The locality of concurrent write barriers

Laurence Hellyer; Richard Jones; Antony L. Hosking

doi:10.1145/1806651.1806666

The locality of concurrent write barriers

Laurence Hellyer^*, Richard Jones, Antony L. Hosking

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Concurrent and incremental collectors require barriers to ensure correct synchronisation between mutator and collector. The overheads imposed by particular barriers on particular systems have been widely studied. Somewhat fewer studies have also compared barriers in terms of their termination properties or the volume of floating garbage they generate. Until now, the consequences for locality of different barrier choices has not been studied, although locality will be of increasing importance for emerging architectures. This paper provides a study of the locality of concurrent write barriers, independent of the processor architecture, virtual machine, compiler or garbage collection algorithm.

Original language	English
Title of host publication	Proceedings of the 2010 International Symposium on Memory Management, ISMM '10
Pages	83-92
Number of pages	10
DOIs	https://doi.org/10.1145/1806651.1806666
Publication status	Published - 2010
Externally published	Yes
Event	2010 International Symposium on Memory Management, ISMM'10 - Toronto, ON, Canada Duration: 5 Jun 2010 → 10 Jun 2010

Publication series

Name	International Symposium on Memory Management, ISMM

Conference

Conference	2010 International Symposium on Memory Management, ISMM'10
Country/Territory	Canada
City	Toronto, ON
Period	5/06/10 → 10/06/10

Access to Document

10.1145/1806651.1806666

Cite this

@inproceedings{6a76f48cc030419e8291d263e1dc9044,

title = "The locality of concurrent write barriers",

abstract = "Concurrent and incremental collectors require barriers to ensure correct synchronisation between mutator and collector. The overheads imposed by particular barriers on particular systems have been widely studied. Somewhat fewer studies have also compared barriers in terms of their termination properties or the volume of floating garbage they generate. Until now, the consequences for locality of different barrier choices has not been studied, although locality will be of increasing importance for emerging architectures. This paper provides a study of the locality of concurrent write barriers, independent of the processor architecture, virtual machine, compiler or garbage collection algorithm.",

keywords = "garbage collection, java, language implementation, memory management",

author = "Laurence Hellyer and Richard Jones and Hosking, {Antony L.}",

year = "2010",

doi = "10.1145/1806651.1806666",

language = "English",

isbn = "9781450300544",

series = "International Symposium on Memory Management, ISMM",

pages = "83--92",

booktitle = "Proceedings of the 2010 International Symposium on Memory Management, ISMM '10",

note = "2010 International Symposium on Memory Management, ISMM'10 ; Conference date: 05-06-2010 Through 10-06-2010",

}

TY - GEN

T1 - The locality of concurrent write barriers

AU - Hellyer, Laurence

AU - Jones, Richard

AU - Hosking, Antony L.

PY - 2010

Y1 - 2010

N2 - Concurrent and incremental collectors require barriers to ensure correct synchronisation between mutator and collector. The overheads imposed by particular barriers on particular systems have been widely studied. Somewhat fewer studies have also compared barriers in terms of their termination properties or the volume of floating garbage they generate. Until now, the consequences for locality of different barrier choices has not been studied, although locality will be of increasing importance for emerging architectures. This paper provides a study of the locality of concurrent write barriers, independent of the processor architecture, virtual machine, compiler or garbage collection algorithm.

AB - Concurrent and incremental collectors require barriers to ensure correct synchronisation between mutator and collector. The overheads imposed by particular barriers on particular systems have been widely studied. Somewhat fewer studies have also compared barriers in terms of their termination properties or the volume of floating garbage they generate. Until now, the consequences for locality of different barrier choices has not been studied, although locality will be of increasing importance for emerging architectures. This paper provides a study of the locality of concurrent write barriers, independent of the processor architecture, virtual machine, compiler or garbage collection algorithm.

KW - garbage collection

KW - java

KW - language implementation

KW - memory management

UR - http://www.scopus.com/inward/record.url?scp=77954737715&partnerID=8YFLogxK

U2 - 10.1145/1806651.1806666

DO - 10.1145/1806651.1806666

M3 - Conference contribution

SN - 9781450300544

T3 - International Symposium on Memory Management, ISMM

SP - 83

EP - 92

BT - Proceedings of the 2010 International Symposium on Memory Management, ISMM '10

T2 - 2010 International Symposium on Memory Management, ISMM'10

Y2 - 5 June 2010 through 10 June 2010

ER -

The locality of concurrent write barriers

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this