SSpMV: A Sparsity-aware SpMV Framework Empowered by Multimodal Machine Learning

Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse operation in scientific computing and artificial intelligence. Efficiently adapting SpMV algorithms to diverse matrices and architectures requires a framework capable of accurately recognizing sparse patterns and selecting the optimal...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Lin, Shengle, Liu, Chubo, Ding, Yan, Zhou, Joey Tianyi, Li, Kenli, Yang, Wangdong
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Accuracy
Libraries
Machine learning
Machine learning algorithms
Neural networks
Pattern recognition
Prediction algorithms
Predictive models
Scientific computing
Sparse matrices
Sparse Matrix
SpMV
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse operation in scientific computing and artificial intelligence. Efficiently adapting SpMV algorithms to diverse matrices and architectures requires a framework capable of accurately recognizing sparse patterns and selecting the optimal implementation. In this work, we introduce Sparsity-aware SpMV (SSpMV), a framework that integrates expert-designed features with multimodal representations to adaptively predict the best-performing algorithm and parameters. For this purpose, we design a multimodal neural network called MM-Adapter, to capture diverse modalities to represent the computational features of SpMV. Experimental results demonstrate that MMAdapter achieves the highest accuracy of 81.05 \%, outperforming existing SpMV prediction models. Furthermore, SSpMV consistently delivers substantial performance improvements over state-of-the-art sparse libraries across various multi-core platforms.
AbstractList Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse operation in scientific computing and artificial intelligence. Efficiently adapting SpMV algorithms to diverse matrices and architectures requires a framework capable of accurately recognizing sparse patterns and selecting the optimal implementation. In this work, we introduce Sparsity-aware SpMV (SSpMV), a framework that integrates expert-designed features with multimodal representations to adaptively predict the best-performing algorithm and parameters. For this purpose, we design a multimodal neural network called MM-Adapter, to capture diverse modalities to represent the computational features of SpMV. Experimental results demonstrate that MMAdapter achieves the highest accuracy of 81.05 \%, outperforming existing SpMV prediction models. Furthermore, SSpMV consistently delivers substantial performance improvements over state-of-the-art sparse libraries across various multi-core platforms.
Author Zhou, Joey Tianyi
Ding, Yan
Li, Kenli
Lin, Shengle
Yang, Wangdong
Liu, Chubo
Author_xml – sequence: 1
  givenname: Shengle
  surname: Lin
  fullname: Lin, Shengle
  email: 1s1036@hnu.edu.cn
  organization: Hunan University,College of Computer Science and Electronic Engineering,China
– sequence: 2
  givenname: Chubo
  surname: Liu
  fullname: Liu, Chubo
  email: liuchubo@hnu.edu.cn
  organization: Hunan University,College of Computer Science and Electronic Engineering,China
– sequence: 3
  givenname: Yan
  surname: Ding
  fullname: Ding, Yan
  email: ding@hnu.edu.cn
  organization: Hunan University,College of Computer Science and Electronic Engineering,China
– sequence: 4
  givenname: Joey Tianyi
  surname: Zhou
  fullname: Zhou, Joey Tianyi
  email: zhouty@cfar.a-star.edu.sg
  organization: Centre for Frontier AI Research, Agency for Science, Technology and Research,Singapore
– sequence: 5
  givenname: Kenli
  surname: Li
  fullname: Li, Kenli
  email: 1k1@hnu.edu.cn
  organization: Hunan University,College of Computer Science and Electronic Engineering,China
– sequence: 6
  givenname: Wangdong
  surname: Yang
  fullname: Yang, Wangdong
  email: yangwangdong@hnu.edu.cn
  organization: Hunan University,College of Computer Science and Electronic Engineering,China
BookMark eNo1j81KxDAYACPoQdd9A5G8QNcvSZsm3krdXYWWPVS9LmnzRYP9I1spfXsV9TQwh4G5Iuf90CMhtww2jIG-e8hyKVSsNxx48q2Y4ErLM7LWqVZCsAQExOqSHKpqLF_vaUar0YSTn5bIzCYg_dF0F0yH8xA-6LYbhxkDWlovtPxsJ98N1rS0NM2775EWaELv-7drcuFMe8L1H1fkZbd9zh-j4rB_yrMiMizVU2RrTJwTjisFII1TSWo5xo5xoRSHBByksQSuG47SomBWg-Milbxhtua1WJGb365HxOMYfGfCcvz_FF9hqEvM
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11132896
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 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 9798331503048
EndPage 7
ExternalDocumentID 11132896
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-dbe5ff3f288006af857d2e4f123882050f0746029c2e6de31d90f23762c1db2b3
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-dbe5ff3f288006af857d2e4f123882050f0746029c2e6de31d90f23762c1db2b3
PageCount 7
ParticipantIDs ieee_primary_11132896
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.2952232
Snippet Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse operation in scientific computing and artificial intelligence. Efficiently adapting SpMV...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Libraries
Machine learning
Machine learning algorithms
Neural networks
Pattern recognition
Prediction algorithms
Predictive models
Scientific computing
Sparse matrices
Sparse Matrix
SpMV
Title SSpMV: A Sparsity-aware SpMV Framework Empowered by Multimodal Machine Learning
URI https://ieeexplore.ieee.org/document/11132896
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFH7Y4sGTihV3cvA6bSazxlupLR5sLYyW3kqWFxFsO9RW8d-bpDOKBw_eQggEXpa35PvyAVxLbu88FWNARU5tgiJlwB3Zh2dGUFQ2RvCli8l9Nhrl0ykfV2R1z4VBRA8-w7Zr-rd8vVQbVyrreFn0nKcNaGRZuiVrVazfkPLObbdnd1Ps6CcsadeDf8mmeK8x2P_nfAfQ-uHfkfG3ZzmEHVwcwUNRlMPJDemSohQeShGID7FC4rrJoAZZkf68dMpnqIn8JJ5fO19q8UqGHjaJpPpR9bkFT4P-Y-8uqOQQAmFPzTrQEhNjIsPskaOpMHmSaYaxsb7Hhsk0ocZph1DGFcNUYxRqTo0DvTAVaslkdAzNxXKBJ0BsHiNCFbnckcYiMZyqONZK2PxPJSHSU2g5a8zK7Y8Xs9oQZ3_0n8Oes7mDUDF2Ac31aoOXsKve1y9vqyu_Tl_DaZOx
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LTgIxFL1RNNGVGjG-7cLtQKczA1N3BCEYAUlAwo70cWtMBCYjaPx72zpoXLhw1zRNmtw-7qPn9ABcS27vPBVjQEVKbYIiZcAd2YfXjaCobIzgSxfjbr3fTycTPijI6p4Lg4gefIYV1_Rv-XqhVq5UVvWy6CmvbcKWk84q6FoF7zekvHrbaNr9FDsCCksq6-G_hFO832jv_XPGfSj_MPDI4Nu3HMAGzg_hYTjMeuMb0iDDTHgwRSDeRY7EdZP2GmZFWrPMaZ-hJvKDeIbtbKHFC-l54CSS4k_VpzI8tlujZicoBBECYc_NMtASE2Miw-yhozVh0qSuGcbGeh8bKNOEGqceQhlXDGsao1BzahzshalQSyajIyjNF3M8BmIzGRGqyGWPNBaJ4VTFsVbCZoAqCZGeQNlZY5p9_XkxXRvi9I_-K9jpjHrdafeuf38Gu87-DlDF2DmUlvkKL2BbvS2fX_NLv2afp7KW-g
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=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=SSpMV%3A+A+Sparsity-aware+SpMV+Framework+Empowered+by+Multimodal+Machine+Learning&rft.au=Lin%2C+Shengle&rft.au=Liu%2C+Chubo&rft.au=Ding%2C+Yan&rft.au=Zhou%2C+Joey+Tianyi&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11132896&rft.externalDocID=11132896