본문

서브메뉴

High-Performance Process-in-Memory Architectures Design and Security Analysis
High-Performance Process-in-Memory Architectures Design and Security Analysis
High-Performance Process-in-Memory Architectures Design and Security Analysis

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152100
ISBN  
9798382739557
DDC  
621.3
저자명  
Wang, Ziyu.
서명/저자  
High-Performance Process-in-Memory Architectures Design and Security Analysis
발행사항  
[Sl] : University of Michigan, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
158 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Lu, Wei.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2024.
초록/해제  
요약The performance of processor-centric von Neumann architectures is greatly hindered by data movement between memory and processor, especially when encountering data-intensive tasks. Memory-centric process-in-memory (PIM) architectures perform computations directly within the memory modules. Hence, the performance and energy penalty associated with data access can be mitigated by minimizing data movement and leveraging high internal bandwidth. In addition to the benefits in performance and energy efficiency, PIM architectures facilitate extensive computing parallelism and scalability, while also provide enhanced security resilience against bus-snoop attacks. PIM architectures have shown their capability in many machine learning applications. Nonetheless, effectively accommodating ultra-large deep neural network (DNN) models, like Transformer, remains an ongoing challenge, and with the continued adoption of PIM architectures, security and vulnerability issues are poised to become looming threats. This dissertation focuses on high-performance PIM architecture design for data-intensive applications. To facilitate PIM architecture design and security studies, the dissertation first proposes event-driven, cycle-accurate simulators and their implementations for PIM architectures based on dynamic random-access memory (DRAM) and resistive random-access memory (RRAM), along with how these simulators can be used for architecture design. The PIM-GPT architecture is then introduced, which offers high performance, high energy efficiency and end-to-end acceleration of GPT inference. PIM-GPT leverages DRAM-based PIM solutions to perform multiply-accumulate (MAC) operations on the DRAM chips, working together with an application-specific integrated chip (ASIC) which supports data communication and other necessary arithmetic computations. At the software level, the mapping scheme is designed to maximize data locality and computation parallelism by partitioning a matrix among DRAM channels and banks to utilize all in-bank computation resources concurrently. Overall, PIM-GPT achieves 41-137x, 631-1074x speedup and 123-383x and 320-602x energy efficiency over GPU and CPU baseline, respectively, on 8 GPT models. Two security and vulnerability investigations are then conducted on RRAM-based analog PIM architectures. These studies employ a dynamic power trace modeling approach at runtime, enabling efficient power and timing side-channel analysis. The susceptibility of PIM architectures to side-channel attacks is analysed. And the study reveals the possibility of extracting complete DNN model architectural information solely from power trace measurements, without prior DNN knowledge. Furthermore, another potential security vulnerability is identified, wherein an adversary can reconstruct a user's private input data through a power side-channel attack, given proper data acquisition and pre-processing. The study employs a machine learning-based attack approach utilizing a generative adversarial network (GAN) to enhance data reconstruction. Notably, these findings illustrate the effectiveness of specific attack methodologies in extracting DNN model structures and user inputs from analog PIM accelerator power leakage, even in the presence of substantial noise levels. Countermeasures against these side-channel attacks are also discussed. In light of these security challenges, there is a growing demand for hardware secure systems capable of providing robust solutions for identification, authentication, and protection against counterfeiting and unauthorized modifications. Physical unclonable functions (PUFs) emerge as a valuable technique for hardware root-of-trust. A PUF system built upon fingerprint-like random planar structures is developed, demonstrating compatibility with the back-end-of-line (BEOL) process and presenting promising potential as a hardware security primitive in the IoT industry. In the end, guiding principles and proposals for future work are deliberated, focusing on three key aspects: 1) hardware modeling and simulation of emerging PIM architectures; 2) hardware/software co-optimization for Transformer models; and 3) security and vulnerabilities in neuromorphic computing systems.
일반주제명  
Computer engineering
일반주제명  
Electrical engineering
키워드  
Process-in-memory
키워드  
Machine learning accelerator
키워드  
Side-channel attack
키워드  
Hardware security
키워드  
Dynamic random-access memory
키워드  
Resistive random-access memory
기타저자  
University of Michigan Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162830
■00520250211152100
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382739557
■035    ▼a(MiAaPQ)AAI31349015
■035    ▼a(MiAaPQ)umichrackham005562
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aWang,  Ziyu.
■24510▼aHigh-Performance  Process-in-Memory  Architectures  Design  and  Security  Analysis
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a158  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Lu,  Wei.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aThe  performance  of  processor-centric  von  Neumann  architectures  is  greatly  hindered  by  data  movement  between  memory  and  processor,  especially  when  encountering  data-intensive  tasks.  Memory-centric  process-in-memory  (PIM)  architectures  perform  computations  directly  within  the  memory  modules.  Hence,  the  performance  and  energy  penalty  associated  with  data  access  can  be  mitigated  by  minimizing  data  movement  and  leveraging  high  internal  bandwidth.  In  addition  to  the  benefits  in  performance  and  energy  efficiency,  PIM  architectures  facilitate  extensive  computing  parallelism  and  scalability,  while  also  provide  enhanced  security  resilience  against  bus-snoop  attacks.  PIM  architectures  have  shown  their  capability  in  many  machine  learning  applications.  Nonetheless,  effectively  accommodating  ultra-large  deep  neural  network  (DNN)  models,  like  Transformer,  remains  an  ongoing  challenge,  and  with  the  continued  adoption  of  PIM  architectures,  security  and  vulnerability  issues  are  poised  to  become  looming  threats.  This  dissertation  focuses  on  high-performance  PIM  architecture  design  for  data-intensive  applications.  To  facilitate  PIM  architecture  design  and  security  studies,  the  dissertation  first  proposes  event-driven,  cycle-accurate  simulators  and  their  implementations  for  PIM  architectures  based  on  dynamic  random-access  memory  (DRAM)  and  resistive  random-access  memory  (RRAM),  along  with  how  these  simulators  can  be  used  for  architecture  design.  The  PIM-GPT  architecture  is  then  introduced,  which  offers  high  performance,  high  energy  efficiency  and  end-to-end  acceleration  of  GPT  inference.  PIM-GPT  leverages  DRAM-based  PIM  solutions  to  perform  multiply-accumulate  (MAC)  operations  on  the  DRAM  chips,  working  together  with  an  application-specific  integrated  chip  (ASIC)  which  supports  data  communication  and  other  necessary  arithmetic  computations.  At  the  software  level,  the  mapping  scheme  is  designed  to  maximize  data  locality  and  computation  parallelism  by  partitioning  a  matrix  among  DRAM  channels  and  banks  to  utilize  all  in-bank  computation  resources  concurrently.    Overall,  PIM-GPT  achieves  41-137x,  631-1074x  speedup  and  123-383x  and  320-602x  energy  efficiency  over  GPU  and  CPU  baseline,  respectively,  on  8  GPT  models.  Two  security  and  vulnerability  investigations  are  then  conducted  on  RRAM-based  analog  PIM  architectures.  These  studies  employ  a  dynamic  power  trace  modeling  approach  at  runtime,  enabling  efficient  power  and  timing  side-channel  analysis.  The  susceptibility  of  PIM  architectures  to  side-channel  attacks  is  analysed.  And  the  study  reveals  the  possibility  of  extracting  complete  DNN  model  architectural  information  solely  from  power  trace  measurements,  without  prior  DNN  knowledge.  Furthermore,  another  potential  security  vulnerability  is  identified,  wherein  an  adversary  can  reconstruct  a  user's  private  input  data  through  a  power  side-channel  attack,  given  proper  data  acquisition  and  pre-processing.  The  study  employs  a  machine  learning-based  attack  approach  utilizing  a  generative  adversarial  network  (GAN)  to  enhance  data  reconstruction.  Notably,  these  findings  illustrate  the  effectiveness  of  specific  attack  methodologies  in  extracting  DNN  model  structures  and  user  inputs  from  analog  PIM  accelerator  power  leakage,  even  in  the  presence  of  substantial  noise  levels.  Countermeasures  against  these  side-channel  attacks  are  also  discussed.  In  light  of  these  security  challenges,  there  is  a  growing  demand  for  hardware  secure  systems  capable  of  providing  robust  solutions  for  identification,  authentication,  and  protection  against  counterfeiting  and  unauthorized  modifications.  Physical  unclonable  functions  (PUFs)  emerge  as  a  valuable  technique  for  hardware  root-of-trust.  A  PUF  system  built  upon  fingerprint-like  random  planar  structures  is  developed,  demonstrating  compatibility  with  the  back-end-of-line  (BEOL)  process  and  presenting  promising  potential  as  a  hardware  security  primitive  in  the  IoT  industry.  In  the  end,  guiding  principles  and  proposals  for  future  work  are  deliberated,  focusing  on  three  key  aspects:  1)  hardware  modeling  and  simulation  of  emerging  PIM  architectures;  2)  hardware/software  co-optimization  for  Transformer  models;  and  3)  security  and  vulnerabilities  in  neuromorphic  computing  systems.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  engineering
■650  4▼aElectrical  engineering
■653    ▼aProcess-in-memory
■653    ▼aMachine  learning  accelerator
■653    ▼aSide-channel  attack
■653    ▼aHardware  security
■653    ▼aDynamic  random-access  memory
■653    ▼aResistive  random-access  memory
■690    ▼a0544
■690    ▼a0464
■71020▼aUniversity  of  Michigan▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162830▼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
    TF10457 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.