본문

서브메뉴

Accelerated Performance Modeling and Tuning of Parallel Programs
Accelerated Performance Modeling and Tuning of Parallel Programs
Accelerated Performance Modeling and Tuning of Parallel Programs

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105703
ISBN  
9798263308018
DDC  
004
저자명  
Hutter, Edward.
서명/저자  
Accelerated Performance Modeling and Tuning of Parallel Programs
발행사항  
[Sl] : University of Illinois at Urbana-Champaign, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
125 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: A.
주기사항  
Advisor: Solomonik, Edgar.
학위논문주기  
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
초록/해제  
요약Novel capabilities provided by an ever-diversifying array of modern architectures have increased the dimension of application parameter spaces and the complexity of performance exhibited across them. Despite a wealth of available performance models and automatic performance tuning (autotuning) frameworks, accurate prediction of high-dimensional application performance remains significantly challenging. This dissertation introduces novel techniques to improve the state-of-the-art in performance modeling and autotuning. We first consider the development of a model to estimate the performance of an application across a high-dimensional parameter space. Provided a collection of observed runtimes, as opposed to relying on expert knowledge of application or architecture, we propose and evaluate the use of tensors for modeling an application's performance. Specifically, we use tensors to represent regular grids that discretize the input and configuration domains of an application. Application execution times mapped within grid-cells are averaged and represented by tensor elements. We show that low-rank Canonical-Polyadic (CP) tensor decomposition is effective in approximating these tensors. To account for unobserved grid-cells, we employ tensor completion to optimize a CP decomposition. We then extend our model to provide accurate runtime estimates for problem sizes larger than those present in the observed subdomain. We fit a piecewise-linear model to a positive rank-1 approximation of each factor matrix to achieve this. We consider alternative piecewise/grid-based (P/G) and supervised learning models for a diverse set of applications and demonstrate that these P/G models are significantly more accurate relative to model size. Among P/G models, our tensor models offer higher prediction accuracy and memory-efficiency, and superior extensibility via application-specific loss functions and domain partitioning. We next consider the problem of search across an application's high-dimensional configuration space, for which alternative error metrics and datasets are present. In this setting, we propose and evaluate profiling techniques for accelerating the selection of optimal tuning parameters of MPI applications at scale during runtime. We introduce a framework for approximate autotuning that achieves a desired confidence in each application configuration's performance by constructing confidence intervals to describe the performance of individual kernels (subroutines of benchmarked applications) invoked by the application. Once a kernel's performance is deemed sufficiently predictable for a set of inputs, subsequent invocations are avoided and replaced with a predictive model of the execution time. We then leverage online critical-path analysis to coordinate selective kernel execution and propagate each kernel's statistical profile. This strategy is effective in the presence of frequently-recurring computation and communication kernels, which is characteristic to algorithms in numerical linear algebra. We encapsulate this framework as part of a new profiling tool, Critter, that automates kernel execution decisions and propagates statistical profiles along critical paths of execution.
일반주제명  
Computer science
키워드  
Performance modeling
키워드  
Autotuning
키워드  
Novel capabilities
기타저자  
University of Illinois at Urbana-Champaign Computer Science
기본자료저록  
Dissertations Abstracts International. 87-05A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017361081
■00520260202105703
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263308018
■035    ▼a(MiAaPQ)AAI32409892
■035    ▼a(MiAaPQ)124368
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aHutter,  Edward.
■24510▼aAccelerated  Performance  Modeling  and  Tuning  of  Parallel  Programs
■260    ▼a[Sl]▼bUniversity  of  Illinois  at  Urbana-Champaign▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a125  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  A.
■500    ▼aAdvisor:  Solomonik,  Edgar.
■5021  ▼aThesis  (Ph.D.)--University  of  Illinois  at  Urbana-Champaign,  2024.
■520    ▼aNovel  capabilities  provided  by  an  ever-diversifying  array  of  modern  architectures  have  increased  the  dimension  of  application  parameter  spaces  and  the  complexity  of  performance  exhibited  across  them.  Despite  a  wealth  of  available  performance  models  and  automatic  performance  tuning  (autotuning)  frameworks,  accurate  prediction  of  high-dimensional  application  performance  remains  significantly  challenging.  This  dissertation  introduces  novel  techniques  to  improve  the  state-of-the-art  in  performance  modeling  and  autotuning.                        We  first  consider  the  development  of  a  model  to  estimate  the  performance  of  an  application  across  a  high-dimensional  parameter  space.  Provided  a  collection  of  observed  runtimes,  as  opposed  to  relying  on  expert  knowledge  of  application  or  architecture,  we  propose  and  evaluate  the  use  of  tensors  for  modeling  an  application's  performance.  Specifically,  we  use  tensors  to  represent  regular  grids  that  discretize  the  input  and  configuration  domains  of  an  application.  Application  execution  times  mapped  within  grid-cells  are  averaged  and  represented  by  tensor  elements.  We  show  that  low-rank  Canonical-Polyadic  (CP)  tensor  decomposition  is  effective  in  approximating  these  tensors.  To  account  for  unobserved  grid-cells,  we  employ  tensor  completion  to  optimize  a  CP  decomposition.  We  then  extend  our  model  to  provide  accurate  runtime  estimates  for  problem  sizes  larger  than  those  present  in  the  observed  subdomain.  We  fit  a  piecewise-linear  model  to  a  positive  rank-1  approximation  of  each  factor  matrix  to  achieve  this.  We  consider  alternative  piecewise/grid-based  (P/G)  and  supervised  learning  models  for  a  diverse  set  of  applications  and  demonstrate  that  these  P/G  models  are  significantly  more  accurate  relative  to  model  size.  Among  P/G  models,  our  tensor  models  offer  higher  prediction  accuracy  and  memory-efficiency,  and  superior  extensibility  via  application-specific  loss  functions  and  domain  partitioning.                        We  next  consider  the  problem  of  search  across  an  application's  high-dimensional  configuration  space,  for  which  alternative  error  metrics  and  datasets  are  present.  In  this  setting,  we  propose  and  evaluate  profiling  techniques  for  accelerating  the  selection  of  optimal  tuning  parameters  of  MPI  applications  at  scale  during  runtime.  We  introduce  a  framework  for  approximate  autotuning  that  achieves  a  desired  confidence  in  each  application  configuration's  performance  by  constructing  confidence  intervals  to  describe  the  performance  of  individual  kernels  (subroutines  of  benchmarked  applications)  invoked  by  the  application.  Once  a  kernel's  performance  is  deemed  sufficiently  predictable  for  a  set  of  inputs,  subsequent  invocations  are  avoided  and  replaced  with  a  predictive  model  of  the  execution  time.  We  then  leverage  online  critical-path  analysis  to  coordinate  selective  kernel  execution  and  propagate  each  kernel's  statistical  profile.  This  strategy  is  effective  in  the  presence  of  frequently-recurring  computation  and  communication  kernels,  which  is  characteristic  to  algorithms  in  numerical  linear  algebra.  We  encapsulate  this  framework  as  part  of  a  new  profiling  tool,  Critter,  that  automates  kernel  execution  decisions  and  propagates  statistical  profiles  along  critical  paths  of  execution.
■590    ▼aSchool  code:  0090.
■650  4▼aComputer  science
■653    ▼aPerformance  modeling
■653    ▼aAutotuning
■653    ▼aNovel  capabilities
■690    ▼a0984
■690    ▼a0729
■71020▼aUniversity  of  Illinois  at  Urbana-Champaign▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-05A.
■790    ▼a0090
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361081▼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
    TF16758 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.