while still guaranteeing efficiency and lock-freedom, is a challenging algorithmic task.</p> <p>We present a lock-free methodology for composing highly concurrent linearizable objects together by unifying their linearization points. This makes it possible to relatively easily introduce atomic lock-free move operations to a wide range of concurrent objects. Experimental evaluation has shown that the operations originally supported by the data objects keep their performance behavior under our methodology.
%@ 978-1-4503-0044-5
@inproceedings{Cederman:2010:SLC:1787275.1787286,
abstract = {Lock-free data objects offer several advantages over their blocking counterparts, such as being immune to deadlocks and convoying and, more importantly, being highly concurrent. However, composing the operations they provide into larger atomic operations, while still guaranteeing efficiency and lock-freedom, is a challenging algorithmic task.</p> <p>We present a lock-free methodology for composing highly concurrent linearizable objects together by unifying their linearization points. This makes it possible to relatively easily introduce atomic lock-free move operations to a wide range of concurrent objects. Experimental evaluation has shown that the operations originally supported by the data objects keep their performance behavior under our methodology.},
acmid = {1787286},
added-at = {2012-08-29T11:22:28.000+0200},
address = {New York, NY, USA},
author = {Cederman, Daniel and Tsigas, Philippas},
biburl = {https://www.bibsonomy.org/bibtex/255b837afdcc04a4013d0fd629d399022/giuliano.losa},
booktitle = {Proceedings of the 7th ACM international conference on Computing frontiers},
description = {Supporting lock-free composition of concurrent data objects},
doi = {10.1145/1787275.1787286},
interhash = {1ed42142e958828a6a4ed3505aaf9889},
intrahash = {55b837afdcc04a4013d0fd629d399022},
isbn = {978-1-4503-0044-5},
keywords = {composition sharedmemory},
location = {Bertinoro, Italy},
numpages = {10},
pages = {53--62},
publisher = {ACM},
series = {CF '10},
timestamp = {2012-08-29T11:22:50.000+0200},
title = {Supporting lock-free composition of concurrent data objects},
url = {http://doi.acm.org/10.1145/1787275.1787286},
year = 2010
}