A Sparsity-Aware Distributed-Memory Algorithm for Sparse-Sparse Matrix Multiplication

Multiplying two sparse matrices (SpGEMM) is a common computational primitive used in many areas including graph algorithms, bioinformatics, algebraic multigrid solvers, and randomized sketching. Distributed-memory parallel algorithms for SpGEMM have mainly focused on sparsity-oblivious approaches th...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:SC24: International Conference for High Performance Computing, Networking, Storage and Analysis s. 1 - 14
Hlavní autori: Hong, Yuxi, Buluc, Aydin
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 17.11.2024
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Multiplying two sparse matrices (SpGEMM) is a common computational primitive used in many areas including graph algorithms, bioinformatics, algebraic multigrid solvers, and randomized sketching. Distributed-memory parallel algorithms for SpGEMM have mainly focused on sparsity-oblivious approaches that use 2D and 3D partitioning. Sparsity-aware 1D algorithms can theoretically reduce communication by not fetching nonzeros of the sparse matrices that do not participate in the multiplication. Here, we present a distributed-memory 1D SpGEMM algorithm and implementation. It uses MPI RDMA operations to mitigate the cost of packing/unpacking submatrices for communication, and it uses a block fetching strategy to avoid excessive finegrained messaging. Our results show that our 1D implementation outperforms state-of-the-art 2D and 3D implementations within CombBLAS for many configurations, inputs, and use cases, while remaining conceptually simpler.
AbstractList Multiplying two sparse matrices (SpGEMM) is a common computational primitive used in many areas including graph algorithms, bioinformatics, algebraic multigrid solvers, and randomized sketching. Distributed-memory parallel algorithms for SpGEMM have mainly focused on sparsity-oblivious approaches that use 2D and 3D partitioning. Sparsity-aware 1D algorithms can theoretically reduce communication by not fetching nonzeros of the sparse matrices that do not participate in the multiplication. Here, we present a distributed-memory 1D SpGEMM algorithm and implementation. It uses MPI RDMA operations to mitigate the cost of packing/unpacking submatrices for communication, and it uses a block fetching strategy to avoid excessive finegrained messaging. Our results show that our 1D implementation outperforms state-of-the-art 2D and 3D implementations within CombBLAS for many configurations, inputs, and use cases, while remaining conceptually simpler.
Author Buluc, Aydin
Hong, Yuxi
Author_xml – sequence: 1
  givenname: Yuxi
  surname: Hong
  fullname: Hong, Yuxi
  email: abuluc@lbl.gov
  organization: Applied Math & Computational Research Division Lawrence Berkeley National Laboratory,Berkeley,USA
– sequence: 2
  givenname: Aydin
  surname: Buluc
  fullname: Buluc, Aydin
  organization: Applied Math & Computational Research Division Lawrence Berkeley National Laboratory,Berkeley,USA
BookMark eNotjM1KxDAURiMoqGNfQFzkBTreJE2TLMv4C1NcjLMekvRWA522pBm0b29hXB3Ox-G7JZf90CMh9wzWjIF53G0KVkC55sCLNQBIcUEyo4wWEoTkhqlrkk1TcCCVEkqAuCH7iu5GG6eQ5rz6sRHpU5hSDO6UsMlrPA5xplX3NcSQvo-0HeK5x_wMWtul_qX1qUth7IK3KQz9HblqbTdh9s8V2b88f27e8u3H6_um2uaWyyLlBi0oDVZ78FBY3ygnWKs4oHGIpZfg9aItLzVfBgBtvDHO6ZK5BnwhVuTh_BsQ8TDGcLRxPjBQRjApxR-M6VLv
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/SC41406.2024.00053
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350352917
EndPage 14
ExternalDocumentID 10793155
Genre orig-research
GrantInformation_xml – fundername: Office of Science
  funderid: 10.13039/100006132
GroupedDBID 6IE
6IL
ACM
ALMA_UNASSIGNED_HOLDINGS
APO
CBEJK
LHSKQ
RIE
RIL
ID FETCH-LOGICAL-a254t-9ea0780a8c0c04acd7b31f720e9bee6c50c8f72f2682bee0089c99bb861bd0c43
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001414891300034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Jan 22 08:32:25 EST 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a254t-9ea0780a8c0c04acd7b31f720e9bee6c50c8f72f2682bee0089c99bb861bd0c43
PageCount 14
ParticipantIDs ieee_primary_10793155
PublicationCentury 2000
PublicationDate 2024-Nov.-17
PublicationDateYYYYMMDD 2024-11-17
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-Nov.-17
  day: 17
PublicationDecade 2020
PublicationTitle SC24: International Conference for High Performance Computing, Networking, Storage and Analysis
PublicationTitleAbbrev SC
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib057737303
Score 1.9048718
Snippet Multiplying two sparse matrices (SpGEMM) is a common computational primitive used in many areas including graph algorithms, bioinformatics, algebraic multigrid...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms 1D algorithm
1D SpGEMM algorithm
Electric breakdown
High performance computing
Load management
Matrices
numerical linear algebra
Parallel algorithms
parallel computing
Partitioning algorithms
RDMA
Software
Software algorithms
Sparse matrices
sparse matrix-matrix multiplication
sparsity-aware 1D SpGEMM algorithm
SpGEMM
Three-dimensional displays
Title A Sparsity-Aware Distributed-Memory Algorithm for Sparse-Sparse Matrix Multiplication
URI https://ieeexplore.ieee.org/document/10793155
WOSCitedRecordID wos001414891300034&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/eLvHCXMwlV1LSwMxEA62ePCkYsU3OXiNZjfZTXIs1eKlpVALvZU8ZlXQttTWx793km3Viwf3sg8WFiazfJnk-74h5FLnztiyAlbl2jMpQDMrIbDMcqGtVqGQLjWbUP2-Ho_NYC1WT1oYAEjkM7iKl2kvP8z8Ki6V4R-O2YQA2CANpVQt1tokT6GUwGwVG2EMN9fDjsTyIfIQ8miRzWMD5F8tVBKCdHf_-e090vrR4tHBN8rsky2YHpBRmw7nNvEpWPvdLoDeRAPc2LsKI9CL7NlP2n5-mGHp__hCcWJavw-sPtFedOb_oL2aTrhet2uRUff2vnPH1g0SmMW6bskMWER4brXnnkvrg3Iiq1TOwTiA0hfca7yt8hKHBADh3nhjnNNl5gL3UhyS5nQ2hSNCpQl4iNJBFmSeB1dkvgwBJxfRrbgIx6QVYzKZ1x4Yk004Tv54fkp2Ytijai9TZ6S5XKzgnGz7t-XT6-IijdwXHTqcEA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4UTfSkRoxve_Ba7Xa7u-2RoAQjS0iAhBvpY1ATBYLg49873QX14sG9dLfZZJOZ2Uyn_b75CLlUwmqTjoCNhHJMxqCYkeBZZHisjMp8Im0hNpG122ow0J0lWb3gwgBAAT6Dq3BbnOX7iVuErTL8wzGaMAGuk41EShGVdK1V-CRZFmO8xitqDNfX3brEAiIgEURoks2DBPIvEZUihzR2_vn1XVL9YePRznee2SNrMN4n_RrtTk2BqGC1dzMDehNa4Ab1KrRBHvCzn7T2_DDB4v_xheLStHwfWDnQPPTm_6B5CShc7txVSb9x26s32VIigRms7OZMg8Ecz41y3HFpnM9sHI0ywUFbgNQl3Cl8HIkUnQKACV87ra1VaWQ9dzI-IJXxZAyHhErt8YpTC5GXQnibRC71HpcXoV9x4o9INdhkOC27YAxX5jj-Y_6CbDV7eWvYumvfn5Dt4ILA4YuyU1KZzxZwRjbd2_zpdXZeePELajafVw
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=SC24%3A+International+Conference+for+High+Performance+Computing%2C+Networking%2C+Storage+and+Analysis&rft.atitle=A+Sparsity-Aware+Distributed-Memory+Algorithm+for+Sparse-Sparse+Matrix+Multiplication&rft.au=Hong%2C+Yuxi&rft.au=Buluc%2C+Aydin&rft.date=2024-11-17&rft.pub=IEEE&rft.spage=1&rft.epage=14&rft_id=info:doi/10.1109%2FSC41406.2024.00053&rft.externalDocID=10793155