서브메뉴
검색
Applications of Machine Learning and Optimization Techniques to Solve Modern Data Movement Challenges
Applications of Machine Learning and Optimization Techniques to Solve Modern Data Movement Challenges
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104854
- ISBN
- 9798288816901
- DDC
- 620
- 서명/저자
- Applications of Machine Learning and Optimization Techniques to Solve Modern Data Movement Challenges
- 발행사항
- [Sl] : Stanford University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 129 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
- 주기사항
- Advisor: Horowitz, Mark.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2025.
- 초록/해제
- 요약Artificial-intelligence (AI) models are growing rapidly, moving the primary system bottleneck from core compute to the high-speed links that transfer data among accelerators, memory, and processors. As data rates climb, frequency-dependent loss, crosstalk, and supply noise become more formidable, yet the I/O power budget must stay tight so as not to encroach on compute resources. Furthermore, because these impairments drift with temperature and workloads, transceivers must periodically readjust their settings. We tackle this problem by combining formal optimization with lightweight machine-learning techniques. First, we propose a generalized decision-feedback equalizer that employs multiple slicer levels and a programmable look-up table, treating inter-symbol interference and crosstalk as observable noise sources. Finding the optimal slicer levels and table entries is a discrete optimization problem solved by integer-linear programming (ILP) methods. However, ILP is too memory-intensive for on-line use. Instead, we train a compact convolutional neural network supervised by ILP-derived solutions and deploy it on a 1GHz RISC-V microcontroller, where a forward pass runs in under 5ms and cuts memory demand from gigabytes to kilobytes. As a complementary measure, we explore constrained coding to mitigate link impairments. Encoder and decoder synthesis is first framed as a satisfiability-modulo-theories (SMT) problem, reducing solution time from months to days for codes up to eight bits. To scale further, we recast the codeword assignment problem as a bipartite-matching task and solve it with a reinforcement-learning agent. This approach handles codes up to ten bits and discovers assignments that minimize gate count, keeping the I/O footprint small and preserving silicon area for compute. Together, these contributions increase link performance without adversely increasing power and area requirements, charting a practical path toward faster and more energy-efficient data movement in next-generation AI systems.
- 일반주제명
- Silicon
- 일반주제명
- Transmitters
- 일반주제명
- Photonics
- 일반주제명
- Codes
- 일반주제명
- Optimization techniques
- 일반주제명
- Parameter estimation
- 일반주제명
- Computer engineering
- 일반주제명
- Electrical engineering
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 87-02B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359239
■00520260202104854
■006m o d
■007cr#unu||||||||
■020 ▼a9798288816901
■035 ▼a(MiAaPQ)AAI32200991
■035 ▼a(MiAaPQ)Stanfordsg461wr4702
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a620
■1001 ▼aSudhakaran, Sunil.
■24510▼aApplications of Machine Learning and Optimization Techniques to Solve Modern Data Movement Challenges
■260 ▼a[Sl]▼bStanford University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a129 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-02, Section: B.
■500 ▼aAdvisor: Horowitz, Mark.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2025.
■520 ▼aArtificial-intelligence (AI) models are growing rapidly, moving the primary system bottleneck from core compute to the high-speed links that transfer data among accelerators, memory, and processors. As data rates climb, frequency-dependent loss, crosstalk, and supply noise become more formidable, yet the I/O power budget must stay tight so as not to encroach on compute resources. Furthermore, because these impairments drift with temperature and workloads, transceivers must periodically readjust their settings. We tackle this problem by combining formal optimization with lightweight machine-learning techniques. First, we propose a generalized decision-feedback equalizer that employs multiple slicer levels and a programmable look-up table, treating inter-symbol interference and crosstalk as observable noise sources. Finding the optimal slicer levels and table entries is a discrete optimization problem solved by integer-linear programming (ILP) methods. However, ILP is too memory-intensive for on-line use. Instead, we train a compact convolutional neural network supervised by ILP-derived solutions and deploy it on a 1GHz RISC-V microcontroller, where a forward pass runs in under 5ms and cuts memory demand from gigabytes to kilobytes. As a complementary measure, we explore constrained coding to mitigate link impairments. Encoder and decoder synthesis is first framed as a satisfiability-modulo-theories (SMT) problem, reducing solution time from months to days for codes up to eight bits. To scale further, we recast the codeword assignment problem as a bipartite-matching task and solve it with a reinforcement-learning agent. This approach handles codes up to ten bits and discovers assignments that minimize gate count, keeping the I/O footprint small and preserving silicon area for compute. Together, these contributions increase link performance without adversely increasing power and area requirements, charting a practical path toward faster and more energy-efficient data movement in next-generation AI systems.
■590 ▼aSchool code: 0212.
■650 4▼aSilicon
■650 4▼aTransmitters
■650 4▼aPhotonics
■650 4▼aCodes
■650 4▼aOptimization techniques
■650 4▼aParameter estimation
■650 4▼aComputer engineering
■650 4▼aElectrical engineering
■653 ▼aMachine-learning techniques
■653 ▼aInteger-linear programming methods
■653 ▼aEncoder and decoder synthesis
■690 ▼a0544
■690 ▼a0464
■690 ▼a0800
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g87-02B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359239▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


