Parallel peak pruning for scalable SMP contour tree computation

As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make ef...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2016 IEEE 6th Symposium on Large Data Analysis and Visualization (LDAV) s. 75 - 84
Hlavní autori: Carr, Hamish A., Weber, Gunther H., Sewell, Christopher M., Ahrens, James P.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.10.2016
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. We report the first shared SMP algorithm for fully parallel contour tree computation, with formal guarantees of O(lg n lg t) parallel steps and O(n lg n) work, and implementations with up to 10× parallel speed up in OpenMP and up to 50× speed up in NVIDIA Thrust.
AbstractList As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. We report the first shared SMP algorithm for fully parallel contour tree computation, with formal guarantees of O(lg n lg t) parallel steps and O(n lg n) work, and implementations with up to 10× parallel speed up in OpenMP and up to 50× speed up in NVIDIA Thrust.
Author Carr, Hamish A.
Weber, Gunther H.
Ahrens, James P.
Sewell, Christopher M.
Author_xml – sequence: 1
  givenname: Hamish A.
  surname: Carr
  fullname: Carr, Hamish A.
  email: H.Carr@leeds.ac.uk
– sequence: 2
  givenname: Gunther H.
  surname: Weber
  fullname: Weber, Gunther H.
  email: GHWeber@lbl.gov
  organization: Lawrence Berkeley Nat. Lab., Univ. of California, Davis, Davis, CA, USA
– sequence: 3
  givenname: Christopher M.
  surname: Sewell
  fullname: Sewell, Christopher M.
  email: csewell@lanl.gov
– sequence: 4
  givenname: James P.
  surname: Ahrens
  fullname: Ahrens, James P.
  email: ahrens@lanl.gov
BookMark eNotj81KAzEURiPoQmsfQNzkBWa8mWSSyUpK1SqMWPBnWzLJjQTTZEhnFr69Bbv6OJvD-a7IecoJCblhUDMG-q5_WH3VDTBZq04JzpozstSqYy1oaGWr4ZLcb00xMWKkI5ofOpY5hfRNfS70YE00Q0T6_rqlNqcpz4VOBfEI-3GezBRyuiYX3sQDLk-7IJ9Pjx_r56p_27ysV30VmISmUq5DJ7kXTknUgzcOHPeuteAQwSomBLbONpoLsN6pY6UaGo_MSaaN0nxBbv-9ARF3Ywl7U353p1v8D82nRwM
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/LDAV.2016.7874312
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
EISBN 9781509056590
1509056599
EndPage 84
ExternalDocumentID 7874312
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i1602-7d8ed63f4d76e9bfad0d3fd5c0dee0c7144e5dc29340cfd79787b2fe1d619a793
IEDL.DBID RIE
IngestDate Thu Jun 29 18:37:48 EDT 2023
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i1602-7d8ed63f4d76e9bfad0d3fd5c0dee0c7144e5dc29340cfd79787b2fe1d619a793
OpenAccessLink https://www.osti.gov/biblio/1379768
PageCount 10
ParticipantIDs ieee_primary_7874312
PublicationCentury 2000
PublicationDate 2016-Oct.
PublicationDateYYYYMMDD 2016-10-01
PublicationDate_xml – month: 10
  year: 2016
  text: 2016-Oct.
PublicationDecade 2010
PublicationTitle 2016 IEEE 6th Symposium on Large Data Analysis and Visualization (LDAV)
PublicationTitleAbbrev LDAV
PublicationYear 2016
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.818617
Snippet As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands...
SourceID ieee
SourceType Publisher
StartPage 75
SubjectTerms Algorithm design and analysis
Analytical models
Computational modeling
contour tree
Data models
data parallel algorithms
merge tree
Solid modeling
topological analysis
Topology
Vegetation
Title Parallel peak pruning for scalable SMP contour tree computation
URI https://ieeexplore.ieee.org/document/7874312
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61ePCk0opvcvDotpvd7Gb3JKIWD1oWfNBbyWZmoCjtsu36-02yS0Xw4i2EQJjJY2Yy8-Vj7Co2EGotkoBQRYEk48DKURxITErIFIhMl55sQk2n2WyWFz12vcXCIKIvPsORa_pcPqxM457KxnZzWXtnL9wdpdIWq9UlKkWYj5_ub99drVY66sb9Ikzx9mKy_7-ZDtjwB3jHi61JOWQ9XA7YTaFrx3jyySvUH7yqG_eWwa23yddWww77xF-eC-6qzu3O4C7PzI1na_BqH7K3ycPr3WPQ8R4EC5HaC0pBhpDGJEGlmJekIYSYIDEhIIZG2RgIEzDWUMvQECgbCKoyIhRgoyFtD9wR6y9XSzxmXCMl0li3QmIsUWSZJkNGUx6lREKWJ2zghJ9X7dcW807u07-7z9ie029by3bO-pu6wQu2a742i3V96dfjG3xlkBc
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6lCnpSacW3OXh022Q3u9k9iailYlsWrNJbyWYmUJR22bb-fpN0qQhevIUQCDN5zExmvnyE3EQamFI8DgzKMBBGO7ByGAUC4wJSCTxVhSebkKNROplkeYPcbrEwiOiLz7Djmj6XDwu9dk9lXbu5rL2zF-5OLETINmitOlXJWdYdPN6_u2qtpFOP_EWZ4i1G7-B_cx2S9g_0juZbo3JEGjhvkbtcVY7z5JOWqD5oWa3dawa1_iZdWh079BN9HebU1Z3bvUFdpplqz9fgFd8mb72n8UM_qJkPghlP7BUlIUVIIiNAJpgVRgGDyECsGSAyLW0UhDFoa6oF0wakDQVlERrkYOMhZY_cMWnOF3M8IVShiYW2joXASCBPU2W00cpkYWIMF8UpaTnhp-Xmc4tpLffZ393XZK8_Hg6mg-fRyznZd7reVLZdkOaqWuMl2dVfq9myuvJr8w0qQZNe
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=2016+IEEE+6th+Symposium+on+Large+Data+Analysis+and+Visualization+%28LDAV%29&rft.atitle=Parallel+peak+pruning+for+scalable+SMP+contour+tree+computation&rft.au=Carr%2C+Hamish+A.&rft.au=Weber%2C+Gunther+H.&rft.au=Sewell%2C+Christopher+M.&rft.au=Ahrens%2C+James+P.&rft.date=2016-10-01&rft.pub=IEEE&rft.spage=75&rft.epage=84&rft_id=info:doi/10.1109%2FLDAV.2016.7874312&rft.externalDocID=7874312