Synchronization-Avoiding Graph Algorithms

Because they were developed for optimal sequential complexity, classical graph algorithms as found in textbooks have strictly-defined orders of operations. Enforcing a prescribed order of operations, or even an approximate order, in a distributed memory setting requires significant amounts of synchr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2018 IEEE 25th International Conference on High Performance Computing (HiPC) s. 52 - 61
Hlavní autori: Firoz, Jesun Sahariar, Zalewski, Marcin, Kanewala, Thejaka, Lumsdaine, Andrew
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.12.2018
Predmet:
ISSN:2640-0316
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Because they were developed for optimal sequential complexity, classical graph algorithms as found in textbooks have strictly-defined orders of operations. Enforcing a prescribed order of operations, or even an approximate order, in a distributed memory setting requires significant amounts of synchronization, which in turn can severely limit scalability. As a result, new algorithms are typically required to achieve scalable performance, even for solving well-known graph problems. Yet, even in these cases, parallel graph algorithms are written according to parallel programming models that evolved for, e.g., scientific computing, and that still have inherent, and scalability-limiting, amounts of synchronization. In this paper we present a new approach to parallel graph algorithms: synchronization-avoiding algorithms. To eliminate synchronization and its associated overhead, synchronization-avoiding algorithms perform work in an unordered and fully asynchronous fashion in such a way that the result is constantly refined toward its final state. "Wasted" work is minimized by locally prioritizing tasks using problem-dependent task utility metrics. We classify algorithms for graph applications into two broad categories: algorithms with monotonic updates (which evince global synchronization) and algorithms with non-monotonic updates (which evince vertex-centric synchronization). We apply our approach to both classes and develop novel, synchronization-avoiding algorithms for solving exemplar problems: SSSP and connected components for the former, graph coloring for the latter. We demonstrate that eliminating synchronization in conjunction with effective scheduling policies and optimizations in the runtime results in improved scalability for both classes of algorithms.
AbstractList Because they were developed for optimal sequential complexity, classical graph algorithms as found in textbooks have strictly-defined orders of operations. Enforcing a prescribed order of operations, or even an approximate order, in a distributed memory setting requires significant amounts of synchronization, which in turn can severely limit scalability. As a result, new algorithms are typically required to achieve scalable performance, even for solving well-known graph problems. Yet, even in these cases, parallel graph algorithms are written according to parallel programming models that evolved for, e.g., scientific computing, and that still have inherent, and scalability-limiting, amounts of synchronization. In this paper we present a new approach to parallel graph algorithms: synchronization-avoiding algorithms. To eliminate synchronization and its associated overhead, synchronization-avoiding algorithms perform work in an unordered and fully asynchronous fashion in such a way that the result is constantly refined toward its final state. "Wasted" work is minimized by locally prioritizing tasks using problem-dependent task utility metrics. We classify algorithms for graph applications into two broad categories: algorithms with monotonic updates (which evince global synchronization) and algorithms with non-monotonic updates (which evince vertex-centric synchronization). We apply our approach to both classes and develop novel, synchronization-avoiding algorithms for solving exemplar problems: SSSP and connected components for the former, graph coloring for the latter. We demonstrate that eliminating synchronization in conjunction with effective scheduling policies and optimizations in the runtime results in improved scalability for both classes of algorithms.
Author Firoz, Jesun Sahariar
Kanewala, Thejaka
Zalewski, Marcin
Lumsdaine, Andrew
Author_xml – sequence: 1
  givenname: Jesun Sahariar
  surname: Firoz
  fullname: Firoz, Jesun Sahariar
– sequence: 2
  givenname: Marcin
  surname: Zalewski
  fullname: Zalewski, Marcin
– sequence: 3
  givenname: Thejaka
  surname: Kanewala
  fullname: Kanewala, Thejaka
– sequence: 4
  givenname: Andrew
  surname: Lumsdaine
  fullname: Lumsdaine, Andrew
BookMark eNotjcFLwzAYxaMoOGfPHrzs6qHdl3xJmh5LcZswcDDvI02-rpEtHW0R5l9vQQ-Pd_g9fu-R3cUuEmPPHDLOoVhuwq7KBHCTAQBXNywpcsMVGm2m6Fs2E1pCCsj1A0uG4WuaiYlpzGfsdX-Nru27GH7sGLqYlt9d8CEeF-veXtpFeTp2fRjb8_DE7ht7Gij57znbr94-q026_Vi_V-U2DQLEmMrau0KjA97UNaITjaqNAU7Tv6JcGeWtdNZSTo30EoRAh4qsb5wnj3P28mcNRHS49OFs--vBaDRcSvwFWWhD-A
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/HiPC.2018.00015
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9781538683866
1538683865
EISSN 2640-0316
EndPage 61
ExternalDocumentID 8638144
Genre orig-research
GroupedDBID 29H
29O
6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i202t-4bdc963c01fbb33c2f5b8801e0315e7585da4caae7ef4d40223c35eadfcded3
IEDL.DBID RIE
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000465758800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 03:02:01 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i202t-4bdc963c01fbb33c2f5b8801e0315e7585da4caae7ef4d40223c35eadfcded3
PageCount 10
ParticipantIDs ieee_primary_8638144
PublicationCentury 2000
PublicationDate 2018-Dec
PublicationDateYYYYMMDD 2018-12-01
PublicationDate_xml – month: 12
  year: 2018
  text: 2018-Dec
PublicationDecade 2010
PublicationTitle 2018 IEEE 25th International Conference on High Performance Computing (HiPC)
PublicationTitleAbbrev HIPC
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002683637
ssj0020125
Score 2.108026
Snippet Because they were developed for optimal sequential complexity, classical graph algorithms as found in textbooks have strictly-defined orders of operations....
SourceID ieee
SourceType Publisher
StartPage 52
SubjectTerms Approximation algorithms
Asynchronous execution
Classification algorithms
Color
Distributed graph algorithms
Image color analysis
Runtime
Synchronization
Task analysis
Title Synchronization-Avoiding Graph Algorithms
URI https://ieeexplore.ieee.org/document/8638144
WOSCitedRecordID wos000465758800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED61FQNTgRZBeSgDCxKmcZI28VhVlE5VpTJ0q-zzGSJBgtq0Ev8eOwmlAwubZcmSH3c-f-e7-wDugoSQ-9owYbEGi0jHTEZKMGtbrDUljmQqsol4NkuWSzFvwMM-F4aIyuAzenTN8i9f57h1rrJ-YoXFAoAmNON4WOVq7f0pwTAJhwdgy168g7qUD_dFf5rOxy6Qy0VO-o4D94BLpTQlk_b_JnEC3d-cPG--tzan0KDsDNo_pAxeraMduF98ZVhWvK0SLNlol6duiPfsalN7o_fXfJ0Wbx-bLiwmTy_jKav5EFga-EHBIqXR6gv63CgVhhiYgbLqx8kxNZB7-GsZoZQUk4m0BYZBiOHAiopBTTo8h1aWZ3QBXiKNrwKhyYKvSJIU5FwgJBJEg4rzS-i4da8-q4IXq3rJvb-7r-DYbWwV43ENrWK9pRs4wl2Rbta35Sl9A82Mk60
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxv9-DFxMputwu7R0JEjEhI4MCN9DGVTXTXwELiv7fdXZGDF29NkyZ9zHT6TWfmA7ilIUrPVZpEBmsQhqpNOBMRMbbFWFP0JOqCbKI9HIbTaTSqwP0mFwYR8-AzfLDN_C9fpXJlXWXN0AiLAQA7sBswRt0iW2vjUaGt0G9twS1z9QZlMR_PjZr9eNS1oVw2dtK1LLhbbCq5MenV_jeNQ2j8ZuU5o429OYIKJsdQ-6FlcEotrcPd-CuRec3bIsWSdNZpbIc4T7Y6tdN5f0sXcTb_WDZg3HucdPukZEQgMXVpRphQ0miMdD0thO9LqgNhFNBDy9WA9umvOJOcYxs1UwYaUl_6gREWLRUq_wSqSZrgKTgh166gkUIDvxhHHqF1gmAUSqml8LwzqNt1zz6Lkhezcsnnf3ffwH5_8jqYDZ6HLxdwYDe5iPi4hGq2WOEV7Ml1Fi8X1_mJfQOtkpb0
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+IEEE+25th+International+Conference+on+High+Performance+Computing+%28HiPC%29&rft.atitle=Synchronization-Avoiding+Graph+Algorithms&rft.au=Firoz%2C+Jesun+Sahariar&rft.au=Zalewski%2C+Marcin&rft.au=Kanewala%2C+Thejaka&rft.au=Lumsdaine%2C+Andrew&rft.date=2018-12-01&rft.pub=IEEE&rft.eissn=2640-0316&rft.spage=52&rft.epage=61&rft_id=info:doi/10.1109%2FHiPC.2018.00015&rft.externalDocID=8638144