Low-Power Scalable TSPI: A Modular Off-Chip Network for Edge AI Accelerators

In this paper, we present a novel off-chip network architecture, the Tile Serial Peripheral Interface (TSPI), designed for low-power, scalable edge AI accelerators. Our approach modifies the conventional SPI to support a modular network structure that facilitates the scalable connection of multiple...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 12; pp. 141448 - 141459
Main Authors: Park, Seunghyun, Park, Daejin
Format: Journal Article
Language:English
Published: Piscataway IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accelerator architectures
Accelerators
Algorithms
Computational modeling
Computer architecture
Distributed databases
Edge AI
Edge computing
edge device
Indexes
low power
Low power electronics
Message passing
Modular structures
MPI
Network architecture
off-chip network
Performance evaluation
Power consumption
Random access memory
Scalability
subset mapping algorithm
TSPI
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this paper, we present a novel off-chip network architecture, the Tile Serial Peripheral Interface (TSPI), designed for low-power, scalable edge AI accelerators. Our approach modifies the conventional SPI to support a modular network structure that facilitates the scalable connection of multiple accelerators. The TSPI network employs a subset mapping algorithm for efficient routing and integrates the message passing interface (MPI) protocol to ensure rapid data distribution and aggregation. This modular architecture significantly reduces power consumption and improves processing speed. Experimental results demonstrate that our proposed TSPI network achieves a 54.7% reduction in power consumption and an 82.3% decrease in switching power compared to traditional SPI networks, along with a 23% increase in processing speed when utilizing 16 nodes. These advancements make the TSPI network an effective solution for enhancing AI performance in edge computing environments.
AbstractList In this paper, we present a novel off-chip network architecture, the Tile Serial Peripheral Interface (TSPI), designed for low-power, scalable edge AI accelerators. Our approach modifies the conventional SPI to support a modular network structure that facilitates the scalable connection of multiple accelerators. The TSPI network employs a subset mapping algorithm for efficient routing and integrates the message passing interface (MPI) protocol to ensure rapid data distribution and aggregation. This modular architecture significantly reduces power consumption and improves processing speed. Experimental results demonstrate that our proposed TSPI network achieves a 54.7% reduction in power consumption and an 82.3% decrease in switching power compared to traditional SPI networks, along with a 23% increase in processing speed when utilizing 16 nodes. These advancements make the TSPI network an effective solution for enhancing AI performance in edge computing environments.
Author Park, Daejin
Park, Seunghyun
Author_xml – sequence: 1
  givenname: Seunghyun
  orcidid: 0000-0002-2416-2472
  surname: Park
  fullname: Park, Seunghyun
  organization: School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, South Korea
– sequence: 2
  givenname: Daejin
  orcidid: 0000-0002-5560-873X
  surname: Park
  fullname: Park, Daejin
  email: boltanut@knu.ac.kr
  organization: School of Electronics Engineering, Kyungpook National University, Daegu, South Korea
BookMark eNpNUcFu1DAQtVCRKKVfAAdLnLN44tiOuUXRAittaaUtZ2sSj0uWsF6crFb8PS6pqs5lRk_z3jzNe8suDvFAjL0HsQIQ9lPTtuvdblWKslrJSmur1St2WYK2hVRSX7yY37DradqLXHWGlLlk2208F3fxTInvehyxG4nf7-42n3nDb6I_jZj4bQhF-3M48u80n2P6xUNMfO0fiDcb3vQ9jZRwjml6x14HHCe6fupX7MeX9X37rdjeft20zbbopbJzITvhy672UiBW1iAYgNoGqJXGWgewJUhRl0i99yb0lTZdZZTS0AnyAoK8YptF10fcu2MafmP66yIO7j8Q04PDNA_9SA67On9EBmEsVgoskg5BCYDOdxCEylofF61jin9ONM1uH0_pkO07CVBmL6as8pZctvoUpylReL4Kwj2m4JYU3GMK7imFzPqwsAYiesHQdf69kf8ALtuBuQ
CODEN IAECCG
Cites_doi 10.1109/DATE.2007.364414
10.1109/JETCAS.2021.3129415
10.1109/TC.1985.6312192
10.1109/ICPADS.2008.44
10.1109/MC.1982.1653825
10.1109/HCS55958.2022.9895534
10.1109/TPDS.2021.3104240
10.1109/TC.2011.237
10.1109/ISCA.2018.00066
10.1016/j.micpro.2020.103138
10.1007/s42979-023-02239-5
10.3390/s20092533
10.23919/DATE.2017.7927211
10.1145/3579371.3589350
10.1016/j.procs.2020.06.048
10.1109/MSPEC.2004.1270547
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
DOA
DOI 10.1109/ACCESS.2024.3466965
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
DatabaseTitleList

Materials Research Database
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Xplore (IEEE/IET Electronic Library - IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 141459
ExternalDocumentID oai_doaj_org_article_ab86693f079a4519ae6ff5011bdb1f05
10_1109_ACCESS_2024_3466965
10689577
Genre orig-research
GrantInformation_xml – fundername: Institute of Information and Communications Technology Planning and Evaluation (IITP)
– fundername: Development of Flexible Software-Hardware (SW-HW) Conjunctive Solution for On-Edge Self-Supervised Learning (30%)
  grantid: RS-2023-00228970
– fundername: Brain Korea 21 4th Generation (BK21 FOUR) Project
  grantid: 4199990113966
– fundername: Ministry of Education (10%, 10%, respectively)
  grantid: NRF-2018R1A6A1A03025109; NRF-2022R1I1A3069260
– fundername: Korea Institute for Advancement of Technology (KIAT)
– fundername: Basic Science Research Program through the National Research Foundation of Korea (NRF)
– fundername: Processing-in-Memory Computing (PIM) Semiconductor Design Research Center (20%)
  grantid: 2022-0-01170
– fundername: Korean Government [Ministry of Trade, Industry and Energy (MOTIE)] through the Human Resources Development (HRD) Program for Industrial Innovation (10%)
  grantid: RS-2024-00415938
– fundername: Korean Government [Ministry of Science and Information Communication Technology (MSIT)] through the Metamorphic Approach of Unstructured Validation/Verification for Analyzing Binary Code (20%)
  grantid: 2021-0-00944
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c359t-3b0d2b8d30aa497a171189f1856a86f19213082aecdd7fc467b475561b0ed01f3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001328992900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:46:18 EDT 2025
Mon Jun 30 15:43:13 EDT 2025
Sat Nov 29 04:27:06 EST 2025
Wed Aug 27 02:18:11 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c359t-3b0d2b8d30aa497a171189f1856a86f19213082aecdd7fc467b475561b0ed01f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-2416-2472
0000-0002-5560-873X
OpenAccessLink https://ieeexplore.ieee.org/document/10689577
PQID 3112921724
PQPubID 4845423
PageCount 12
ParticipantIDs ieee_primary_10689577
proquest_journals_3112921724
doaj_primary_oai_doaj_org_article_ab86693f079a4519ae6ff5011bdb1f05
crossref_primary_10_1109_ACCESS_2024_3466965
PublicationCentury 2000
PublicationDate 20240000
2024-00-00
20240101
2024-01-01
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 20240000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref14
ref11
ref10
ref2
ref1
ref17
ref16
Coates (ref15)
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – ident: ref17
  doi: 10.1109/DATE.2007.364414
– ident: ref2
  doi: 10.1109/JETCAS.2021.3129415
– ident: ref13
  doi: 10.1109/TC.1985.6312192
– ident: ref14
  doi: 10.1109/ICPADS.2008.44
– ident: ref8
  doi: 10.1109/MC.1982.1653825
– ident: ref7
  doi: 10.1109/HCS55958.2022.9895534
– ident: ref9
  doi: 10.1109/TPDS.2021.3104240
– ident: ref11
  doi: 10.1109/TC.2011.237
– ident: ref4
  doi: 10.1109/ISCA.2018.00066
– ident: ref10
  doi: 10.1016/j.micpro.2020.103138
– ident: ref12
  doi: 10.1007/s42979-023-02239-5
– ident: ref1
  doi: 10.3390/s20092533
– ident: ref16
  doi: 10.23919/DATE.2017.7927211
– ident: ref6
  doi: 10.1145/3579371.3589350
– start-page: 1337
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref15
  article-title: Deep learning with COTS HPC systems
– ident: ref3
  doi: 10.1016/j.procs.2020.06.048
– ident: ref5
  doi: 10.1109/MSPEC.2004.1270547
SSID ssj0000816957
Score 2.2996225
Snippet In this paper, we present a novel off-chip network architecture, the Tile Serial Peripheral Interface (TSPI), designed for low-power, scalable edge AI...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Index Database
Publisher
StartPage 141448
SubjectTerms Accelerator architectures
Accelerators
Algorithms
Computational modeling
Computer architecture
Distributed databases
Edge AI
Edge computing
edge device
Indexes
low power
Low power electronics
Message passing
Modular structures
MPI
Network architecture
off-chip network
Performance evaluation
Power consumption
Random access memory
Scalability
subset mapping algorithm
TSPI
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELUQYoAB8SkKBXlgJNSpncRmC1UrKpVSqYC6Wf6ELm3VFvj7nJMURWJgYXWsOH7n-O6cy3sIXVsaJ9y3WcS4d5CgJGnEDXeRUdwQC_E5LzQjXwfZcMgnEzGqSX2FmrCSHrgErqU0T1NBPcmEClQoyqXeJ7AqtdWxL9lL4VotmSr2YB6nIskqmqGYiFbe6cCMICFss1vK4JbBndRcUcHYX0ms_NqXC2fTO0D7VZSI8_LpDtGWmx2hvRp34DEaDOZf0ShonOEx4Bz-gMLP41H_Duf4cW5DdSl-8j7qvE8XeFgWe2OIUHHXvjmc93FuDLic4iv76gS99LrPnYeokkaIDE3EOqKa2LbmlhKlmMhUnEGiIDw431Tx1AeSs8BDo5yxNvMGdkPNsqCEqYmzJPb0FG3P5jN3hrBS0MoJuCWqmWdeO8WV8lpQ6Gh9u4FuNijJRcmAIYvMgQhZgioDqLICtYHuA5I_XQN9ddEARpWVUeVfRm2gk2CH2ngpB3NmDdTcGEZW79pK0hAyBp0tdv4fY1-g3TCf8pilibbXyw93iXbM53q6Wl4Vy-wbxeDRtg
  priority: 102
  providerName: Directory of Open Access Journals
Title Low-Power Scalable TSPI: A Modular Off-Chip Network for Edge AI Accelerators
URI https://ieeexplore.ieee.org/document/10689577
https://www.proquest.com/docview/3112921724
https://doaj.org/article/ab86693f079a4519ae6ff5011bdb1f05
Volume 12
WOSCitedRecordID wos001328992900001&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
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT9swFLYG2gEOYzDQygD5sCMBp3Zie7dQFYFUukqwiZvln6yXFtEybvztvOcEVGnisEsUOS-J4y_2e8_2-x4h3wMvK5X6ohAqRXBQqrpQXsXCW-VZAPtc5ZyRv0dyPFa3t3rSBavnWJgYY958Fk_wNK_lh7l_xKky6OG10pWUa2RNyroN1nqbUMEMEnCxYxYqmT5tBgP4CPAB--KEi7rWqEFWtE8m6e-yqvwzFGf9cr71nzX7TD51hiRtWuS3yYc42yGbK_SCX8hoNH8qJpgGjV4DFBgkRW-uJ5c_aEOv5gE3oNKfKRWDP9N7Om73g1MwYukw3EXaXNLGe9BKeSF-sUt-nQ9vBhdFlz2h8LzSy4I7FvpOBc6sFVraUoIvoRPo59qqOiEPGlLV2OhDkMnDgOmExGSZjsXAysT3yPpsPotfCbUWShUDzcWdSCK5aJW1yWkOgiH1e-T4tVXNfUuSYbJzwbRpQTAIgulA6JEzbPk3UWS4zgXQpKbrMMY6BcI8MaktUuDYWKdUwWjkgisTg4fsIgwr72sR6JGDVyBN1x0XhqNViam4xP47t30jG1jFdnLlgKwvHx7jIfno_y6ni4ej7KnD8ep5eJT_uhd47NGQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwELUoVCocSj-oWEqpDz021ImdxOYWViBWDduV2FbcLH9SLruIXeDvM-MEtFLFobcocRLHL_bM2J73CPnmeV7KWIhMyBggQCmrTDoZMmekYx78c5k0I_-09XgsLy_VpE9WT7kwIYS0-Swc4mFay_dzd4dTZdDDK6nKun5FNkohCtalaz1PqaCGBFzuuYVypn40wyF8BkSBhTjkoqoU2pAV-5No-ntdlX8G42RhTrf_s27vyNvelaRNh_17shZmH8jWCsHgR9K284dsgkJo9ALAwDQpOr2YjI5oQ8_nHreg0l8xZsO_1zd03O0Ip-DG0hN_FWgzoo1zYJfSUvxih_w-PZkOz7JePyFzvFTLjFvmCys9Z8YIVZu8hmhCRbDQlZFVRCY0JKsxwXlfRwdDphU1ymVaFjzLI_9E1mfzWdgl1Bg4KxnYLm5FFNEGI42JVnEo6GMxIN-fWlXfdDQZOoUXTOkOBI0g6B6EATnGln8uihzX6QQ0qe67jDZWQmEeWa0MkuCYUMVYwnhkvc0jg4fsIAwr7-sQGJD9JyB13yEXmqNfiWJcYu-F276SN2fT81a3o_HPz2QTq9tNteyT9eXtXfhCXrv75fXi9iD9dY-nzNKx
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%3Ajournal&rft.genre=article&rft.atitle=Low-Power+Scalable+TSPI%3A+A+Modular+Off-Chip+Network+for+Edge+AI+Accelerators&rft.jtitle=IEEE+access&rft.au=Park%2C+Seunghyun&rft.au=Park%2C+Daejin&rft.date=2024&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=12&rft.spage=141448&rft.epage=141459&rft_id=info:doi/10.1109%2FACCESS.2024.3466965&rft.externalDocID=10689577
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon