An N-Way Group Association Architecture and Sparse Data Group Association Load Balancing Algorithm for Sparse CNN Accelerators

In recent years, ASIC CNN Accelerators have attracted great attention among researchers for the high performance and energy efficiency. Some former works utilize the sparsity of CNN networks to improve the performance and the energy efficiency. However, these methods bring tremendous overhead to the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2019 24th Asia and South Pacific Design Automation Conference (ASP-DAC) s. 1 - 6
Hlavní autoři: Wang, Jingyu, Yuan, Zhe, Liu, Ruoyang, Yang, Huazhong, Liu, Yongpan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 21.01.2019
Témata:
ISSN:2153-697X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In recent years, ASIC CNN Accelerators have attracted great attention among researchers for the high performance and energy efficiency. Some former works utilize the sparsity of CNN networks to improve the performance and the energy efficiency. However, these methods bring tremendous overhead to the output memory, and the performance suffers from the hash collision. This paper presents: 1) an N-Way Group Association Architecture to reduce the memory overhead for Sparse CNN Accelerators; 2) a Sparse Data Group Association Load Balancing Algorithm which is implemented by the Scheduler module in the architecture to reduce the collision rate and improve the performance. Compared with the state-of-art accelerator, this work achieves either 1) 1.74x performance with 50% memory overhead reduction in the 4-way associated design or 2) 1.91x performance without memory overhead reduction in the 2-way associated design, which is close to the theoretical performance limit (without collision).
AbstractList In recent years, ASIC CNN Accelerators have attracted great attention among researchers for the high performance and energy efficiency. Some former works utilize the sparsity of CNN networks to improve the performance and the energy efficiency. However, these methods bring tremendous overhead to the output memory, and the performance suffers from the hash collision. This paper presents: 1) an N-Way Group Association Architecture to reduce the memory overhead for Sparse CNN Accelerators; 2) a Sparse Data Group Association Load Balancing Algorithm which is implemented by the Scheduler module in the architecture to reduce the collision rate and improve the performance. Compared with the state-of-art accelerator, this work achieves either 1) 1.74x performance with 50% memory overhead reduction in the 4-way associated design or 2) 1.91x performance without memory overhead reduction in the 2-way associated design, which is close to the theoretical performance limit (without collision).
Author Wang, Jingyu
Yang, Huazhong
Yuan, Zhe
Liu, Yongpan
Liu, Ruoyang
Author_xml – sequence: 1
  givenname: Jingyu
  surname: Wang
  fullname: Wang, Jingyu
  organization: Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering,Beijing,China
– sequence: 2
  givenname: Zhe
  surname: Yuan
  fullname: Yuan, Zhe
  organization: Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering,Beijing,China
– sequence: 3
  givenname: Ruoyang
  surname: Liu
  fullname: Liu, Ruoyang
  organization: Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering,Beijing,China
– sequence: 4
  givenname: Huazhong
  surname: Yang
  fullname: Yang, Huazhong
  organization: Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering,Beijing,China
– sequence: 5
  givenname: Yongpan
  surname: Liu
  fullname: Liu, Yongpan
  email: ypliu@tsinghua.edu.cn
  organization: Tsinghua University,Beijing National Research Center for Information Science and Technology (BNRist),Department of Electronic Engineering,Beijing,China
BookMark eNptkD1PAkEYhFejiYDUNhb7Bw73e6E8UdGEYKFGO_Ky-x6sOW7J7lLQ-NslUTuneZLJzBTTJ2dd7JCQK85GnCt9I8XYGqFGPzQnpH90mTSMWXNKeoJrWZmJ_bggw5w_2VGaCctZj3zVHV1U73CgsxT3O1rnHF2AEmJH6-Q2oaAr-4QUOk9fdpAy0jso8E98HsHTW2ihc6Fb07pdxxTKZkubmP6q08WC1s5hiwlKTPmSnDfQZhz-ckDeHu5fp4_V_Hn2NK3nFUglSmU54Mr7hltlJDfCT1BYh16DbXDC0ALXQikl2KqRwkrkXEgvGrvSY4PWywG5_tkNiLjcpbCFdFjy4w1MayO_AXX8YF4
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1145/3287624.3287626
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISBN 1450360076
9781450360074
EISSN 2153-697X
EndPage 6
ExternalDocumentID 10500556
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 61674094,61720106013
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IL
ACM
ALMA_UNASSIGNED_HOLDINGS
APO
CBEJK
GUFHI
LHSKQ
RIE
RIL
ID FETCH-LOGICAL-a342t-71aebddf17463162d9e27ced5a7fe90e7a15244420bf3273e1123d2f7b586e7d3
IEDL.DBID RIE
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000507459700061&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:10:38 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a342t-71aebddf17463162d9e27ced5a7fe90e7a15244420bf3273e1123d2f7b586e7d3
PageCount 6
ParticipantIDs ieee_primary_10500556
PublicationCentury 2000
PublicationDate 2019-01-21
PublicationDateYYYYMMDD 2019-01-21
PublicationDate_xml – month: 01
  year: 2019
  text: 2019-01-21
  day: 21
PublicationDecade 2010
PublicationTitle 2019 24th Asia and South Pacific Design Automation Conference (ASP-DAC)
PublicationTitleAbbrev ASP-DAC
PublicationYear 2019
Publisher ACM
Publisher_xml – name: ACM
SSID ssj0000502710
ssj0002869603
Score 1.7576666
Snippet In recent years, ASIC CNN Accelerators have attracted great attention among researchers for the high performance and energy efficiency. Some former works...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Asia
C++ languages
CNN accelerator
Codes
Design automation
Energy efficiency
group association
load balancing
Load management
optimization algorithm
Scheduler
Simulation
Title An N-Way Group Association Architecture and Sparse Data Group Association Load Balancing Algorithm for Sparse CNN Accelerators
URI https://ieeexplore.ieee.org/document/10500556
WOSCitedRecordID wos000507459700061&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/eLvHCXMwlV1NT8IwGG6EeNALihi_04PXIuu2djtO1HggC4kauZHSvlWMbgSGiRd_u-_KQEz04GnLvtJ0657neT8JOfcMohz4lgkDKFAiTzAlbMgUH-lI2CjW2nUt6ck0jQaDuF8lq7tcGABwwWfQLnedL9_kel6aynCFh2XNKFEjNSnFIllrZVDBc1xWWPbirEYC2blflfPxgvDC5-XSD9qLrfjRT8XByU3jnwPZIa3vxDzaX0HOLtmArEkay84MtFqoTbK9VmZwj3wmGU3Zo_qgztJE114JTdYcCVRlht5NUOoCvVKF-uXyXq4MvSzDITU-miavT_l0XDy_UeS-y1u7aUoTrRHPnAt_1iIPN9f33VtW9V1gyg94waSnYGSMRbEifE9wEwOXGkyopIW4A1Ih6AdBwDsj6yP9AeRsvuFWjsJIgDT-PqlneQYHhJaEDhW4hNDwQKAa4TH-1YwFi1IqhPiQtMrZHU4WpTWGy4k9-uP4MdlCxlJGeDHunZB6MZ3DKdnU78V4Nj1zH8QXPhm1JQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA46BfWizonf5uC1atM2aY_1YyjWMnCit5Elb3SincxO8OJv903WzQl68NTSL0La9Hme95OQA18jykFgPK4BBUrsc09yE3mSdVXMTZwo5bqWZCLP4_v7pFUlq7tcGABwwWdwaHedL1_31dCaynCFR7ZmFJ8lc7Z1VpWuNTGp4FkmKjR7cnYjjvw8qAr6-GF0FDC7-MPD0Zb_6KjiAKW5_M-hrJDGd2oebU1AZ5XMQFEny-PeDLRaqnWyNFVocI18pgXNvTv5QZ2tiU69FJpOuRKoLDS9eUWxC_RMlvKXy7O-1PTEBkQqfDRNnx_6g175-EKR_Y5vPc1zmiqFiOac-G8Ncts8b59eeFXnBU8GISs94Uvoam1QrvDA50wnwIQCHUlhIDkGIRH2wzBkx10TIAECZG2BZkZ0o5iD0ME6qRX9AjYItZQONbiASLOQox5hCf7XtAGDYiqCZJM07Ox2XkfFNTrjid364_g-WbhoX2ed7DK_2iaLyF9svJfH_B1SKwdD2CXz6r3svQ323MfxBdu4uG4
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=proceeding&rft.title=2019+24th+Asia+and+South+Pacific+Design+Automation+Conference+%28ASP-DAC%29&rft.atitle=An+N-Way+Group+Association+Architecture+and+Sparse+Data+Group+Association+Load+Balancing+Algorithm+for+Sparse+CNN+Accelerators&rft.au=Wang%2C+Jingyu&rft.au=Yuan%2C+Zhe&rft.au=Liu%2C+Ruoyang&rft.au=Yang%2C+Huazhong&rft.date=2019-01-21&rft.pub=ACM&rft.eissn=2153-697X&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1145%2F3287624.3287626&rft.externalDocID=10500556