본문

서브메뉴

Making Neural Network Models More Efficient- [electronic resource]
Making Neural Network Models More Efficient - [electronic resource]
Making Neural Network Models More Efficient- [electronic resource]

Detailed Information

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100445
ISBN  
9798379717254
DDC  
004
저자명  
Su, Yushan.
서명/저자  
Making Neural Network Models More Efficient - [electronic resource]
발행사항  
[S.l.]: : Princeton University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(94 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
주기사항  
Advisor: Li, Kai.
학위논문주기  
Thesis (Ph.D.)--Princeton University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Complex machine learning tasks typically require large neural network models. However, training and inference on neural models require substantial compute power and large memory foot-prints, and incur significant costs. My thesis studies methods to make neural networks efficient at a relatively low cost.First, we explore how to utilize CPU servers for training and inference. CPU servers are more readily available, have larger memories, and cost much less than GPUs or hardware accelerators. However, they are much less efficient for training and inference tasks. My thesis studies how to design efficient software kernels for sparse neural networks that allow unstructured pruning to achieve efficiency of training or inference . Our evaluation shows that our sparse kernels can achieve 6.4x-20.0x speedups for medium sparsities over the commonly used Intel MKL sparse library for CPUs and greatly reduce the performance gap with those for GPUs.Second, we study how to achieve high-throughput inference for large models. We propose PruMUX, a method to combine data multiplexing with model compression. We find that in most cases, PruMUX can achieve better throughput than using each approach alone for a given accuracy loss budget.Third, we study how to find best sets of parameters for PruMUX in order to make it practical. We propose Auto-PruMUX, which uses performance modeling based on a set of data points to predict multiplexing parameters for DataMUX and sparsity parameters for a given model compression technique. Our evaluation shows that Auto-PruMUX can successfully find or predict parameters to achieve the best throughput given an accuracy loss budget.This dissertation also proposes several future research directions in the areas of our studies.
일반주제명  
Computer science.
일반주제명  
Computer engineering.
키워드  
Neural network
키워드  
Compute power
키워드  
Hardware accelerators
키워드  
Multiplexing parameters
키워드  
Model compression
기타저자  
Princeton University Computer Science
기본자료저록  
Dissertations Abstracts International. 84-12B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016932338
■00520240214100445
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379717254
■035    ▼a(MiAaPQ)AAI30491635
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aSu,  Yushan.
■24510▼aMaking  Neural  Network  Models  More  Efficient▼h[electronic  resource]
■260    ▼a[S.l.]:▼bPrinceton  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(94  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  B.
■500    ▼aAdvisor:  Li,  Kai.
■5021  ▼aThesis  (Ph.D.)--Princeton  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aComplex  machine  learning  tasks  typically  require  large  neural  network  models.  However,  training  and  inference  on  neural  models  require  substantial  compute  power  and  large  memory  foot-prints,  and  incur  significant  costs.  My  thesis  studies  methods  to  make  neural  networks  efficient  at  a  relatively  low  cost.First,  we  explore  how  to  utilize  CPU  servers  for  training  and  inference.  CPU  servers  are  more  readily  available,  have  larger  memories,  and  cost  much  less  than  GPUs  or  hardware  accelerators.  However,  they  are  much  less  efficient  for  training  and  inference  tasks.  My  thesis  studies  how  to  design  efficient  software  kernels  for  sparse  neural  networks  that  allow  unstructured  pruning  to  achieve  efficiency  of  training  or  inference  .  Our  evaluation  shows  that  our  sparse  kernels  can  achieve  6.4x-20.0x  speedups  for  medium  sparsities  over  the  commonly  used  Intel  MKL  sparse  library  for  CPUs  and  greatly  reduce  the  performance  gap  with  those  for  GPUs.Second,  we  study  how  to  achieve  high-throughput  inference  for  large  models.  We  propose  PruMUX,  a  method  to  combine  data  multiplexing  with  model  compression.  We  find  that  in  most  cases,  PruMUX  can  achieve  better  throughput  than  using  each  approach  alone  for  a  given  accuracy  loss  budget.Third,  we  study  how  to  find  best  sets  of  parameters  for  PruMUX  in  order  to  make  it  practical.  We  propose  Auto-PruMUX,  which  uses  performance  modeling  based  on  a  set  of  data  points  to  predict  multiplexing  parameters  for  DataMUX  and  sparsity  parameters  for  a  given  model  compression  technique.  Our  evaluation  shows  that  Auto-PruMUX  can  successfully  find  or  predict  parameters  to  achieve  the  best  throughput  given  an  accuracy  loss  budget.This  dissertation  also  proposes  several  future  research  directions  in  the  areas  of  our  studies.
■590    ▼aSchool  code:  0181.
■650  4▼aComputer  science.
■650  4▼aComputer  engineering.
■653    ▼aNeural  network
■653    ▼aCompute  power
■653    ▼aHardware  accelerators
■653    ▼aMultiplexing  parameters
■653    ▼aModel  compression
■690    ▼a0984
■690    ▼a0464
■71020▼aPrinceton  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g84-12B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0181
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932338▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF05910 전자도서 My Folder 부재도서신고 비도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.