RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs

Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resource-constrained (e.g., computation, I/O, and memory-bound) edge computing systems. While efficient execution of their comp...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2023 60th ACM/IEEE Design Automation Conference (DAC) s. 1 - 6
Hlavní autori: Yin, Jiaqi, Li, Yingjie, Robinson, Daniel, Yu, Cunxi
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 09.07.2023
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resource-constrained (e.g., computation, I/O, and memory-bound) edge computing systems. While efficient execution of their computational graph requires an effective scheduling algorithm, generating the optimal scheduling solution is a challenging NP-hard problem. Furthermore, the complexity of scheduling DNN computational graphs will further increase on pipelined multi-core systems considering memory communication cost, as well as the increasing size of DNNs. Using the synthetic graph for the training dataset, this work presents a reinforcement learning (RL) based scheduling framework RESPECT, which learns the behaviors of optimal optimization algorithms and generates near-optimal scheduling results with short solving runtime overhead. Our framework has demonstrated up to ∼ 2.5 × real-world on-chip inference runtime speedups over the commercial compiler with ten popular ImageNet models deployed on the physical Coral Edge TPUs system. Moreover, compared to the exact optimization methods, the proposed RL scheduling improves the scheduling optimization runtime by up to 683× speedups compared to the commercial compiler and matches the exact optimal solutions with up to 930× speedups. Finally, we perform a comprehensive generalizability test, which demonstrates RESPECT successfully imitates optimal solving behaviors from small synthetic graphs to large real-world DNNs computational graphs.
AbstractList Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resource-constrained (e.g., computation, I/O, and memory-bound) edge computing systems. While efficient execution of their computational graph requires an effective scheduling algorithm, generating the optimal scheduling solution is a challenging NP-hard problem. Furthermore, the complexity of scheduling DNN computational graphs will further increase on pipelined multi-core systems considering memory communication cost, as well as the increasing size of DNNs. Using the synthetic graph for the training dataset, this work presents a reinforcement learning (RL) based scheduling framework RESPECT, which learns the behaviors of optimal optimization algorithms and generates near-optimal scheduling results with short solving runtime overhead. Our framework has demonstrated up to ∼ 2.5 × real-world on-chip inference runtime speedups over the commercial compiler with ten popular ImageNet models deployed on the physical Coral Edge TPUs system. Moreover, compared to the exact optimization methods, the proposed RL scheduling improves the scheduling optimization runtime by up to 683× speedups compared to the commercial compiler and matches the exact optimal solutions with up to 930× speedups. Finally, we perform a comprehensive generalizability test, which demonstrates RESPECT successfully imitates optimal solving behaviors from small synthetic graphs to large real-world DNNs computational graphs.
Author Robinson, Daniel
Yin, Jiaqi
Yu, Cunxi
Li, Yingjie
Author_xml – sequence: 1
  givenname: Jiaqi
  surname: Yin
  fullname: Yin, Jiaqi
  email: jiaqi.yin@utah.edu
  organization: University of Utah,Salt Lake City,US
– sequence: 2
  givenname: Yingjie
  surname: Li
  fullname: Li, Yingjie
  email: yingjie.li@utah.edu
  organization: University of Utah,Salt Lake City,US
– sequence: 3
  givenname: Daniel
  surname: Robinson
  fullname: Robinson, Daniel
  email: u0714849@umail.utah.edu
  organization: University of Utah,Salt Lake City,US
– sequence: 4
  givenname: Cunxi
  surname: Yu
  fullname: Yu, Cunxi
  email: cunxi.yu@utah.edu
  organization: University of Utah,Salt Lake City,US
BookMark eNo1T9tKw0AUXEFBrfkDkfxA4t4vvpUYLxAwpOlz2d2c1IV0U5L64N8bqT7NMDMMM7foMo4REHogOCcEm8fndSGkoSanmLKcYMqVwvICJUYZzQRmlHFNrlEyz8FhiYXmWPIb1DTlpi6L9iltIMR-nDwcIJ7SCuwUQ9ynzs7QpWW3h3TjP6H7Gn7VMaZ1OMLCF7MYJzucI229ne_QVW-HGZI_XKHtS9kWb1n18fperKvMUoNPmV9mc0-16I3hxnnbmR4bbSwnVAglJPeOYAW91JJ0vJOEEiaUVk5Z57lgK3R_7g0AsDtO4WCn793_dfYDt4JPNw
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC56929.2023.10247706
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 9798350323481
EndPage 6
ExternalDocumentID 10247706
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IH
ACM
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a290t-c1094c285f9949bcad9f0989a412557564cb107ef6861d4d612135787b7abc453
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001073487300041&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 02:51:00 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a290t-c1094c285f9949bcad9f0989a412557564cb107ef6861d4d612135787b7abc453
PageCount 6
ParticipantIDs ieee_primary_10247706
PublicationCentury 2000
PublicationDate 2023-July-9
PublicationDateYYYYMMDD 2023-07-09
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-July-9
  day: 09
PublicationDecade 2020
PublicationTitle 2023 60th ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib060584064
Score 2.2723522
Snippet Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Image edge detection
Optimal scheduling
Optimization methods
Processor scheduling
Reinforcement learning
Runtime
Training
Title RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs
URI https://ieeexplore.ieee.org/document/10247706
WOSCitedRecordID wos001073487300041&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/eLvHCXMwlV07T8MwELagYmACRBFveWB1SdKLnWNDoRUDqqLSSt2q-JGqS1r1we-vz01BDAxslh3Lyl2s72Lf9x1jT0qDLrWxAqUDAdqA0JjFwodG1gfsUZq4IJn_oQaDbDLBoiGrBy6Mcy4kn7kONcNdvl2YLR2V-R2egFIksH2slNyTtQ4fD13veXCChgUcR_j89pqn0sN_h0qEdw6Tf5VRCSjSP_vn-ues_cPH48U30lywI1dfsqG3XdHLRy986IL8qQknfbxRTJ1xAijLe3bm-Kd3jaWc8xlf1LyYL4mF7gdz4ufvHxkV43Wbjfu9Uf4umgoJokww2gjjXxNMkqUVIqA2pcUqwgxL8HGLD8QkGO3_71wlMxlbsCQXRvI2SivvIEi7V6xVL2p3zThCZrpAwsWoqRyx1kZ2KxlZSNHFTt6wNhlkutyLYEwPtrj9o_-OnZLZQ2Yr3rPWZrV1D-zEfG3m69VjcN0OWsaXZw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT4NAEN2YaqInNdb47R68UoEOC-PNYJsaa0MqTXpr2A-aXmjTD3-_O1uq8eDBGwE2gRk289id9x5jD7EEWUilPRQGPJAKPIlJ4FlopC1g96PQOMn8fjwYJOMxZjVZ3XFhjDGu-cy06NDt5eu52tBSmZ3hIcQxCWzvk3VWTdfafT60wWfLE9Q84MDHx5fnNBIWALTIJLy1G_7LSMXVke7xP5_ghDV_GHk8-641p2zPVGdsaKOXddL8iQ-NE0BVbq2P15qpU04lSvOOnhr-YZOjqet8yucVz2YL4qHbiykx9Le35Nlo1WSjbidPe17tkeAVIfprT9nXBBUmUYkIKFWhsfQxwQIscrFQTICS9g_PlCIRgQZNgmEkcBPL2KYIovY5a1TzylwwjpCoNpB0MUoyJJZSiXYpfA0RmsCIS9akgEwWWxmMyS4WV3-cv2eHvfy9P-m_Dt6u2RGlwPW54g1rrJcbc8sO1Od6tlreuTR-AXMQmrA
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=2023+60th+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=RESPECT%3A+Reinforcement+Learning+based+Edge+Scheduling+on+Pipelined+Coral+Edge+TPUs&rft.au=Yin%2C+Jiaqi&rft.au=Li%2C+Yingjie&rft.au=Robinson%2C+Daniel&rft.au=Yu%2C+Cunxi&rft.date=2023-07-09&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FDAC56929.2023.10247706&rft.externalDocID=10247706