File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Reduction of false sharing by using process affinity in page-based distributed shared memory mutiprocessor systems

TitleReduction of false sharing by using process affinity in page-based distributed shared memory mutiprocessor systems
Authors
KeywordsAffinity scheduling
process affinity
data locality
spatial locality
temporal locality
Issue Date1996
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000029
Citation
The 2nd International Conference on Algorithms and Architectures for Parallel Processing, Singapore, 11-13 June 1996. In Conference Proceedings, 1996, p. 383-390 How to Cite?
AbstractIn page-based distributed shared memory systems, a large page size makes efficient use of interconnection network, but increases the chance of false sharing, while a small page size reduces the level of false sharing but results in an inefficient use of the network. This paper proposes a technique that uses process affinity to achieve data pages clustering so as to optimize the temporal data locality on DSM systems, and therefore reduces the chance of false sharing and improves the data locality. To quantify the degree of process affinity for a piece of data, a measure called process affinity index is used that indicates the closeness between this piece of data and the process. Simulation results show that process affinity technique improves the execution performance as page size increases due to the effective reduction of fair sharing. In the best case an order of magnitude performance improvement is achieved.
Persistent Identifierhttp://hdl.handle.net/10722/45851
References

 

DC FieldValueLanguage
dc.contributor.authorHung, KPen_HK
dc.contributor.authorYung, NHCen_HK
dc.contributor.authorCheung, PYSen_HK
dc.date.accessioned2007-10-30T06:36:55Z-
dc.date.available2007-10-30T06:36:55Z-
dc.date.issued1996en_HK
dc.identifier.citationThe 2nd International Conference on Algorithms and Architectures for Parallel Processing, Singapore, 11-13 June 1996. In Conference Proceedings, 1996, p. 383-390en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45851-
dc.description.abstractIn page-based distributed shared memory systems, a large page size makes efficient use of interconnection network, but increases the chance of false sharing, while a small page size reduces the level of false sharing but results in an inefficient use of the network. This paper proposes a technique that uses process affinity to achieve data pages clustering so as to optimize the temporal data locality on DSM systems, and therefore reduces the chance of false sharing and improves the data locality. To quantify the degree of process affinity for a piece of data, a measure called process affinity index is used that indicates the closeness between this piece of data and the process. Simulation results show that process affinity technique improves the execution performance as page size increases due to the effective reduction of fair sharing. In the best case an order of magnitude performance improvement is achieved.en_HK
dc.languageengen_HK
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000029en_HK
dc.relation.ispartofInternational Conference on Algorithms and Architectures for Parallel Processing Proceedings-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©1996 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.subjectAffinity schedulingen_HK
dc.subjectprocess affinityen_HK
dc.subjectdata localityen_HK
dc.subjectspatial localityen_HK
dc.subjecttemporal localityen_HK
dc.titleReduction of false sharing by using process affinity in page-based distributed shared memory mutiprocessor systemsen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailYung, NHC:nyung@eee.hku.hk-
dc.identifier.emailCheung, YS:paul.cheung@hku.hk-
dc.identifier.authorityYung, NHC=rp00226-
dc.identifier.authorityCheung, YS=rp00077-
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICAPP.1996.562899en_HK
dc.identifier.scopuseid_2-s2.0-0030382731-
dc.identifier.hkuros11676-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0030382731&selection=ref&src=s&origin=recordpage-
dc.identifier.spage383-
dc.identifier.epage390-
dc.identifier.scopusauthoridHung, KP=7202728414-
dc.identifier.scopusauthoridYung, NHC=7003473369-
dc.identifier.scopusauthoridCheung, YS=7202595335-
dc.customcontrol.immutablesml 151028 - merged-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats