SAGA: A Memory-Efficient Accelerator for GANN Construction via Harnessing Vertex Similarity

Graph-traversal-based Approximate Nearest Neighbor (GANN) search and construction have become key retrieval techniques in various domains, such as recommendation systems and social networks. However, deploying GANN in real-world scenarios faces significant challenges, as high-dimensional vertices wi...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Chen, Ruiyang, Liu, Xueyuan, Qi, Chunyu, Yao, Yuanzheng, Sun, Yanan, Liang, Xiaoyao, Song, Zhuoran
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Accuracy
Energy conservation
Energy efficiency
Faces
Graphics processing units
Hardware
Quantization (signal)
Recommender systems
Scheduling algorithms
Social networking (online)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Graph-traversal-based Approximate Nearest Neighbor (GANN) search and construction have become key retrieval techniques in various domains, such as recommendation systems and social networks. However, deploying GANN in real-world scenarios faces significant challenges, as high-dimensional vertices within the graph can lead to intensive memory demands. Although architectures like NDSearch have been proposed to accelerate GANN search, they are hard to deploy for GANN construction, as their pre-processing methods introduce massive overhead in dynamic graphs. In this paper, given the observation that neighboring vertices in a dynamic graph exhibit feature similarity, we propose SAGA, the first accelerator that alleviates memory bound in GANN construction. To capture this similarity, we directly leverage the first step of construction to gather vertices with the same starting point into a cluster to minimize the similarity detection overhead. Next, we decompose vertices into key and non-key ones, where their deltas fall in a narrow range, which is suitable to be quantized to lower bit widths. Building upon this approach, we design a specialized architecture, which efficiently implements the GANN construction by twolevel scheduling and a mixed-precision supported bit-serial unit. Through comprehensive evaluation, we demonstrate that SAGA can achieve an average speedup of 9.30 \times 4.87 \times 4.15 \times and 35.46 \times 7.60 \times 5.15 \times energy savings over CPU, GPU and NDSearch, respectively, while retaining task accuracy.
AbstractList Graph-traversal-based Approximate Nearest Neighbor (GANN) search and construction have become key retrieval techniques in various domains, such as recommendation systems and social networks. However, deploying GANN in real-world scenarios faces significant challenges, as high-dimensional vertices within the graph can lead to intensive memory demands. Although architectures like NDSearch have been proposed to accelerate GANN search, they are hard to deploy for GANN construction, as their pre-processing methods introduce massive overhead in dynamic graphs. In this paper, given the observation that neighboring vertices in a dynamic graph exhibit feature similarity, we propose SAGA, the first accelerator that alleviates memory bound in GANN construction. To capture this similarity, we directly leverage the first step of construction to gather vertices with the same starting point into a cluster to minimize the similarity detection overhead. Next, we decompose vertices into key and non-key ones, where their deltas fall in a narrow range, which is suitable to be quantized to lower bit widths. Building upon this approach, we design a specialized architecture, which efficiently implements the GANN construction by twolevel scheduling and a mixed-precision supported bit-serial unit. Through comprehensive evaluation, we demonstrate that SAGA can achieve an average speedup of 9.30 \times 4.87 \times 4.15 \times and 35.46 \times 7.60 \times 5.15 \times energy savings over CPU, GPU and NDSearch, respectively, while retaining task accuracy.
Author Liu, Xueyuan
Song, Zhuoran
Chen, Ruiyang
Qi, Chunyu
Sun, Yanan
Liang, Xiaoyao
Yao, Yuanzheng
Author_xml – sequence: 1
  givenname: Ruiyang
  surname: Chen
  fullname: Chen, Ruiyang
  email: chenruiyang@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 2
  givenname: Xueyuan
  surname: Liu
  fullname: Liu, Xueyuan
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 3
  givenname: Chunyu
  surname: Qi
  fullname: Qi, Chunyu
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 4
  givenname: Yuanzheng
  surname: Yao
  fullname: Yao, Yuanzheng
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 5
  givenname: Yanan
  surname: Sun
  fullname: Sun, Yanan
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 6
  givenname: Xiaoyao
  surname: Liang
  fullname: Liang, Xiaoyao
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 7
  givenname: Zhuoran
  surname: Song
  fullname: Song, Zhuoran
  email: songzhuoran@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
BookMark eNo1j81KxDAUhSPoQsd5A5G8QMf8tE3jLtSxI4zjYgY3Lob0eiOBNpU0in37KaiLw4ED34HvipyHISAht5ytOGf67sHUpaxyvRJMFPPEpZSsOCNLrXQlJS-YZHl1Sd72pjH31NBn7Ic4ZWvnPHgMiRoA7DDaNETq5jRmt6P1EMYUvyD5IdBvb-nGxoDj6MMHfcWY8Ifufe87G32arsmFs92Iy79ekMPj-lBvsu1L81SbbWa50inDHFypWwCnNDpgSoNolRI5b4XGKgcQVpVCifcSoWCgnbDWFm01U_nssiA3v7ceEY-f0fc2Tsd_ZXkCfVJQ7g
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133305
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11133305
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
– fundername: Natural Science Foundation of Shanghai
  funderid: 10.13039/100007219
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-e4cf69bccf79efc079c2b77241b29e84cc2a76272d6ec50c9f2aaa5b8f694833
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-e4cf69bccf79efc079c2b77241b29e84cc2a76272d6ec50c9f2aaa5b8f694833
PageCount 7
ParticipantIDs ieee_primary_11133305
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 2.2951672
Snippet Graph-traversal-based Approximate Nearest Neighbor (GANN) search and construction have become key retrieval techniques in various domains, such as...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Energy conservation
Energy efficiency
Faces
Graphics processing units
Hardware
Quantization (signal)
Recommender systems
Scheduling algorithms
Social networking (online)
Title SAGA: A Memory-Efficient Accelerator for GANN Construction via Harnessing Vertex Similarity
URI https://ieeexplore.ieee.org/document/11133305
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPHhSseKbHLymbbLZzcbbUvu4uBRapOChJLMJ7MFWai36752kreLBg7clbBIyecxMMt98hNxlynrBpWc2cxWTac6Z5Vox9DVy6TUumdRHsglVlvl0qkdbsHrEwjjnYvCZa4XP-JZfLeA9XJW1Ay06-t_pPtlXKtuAtbaoX97R7Yeii6tJBviJSFu7n3_RpkSt0T_6Z3_HpPmDv6Ojb81yQvbc_JQ8j4tBcU8L-hiCYz9ZLyZ_wAZoAYDKI76XU7RB6aAoSxqYOHe5Yem6NnRoluFYwwbpk1uu3Acd1y81OrZohzfJpN-bdIdsS43ADO6gFXMSfKYtgFfaeegoDcKioSy5FdrlEkAYPOaUqDIHaQe0F8aY1OZYS-ZJckYa88XcnROa8MR4rZy26Oih9WB5BjL12nsOlTbZBWkGwcxeN8kvZjuZXP5RfkUOg_hDNJUQ16SBI3U35ADWq_pteRun7AsolZju
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8MgFCY6TfSkxhl_y8Er26DQFm_N3A_j1izZYpZ4WIBC0oObmXPR_94H2zQePHgjDdAUKO998L73IXQbJ9oxyh3RsS0IFyklmsqEANZIuZOwZIQLYhNJnqfjsRysyeqBC2OtDcFntuaL4S6_mJl3f1RW97LogL_FNtoRHIDPiq615v3ShqzfZ01YT9wTUJiobar_Ek4JdqN98M83HqLqDwMPD75tyxHastNj9DzMOtkdznDfh8d-klZI_wAd4MwYMB_hxhyDF4o7WZ5jr8W5yQ6Ll6XCXTX3Gxt0iJ_sfGE_8LB8KQHagideRaN2a9TskrU4AlHwDy2I5cbFUhvjEmmdaSTSMA2uMqeaSZtyY5iCjS5hRWyNaBjpmFJK6BRa8TSKTlBlOpvaU4QjGiknEys1QD3wHzSNDRdOOkdNIVV8hqp-YCavq_QXk82YnP_x_AbtdUf93qT3kD9eoH0_FT62irFLVIGvtldo1ywX5dv8OkzfF0uAnDU
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=SAGA%3A+A+Memory-Efficient+Accelerator+for+GANN+Construction+via+Harnessing+Vertex+Similarity&rft.au=Chen%2C+Ruiyang&rft.au=Liu%2C+Xueyuan&rft.au=Qi%2C+Chunyu&rft.au=Yao%2C+Yuanzheng&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133305&rft.externalDocID=11133305