A Tale of Two Domains: Exploring Efficient Architecture Design for Truly Autonomous Things

Autonomous Things (AuT) refers to a collection of self-sufficient tiny devices capable of performing intelligent computations. Looking ahead, AuT promises to enable ubiquitous deployment of intelligence on many emerging consumer electronics and mission-critical infrastructures. Nevertheless, there i...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA) s. 167 - 181
Hlavní autoři: Hou, Xiaofeng, Xu, Tongqiao, Li, Chao, Xu, Cheng, Liu, Jiacheng, Hu, Yang, Zhao, Jieru, Leng, Jingwen, Cheng, Kwang-Ting, Guo, Minyi
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 29.06.2024
Témata:
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Autonomous Things (AuT) refers to a collection of self-sufficient tiny devices capable of performing intelligent computations. Looking ahead, AuT promises to enable ubiquitous deployment of intelligence on many emerging consumer electronics and mission-critical infrastructures. Nevertheless, there is an important research gap to date: architecting efficient AuT systems requires both energy autonomy (EA) and inference autonomy (IA). In other words, practical AuT application scenarios necessitate tailored architectures with significantly expanded inference performance and more efficient use of energy.We present CHRYSALIS, a novel automated EA/IA co-design methodology for autonomous things. It aims to guide the transition from a traditional EA-only and IA-only design approach to a truly AuT-oriented architecture design. To fully understand the interrelationship between the EA domain and the IA domain, CHRYSALIS first introduces an architectural modeling framework encompassing every key AuT module involving energy harvesting, intermittent execution, and accelerator control. Based on the holistic system model, we design an intelligent architecture generation tool that can help find the ideal design for targeted AuT scenarios adhering to different SWaP (Size, Weight and Power) constraints. To validate our work, we use CHRYSALIS for fast construction and exploration of efficient AuT design and pre-RTL design in representative AuT scenarios. Extensive evaluation shows that CHRYSALIS outperforms state-of-the-art designs and our proposed technique shows 56.4% better performance on average. We believe that the methodology and tools developed in this paper will foster the development of more performant and practical architectures in the upcoming AuT era.
AbstractList Autonomous Things (AuT) refers to a collection of self-sufficient tiny devices capable of performing intelligent computations. Looking ahead, AuT promises to enable ubiquitous deployment of intelligence on many emerging consumer electronics and mission-critical infrastructures. Nevertheless, there is an important research gap to date: architecting efficient AuT systems requires both energy autonomy (EA) and inference autonomy (IA). In other words, practical AuT application scenarios necessitate tailored architectures with significantly expanded inference performance and more efficient use of energy.We present CHRYSALIS, a novel automated EA/IA co-design methodology for autonomous things. It aims to guide the transition from a traditional EA-only and IA-only design approach to a truly AuT-oriented architecture design. To fully understand the interrelationship between the EA domain and the IA domain, CHRYSALIS first introduces an architectural modeling framework encompassing every key AuT module involving energy harvesting, intermittent execution, and accelerator control. Based on the holistic system model, we design an intelligent architecture generation tool that can help find the ideal design for targeted AuT scenarios adhering to different SWaP (Size, Weight and Power) constraints. To validate our work, we use CHRYSALIS for fast construction and exploration of efficient AuT design and pre-RTL design in representative AuT scenarios. Extensive evaluation shows that CHRYSALIS outperforms state-of-the-art designs and our proposed technique shows 56.4% better performance on average. We believe that the methodology and tools developed in this paper will foster the development of more performant and practical architectures in the upcoming AuT era.
Author Hou, Xiaofeng
Xu, Tongqiao
Xu, Cheng
Liu, Jiacheng
Zhao, Jieru
Cheng, Kwang-Ting
Li, Chao
Leng, Jingwen
Hu, Yang
Guo, Minyi
Author_xml – sequence: 1
  givenname: Xiaofeng
  surname: Hou
  fullname: Hou, Xiaofeng
  email: hou-xf@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 2
  givenname: Tongqiao
  surname: Xu
  fullname: Xu, Tongqiao
  email: tqxu23@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 3
  givenname: Chao
  surname: Li
  fullname: Li, Chao
  email: lichao@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 4
  givenname: Cheng
  surname: Xu
  fullname: Xu, Cheng
  email: jerryxu@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 5
  givenname: Jiacheng
  surname: Liu
  fullname: Liu, Jiacheng
  email: jcliu@cse.cuhk.edu.hk
  organization: CUHK,Hong Kong,China
– sequence: 6
  givenname: Yang
  surname: Hu
  fullname: Hu, Yang
  email: hu_yang@tsinghua.edu.cn
  organization: Tsinghua University,Beijing,China
– sequence: 7
  givenname: Jieru
  surname: Zhao
  fullname: Zhao, Jieru
  email: zhao-jieru@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 8
  givenname: Jingwen
  surname: Leng
  fullname: Leng, Jingwen
  email: leng-jw@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
– sequence: 9
  givenname: Kwang-Ting
  surname: Cheng
  fullname: Cheng, Kwang-Ting
  email: timcheng@ust.hk
  organization: HKUST,Hong Kong,China
– sequence: 10
  givenname: Minyi
  surname: Guo
  fullname: Guo, Minyi
  email: guo-my@cs.sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Shanghai,China
BookMark eNotj09LwzAcQCMoqHPfYId8gc5fkyZpvJVtzsHAg_XiZaT5swXaZCQtum-vqKd3eg_ePboOMViEFiUsyxLk4-5t1TAJQiwJkGoJAIRcobkUsqYMKOGsLm_RPGffAQcpqKjZHfpocKt6i6PD7WfE6zgoH_IT3nyd-5h8OOKNc157G0bcJH3yo9XjlCxe2-yPAbuYcJum_oKbaYwhDnHKuD39iPkB3TjVZzv_5wy9P2_a1Uuxf93uVs2-UITVY-GMEkTUhlam4lRqR7QTVkBV1qBYRzpFpHGmY1woWXUV1Z3kxEqjreFKczpDi7-ut9YezskPKl0O5e8kCPoNdg1U7w
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ISCA59077.2024.00022
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350326581
EndPage 181
ExternalDocumentID 10609707
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IH
ACM
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a258t-fda7278d34d4639cf2cf7e704180a5b2ba29dfdb567a94b43cb962e9dced6ac63
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001290320700012&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 02:34:55 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a258t-fda7278d34d4639cf2cf7e704180a5b2ba29dfdb567a94b43cb962e9dced6ac63
PageCount 15
ParticipantIDs ieee_primary_10609707
PublicationCentury 2000
PublicationDate 2024-June-29
PublicationDateYYYYMMDD 2024-06-29
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-June-29
  day: 29
PublicationDecade 2020
PublicationTitle 2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)
PublicationTitleAbbrev ISCA
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib060973785
Score 2.274468
Snippet Autonomous Things (AuT) refers to a collection of self-sufficient tiny devices capable of performing intelligent computations. Looking ahead, AuT promises to...
SourceID ieee
SourceType Publisher
StartPage 167
SubjectTerms Accelerator
Autonomous Embedded Systems
Computer architecture
Deep Learning
Edge Artificial Intelligence
Energy efficiency
Industries
Intermittent Computing
Learning (artificial intelligence)
Mission critical systems
Performance evaluation
Technological innovation
Title A Tale of Two Domains: Exploring Efficient Architecture Design for Truly Autonomous Things
URI https://ieeexplore.ieee.org/document/10609707
WOSCitedRecordID wos001290320700012&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/eLvHCXMwlV1JSwMxFA5aPHhSseJODl6jmSyTxNvQBQUpBUcoXkomCwjakXZG8d-bpItePHgLSUjgZXsv733fA-CKUY0jxwvyTmHEcqyQZlmGuOXESUOU9oln9kGMRnIyUeMVWD1hYZxzKfjMXcdi8uXb2rTxqyyc8DCWiNjxbSHyJVhrvXliCxWSr-BxGVY394-9ggfjTwQzkESSbBxT5P5KopLekOHeP2ffB90fNB4cb96ZA7DlZofguYBluNth7WH5WcN-_RZM_MUt3MTUwUEihwhDwuKXswD2U8gGDLoqLOft6xcs2iYCG-p2AZdJPLvgaTgoe3dolScBacJlg7zVQQuRljLLgsJhPDFeOIFZJrHmFak0UdbbiudCK1YxaiqVE6escTbXJqdHoDOrZ-4YQE4JDxceJzYYWj4RRUmPQzciOLOenoBuFMz0fUmFMV3L5PSP-jOwG2UfY6uIOgedZt66C7BjPpqXxfwyLeA30CWcnA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA4yBT2pOPHbHLxW0zRpGm9lH2w4x8AKw8tI8wGCtrK1iv_eJOvmLh68hSQkkM_3Td7neQC4IZFAjuMlMJqjgMSIB4KEYUAVxTqRmAvjeWZHbDxOplM-acDqHgujtfbBZ_rWJf1fvipl7Z7K7A63bTGHHd920lkNXGu1fFxZxBLaAORCxO-GT52UWvePWUcQO5ps5ERyN2RU_C3S3_9n_weg_YvHg5P1TXMItnRxBF5SmNnTHZYGZl8l7Jbv1slf3MN1VB3seXoI2yRMN74LYNcHbUBrrcJsXr99w7SuHLShrBdwKePZBs_9XtYZBI1SQiAwTarAKGHtkERFRBFrckiDpWGaIRImSNAc5wJzZVROYyY4yUkkcx5jzZXUKhYyjo5BqygLfQIgjTC1Rx7FyrpaxlNFJQbZaphRokx0CtpuYGYfSzKM2WpMzv7Ivwa7g-xxNBsNxw_nYM_Ng4u0wvwCtKp5rS_BjvysXhfzKz-ZPyeun-U
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=2024+ACM%2FIEEE+51st+Annual+International+Symposium+on+Computer+Architecture+%28ISCA%29&rft.atitle=A+Tale+of+Two+Domains%3A+Exploring+Efficient+Architecture+Design+for+Truly+Autonomous+Things&rft.au=Hou%2C+Xiaofeng&rft.au=Xu%2C+Tongqiao&rft.au=Li%2C+Chao&rft.au=Xu%2C+Cheng&rft.date=2024-06-29&rft.pub=IEEE&rft.spage=167&rft.epage=181&rft_id=info:doi/10.1109%2FISCA59077.2024.00022&rft.externalDocID=10609707