Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/9013
DC FieldValueLanguage
dc.contributor.authorSoteriou, Vassos-
dc.contributor.authorTheocharides, Theocharis-
dc.contributor.authorKakoulli, Elena-
dc.contributor.otherΣωτηρίου, Βάσος-
dc.contributor.otherΚακουλλή, Έλενα-
dc.date.accessioned2017-01-12T11:50:29Z-
dc.date.available2017-01-12T11:50:29Z-
dc.date.issued2016-03-01-
dc.identifier.citationIEEE Transactions on Computers, 2016, vol. 65, no. 3, pp. 819-833en_US
dc.identifier.issn0018-9340-
dc.identifier.urihttp://ktisis.cut.ac.cy/handle/10488/9013-
dc.description.abstractTraffic hotspots, a severe form of network congestion, can be caused unexpectedly in a network-on-chip (NoC) due to the immanent spatio-temporal unevenness of application traffic. Hotspots reduce the NoC's effective throughput, where in the worst-case scenario, network traffic flows can be frozen indefinitely. To alleviate this problematic phenomenon several adaptive routing algorithms employ online load-balancing schemes, aiming to reduce the possibility of hotspots arising. Since most are not explicitly hotspot-agnostic, they cannot completely prevent hotspot formation(s) as their reactive capability to hotspots is merely passive. This paper presents a pro-active Hotspot-Preventive Routing Algorithm (HPRA) which uses the advance knowledge gained from network-embedded artificial neural network-based (ANN) hotspot predictors to guide packet routing in mitigating any unforeseen near-future hotspot occurrences. First, these ANN-based predictors are trained offline and during multicore operation they gather online statistical data to predict about-to-be-formed hotspots, promptly informing HPRA to take appropriate hotspot-preventive action(s). Next, in a holistic approach, additional ANN training is performed with data acquired after HPRA interferes, so as to further improve hotspot prediction accuracy; hence, the ANN mechanism does not only predict hotspots, but is also aware of changes that HPRA imposes upon the interconnect infrastructure. Evaluation results, including utilizing real application traffic traces gathered from parallelized workload executions onto a chip multiprocessor architecture, show that HPRA can improve network throughput up to 81 percent when compared with prior-art. Hardware synthesis results affirm the HPRA mechanism's moderate overhead requisites.en_US
dc.formatpdfen_US
dc.language.isoenen_US
dc.publisherIEEE Computer Societyen_US
dc.relation.ispartofIEEE Transactions on Computersen_US
dc.rights© 1968-2012 IEEEen_US
dc.subjectMultiprocessor interconnectionen_US
dc.subjectNeural network hardwareen_US
dc.subjectOn-chip networken_US
dc.subjectUltra-scale integrationen_US
dc.titleA holistic approach towards intelligent hotspot prevention in network-on-chip-based multicoresen_US
dc.typeArticleen_US
dc.collaborationCyprus University of Technologyen_US
dc.collaborationUniversity of Cyprusen_US
dc.subject.categoryElectrical Engineering - Electronic Engineering - Information Engineeringen_US
dc.journalsSubscription Journalen_US
dc.countryCyprusen_US
dc.subject.fieldEngineering and Technologyen_US
dc.publicationPeer Revieweden_US
dc.identifier.doi10.1109/TC.2015.2435748en_US
cut.common.academicyear2015-2016en_US
item.fulltextNo Fulltext-
item.languageiso639-1other-
item.grantfulltextnone-
crisitem.author.deptDepartment of Electrical Engineering, Computer Engineering and Informatics-
crisitem.author.deptDepartment of Electrical Engineering, Computer Engineering and Informatics-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.orcid0000-0002-2818-0459-
crisitem.author.orcid0000-0003-1489-807X-
crisitem.author.parentorgFaculty of Engineering and Technology-
crisitem.author.parentorgFaculty of Engineering and Technology-
crisitem.journal.journalissn0018-9340-
crisitem.journal.publisherIEEE-
Appears in Collections:Άρθρα/Articles
Show simple item record

WEB OF SCIENCETM
Citations

2
checked on Jul 13, 2019

Page view(s)

100
Last Week
1
Last month
15
checked on Jul 16, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.