IPLAM: A High-Dimensional Expensive Simulation Optimization Method, With Application to Design Space Exploration in Processor

Design Space Exploration (DSE) in processors is an expensive discrete simulation optimization problem. The data requirements of the regular data-driven methods are so large that it is challenging to converge to a satisfactory solution within a limited simulation budget. Based on binary integer linea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on automation science and engineering Jg. 22; S. 18761 - 18772
Hauptverfasser: Lv, Xiaoliang, Zhai, Qiaozhu, Zhu, Yuhang, Hu, Jianchen, Guan, Xiaohong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 2025
Schlagworte:
ISSN:1545-5955, 1558-3783
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Design Space Exploration (DSE) in processors is an expensive discrete simulation optimization problem. The data requirements of the regular data-driven methods are so large that it is challenging to converge to a satisfactory solution within a limited simulation budget. Based on binary integer linear programming (BILP), an iteratively piecewise linear approximate method (IPLAM) is proposed for this kind of problems to reduce the dependence of simulation data. IPLAM starts from an initial reference point. Each iteration generates a set of trial points based on the most promising reference point by piecewise shift method. After evaluating the trial points, a local surrogate model is constructed for the unit neighborhood of the reference point. The surrogate model is then used to guide the exploration of the next reference point. In theory, IPLAM can converge to the global optimal point under mild assumptions, which is further verified by the numerical experiments. Meanwhile, the numerical experiments demonstrate that IPLAM outperforms the advanced Bayesian optimization and differential evolution methods on high-dimensional discrete closed-box test functions. Besides, the practical effectiveness of IPLAM is validated by an industrial case for processor DSE. Note to Practitioners-This paper proposes an efficient optimization method, IPLAM, for high-dimensional expensive simulation problems. To cope with the extremely limited simulation data, we construct the surrogate objective for the local space around the reference point by evaluating a set of trail points. The surrogate objective is then based on to locate the most promising point as the next reference point. We also provide theoretical guarantees of convergence for the proposed method. According to the numerical experiments, the proposed method demonstrates a much superior exploration efficiency and a lower simulation data requirement than competing methods. Besides, compared with an advanced Bayesian optimization method (HEBO) in an industrial case of processor DSE, the proposed method achieves a 47% improvement in convergence speed and a 15% reduction in simulation overhead while the difference of simulation score is marginal.
AbstractList Design Space Exploration (DSE) in processors is an expensive discrete simulation optimization problem. The data requirements of the regular data-driven methods are so large that it is challenging to converge to a satisfactory solution within a limited simulation budget. Based on binary integer linear programming (BILP), an iteratively piecewise linear approximate method (IPLAM) is proposed for this kind of problems to reduce the dependence of simulation data. IPLAM starts from an initial reference point. Each iteration generates a set of trial points based on the most promising reference point by piecewise shift method. After evaluating the trial points, a local surrogate model is constructed for the unit neighborhood of the reference point. The surrogate model is then used to guide the exploration of the next reference point. In theory, IPLAM can converge to the global optimal point under mild assumptions, which is further verified by the numerical experiments. Meanwhile, the numerical experiments demonstrate that IPLAM outperforms the advanced Bayesian optimization and differential evolution methods on high-dimensional discrete closed-box test functions. Besides, the practical effectiveness of IPLAM is validated by an industrial case for processor DSE. Note to Practitioners-This paper proposes an efficient optimization method, IPLAM, for high-dimensional expensive simulation problems. To cope with the extremely limited simulation data, we construct the surrogate objective for the local space around the reference point by evaluating a set of trail points. The surrogate objective is then based on to locate the most promising point as the next reference point. We also provide theoretical guarantees of convergence for the proposed method. According to the numerical experiments, the proposed method demonstrates a much superior exploration efficiency and a lower simulation data requirement than competing methods. Besides, compared with an advanced Bayesian optimization method (HEBO) in an industrial case of processor DSE, the proposed method achieves a 47% improvement in convergence speed and a 15% reduction in simulation overhead while the difference of simulation score is marginal.
Author Lv, Xiaoliang
Guan, Xiaohong
Hu, Jianchen
Zhai, Qiaozhu
Zhu, Yuhang
Author_xml – sequence: 1
  givenname: Xiaoliang
  orcidid: 0009-0008-6565-6701
  surname: Lv
  fullname: Lv, Xiaoliang
  email: xiaoliang.lv@stu.xjtu.edu.cn
  organization: Systems Engineering Institute, MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China
– sequence: 2
  givenname: Qiaozhu
  orcidid: 0000-0002-7312-4923
  surname: Zhai
  fullname: Zhai, Qiaozhu
  email: qzzhai@sei.xjtu.edu.cn
  organization: Systems Engineering Institute, MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China
– sequence: 3
  givenname: Yuhang
  orcidid: 0009-0003-1282-3805
  surname: Zhu
  fullname: Zhu, Yuhang
  email: zhuyh21@mails.tsinghua.edu.cn
  organization: Center for Intelligent and Networked Systems and TNLIST, Tsinghua University, Beijing, China
– sequence: 4
  givenname: Jianchen
  orcidid: 0000-0002-4143-9955
  surname: Hu
  fullname: Hu, Jianchen
  email: horace89@xjtu.edu.cn
  organization: Systems Engineering Institute, MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China
– sequence: 5
  givenname: Xiaohong
  orcidid: 0000-0002-8826-0362
  surname: Guan
  fullname: Guan, Xiaohong
  email: xhguan@sei.xjtu.edu.cn
  organization: Systems Engineering Institute, MOE KLINNS Lab, Xi'an Jiaotong University, Xi'an, China
BookMark eNpFkEFLw0AQhRepYFv9AYKH_QGmzmaz2ay3UKsttLTQisewTSbtSpIN2Sgq-N9tSMHTvJk37x2-ERlUtkJCbhlMGAP1sIu3s4kPvphwEUU-kxdkyISIPC4jPuh0IDyhhLgiI-feAfwgUjAkv4vNMl490pjOzeHoPZkSK2dspQs6-6o7_Yl0a8qPQrenM13XrSnNT7-ssD3a7J6-mfZI47ouTNobraVP6Myhottap9hVFbbpPVPRTWNTdM421-Qy14XDm_Mck9fn2W4695brl8U0Xnqp70ProWYhlwyCEHSWIwahVgFIqRTnTO1Rg0w5Msl1pgF5FkGu1D5nEoO9CsOMjwnre9PGOtdgntSNKXXznTBIOn5Jxy_p-CVnfqfMXZ8xiPj_z-AEVPr8D0wQb6w
CODEN ITASC7
Cites_doi 10.1007/s11081-022-09740-5
10.1016/j.cam.2019.112571
10.1115/1.2803251
10.1109/TASE.2020.3017644
10.1016/j.ifacol.2021.06.152
10.1093/oso/9780195099713.001.0001
10.1016/j.cma.2018.12.026
10.1016/j.asoc.2020.106154
10.1023/A:1011255519438
10.1007/s12532-018-0144-7
10.1109/TVLSI.2020.2968904
10.23919/DATE.2019.8714788
10.1016/j.cma.2020.112861
10.1016/j.ejor.2011.12.030
10.1115/DETC2000/DAC-14264
10.1007/978-3-030-58112-1_12
10.1016/j.ins.2023.119308
10.1007/s11432-023-3963-7
10.1109/TASE.2021.3114157
10.1007/s11432-021-3416-y
10.1613/jair.1.13643
10.1109/TCAD.2024.3443006
10.1109/TC.2017.2780239
10.1109/TCAD.2024.3457376
10.1145/2897937.2898012
10.1109/LCA.2018.2849983
10.1109/TASE.2021.3096964
10.1016/j.ins.2024.120246
10.1109/TASE.2022.3200376
10.1109/TASE.2024.3454176
10.1007/s00158-013-0919-4
10.1198/004017005000000526
10.1016/j.ins.2023.119697
10.1109/TCAD.2021.3054811
10.1109/TII.2019.2940475
10.1016/j.knosys.2021.107653
10.1007/978-3-642-20859-1_4
10.1109/TASE.2019.2941167
10.1016/j.ins.2014.05.033
10.1109/TCSI.2017.2768826
10.1109/TASE.2025.3551716
10.1145/3548775
10.1021/nn900523p
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TASE.2025.3588217
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL) (UW System Shared)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-3783
EndPage 18772
ExternalDocumentID 10_1109_TASE_2025_3588217
11078372
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of Sichuan Province; Sichuan Natural Science Foundation
  grantid: 2023NSFSC1434
  funderid: 10.13039/501100018542
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
ID FETCH-LOGICAL-c220t-ea163710460adfee46a94077993319bea07c3e173ada0e3d80f99bf17e4b966d3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001540905400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1545-5955
IngestDate Sat Nov 29 07:37:28 EST 2025
Wed Aug 27 01:45:08 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c220t-ea163710460adfee46a94077993319bea07c3e173ada0e3d80f99bf17e4b966d3
ORCID 0009-0008-6565-6701
0000-0002-4143-9955
0000-0002-8826-0362
0000-0002-7312-4923
0009-0003-1282-3805
PageCount 12
ParticipantIDs crossref_primary_10_1109_TASE_2025_3588217
ieee_primary_11078372
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationTitle IEEE transactions on automation science and engineering
PublicationTitleAbbrev TASE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref15
ref14
ref11
ref10
ref17
ref16
ref19
ref18
Molga (ref40) 2005; 101
ref46
ref45
ref48
ref47
ref41
ref43
ref49
ref8
ref7
ref9
ref3
ref6
ref5
Rolland (ref31)
Pohlheim (ref39) 2007; 4
ref35
ref34
ref37
ref36
ref30
ref33
ref32
ref2
ref1
ref38
Rahman (ref42) 2023
Celio (ref44) 2015
ref24
ref23
ref26
ref25
ref20
ref22
Vahid (ref4) 2001
ref21
ref28
ref27
ref29
References_xml – ident: ref25
  doi: 10.1007/s11081-022-09740-5
– volume: 4
  start-page: 2012
  issue: 10
  year: 2007
  ident: ref39
  article-title: Examples of objective functions
  publication-title: Retrieved
– ident: ref8
  doi: 10.1016/j.cam.2019.112571
– ident: ref12
  doi: 10.1115/1.2803251
– ident: ref13
  doi: 10.1109/TASE.2020.3017644
– year: 2015
  ident: ref44
  article-title: The Berkeley out-of-order machine (boom): An industry-competitive, synthesizable, parameterized risc-v processor
– ident: ref9
  doi: 10.1016/j.ifacol.2021.06.152
– ident: ref49
  doi: 10.1093/oso/9780195099713.001.0001
– ident: ref3
  doi: 10.1016/j.cma.2018.12.026
– ident: ref23
  doi: 10.1016/j.asoc.2020.106154
– ident: ref20
  doi: 10.1023/A:1011255519438
– ident: ref21
  doi: 10.1007/s12532-018-0144-7
– ident: ref28
  doi: 10.1109/TVLSI.2020.2968904
– ident: ref14
  doi: 10.23919/DATE.2019.8714788
– ident: ref22
  doi: 10.1016/j.cma.2020.112861
– ident: ref38
  doi: 10.1016/j.ejor.2011.12.030
– ident: ref46
  doi: 10.1115/DETC2000/DAC-14264
– ident: ref32
  doi: 10.1007/978-3-030-58112-1_12
– ident: ref2
  doi: 10.1016/j.ins.2023.119308
– ident: ref45
  doi: 10.1007/s11432-023-3963-7
– ident: ref19
  doi: 10.1109/TASE.2021.3114157
– ident: ref43
  doi: 10.1007/s11432-021-3416-y
– ident: ref35
  doi: 10.1613/jair.1.13643
– ident: ref30
  doi: 10.1109/TCAD.2024.3443006
– volume-title: Global Optimization Test Problems
  year: 2023
  ident: ref42
– ident: ref27
  doi: 10.1109/TC.2017.2780239
– ident: ref10
  doi: 10.1109/TCAD.2024.3457376
– ident: ref1
  doi: 10.1145/2897937.2898012
– ident: ref29
  doi: 10.1109/LCA.2018.2849983
– ident: ref34
  doi: 10.1109/TASE.2021.3096964
– ident: ref11
  doi: 10.1016/j.ins.2024.120246
– ident: ref17
  doi: 10.1109/TASE.2022.3200376
– ident: ref18
  doi: 10.1109/TASE.2024.3454176
– ident: ref41
  doi: 10.1007/s00158-013-0919-4
– volume-title: Embedded System Design: A Unified Hardware/software Introduction
  year: 2001
  ident: ref4
– start-page: 298
  volume-title: Proc. Int. Conf. Artif. Intell. Statist.
  ident: ref31
  article-title: High-dimensional Bayesian optimization via additive models with overlapping groups
– ident: ref47
  doi: 10.1198/004017005000000526
– ident: ref5
  doi: 10.1016/j.ins.2023.119697
– ident: ref16
  doi: 10.1109/TCAD.2021.3054811
– ident: ref24
  doi: 10.1109/TII.2019.2940475
– ident: ref36
  doi: 10.1016/j.knosys.2021.107653
– ident: ref37
  doi: 10.1007/978-3-642-20859-1_4
– volume: 101
  start-page: 48
  year: 2005
  ident: ref40
  article-title: Test functions for optimization needs
  publication-title: Test Functions Optim. Needs
– ident: ref33
  doi: 10.1109/TASE.2019.2941167
– ident: ref6
  doi: 10.1016/j.ins.2014.05.033
– ident: ref15
  doi: 10.1109/TCSI.2017.2768826
– ident: ref7
  doi: 10.1109/TASE.2025.3551716
– ident: ref26
  doi: 10.1145/3548775
– ident: ref48
  doi: 10.1021/nn900523p
SSID ssj0024890
Score 2.3898587
Snippet Design Space Exploration (DSE) in processors is an expensive discrete simulation optimization problem. The data requirements of the regular data-driven methods...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 18761
SubjectTerms Automation
Bayes methods
binary integer linear programming
Closed box
Convergence
Costs
Data models
design space exploration
Expensive simulation system
high-dimensional discrete optimization
Optimization methods
Piecewise linear approximation
Predictive models
Space exploration
Title IPLAM: A High-Dimensional Expensive Simulation Optimization Method, With Application to Design Space Exploration in Processor
URI https://ieeexplore.ieee.org/document/11078372
Volume 22
WOSCitedRecordID wos001540905400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE/IET Electronic Library
  customDbUrl:
  eissn: 1558-3783
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0024890
  issn: 1545-5955
  databaseCode: RIE
  dateStart: 20040101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27TsMwFLWgYoCBZxHlJQ9MCLdpnMQ1W0RbgdSWSi3QLXKcG5GhCSopG_-O7RilCwNblMRS5OvY59zHuQjdKEgBTKRdkqSSEc8VkgghPeKJxPUBqPCN2ufriE0mvcWCT22xuqmFAQCTfAZtfWli-Ukh19pV1tFcRREqteNuMxZUxVq1sF7POFQ0JCA-930bwuw6vDMPZwNFBV2_TX2FKE1zsvoQ2uiqYg6V4cE_P-cQ7Vv0iMPK3EdoC_JjtLehKXiCvp-mo3B8j0OsUzhIX6v3V8obWMsam3R1PMuWtm0XflZ7xtIWY-Kx6Sd9h9-y8h2HdWwblwXum1wPPFMkG3CVulc9y3Jsyw2KVRO9DAfzh0dieywQ6bpOSUAoQMZ0oNcRSQrgBYIrjscUbFE_ZwzCYZJCl1GRCAdo0nNSzuO0y8CLFVNK6Clq5EUOZwiDTBUcCmgAkHpc0pgpe3OQyjZqsBe00O3vpEcflZRGZCiIwyNtoUhbKLIWaqGmnvD6RTvX53_cv0C7enjlHLlEjXK1hiu0I7_K7HN1bVbKDyfOvjk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8IwGG4MmqgHPzHiZw-ejIVt3Sj1tggE4kASULktXfcucgAMDm_-d9uuZl48eFu2bln6bu3zvB_Pi9CNghTAROaSNJOM-J6QRAjpE1-kXgBARWDUPl8iNhy2plM-ssXqphYGAEzyGdT1oYnlp0u51q6yhuYqilCpFXdTt86y5VqltF7LuFQ0KCABDwIbxHQd3piE444ig15Qp4HClKY9WbkN_eqrYraV7v4_X-gA7Vn8iMPC4IdoAxZHaPeXquAx-uqPonBwj0OskzhIW-v3F9obWAsbm4R1PJ7NbeMu_KRWjbktx8QD01H6Dr_O8jccltFtnC9x22R74LGi2YCL5L3i2myBbcHBclVFz93O5KFHbJcFIj3PyQkIBcmYDvU6Is0A_KbgiuUxBVzU75mAcJik4DIqUuEATVtOxnmSuQz8RHGllJ6gymK5gFOEQWYKEDVpEyDzuaQJUxbnIJVt1M1-s4ZufyY9fi_ENGJDQhweawvF2kKxtVANVfWElwPtXJ_9cf4abfcmgyiO-sPHc7SjH1W4Si5QJV-t4RJtyc989rG6Ml_NNzz3wYI
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=IPLAM%3A+A+High-Dimensional+Expensive+Simulation+Optimization+Method%2C+With+Application+to+Design+Space+Exploration+in+Processor&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Lv%2C+Xiaoliang&rft.au=Zhai%2C+Qiaozhu&rft.au=Zhu%2C+Yuhang&rft.au=Hu%2C+Jianchen&rft.date=2025&rft.issn=1545-5955&rft.eissn=1558-3783&rft.volume=22&rft.spage=18761&rft.epage=18772&rft_id=info:doi/10.1109%2FTASE.2025.3588217&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TASE_2025_3588217
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon