서브메뉴
검색
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
- Design techniques
- 일반주제명
- Integrated circuits
- 일반주제명
- Neural networks
- 일반주제명
- Energy efficiency
- 일반주제명
- Data transmission
- 일반주제명
- Ultrasonic imaging
- 일반주제명
- Computer science
- 일반주제명
- Electrical engineering
- 일반주제명
- Mathematics
- 일반주제명
- Medical imaging
- 일반주제명
- Sustainability
- 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.


