본문

서브메뉴

Efficient and Robust Compute-In-Memory for Edge Intelligence
Efficient and Robust Compute-In-Memory for Edge Intelligence
Efficient and Robust Compute-In-Memory for Edge Intelligence

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105546
ISBN  
9798263394028
DDC  
006
저자명  
Li, Wantong.
서명/저자  
Efficient and Robust Compute-In-Memory for Edge Intelligence
발행사항  
[Sl] : Georgia Institute of Technology, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
128 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
주기사항  
Advisor: Yu, Shimeng.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2024.
초록/해제  
요약With deep neural networks (DNNs) fueling major advancements in artificial intelligence (AI), the demand for efficient computing solutions has never been higher. This dissertation delves into the challenges and innovations in the field of compute-in-memory (CIM) technologies, a key area for advancing sustainable computing to address the growing carbon footprint associated with intensive AI workloads. CIM is an emerging computing paradigm aimed at processing data within memory arrays where data is stored, promising significant gains in energy efficiency and computational speed. This dissertation focuses on building efficient, robust, and heterogeneous CIM solutions for edge intelligence. The dissertation first presents the prototype chip development of CIM primitives as AI inference engine, demonstrating the feasibility of analog computations within resistive random-access memory (RRAM). Additional design challenges are addressed through novel circuit-level design techniques including lightweight on-chip write-verify, in-situ error correction, temperature-tracking references, and embedded model encryption. Exploring beyond traditional scaling methods, the dissertation next proposes vertically stacking silicon dies into a heterogeneous 3-D (H3D) system for the flexibility to combine different process nodes and high-bandwidth data transmission. A H3D integrated accelerator is designed to target vision transformer models through a hybrid analog and digital CIM approach. Thorough thermal and signaling evaluations are conducted to understand the trade-offs of die stacking. Finally, domain-specific CIM architectures for edge computing are investigated, focusing on integrating CIM hardware with sensor frontends for intelligent data volume reduction. An algorithm/hardware co-design approach is proposed to reduce power consumption of portable medical ultrasound imaging and to improve communication bandwidth for autonomous driving, showcasing the potential of CIM to efficiently insert local intelligence in diverse applications.
일반주제명  
Deep learning
일반주제명  
Semiconductors
일반주제명  
Bandwidths
일반주제명  
Data processing
일반주제명  
CMOS
일반주제명  
Carbon footprint
일반주제명  
Co-design
일반주제명  
Field programmable gate arrays
일반주제명  
Design techniques
일반주제명  
Integrated circuits
일반주제명  
Error correction & detection
일반주제명  
Neural networks
일반주제명  
Multiplication & division
일반주제명  
Energy efficiency
일반주제명  
Data transmission
일반주제명  
Ultrasonic imaging
일반주제명  
Computer science
일반주제명  
Electrical engineering
일반주제명  
Mathematics
일반주제명  
Medical imaging
일반주제명  
Sustainability
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017360554
■00520260202105546
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263394028
■035    ▼a(MiAaPQ)AAI32315576
■035    ▼a(MiAaPQ)GeorgiaTech75620
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a006
■1001  ▼aLi,  Wantong.
■24510▼aEfficient  and  Robust  Compute-In-Memory  for  Edge  Intelligence
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a128  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  A.
■500    ▼aAdvisor:  Yu,  Shimeng.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2024.
■520    ▼aWith  deep  neural  networks  (DNNs)  fueling  major  advancements  in  artificial  intelligence  (AI),  the  demand  for  efficient  computing  solutions  has  never  been  higher.  This  dissertation  delves  into  the  challenges  and  innovations  in  the  field  of  compute-in-memory  (CIM)  technologies,  a  key  area  for  advancing  sustainable  computing  to  address  the  growing  carbon  footprint  associated  with  intensive  AI  workloads.  CIM  is  an  emerging  computing  paradigm  aimed  at  processing  data  within  memory  arrays  where  data  is  stored,  promising  significant  gains  in  energy  efficiency  and  computational  speed.  This  dissertation  focuses  on  building  efficient,  robust,  and  heterogeneous  CIM  solutions  for  edge  intelligence.  The  dissertation  first  presents  the  prototype  chip  development  of  CIM  primitives  as  AI  inference  engine,  demonstrating  the  feasibility  of  analog  computations  within  resistive  random-access  memory  (RRAM).  Additional  design  challenges  are  addressed  through  novel  circuit-level  design  techniques  including  lightweight  on-chip  write-verify,  in-situ  error  correction,  temperature-tracking  references,  and  embedded  model  encryption.  Exploring  beyond  traditional  scaling  methods,  the  dissertation  next  proposes  vertically  stacking  silicon  dies  into  a  heterogeneous  3-D  (H3D)  system  for  the  flexibility  to  combine  different  process  nodes  and  high-bandwidth  data  transmission.  A  H3D  integrated  accelerator  is  designed  to  target  vision  transformer  models  through  a  hybrid  analog  and  digital  CIM  approach.  Thorough  thermal  and  signaling  evaluations  are  conducted  to  understand  the  trade-offs  of  die  stacking.  Finally,  domain-specific  CIM  architectures  for  edge  computing  are  investigated,  focusing  on  integrating  CIM  hardware  with  sensor  frontends  for  intelligent  data  volume  reduction.  An  algorithm/hardware  co-design  approach  is  proposed  to  reduce  power  consumption  of  portable  medical  ultrasound  imaging  and  to  improve  communication  bandwidth  for  autonomous  driving,  showcasing  the  potential  of  CIM  to  efficiently  insert  local  intelligence  in  diverse  applications.
■590    ▼aSchool  code:  0078.
■650  4▼aDeep  learning
■650  4▼aSemiconductors
■650  4▼aBandwidths
■650  4▼aData  processing
■650  4▼aCMOS
■650  4▼aCarbon  footprint
■650  4▼aCo-design
■650  4▼aField  programmable  gate  arrays
■650  4▼aDesign  techniques
■650  4▼aIntegrated  circuits
■650  4▼aError  correction  &  detection
■650  4▼aNeural  networks
■650  4▼aMultiplication  &  division
■650  4▼aEnergy  efficiency
■650  4▼aData  transmission
■650  4▼aUltrasonic  imaging
■650  4▼aComputer  science
■650  4▼aElectrical  engineering
■650  4▼aMathematics
■650  4▼aMedical  imaging
■650  4▼aSustainability
■690    ▼a0800
■690    ▼a0984
■690    ▼a0544
■690    ▼a0405
■690    ▼a0574
■690    ▼a0640
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05A.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360554▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF14937 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.