Article(id=1327011732247130887, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011511924535414, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330348, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1683388800000, receivedDateStr=2023-05-07, revisedDate=1705248000000, revisedDateStr=2024-01-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1794313851652, onlineDateStr=2026-11-10, pubDate=1735660800000, pubDateStr=2025-01-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794313851652, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794313851652, creator=13701087609, updateTime=1794313851652, updator=13701087609, issue=Issue{id=1327011511924535414, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='1', pageStart='1', pageEnd='283', issueExtLink='null', onlineDate='null', pubDate='1735660800000', pubDateStr='2025-01-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794313799123, creator='13701087609', updateTime=1794376660021, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327275170160554491, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011511924535414, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327275170160554492, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011511924535414, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=22, endPage=57, ext={EN=ArticleExt(id=1327011732452651785, articleId=1327011732247130887, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Acceleration Methods for Processor Microarchitecture Design Space Exploration: A Survey, columnId=1327010444570637032, journalTitle=Journal of Computer Research and Development, columnName=Computer Achitecture, runingTitle=null, highlight=null, articleAbstract=
Central processing unit is the most important computing infrastructure nowadays. To maximize the profit, architects design the processor microarchitecture by trading-off multiple objectives including performance, power, and area. However, because of the tremendous instructions of workloads running on the processors, the evaluation of individual microarchitecture design point costs minutes to hours. Furthermore, the design space of the microarchitecture is huge, which results that the exploration of comprehensive design space is unrealistic. Therefore, many machine-learning-assisted design space exploration acceleration methods are proposed to reduce the size of evaluated design space or accelerate the evaluation of a design point. However, a comprehensive survey summarizing and systematically classifying recent acceleration methods is missing. This survey paper systematically summarizes and classifies the five kinds of acceleration methods for the design space exploration of the processor microarchitecture, including the workload selection of software design space, the partial simulation of workload instructions, the design point selection, the simulation tools, and the performance models. This paper systematically compares the similarities and differences between papers in the acceleration methods, and covers the complete exploration process from the software workload selection to the hardware microarchitecture design. Finally, the research direction is summarized, and the future development trend is discussed.
, authors=Duo Wang
1, 2, Jinglei Liu
3, Mingyu Yan
1, 2, *, Yihan Teng
1, 2, Dengke Han
1, 2, Xiaochun Ye
1, 2, Dongrui Fan
1, 2, authorsList=Duo Wang, Jinglei Liu, Mingyu Yan, Yihan Teng, Dengke Han, Xiaochun Ye, Dongrui Fan, authorCompany=null, correspAuthors=Mingyu Yan, authorNote=
born in 1995. PhD. Student member of CCF. His main research interests include processor design space exploration and computer architecture
born in 1982. Master, senior engineer. His main research interests include computility network and computer architecture
born in 1990. PhD, associate professor. Member of CCF. His main research interest includes graph based hardware accelerator and dataflow architecture
born in 2000. Master. His main research interests include graph-based hardware accelerator and high-throughput computer architecture
born in 1998. Master candidate. His main research interest includes graph-based hardware accelerator and high-throughput computer architecture
born in 1981. PhD, professor. Member of CCF. His main research interests include software simulation, algorithm paralleling and optimizing, and architecture for high performance computer
born in 1979. PhD, professor. Distinguished member of CCF. His main research interests include manycore processor design, high throughput processor design, and low power microarchitecture
, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327011736474989347, articleId=1327011732247130887, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=面向处理器微架构设计空间探索的加速方法综述, columnId=1325489904427344387, journalTitle=计算机研究与发展, columnName=体系结构, runingTitle=null, highlight=null, articleAbstract=
中央处理器是目前最重要的算力基础设施. 为了最大化收益,架构师在设计处理器微架构时需要权衡性能、功耗、面积等多个目标. 但处理器运行负载的指令多,单个微架构设计点的评估耗时从10 min到数十小时不等. 加之微架构设计空间巨大,全设计空间暴力搜索难以实现. 近些年来许多机器学习辅助的设计空间探索加速方法被提出,以减少需要探索的设计空间或加速设计点的评估,但缺少对加速方法的全面调研和系统分类的综述. 对处理器微架构设计空间探索的加速方法进行系统总结及分类,包含软件设计空间的负载选择、负载指令的部分模拟、设计点选择、模拟工具、性能模型5类加速方法. 对比了各加速方法内文献的异同,覆盖了从软件选择到硬件设计的完整探索流程. 最后对该领域的前沿研究方向进行了总结,并放眼于未来的发展趋势.
, authors=王铎
1, 2, 刘景磊
3, 严明玉
1, 2, *, 滕亦涵
1, 2, 韩登科
1, 2, 叶笑春
1, 2, 范东睿
1, 2, authorsList=王铎, 刘景磊, 严明玉, 滕亦涵, 韩登科, 叶笑春, 范东睿, authorCompany=null, correspAuthors=严明玉, authorNote=
 |
1995年生. 博士. CCF学生会员. 主要研究方向为处理器设计空间探索、计算机体系结构 |
 |
1982年生. 硕士,高级工程师. 主要研究方向为算力网络、计算机体系结构 |
 |
1990年生. 博士,副研究员. CCF会员. 主要研究方向为基于图的硬件加速器、数据流架构 |
 |
2000年生. 硕士. 主要研究方向为基于图的硬件加速器和高吞吐量计算体系结构 |
 |
1998年生. 硕士研究生. 主要研究方向为基于图的硬件加速器和高吞吐量计算体系结构 |
 |
1981年生. 博士,研究员. CCF会员. 主要研究方向为软件仿真、算法并行优化、高性能计算机架构 |
 |
1979年生. 博士,研究员. CCF杰出会员. 主要研究方向为众核处理器设计、高通量处理器设计、低功耗微架构 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=/Hqs4d6UHOkGldbpoDfvdQ==, magXml=N6fwT0/fhvBIpc9RBzo4tw==, pdfUrl=null, pdf=04Y4p3S23P2ZA6dER2FoTA==, pdfFileSize=2338007, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=0vo/5ihQEAYbB0QvoN7SqA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=XIZWkaDiCiyWKSZdI3in6A==, mapNumber=null, fund=null)}, authors=[Author(id=1327011915584352449, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangduo@ict.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011915764707524, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011915584352449, language=EN, stringName=Duo Wang, firstName=Duo, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1995. PhD. Student member of CCF. His main research interests include processor design space exploration and computer architecture
"}, bioImg=null, bioContent=
born in 1995. PhD. Student member of CCF. His main research interests include processor design space exploration and computer architecture
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011915831816389, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011915584352449, language=CN, stringName=王铎, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190
2中国科学院大学计算机科学与技术学院 北京 100049, bio={"img":"d0SFCrTBCBeyMOZ2yDwGRg==","content":"
1995年生. 博士. CCF学生会员. 主要研究方向为处理器设计空间探索、计算机体系结构
"}, bioImg=d0SFCrTBCBeyMOZ2yDwGRg==, bioContent=
1995年生. 博士. CCF学生会员. 主要研究方向为处理器设计空间探索、计算机体系结构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)])]), Author(id=1327011915903119559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011916012171466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011915903119559, language=EN, stringName=Jinglei Liu, firstName=Jinglei, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
3, address=
3China Mobile Communications Research Institute, Beijing 100053, bio={"content":"
born in 1982. Master, senior engineer. His main research interests include computility network and computer architecture
"}, bioImg=null, bioContent=
born in 1982. Master, senior engineer. His main research interests include computility network and computer architecture
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011916138000587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011915903119559, language=CN, stringName=刘景磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
3, address=
3中国移动研究院 北京 100053, bio={"img":"XPECG8daZZhsXcDUqJ6IAQ==","content":"
1982年生. 硕士,高级工程师. 主要研究方向为算力网络、计算机体系结构
"}, bioImg=XPECG8daZZhsXcDUqJ6IAQ==, bioContent=
1982年生. 硕士,高级工程师. 主要研究方向为算力网络、计算机体系结构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915508854973, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=3, ext=[AuthorCompanyExt(id=1327011915517243582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915508854973, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3China Mobile Communications Research Institute, Beijing 100053), AuthorCompanyExt(id=1327011915521437887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915508854973, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3中国移动研究院 北京 100053)])]), Author(id=1327011916238663885, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yanmingyu@ict.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327011916339327184, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916238663885, language=EN, stringName=Mingyu Yan, firstName=Mingyu, middleName=null, lastName=Yan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, *, address=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1990. PhD, associate professor. Member of CCF. His main research interest includes graph based hardware accelerator and dataflow architecture
"}, bioImg=null, bioContent=
born in 1990. PhD, associate professor. Member of CCF. His main research interest includes graph based hardware accelerator and dataflow architecture
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011916419018961, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916238663885, language=CN, stringName=严明玉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, *, address=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190
2中国科学院大学计算机科学与技术学院 北京 100049, bio={"img":"ho0IYse9msTBmNDuK9iUKA==","content":"
1990年生. 博士,副研究员. CCF会员. 主要研究方向为基于图的硬件加速器、数据流架构
"}, bioImg=ho0IYse9msTBmNDuK9iUKA==, bioContent=
1990年生. 博士,副研究员. CCF会员. 主要研究方向为基于图的硬件加速器、数据流架构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)])]), Author(id=1327011916515487955, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011916620345558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916515487955, language=EN, stringName=Yihan Teng, firstName=Yihan, middleName=null, lastName=Teng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 2000. Master. His main research interests include graph-based hardware accelerator and high-throughput computer architecture
"}, bioImg=null, bioContent=
born in 2000. Master. His main research interests include graph-based hardware accelerator and high-throughput computer architecture
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011916691648727, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916515487955, language=CN, stringName=滕亦涵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190
2中国科学院大学计算机科学与技术学院 北京 100049, bio={"img":"X5PZIwELp59VQVQSVpwZkQ==","content":"
2000年生. 硕士. 主要研究方向为基于图的硬件加速器和高吞吐量计算体系结构
"}, bioImg=X5PZIwELp59VQVQSVpwZkQ==, bioContent=
2000年生. 硕士. 主要研究方向为基于图的硬件加速器和高吞吐量计算体系结构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)])]), Author(id=1327011916771340505, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011916859420892, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916771340505, language=EN, stringName=Dengke Han, firstName=Dengke, middleName=null, lastName=Han, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1998. Master candidate. His main research interest includes graph-based hardware accelerator and high-throughput computer architecture
"}, bioImg=null, bioContent=
born in 1998. Master candidate. His main research interest includes graph-based hardware accelerator and high-throughput computer architecture
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011916918141149, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916771340505, language=CN, stringName=韩登科, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190
2中国科学院大学计算机科学与技术学院 北京 100049, bio={"img":"rIYplVFnqm61pKS+IuhpPA==","content":"
1998年生. 硕士研究生. 主要研究方向为基于图的硬件加速器和高吞吐量计算体系结构
"}, bioImg=rIYplVFnqm61pKS+IuhpPA==, bioContent=
1998年生. 硕士研究生. 主要研究方向为基于图的硬件加速器和高吞吐量计算体系结构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)])]), Author(id=1327011916997832927, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011917111079138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916997832927, language=EN, stringName=Xiaochun Ye, firstName=Xiaochun, middleName=null, lastName=Ye, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1981. PhD, professor. Member of CCF. His main research interests include software simulation, algorithm paralleling and optimizing, and architecture for high performance computer
"}, bioImg=null, bioContent=
born in 1981. PhD, professor. Member of CCF. His main research interests include software simulation, algorithm paralleling and optimizing, and architecture for high performance computer
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011917182382307, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011916997832927, language=CN, stringName=叶笑春, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190
2中国科学院大学计算机科学与技术学院 北京 100049, bio={"img":"Yk+OEcvYo3DvtjK2eqyZTg==","content":"
1981年生. 博士,研究员. CCF会员. 主要研究方向为软件仿真、算法并行优化、高性能计算机架构
"}, bioImg=Yk+OEcvYo3DvtjK2eqyZTg==, bioContent=
1981年生. 博士,研究员. CCF会员. 主要研究方向为软件仿真、算法并行优化、高性能计算机架构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)])]), Author(id=1327011917249491173, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011917320794344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011917249491173, language=EN, stringName=Dongrui Fan, firstName=Dongrui, middleName=null, lastName=Fan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, bio={"content":"
born in 1979. PhD, professor. Distinguished member of CCF. His main research interests include manycore processor design, high throughput processor design, and low power microarchitecture
"}, bioImg=null, bioContent=
born in 1979. PhD, professor. Distinguished member of CCF. His main research interests include manycore processor design, high throughput processor design, and low power microarchitecture
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011917392097513, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, authorId=1327011917249491173, language=CN, stringName=范东睿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190
2中国科学院大学计算机科学与技术学院 北京 100049, bio={"img":"tmWGZ2X9c+GTfQKGtvNNFw==","content":"
1979年生. 博士,研究员. CCF杰出会员. 主要研究方向为众核处理器设计、高通量处理器设计、低功耗微架构
"}, bioImg=tmWGZ2X9c+GTfQKGtvNNFw==, bioContent=
1979年生. 博士,研究员. CCF杰出会员. 主要研究方向为众核处理器设计、高通量处理器设计、低功耗微架构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)])])], keywords=[Keyword(id=1327011917526315242, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, orderNo=1, keyword=processor microarchitecture design), Keyword(id=1327011917589229803, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, orderNo=2, keyword=design space exploration), Keyword(id=1327011917673115884, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, orderNo=3, keyword=performance model), Keyword(id=1327011917740224749, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, orderNo=4, keyword=workload selection), Keyword(id=1327011917807333614, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, orderNo=5, keyword=software simulation), Keyword(id=1327011919405363439, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, orderNo=1, keyword=处理器微架构设计), Keyword(id=1327011919510221040, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, orderNo=2, keyword=设计空间探索), Keyword(id=1327011919589912817, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, orderNo=3, keyword=性能模型), Keyword(id=1327011919677993202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, orderNo=4, keyword=负载选择), Keyword(id=1327011919757684979, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, orderNo=5, keyword=软件模拟)], refs=[Reference(id=1327011926254661928, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Azizi O, Mahesri A, Lee B C, et al. Energy-performance tradeoffs in processor architecture and circuit design: A marginal cost analysis[C]//Proc of the 27th Annual Int Symp on Computer Architecture. New York: ACM, 2010: 26–36, articleTitle=null, refAbstract=null), Reference(id=1327011926321770793, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee B C, Brooks D M. Illustrative design space studies with microarchitectural regression models[C]//Proc of the 13th Int Conf on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2007: 340–351, articleTitle=null, refAbstract=null), Reference(id=1327011926388879658, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Ipek E, McKee S A, Caruana R, et al. Efficiently exploring architectural design spaces via predictive modeling[C]//Proc of the 12th Int Conf on Architectural Support for Programming Languages and Operating Systems. New York: ACM, 2006: 195–206, articleTitle=null, refAbstract=null), Reference(id=1327011926455988523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee B C, Brooks D M. Accurate and efficient regression modeling for microarchitectural performance and power prediction[C]//Proc of the 12th Int Conf on Architectural Support for Programming Languages and Operating Systems. New York: ACM, 2006: 185–194, articleTitle=null, refAbstract=null), Reference(id=1327011926527291692, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee B C, Collins J D, Wang Hong, et al. CPR: Composable performance regression for scalable multiprocessor models[C]//Proc of the 41st Annual IEEE/ACM Int Symp on Microarchitecture. Piscataway, NJ: IEEE, 2008: 270–281, articleTitle=null, refAbstract=null), Reference(id=1327011926611177773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Dandan, Yao Shuzhen, Wang Senzhang, et al. Cross-program design space exploration by ensemble transfer learning[C]//Proc of the 36th IEEE/ACM Int Conf on Computer-Aided Design. Piscataway, NJ: IEEE, 2017: 201–208, articleTitle=null, refAbstract=null), Reference(id=1327011926678286638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Dandan, Wang Senzhang, Yao Shuzhen, et al. Efficient design space exploration by knowledge transfer[C]//Proc of the 11th IEEE/ACM/IFIP Int Conf on Hardware/Software Codesign and System Synthesis. New York: ACM, 2016: 12: 1−12: 10, articleTitle=null, refAbstract=null), Reference(id=1327011926774755632, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Weidan, Lee B C. Inferred models for dynamic and sparse hardware-software spaces[C]//Proc of the 45th Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2012: 413–424, articleTitle=null, refAbstract=null), Reference(id=1327011928456671537, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yu, Lee V, Wei G Y, et al. Predicting new workload or CPU performance by analyzing public datasets[J]. ACM Transactions on Architecture and Code Optimization, 2019, 15(4): 53: 1−53: 21, articleTitle=null, refAbstract=null), Reference(id=1327011928548946226, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Dubach C, Jones T M, O’Boyle M F P. An empirical architecture-centric approach to microarchitectural design space exploration[J]. IEEE Transactions on Computers, 2011, 60(10): 1445−1458, articleTitle=null, refAbstract=null), Reference(id=1327011928695746867, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Dubach C, Jones T M, O’Boyle M F P. Microarchitectural design space exploration using an architecture-centric approach[C]//Proc of the 40th Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2007: 262–271, articleTitle=null, refAbstract=null), Reference(id=1327011928863519028, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Eeckhout L, De Bosschere K. Speeding up architectural simulations for high-performance processors[J]. Simulation, 2004, 80(9): 451−468, articleTitle=null, refAbstract=null), Reference(id=1327011928930627893, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hongwei, Shi Jinglin, Zhu Ziyuan. An expected hypervolume improvement algorithm for architectural exploration of embedded processors[C]//Proc of the 53rd Annual Design Automation Conf. New York: ACM, 2016: 161: 1−161: 6, articleTitle=null, refAbstract=null), Reference(id=1327011929001931062, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Bai Chen, Sun Qi, Zhai Jianwang, et al. BOOM-Explorer: RISC-V BOOM microarchitecture design space exploration framework[C/OL]//Proc of the 40th IEEE/ACM Int Conf on Computer Aided Design. Piscataway, NJ: IEEE, 2021[2023-12-17]. https://ieeexplore.ieee.org/document/9643455, articleTitle=null, refAbstract=null), Reference(id=1327011929090011447, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi J J, Lilja D J, Hawkins D M. A statistically rigorous approach for improving simulation methodology[C]//Proc of the 9th Int Symp on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2003: 281–291, articleTitle=null, refAbstract=null), Reference(id=1327011929261977912, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Monchiero M, Canal R, González A. Power/performance/thermal design-space exploration for multicore architectures[J]. IEEE Transactions on Parallel and Distributed Systems, 2008, 19(5): 666−681, articleTitle=null, refAbstract=null), Reference(id=1327011929345863993, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=包云岗,常轶松,韩银和,等. 处理器芯片敏捷设计方法:问题与挑战[J]. 计算机研究与发展,2021,58(6):1131−1145, articleTitle=null, refAbstract=null), Reference(id=1327011929429750074, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Bao Yungang, Chang Yisong, Han Yinhe, et al. Agile design of processor chips: Issues and challenges[J]. Journal of Computer Research and Development, 2021, 58(6): 1131−1145 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011929496858939, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Standard Performance Evaluation Corporation. SPEC CPU2017[EB/OL]. (2012-12-06)[2023-12-01]. https://www.spec.org/cpu2017, articleTitle=null, refAbstract=null), Reference(id=1327011929610105148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi J J, Lilja D J. Simulation of computer architectures: Simulators, benchmarks, methodologies, and recommendations[J]. IEEE Transactions on Computers, 2006, 55(3): 268−280, articleTitle=null, refAbstract=null), Reference(id=1327011929685602621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Qi, Chen Tianshi, Chen Yunji, et al. Accelerating architectural simulation via statistical techniques: A survey[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2016, 35(3): 433−446, articleTitle=null, refAbstract=null), Reference(id=1327011929765294398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=O’Neal K, Brisk P. Predictive modeling for CPU, GPU, and FPGA performance and power consumption: A survey[C]//Proc of the 2018 IEEE Computer Society Annual Symp on VLSI. Los Alamitos, CA: IEEE Computer Society, 2018: 763–768, articleTitle=null, refAbstract=null), Reference(id=1327011929844986175, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Tianshi, Guo Qi, Tang Ke, et al. ArchRanker: A ranking approach to design space exploration[C]//Proc of the 41st Int Symp on Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2014: 85–96, articleTitle=null, refAbstract=null), Reference(id=1327011929949843777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Yi, Mishra N, Hoffmann H. Generative and multi-phase learning for computer systems optimization[C]//Proc of the 46th Int Symp on Computer Architecture. New York: ACM, 2019: 39–52, articleTitle=null, refAbstract=null), Reference(id=1327011930079867202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Panerati J, Beltrame G. A comparative evaluation of multi-objective exploration algorithms for high-level design[J]. ACM Transactions on Design Automation of Electronic Systems, 2014, 19(2): 15: 1–15: 22, articleTitle=null, refAbstract=null), Reference(id=1327011930230862147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Palermo G, Silvano C, Zaccaria V. ReSPIR: A response surface-based pareto iterative refinement for application-specific design space exploration[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2009, 28(12): 1816−1829, articleTitle=null, refAbstract=null), Reference(id=1327011930314748228, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Zaccaria V, et al. DeSpErate++: An enhanced design space exploration framework using predictive simulation scheduling[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015, 34(2): 293−306, articleTitle=null, refAbstract=null), Reference(id=1327011930394440005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Cammarota R, Beni L A, Nicolau A, et al. Effective evaluation of multi-core based systems[C]//Proc of the 12th Int Symp on Parallel and Distributed Computing. Piscataway, NJ: IEEE, 2013: 19–25, articleTitle=null, refAbstract=null), Reference(id=1327011930474131782, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=KleinOsowski A J, Lilja D J. MinneSPEC: A new spec benchmark workload for simulation-based computer architecture research[J]. IEEE Computer Architecture Letters, 2002, 1(1): 7−10, articleTitle=null, refAbstract=null), Reference(id=1327011930570600775, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Eeckhout L, Vandierendonck H, De Bosschere K. Workload design: Selecting representative program-input pairs[C]//Proc of the 11th Int Conf on Parallel Architectures and Compilation Techniques. Los Alamitos, CA: IEEE Computer Society, 2002: 83–94, articleTitle=null, refAbstract=null), Reference(id=1327011930818064712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Breughe M, Eeckhout L. Selecting representative benchmark inputs for exploring microprocessor design spaces[J]. ACM Transactions on Architecture and Code Optimization, 2013, 10(4): 37: 1−37: 24, articleTitle=null, refAbstract=null), Reference(id=1327011930897756489, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Joshi A, Phansalkar A, Eeckhout L, et al. Measuring benchmark similarity using inherent program characteristics[J]. IEEE Transactions on Computers, 2006, 55(6): 769−782, articleTitle=null, refAbstract=null), Reference(id=1327011930990031178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Vandeputte F, Eeckhout L. Phase complexity surfaces: Characterizing time-varying program behavior[C]//Proc of the 3rd High Performance Embedded Architectures and Compilers. Berlin: Springer, 2008: 320–334, articleTitle=null, refAbstract=null), Reference(id=1327011931078111563, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhan Hongping, Lin Weiwei, Mao Feiqiao, et al. BenchSubset: A framework for selecting benchmark subsets based on consensus clustering[J]. International Journal of Intelligent Systems, 2022, 37(8): 5248−5271, articleTitle=null, refAbstract=null), Reference(id=1327011931157803340, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Sheidaeian H, Fatemi O. Toward a general framework for jointly processor-workload empirical modeling[J]. The Journal of Supercomputing, 2021, 77(6): 5319−5353, articleTitle=null, refAbstract=null), Reference(id=1327011931229106509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Phansalkar A, Joshi A, John L K. Analysis of redundancy and application balance in the SPEC CPU2006 benchmark suite[C]//Proc of the 34th Int Symp on Computer Architecture. New York: ACM, 2007: 412–423, articleTitle=null, refAbstract=null), Reference(id=1327011931300409678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Limaye A, Adegbija T. A workload characterization of the SPEC CPU2017 benchmark suite[C]//Proc of the 2018 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2018: 149–158, articleTitle=null, refAbstract=null), Reference(id=1327011932973936976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Panda R, Song Shuang, Dean J, et al. Wait of a decade: Did SPEC CPU 2017 broaden the performance horizon[C]//Proc of the 23rd IEEE Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2018: 271–282, articleTitle=null, refAbstract=null), Reference(id=1327011933053628753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Qingrui, Wu Xiaolong, Kittinger L, et al. BenchPrime: Effective building of a hybrid benchmark suite[J]. ACM Transactions in Embedded Computing Systems, 2017, 16(5): 179: 1−179: 22, articleTitle=null, refAbstract=null), Reference(id=1327011933116543314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Wunderlich R E, Wenisch T F, Falsafi B, et al. SMARTS: Accelerating microarchitecture simulation via rigorous statistical sampling[C]//Proc of the 30th Annual Int Symp on Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2003: 84–95, articleTitle=null, refAbstract=null), Reference(id=1327011933229789523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Hassani S, Southern G, Renau J. LiveSim: Going live with microarchitecture simulation[C]//Proc of the 22nd IEEE Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2016: 606–617, articleTitle=null, refAbstract=null), Reference(id=1327011933292704084, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Hamerly G, Perelman E, Lau J, et al. SimPoint 3.0: Faster and more flexible program phase analysis[J/OL]. Journal of Instruction-Level Parallelism, 2005[2023-12-18]. http://www.jilp.org/vol7/v7paper14.pdf, articleTitle=null, refAbstract=null), Reference(id=1327011933355618645, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Sherwood T, Perelman E, Hamerly G, et al. Discovering and exploiting program phases[J]. IEEE Micro, 2003, 23(6): 84−93, articleTitle=null, refAbstract=null), Reference(id=1327011933414338902, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Xipeng, Zhong Yutao, Ding Chen. Locality phase prediction[C]//Proc of the 11th Int Conf on Architectural Support for Programming Languages and Operating Systems. New York: ACM, 2004: 165–176, articleTitle=null, refAbstract=null), Reference(id=1327011933468864855, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Ardestani E K, Renau J. ESESC: A fast multicore simulator using time-based sampling[C]//Proc of the 19th Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2013: 448–459, articleTitle=null, refAbstract=null), Reference(id=1327011933531779416, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Chuntao, Yu Zhibin, Jin Hai, et al. PCantorSim: Accelerating parallel architecture simulation through fractal-based sampling[J]. ACM Transactions on Architecture and Code Optimization, 2013, 10(4): 49: 1–49: 24, articleTitle=null, refAbstract=null), Reference(id=1327011933590499673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Sabu A, Patil H, Heirman W, et al. LoopPoint: Checkpoint-driven sampled simulation for multi-threaded applications[C]//Proc of the 28th Int Symp on High-Performance Computer Architecture. Piscataway, NJ: IEEE, 2022: 604–618, articleTitle=null, refAbstract=null), Reference(id=1327011933649219930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlson T E, Heirman W, Van Craeynest K, et al. BarrierPoint: Sampled simulation of multi-threaded applications[C]//Proc of the 2014 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2014: 2–12, articleTitle=null, refAbstract=null), Reference(id=1327011933703745883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Grass T, Carlson T E, Rico A, et al. Sampled simulation of task-based programs[J]. IEEE Transactions on Computers, 2019, 68(2): 255−269, articleTitle=null, refAbstract=null), Reference(id=1327011933762466140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Wenisch T F, Wunderlich R E, Ferdman M, et al. SimFlex: Statistical sampling of computer system simulation[J]. IEEE Micro, 2006, 26(4): 18−31, articleTitle=null, refAbstract=null), Reference(id=1327011933833769309, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Yinan, Yu Zihao, Tang Dan, et al. Towards developing high performance RISC-V processors using agile methodology[C]//Proc of the 55th IEEE/ACM Int Symp on Microarchitecture. Piscataway, NJ: IEEE, 2022: 1178–1199, articleTitle=null, refAbstract=null), Reference(id=1327011933896683870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Bryan P D, Rosier M C, Conte T M. Reverse state reconstruction for sampled microarchitectural simulation[C]//Proc of the 2007 IEEE Int Symp on Performance Analysis of Systems & Software. Los Alamitos, CA: IEEE Computer Society, 2007: 190–199, articleTitle=null, refAbstract=null), Reference(id=1327011933972181343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Nussbaum S, Smith J E. Modeling superscalar processors via statistical simulation[C]//Proc of the 10th Int Conf on Parallel Architectures and Compilation Techniques. Los Alamitos, CA: IEEE Computer Society, 2001: 15–24, articleTitle=null, refAbstract=null), Reference(id=1327011934047678816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Eeckhout L, Nussbaum S, Smith J E, et al. Statistical simulation: Adding efficiency to the computer designer’s toolbox[J]. IEEE Micro, 2003, 23(5): 26−38, articleTitle=null, refAbstract=null), Reference(id=1327011934110593377, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Oskin M, Chong F T, Farrens M. HLS: Combining statistical and symbolic simulation to guide microprocessor designs[C]//Proc of the 27th Int Symp on Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2000: 71–82, articleTitle=null, refAbstract=null), Reference(id=1327011934173507938, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Bell R H, John L K. Improved automatic testcase synthesis for performance model validation[C]//Proc of the 19th Annual Int Conf on Supercomputing. New York: ACM, 2000: 111–120, articleTitle=null, refAbstract=null), Reference(id=1327011934253199715, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Genbrugge D, Eeckhout L. Statistical simulation of chip multiprocessors running multi-program workloads[C]//Proc of the 25th Int Conf on Computer Design. Piscataway, NJ: IEEE, 2007: 464–471, articleTitle=null, refAbstract=null), Reference(id=1327011934324502884, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Genbrugge D, Eeckhout L. Chip multiprocessor design space exploration through statistical simulation[J]. IEEE Transactions on Computers, 2009, 58(12): 1668−1681, articleTitle=null, refAbstract=null), Reference(id=1327011934387417445, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Hughes C, Li T. Accelerating multi-core processor design space evaluation using automatic multi-threaded workload synthesis[C]//Proc of the 4th Int Symp on Workload Characterization. Los Alamitos, CA: IEEE Computer Society, 2008: 163–172, articleTitle=null, refAbstract=null), Reference(id=1327011934454526310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Balakrishnan G, Solihin Y. WEST: Cloning data cache behavior using stochastic traces[C]//Proc of the 18th IEEE Int Symp on High-Performance Comp Architecture. Los Alamitos, CA: IEEE Computer Society, 2012: 1–12, articleTitle=null, refAbstract=null), Reference(id=1327011934521635175, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Awad A, Solihin Y. STM: Cloning the spatial and temporal memory access behavior[C]//Proc of the 20th IEEE Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2014: 237–247, articleTitle=null, refAbstract=null), Reference(id=1327011934588744040, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yipeng, Awad A, Solihin Y. Clone morphing: Creating new workload behavior from existing applications[C]//Proc of the 2017 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2017: 97–108, articleTitle=null, refAbstract=null), Reference(id=1327011934660047209, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yipeng, Balakrishnan G, Solihin Y. MeToo: Stochastic modeling of memory traffic timing behavior[C]//Proc of the 24th Int Conf on Parallel Architecture and Compilation. Los Alamitos, CA: IEEE Computer Society, 2015: 457–467, articleTitle=null, refAbstract=null), Reference(id=1327011934718767466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Hekstra G J, La Hei G D, Bingley P, et al. TriMedia CPU64 design space exploration[C]//Proc of the 17th IEEE Int Conf on Computer Design: VLSI in Computers and Processors. Los Alamitos, CA: IEEE Computer Society, 1999: 599–606, articleTitle=null, refAbstract=null), Reference(id=1327011934777487723, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Fornaciari W, Sciuto D, Silvano C, et al. A design framework to efficiently explore energy-delay tradeoffs[C]//Proc of the 9th Int Symp on Hardware/Software Codesign. New York: ACM, 2001: 260–265, articleTitle=null, refAbstract=null), Reference(id=1327011934844596588, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Fornaciari W, Sciuto D, Silvano C, et al. A sensitivity-based design space exploration methodology for embedded systems[J]. Design Automation for Embedded Systems, 2002, 7(1): 7−33, articleTitle=null, refAbstract=null), Reference(id=1327011934903316845, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Sheldon D, Kumar R, Lysecky R, et al. Application-specific customization of parameterized FPGA soft-core processors[C]//Proc of the 25th IEEE/ACM Int Conf on Computer-Aided Design. New York: ACM, 2006: 261–268, articleTitle=null, refAbstract=null), Reference(id=1327011934962037102, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Dandan, Yao Shuzhen, Liu Yuhang, et al. Efficient design space exploration via statistical sampling and AdaBoost learning[C]//Proc of the 53rd Annual Design Automation Conf. New York: ACM, 2016: 142: 1−142: 6, articleTitle=null, refAbstract=null), Reference(id=1327011935029145967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hongwei, Zhu Ziyuan, Shi Jinglin, et al. An accurate acosso metamodeling technique for processor architecture design space exploration[C]//Proc of the 20th Asia and South Pacific Design Automation Conf. Piscataway, NJ: IEEE, 2015: 689–694, articleTitle=null, refAbstract=null), Reference(id=1327011935092060528, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Zaccaria V, et al. Design-space exploration and runtime resource management for multicores[J]. ACM Transactions on Embedded Computing Systems, 2013, 13(2): 20: 1−20: 27, articleTitle=null, refAbstract=null), Reference(id=1327011935150780785, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Jahr R, Calborean H, Vintan L, et al. Boosting design space explorations with existing or automatically learned knowledge[C]//Proc of the 15th Measurement, Modelling, and Evaluation of Computing Systems and Dependability and Fault Tolerance. Berlin: Springer, 2012: 221–235, articleTitle=null, refAbstract=null), Reference(id=1327011935217889650, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Palesi M, Givargis T. Multi-objective design space exploration using genetic algorithms[C]//Proc of the 10th Int Symp on Hardware/Software Codesign. New York: ACM, 2002: 67–72, articleTitle=null, refAbstract=null), Reference(id=1327011935297581427, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Eyerman S, Eeckhout L, De Bosschere K. Efficient design space exploration of high performance embedded out-of-order processors[C]//Proc of the 9th Design, Automation & Test in Europe Conf and Exhibition. Piscataway, NJ: IEEE, 2006: 351−356, articleTitle=null, refAbstract=null), Reference(id=1327011935364690292, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Ascia G, Catania V, Di Nuovo A G, et al. Efficient design space exploration for application specific systems-on-a-chip[J]. Journal of Systems Architecture, 2007, 53(10): 733−750, articleTitle=null, refAbstract=null), Reference(id=1327011935431799157, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Silvano C, et al. Multi-processor system-on-chip design space exploration based on multi-level modeling techniques[C]//Proc of the 9th Int Conf on Embedded Computer Systems: Architectures, Modeling and Simulation. Piscataway, NJ: IEEE, 2009: 118–124, articleTitle=null, refAbstract=null), Reference(id=1327011935494713718, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Zaccaria V, et al. OSCAR: An optimization methodology exploiting spatial correlation in multicore design spaces[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2012, 31(5): 740−753, articleTitle=null, refAbstract=null), Reference(id=1327011935557628279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Burger D, Austin T M. The SimpleScalar tool set, version 2.0[J]. ACM SIGARCH Computer Architecture News, 1997, 25(3): 13−25, articleTitle=null, refAbstract=null), Reference(id=1327011935620542840, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Renau J, Fraguela B, Tuck J, et al. SESC simulator[EB/OL]. 2005[2023-12-01]. http://sesc.sourceforge.net, articleTitle=null, refAbstract=null), Reference(id=1327011935708623225, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Binkert N, Beckmann B, Black G, et al. The gem5 simulator[J]. ACM SIGARCH Computer Architecture News, 2011, 39(2): 1−7, articleTitle=null, refAbstract=null), Reference(id=1327011935771537786, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Chiou D, Sunwoo D, Kim J, et al. FPGA-accelerated simulation technologies (FAST): Fast, full-system, cycle-accurate simulators[C]//Proc of the 40th Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2007: 249–261, articleTitle=null, refAbstract=null), Reference(id=1327011937432482171, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Chung E S, Nurvitadhi E, Hoe J C, et al. A complexity-effective architecture for accelerating full-system multiprocessor simulations using FPGAs[C]//Proc of the 16th Int ACM/SIGDA Symp on Field Programmable Gate Arrays. New York: ACM, 2008: 77–86, articleTitle=null, refAbstract=null), Reference(id=1327011937503785341, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Chung E S, Papamichael M K, Nurvitadhi E, et al. ProtoFlex: Towards scalable, full-system multiprocessor simulations using FPGAs[J]. ACM Transactions on Reconfigurable Technology and Systems, 2009, 2(2): 15: 1–15: 32, articleTitle=null, refAbstract=null), Reference(id=1327011937583477118, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Zhangxi, Waterman A, Avizienis R, et al. RAMP Gold: An FPGA-based architecture simulator for multiprocessors[C]//Proc of the 47th Design Automation Conf. New York: ACM, 2010: 463–468, articleTitle=null, refAbstract=null), Reference(id=1327011937700917631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Pellauer M, Adler M, Kinsy M, et al. HAsim: FPGA-based high-detail multicore simulation using time-division multiplexing[C]//Proc of the 17th Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2011: 406–417, articleTitle=null, refAbstract=null), Reference(id=1327011937818358144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Karandikar S, Mao H, Kim D, et al. FireSim: FPGA-accelerated cycle-exact scale-out system simulation in the public cloud[C]//Proc of the 45th Annual Int Symp on Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2018: 29–42, articleTitle=null, refAbstract=null), Reference(id=1327011938007101825, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Balkind J, McKeown M, Fu Yaosheng, et al. OpenPiton: An open source manycore research framework[C]//Proc of the 21st Int Conf on Architectural Support for Programming Languages and Operating Systems. New York: ACM, 2016: 217–232, articleTitle=null, refAbstract=null), Reference(id=1327011938086793602, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Shenghong, Possignolo R T, Skinner H B, et al. LiveHD: A productive live hardware development flow[J]. IEEE Micro, 2020, 40(4): 67−75, articleTitle=null, refAbstract=null), Reference(id=1327011938191651203, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Petrisko D, Gilani F, Wyse M, et al. BlackParrot: An agile open-source RISC-V multicore for accelerator socs[J]. IEEE Micro, 2020, 40(4): 93−102, articleTitle=null, refAbstract=null), Reference(id=1327011938325868932, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Sizhuo, Wright A, Bourgeat T, et al. Composable building blocks to open up processor design[C]//Proc of the 51st Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2018: 68–81, articleTitle=null, refAbstract=null), Reference(id=1327011938397172101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Amid A, Biancolin D, Gonzalez A, et al. Chipyard: Integrated design, simulation, and implementation framework for custom socs[J]. IEEE Micro, 2020, 40(4): 10−21, articleTitle=null, refAbstract=null), Reference(id=1327011938455892358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Joseph P J, Vaswani K, Thazhuthaveetil M J. Construction and use of linear regression models for processor performance analysis[C]//Proc of the 12th Int Symp on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2006: 99–108, articleTitle=null, refAbstract=null), Reference(id=1327011938548167047, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Agarwal N, Jain T, Zahran M. Performance prediction for multi-threaded applications[C]//Proc of the 2nd Int Workshop on AI-assisted Design for Architecture. New York: ACM, 2019: 71−76, articleTitle=null, refAbstract=null), Reference(id=1327011938632053128, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Joseph P J, Vaswani K, Thazhuthaveetil M J. A predictive performance model for superscalar processors[C]//Proc of the 39th Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2006: 161–170, articleTitle=null, refAbstract=null), Reference(id=1327011938720133513, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Cho C B, Zhang Wangyuan, Li Tao. Informed microarchitecture design space exploration using workload dynamics[C]//Proc of the 40th Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2007: 274–285, articleTitle=null, refAbstract=null), Reference(id=1327011938778853770, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Ould-Ahmed-Vall E, Woodlee J, Yount C, et al. Using model trees for computer architecture performance analysis of software applications[C]//Proc of the 2007 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2007: 116–125, articleTitle=null, refAbstract=null), Reference(id=1327011938871128459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Powell A, Savvas-Bouganis C, Cheung P Y K. High-level power and performance estimation of FPGA-based soft processors and its application to design space exploration[J]. Journal of Systems Architecture, 2013, 59(10): 1144−1156, articleTitle=null, refAbstract=null), Reference(id=1327011938955014540, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Mankodi A, Bhatt A, Chaudhury B. Predicting physical computer systems performance and power from simulation systems using machine learning model[J]. Computing, 2022, 105(5): 1−19, articleTitle=null, refAbstract=null), Reference(id=1327011939106009485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Dandan, Yao Shuzhen, Wang Ying. Processor design space exploration via statistical sampling and semi-supervised ensemble learning[J]. IEEE Access, 2018, 6: 25495−25505, articleTitle=null, refAbstract=null), Reference(id=1327011939206672782, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Qi, Chen Tianshi, Chen Yunji, et al. Effective and efficient microprocessor design space exploration using unlabeled design configurations[C]//Proc of the 22nd Int Joint Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2011: 1671–1677, articleTitle=null, refAbstract=null), Reference(id=1327011939257004431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Hoste K, Phansalkar A, Eeckhout L, et al. Performance prediction based on inherent program similarity[C]//Proc of the 15th Int Conf on Parallel Architectures and Compilation Techniques. New York: ACM, 2006: 114–122, articleTitle=null, refAbstract=null), Reference(id=1327011939315724688, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Qi, Chen Tianshi, Chen Yunji, et al. Microarchitectural design space exploration made fast[J]. Microprocessors and Microsystems, 2013, 37(1): 41−51, articleTitle=null, refAbstract=null), Reference(id=1327011939374444945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahmadinejad H, Fatemi O. Moving towards grey-box predictive models at micro-architecture level by investigating inherent program characteristics[J]. IET Computers Digital Techniques, 2018, 12(2): 53−61, articleTitle=null, refAbstract=null), Reference(id=1327011939428970898, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Taha T M, Wills S. An instruction throughput model of superscalar processors[J]. IEEE Transactions on Computers, IEEE, 2008, 57(3): 389−403, articleTitle=null, refAbstract=null), Reference(id=1327011939496079763, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Chi, Chen Xi, Dick R P, et al. Cache contention and application performance prediction for multi-core systems[C]//Proc of the 2010 IEEE Int Symp on Performance Analysis of Systems & Software. Los Alamitos, CA: IEEE Computer Society, 2010: 76–86, articleTitle=null, refAbstract=null), Reference(id=1327011939579965844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Eyerman S, Eeckhout L, Karkhanis T, et al. A mechanistic performance model for superscalar out-of-order processors[J]. ACM Transactions on Computer Systems, 2009, 27(2): 3: 1–3: 37, articleTitle=null, refAbstract=null), Reference(id=1327011939642880405, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Breughe M B, Eyerman S, Eeckhout L. Mechanistic analytical modeling of superscalar in-order processor performance[J]. ACM Transactions on Architecture and Code Optimization, 2015, 11(4): 50: 1–50: 26, articleTitle=null, refAbstract=null), Reference(id=1327011939701600662, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlson T E, Heirman W, Eeckhout L. Sniper: Exploring the level of abstraction for scalable and accurate parallel multi-core simulation[C]//Proc of the 2011 Conf on High Performance Computing Networking, Storage and Analysis. New York: ACM, 2011: 52: 1−52: 12, articleTitle=null, refAbstract=null), Reference(id=1327011939760320919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Lei, Tang Yuxing, Deng Yu, et al. A scalable and fast microprocessor design space exploration methodology[C]//Proc of the 9th Int Symp on Embedded Multicore/Many-core Systems-on-Chip. Los Alamitos, CA: IEEE Computer Society, 2015: 33–40, articleTitle=null, refAbstract=null), Reference(id=1327011939848401304, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee J, Jang H, Kim J. RpStacks: Fast and accurate processor design space exploration using representative stall-event stacks[C]//Proc of the 47th Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2014: 255–267, articleTitle=null, refAbstract=null), Reference(id=1327011939919704473, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Jang H, Jo J E, Lee J, et al. RpStacks-MT: A high-throughput design evaluation methodology for multi-core processors[C]//Proc of the 51st Annual IEEE/ACM Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2018: 586–599, articleTitle=null, refAbstract=null), Reference(id=1327011939978424730, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Noonburg D B, Shen J P. A framework for statistical modeling of superscalar processor performance[C]//Proc of the 3rd Int Symp on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 1997: 298–309, articleTitle=null, refAbstract=null), Reference(id=1327011940041339291, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen X E, Aamodt T M. A first-order fine-grained multithreaded throughput model[C]//Proc of the 15th Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2009: 329–340, articleTitle=null, refAbstract=null), Reference(id=1327011940095865244, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Y, Mitra T. An analytical approach for fast and accurate design space exploration of instruction caches[J]. ACM Transactions on Embedded Computing Systems, 2013, 13(3): 43: 1−43: 29, articleTitle=null, refAbstract=null), Reference(id=1327011940179751325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Hartstein A, Puzak T R. The optimum pipeline depth for a microprocessor[C]//Proc of the 29th Annual Int Symp on Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2002: 7–13, articleTitle=null, refAbstract=null), Reference(id=1327011940238471582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen X E, Aamodt T M. Hybrid analytical modeling of pending cache hits, data prefetching, and mshrs[J]. ACM Transactions on Architecture and Code Optimization, 2011, 8(3): 59−70, articleTitle=null, refAbstract=null), Reference(id=1327011940309774751, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Li L, Pandey S, Flynn T, et al. SimNet: Accurate and high-performance computer architecture simulation using deep learning[C]//Proc of the 2022 ACM SIGMETRICS/IFIP Performance Joint Int Conf on Measurement and Modeling of Computer Systems. New York: ACM, 2022: 67–68, articleTitle=null, refAbstract=null), Reference(id=1327011941958136224, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Panda R, John L K. Proxy benchmarks for emerging big-data workloads[C]//Proc of the 26th Int Conf on Parallel Architectures and Compilation Techniques. Los Alamitos, CA: IEEE Computer Society, 2017: 105–116, articleTitle=null, refAbstract=null), Reference(id=1327011942025245089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Kang S, Kumar R. Magellan: A search and machine learning-based framework for fast multi-core design space exploration and optimization[C]//Proc of the 2008 Design, Automation and Test in Europe. New York: ACM, 2008: 1432–1437, articleTitle=null, refAbstract=null), Reference(id=1327011942117519778, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Qi, Chen Tianshi, Zhou Zhihua, et al. Robust design space modeling[J]. ACM Transactions on Design Automation of Electronic Systems, 2015, 20(2): 18: 1–18: 22, articleTitle=null, refAbstract=null), Reference(id=1327011942176240035, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=张乾龙,侯锐,杨思博,等. 体系结构模拟器在处理器设计过程中的作用[J]. 计算机研究与发展,2019,56(12):2702−2719, articleTitle=null, refAbstract=null), Reference(id=1327011942243348900, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Qianlong, Hou Rui, Yang Sibo, et al. The role of architecture simulators in the process of CPU design[J]. Journal of Computer Research and Development, 2019, 56(12): 2702−2719 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011942323040677, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Hoste K, Eeckhout L. Microarchitecture-independent workload characterization[J]. IEEE Micro, 2007, 27(3): 63−72, articleTitle=null, refAbstract=null), Reference(id=1327011942385955238, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Zhanpeng, Cheng A C. Evolutionary benchmark subsetting[J]. IEEE Micro, 2008, 28(6): 20−36, articleTitle=null, refAbstract=null), Reference(id=1327011942453064103, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Zhanpeng, Cheng A C. SubsetTrio: An evolutionary, geometric, and statistical benchmark subsetting framework[J]. ACM Transactions on Modeling and Computer Simulation, 2011, 21(3): 21: 1–21: 23, articleTitle=null, refAbstract=null), Reference(id=1327011942536950184, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Zhanpeng, Cheng A C. Improve simulation efficiency using statistical benchmark subsetting: An implantbench case study[C]//Proc of the 45th Annual Design Automation Conf. New York: ACM, 2008: 970–973, articleTitle=null, refAbstract=null), Reference(id=1327011942620836265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee C, Potkonjak M, Mangione-Smith W H. MediaBench: A tool for evaluating and synthesizing multimedia and communications systems[C]//Proc of the 30th Annual Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 1997: 330–335, articleTitle=null, refAbstract=null), Reference(id=1327011942704722346, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Guthaus M R, Ringenberg J S, Ernst D, et al. MiBench: A free, commercially representative embedded benchmark suite[C]//Proc of the 4th Annual IEEE Int Workshop on Workload Characterization. Piscataway, NJ: IEEE, 2001: 3–14, articleTitle=null, refAbstract=null), Reference(id=1327011942776025515, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Standard Performance Evaluation Corporation. SPEC CPU2000[EB/OL]. (2007-06-07)[2023-12-01]. https://www.spec.org/cpu2000, articleTitle=null, refAbstract=null), Reference(id=1327011942838940077, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=127, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Standard Performance Evaluation Corporation. SPEC CPU2006[EB/OL]. (2023-01-06)[2023-12-01]. https://www.spec.org/cpu2006, articleTitle=null, refAbstract=null), Reference(id=1327011942914437550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=128, rfOrder=129, authorNames=null, journalName=null, refType=null, unstructuredReference=Bienia C, Kumar S, Singh J P, et al. The parsec benchmark suite: Characterization and architectural implications[C]//Proc of the 17th Int Conf on Parallel Architectures and Compilation Techniques. New York: ACM, 2008: 72–81, articleTitle=null, refAbstract=null), Reference(id=1327011943002517935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=129, rfOrder=130, authorNames=null, journalName=null, refType=null, unstructuredReference=Woo S C, Ohara M, Torrie E, et al. The splash−2 programs: Characterization and methodological considerations[C]//Proc of the 22nd Annual Int Symp on Computer architecture. New York: ACM, 1995: 24–36, articleTitle=null, refAbstract=null), Reference(id=1327011943078015408, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=130, rfOrder=131, authorNames=null, journalName=null, refType=null, unstructuredReference=Chandra D, Guo Fei, Kim S, et al. Predicting inter-thread cache contention on a chip multi-processor architecture[C]//Proc of the 11th Int Symp on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2005: 340–351, articleTitle=null, refAbstract=null), Reference(id=1327011943140929969, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=131, rfOrder=132, authorNames=null, journalName=null, refType=null, unstructuredReference=Hsu W C, Chen H, Yew P C, et al. On the predictability of program behavior using different input data sets[C]//Proc of the 6th Annual Workshop on Interaction between Compilers and Computer Architectures. Los Alamitos, CA: IEEE Computer Society, 2002: 45–53, articleTitle=null, refAbstract=null), Reference(id=1327011943283536306, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=132, rfOrder=133, authorNames=null, journalName=null, refType=null, unstructuredReference=Hoste K, Eeckhout L. Comparing benchmarks using key microarchitecture-independent characteristics[C]//Proc of the 2nd IEEE Int Symp on Workload Characterization. Los Alamitos, CA: IEEE Computer Society, 2006: 83–92, articleTitle=null, refAbstract=null), Reference(id=1327011943480668595, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=133, rfOrder=134, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi J J, Sendag R, Eeckhout L, et al. Evaluating benchmark subsetting approaches[C]//Proc of the 2nd IEEE Int Symp on Workload Characterization. Los Alamitos, CA: IEEE Computer Society, 2006: 93–104, articleTitle=null, refAbstract=null), Reference(id=1327011943774269876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=134, rfOrder=135, authorNames=null, journalName=null, refType=null, unstructuredReference=Conte T M, Hirsch M A, Menezes K N. Reducing state loss for effective trace sampling of superscalar processors[C]//Proc of the 14th Int Conf on Computer Design. Los Alamitos, CA: IEEE Computer Society, 1996: 468–477, articleTitle=null, refAbstract=null), Reference(id=1327011943862350261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=135, rfOrder=136, authorNames=null, journalName=null, refType=null, unstructuredReference=Patil H, Cohn R, Charney M, et al. Pinpointing representative portions of large Intel® Itanium® programs with dynamic instrumentation[C]//Proc of the 37th Int Symp on Microarchitecture. Los Alamitos, CA: IEEE Computer Society, 2004: 81–92, articleTitle=null, refAbstract=null), Reference(id=1327011944009150902, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=136, rfOrder=137, authorNames=null, journalName=null, refType=null, unstructuredReference=Nair A A, John L K. Simulation points for SPEC CPU 2006[C]//Proc of the 26th Int Conf on Computer Design. Los Alamitos, CA: IEEE Computer Society, 2008: 397–403, articleTitle=null, refAbstract=null), Reference(id=1327011944088842679, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=137, rfOrder=138, authorNames=null, journalName=null, refType=null, unstructuredReference=Lau J, Perelman E, Calder B. Selecting software phase markers with code structure analysis[C]//Proc of the 4th Int Symp on Code Generation and Optimization. Los Alamitos, CA: IEEE Computer Society, 2006: 135–146, articleTitle=null, refAbstract=null), Reference(id=1327011944160145848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=138, rfOrder=139, authorNames=null, journalName=null, refType=null, unstructuredReference=Lahiri K, Kunnoth S. Fast IPC estimation for performance projections using proxy suites and decision trees[C]//Proc of the 2017 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2017: 77–86, articleTitle=null, refAbstract=null), Reference(id=1327011944285974969, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=139, rfOrder=140, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlson T E, Heirman W, Eeckhout L. Sampled simulation of multi-threaded applications[C]//Proc of the 2013 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2013: 2–12, articleTitle=null, refAbstract=null), Reference(id=1327011944353083834, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=140, rfOrder=141, authorNames=null, journalName=null, refType=null, unstructuredReference=Patil H, Pereira C, Stallcup M, et al. PinPlay: A framework for deterministic replay and reproducible analysis of parallel programs[C]//Proc of the 8th Annual IEEE/ACM Int Symp on Code Generation and Optimization. New York: ACM, 2010: 2–11, articleTitle=null, refAbstract=null), Reference(id=1327011944436969915, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=141, rfOrder=142, authorNames=null, journalName=null, refType=null, unstructuredReference=Patil H, Isaev A, Heirman W, et al. ELFies: Executable region checkpoints for performance analysis and simulation[C]//Proc of the 19th IEEE/ACM Int Symp on Code Generation and Optimization. Piscataway, NJ: IEEE, 2021: 126–136, articleTitle=null, refAbstract=null), Reference(id=1327011944525050300, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=142, rfOrder=143, authorNames=null, journalName=null, refType=null, unstructuredReference=Wenisch T F, Wunderlich R E, Falsafi B, et al. TurboSMARTS: Accurate microarchitecture simulation sampling in minutes[J]. ACM SIGMETRICS Performance Evaluation Review, 2005, 33(1): 408−409, articleTitle=null, refAbstract=null), Reference(id=1327011944592159165, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=143, rfOrder=144, authorNames=null, journalName=null, refType=null, unstructuredReference=Khan T M, Pérez D G, Temam O. Transparent sampling[C]//Proc of the 10th Int Conf on Embedded Computer Systems: Architectures, Modeling and Simulation. Piscataway, NJ: IEEE, 2010: 28–36, articleTitle=null, refAbstract=null), Reference(id=1327011944667656638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=144, rfOrder=145, authorNames=null, journalName=null, refType=null, unstructuredReference=Eeckhout L, Luo Yue, De Bosschere K, et al. BLRL: Accurate and efficient warmup for sampled processor simulation[J]. The Computer Journal, 2005, 48(4): 451−459, articleTitle=null, refAbstract=null), Reference(id=1327011944743154111, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=145, rfOrder=146, authorNames=null, journalName=null, refType=null, unstructuredReference=Haskins J W, Skadron K. Accelerated warmup for sampled microarchitecture simulation[J]. ACM Transactions on Architecture and Code Optimization, 2005, 2(1): 78−108, articleTitle=null, refAbstract=null), Reference(id=1327011944848011712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=146, rfOrder=147, authorNames=null, journalName=null, refType=null, unstructuredReference=Van Ertvelde L, Hellebaut F, Eeckhout L. Accurate and efficient cache warmup for sampled processor simulation through NSL–BLRL[J]. The Computer Journal, 2008, 51(2): 192−206, articleTitle=null, refAbstract=null), Reference(id=1327011946462818753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=147, rfOrder=148, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Chuntao, Yu Zhibin, Jin Hai, et al. Shorter on-line warmup for sampled simulation of multi-threaded applications[C]//Proc of the 44th Int Conf on Parallel Processing. Los Alamitos, CA: IEEE Computer Society, 2015: 350–359, articleTitle=null, refAbstract=null), Reference(id=1327011946529927618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=148, rfOrder=149, authorNames=null, journalName=null, refType=null, unstructuredReference=Bell R, Eeckhout L, John L, et al. Deconstructing and improving statistical simulation in HLS[C]//Proc of the 2004 Workshop on Duplicating, Deconstructing and Debunking held in Conjunction with the 31st Annual Int Symp on Computer Architecture. New York: ACM, 2004: 2−12, articleTitle=null, refAbstract=null), Reference(id=1327011946605425091, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=149, rfOrder=150, authorNames=null, journalName=null, refType=null, unstructuredReference=Joshi A, Yi J J, Bell R H, et al. Evaluating the efficacy of statistical simulation for design space exploration[C]//Proc of the 2006 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2006: 70–79, articleTitle=null, refAbstract=null), Reference(id=1327011946664145348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=150, rfOrder=151, authorNames=null, journalName=null, refType=null, unstructuredReference=Eeckhout L, Bell R H, Stougie B, et al. Control flow modeling in statistical simulation for accurate and efficient processor design studies[C]//Proc of the 31st Annual Int Symp on Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2004: 350–361, articleTitle=null, refAbstract=null), Reference(id=1327011946752225733, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=151, rfOrder=152, authorNames=null, journalName=null, refType=null, unstructuredReference=Bell R H, Bhatia R R, John L K, et al. Automatic testcase synthesis and performance model validation for high performance PowerPC processors[C]//Proc of the 2006 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2006: 154–165, articleTitle=null, refAbstract=null), Reference(id=1327011946836111814, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=152, rfOrder=153, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee H R, Sánchez D. Datamime: Generating representative benchmarks by automatically synthesizing datasets[C]//Proc of the 55th IEEE/ACM Int Symp on Microarchitecture. Piscataway, NJ: IEEE, 2022: 1144–1159, articleTitle=null, refAbstract=null), Reference(id=1327011946928386503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=153, rfOrder=154, authorNames=null, journalName=null, refType=null, unstructuredReference=Joshi A, Eeckhout L, Bell R H, et al. Performance cloning: A technique for disseminating proprietary applications as benchmarks[C]//Proc of the 2nd IEEE Int Symp on Workload Characterization. Los Alamitos, CA: IEEE Computer Society, 2006: 105–115, articleTitle=null, refAbstract=null), Reference(id=1327011947024855496, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=154, rfOrder=155, authorNames=null, journalName=null, refType=null, unstructuredReference=Joshi A M, Eeckhout L, John L K, et al. Automated microprocessor stressmark generation[C]//Proc of the 14th Int Symp on High Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2008: 229–239, articleTitle=null, refAbstract=null), Reference(id=1327011947121324489, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=155, rfOrder=156, authorNames=null, journalName=null, refType=null, unstructuredReference=Joshi A, Eeckhout L, Bell R H, et al. Distilling the essence of proprietary workloads into miniature benchmarks[J]. ACM Transactions on Architecture and Code Optimization, 2008, 5(2): 10: 1–10: 33, articleTitle=null, refAbstract=null), Reference(id=1327011947184239050, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=156, rfOrder=157, authorNames=null, journalName=null, refType=null, unstructuredReference=Ganesan K, John L K. Automatic generation of miniaturized synthetic proxies for target applications to efficiently design multicore processors[J]. IEEE Transactions on Computers, 2014, 63(4): 833−846, articleTitle=null, refAbstract=null), Reference(id=1327011947259736523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=157, rfOrder=158, authorNames=null, journalName=null, refType=null, unstructuredReference=Deniz E, Sen A, Kahne B, et al. MINIME: Pattern-aware multicore benchmark synthesizer[J]. IEEE Transactions on Computers, 2015, 64(8): 2239−2252, articleTitle=null, refAbstract=null), Reference(id=1327011947326845388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=158, rfOrder=159, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee K, Evans S, Cho S. Accurately approximating superscalar processor performance from traces[C]//Proc of the 2009 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2009: 238–248, articleTitle=null, refAbstract=null), Reference(id=1327011947385565645, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=159, rfOrder=160, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee K, Cho S. In-N-Out: Reproducing out-of-order superscalar processor behavior from reduced in-order traces[C]//Proc of the 19th Annual Int Symp on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems. Los Alamitos, CA: IEEE Computer Society, 2011: 126–135, articleTitle=null, refAbstract=null), Reference(id=1327011947448480206, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=160, rfOrder=161, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee K, Cho S. Accurately modeling superscalar processor performance with reduced trace[J]. Journal of Parallel and Distributed Computing, 2013, 73(4): 509−521, articleTitle=null, refAbstract=null), Reference(id=1327011947511394767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=161, rfOrder=162, authorNames=null, journalName=null, refType=null, unstructuredReference=Ganesan K, Jo J, John L K. Synthesizing memory-level parallelism aware miniature clones for SPEC CPU2006 and ImplantBench workloads[C]//Proc of the 2010 IEEE Int Symp on Performance Analysis of Systems & Software. Los Alamitos, CA: IEEE Computer Society, 2010: 33–44, articleTitle=null, refAbstract=null), Reference(id=1327011947578503632, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=162, rfOrder=163, authorNames=null, journalName=null, refType=null, unstructuredReference=Panda R, Zheng Xinnian, John L K. Accurate address streams for LLC and beyond (SLAB): A methodology to enable system exploration[C]//Proc of the 2017 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2017: 87–96, articleTitle=null, refAbstract=null), Reference(id=1327011947641418193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=163, rfOrder=164, authorNames=null, journalName=null, refType=null, unstructuredReference=Van Biesbrouck M, Sherwood T, Calder B. A co-phase matrix to guide simultaneous multithreading simulation[C]//Proc of the 2004 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2004: 45–56, articleTitle=null, refAbstract=null), Reference(id=1327011947708527058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=164, rfOrder=165, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi J J, Kodakara S V, Sendag R, et al. Characterizing and comparing prevailing simulation techniques[C]//Proc of the 11th Int Symp on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2005: 266–277, articleTitle=null, refAbstract=null), Reference(id=1327011947775635923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=165, rfOrder=166, authorNames=null, journalName=null, refType=null, unstructuredReference=Tairum Cruz M, Bischoff S, Rusitoru R. Shifting the barrier: Extending the boundaries of the barrierpoint methodology[C]//Proc of the 2018 IEEE Int Symp on Performance Analysis of Systems and Software. Los Alamitos, CA: IEEE Computer Society, 2018: 120–122, articleTitle=null, refAbstract=null), Reference(id=1327011947855327700, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=166, rfOrder=167, authorNames=null, journalName=null, refType=null, unstructuredReference=Bell R H, John L K. Efficient power analysis using synthetic testcases[C]//Proc of the 1st IEEE Int Symp Workload Characterization. Piscataway, NJ: IEEE, 2005: 110–118, articleTitle=null, refAbstract=null), Reference(id=1327011947935019477, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=167, rfOrder=168, authorNames=null, journalName=null, refType=null, unstructuredReference=Penry D A, Fay D, Hodgdon D, et al. Exploiting parallelism and structure to accelerate the simulation of chip multi-processors[C]//Proc of the 12th Int Symp on High-Performance Computer Architecture. Los Alamitos, CA: IEEE Computer Society, 2006: 29–40, articleTitle=null, refAbstract=null), Reference(id=1327011948014711254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=168, rfOrder=169, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Zaccaria V, et al. DeSpErate: Speeding-up design space exploration by using predictive simulation scheduling[C/OL]//Proc of the 17th Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2014[2023-12-18]. https://ieeexplore.ieee.org/document/6800432?arnumber=6800432, articleTitle=null, refAbstract=null), Reference(id=1327011948098597335, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=169, rfOrder=170, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Bin, Peng Lu, Ramadass B. Accurate and efficient processor performance prediction via regression tree based modeling[J]. Journal of Systems Architecture, 2009, 55(10): 457−467, articleTitle=null, refAbstract=null), Reference(id=1327011948195066328, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=170, rfOrder=171, authorNames=null, journalName=null, refType=null, unstructuredReference=Pang Jiufeng, Li Xiafeng, Xie Jinsong, et al. Microarchitectural design space exploration via support vector machine[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2010, 46(1): 55−63, articleTitle=null, refAbstract=null), Reference(id=1327011948312506841, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=171, rfOrder=172, authorNames=null, journalName=null, refType=null, unstructuredReference=Cook H, Skadron K. Predictive design space exploration using genetically programmed response surfaces[C]//Proc of the 45th Annual Design Automation Conf. New York: ACM, 2008: 960–965, articleTitle=null, refAbstract=null), Reference(id=1327011948459307482, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=172, rfOrder=173, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhai Jianwang, Bai Chen, Zhu Binwu, et al. McPAT-Calib: A microarchitecture power modeling framework for modern CPUs[C/OL]//Proc of the 40th IEEE/ACM Int Conf on Computer Aided Design. Piscataway, NJ: IEEE, 2021[2023-12-18]. https://ieeexplore.ieee.org/document/9643508, articleTitle=null, refAbstract=null), Reference(id=1327011948547387867, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=173, rfOrder=174, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhai Jianwang, Bai Chen, Zhu Binwu, et al. McPAT-calib: A RISC-V boom microarchitecture power modeling framework[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023, 42(1): 243−256, articleTitle=null, refAbstract=null), Reference(id=1327011948627079644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=174, rfOrder=175, authorNames=null, journalName=null, refType=null, unstructuredReference=Givargis T, Vahid F, Henkel J. System-level exploration for Pareto-optimal configurations in parameterized systems-on-a-chip[C]//Proc of the 20th IEEE/ACM Int Conf on Computer Aided Design. Los Alamitos, CA: IEEE Computer Society, 2001: 25–30, articleTitle=null, refAbstract=null), Reference(id=1327011948723548637, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=175, rfOrder=176, authorNames=null, journalName=null, refType=null, unstructuredReference=Yazdani R, Sheidaeian H, Salehi M E. A fast design space exploration for VLIW architectures[C]//Proc of the 22nd Iranian Conf on Electrical Engineering. Piscataway, NJ: IEEE, 2014: 856–861, articleTitle=null, refAbstract=null), Reference(id=1327011948820017630, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=176, rfOrder=177, authorNames=null, journalName=null, refType=null, unstructuredReference=Kansakar P, Munir A. A design space exploration methodology for parameter optimization in multicore processors[J]. IEEE Transactions on Parallel and Distributed Systems, 2018, 29(1): 2−15, articleTitle=null, refAbstract=null), Reference(id=1327011948933263840, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=177, rfOrder=178, authorNames=null, journalName=null, refType=null, unstructuredReference=Ascia G, Catania V, Di Nuovo A G, et al. Performance evaluation of efficient multi-objective evolutionary algorithms for design space exploration of embedded computer systems[J]. Applied Soft Computing, 2011, 11(1): 382−398, articleTitle=null, refAbstract=null), Reference(id=1327011949025538529, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=178, rfOrder=179, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Silvano C, et al. An efficient design space exploration methodology for multi-cluster VLIW architectures based on artificial neural networks[C]//Proc of the 16th IFIP/IEEE Int Conf on Very Large Scale Integration. Piscataway, NJ: IEEE, 2008: 13−15, articleTitle=null, refAbstract=null), Reference(id=1327011949101036003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=179, rfOrder=180, authorNames=null, journalName=null, refType=null, unstructuredReference=Zaccaria V, Palermo G, Castro F, et al. MULTICUBE Explorer: An open source framework for design space exploration of chip multi-processors[C]//Proc of the 23rd Int Conf on Architecture of Computing Systems. Hannover, Germany: VDE Verlag, 2010: 325–331, articleTitle=null, refAbstract=null), Reference(id=1327011949168144868, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=180, rfOrder=181, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Brankovic A, Palermo G, et al. A correlation-based design space exploration methodology for multi-processor systems-on-chip[C]//Proc of the 47th Design Automation Conf. New York: ACM, 2010: 120–125, articleTitle=null, refAbstract=null), Reference(id=1327011949231059429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=181, rfOrder=182, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Duo, Yan Mingyu, Liu Xin, et al. A high-accurate multi-objective exploration framework for design space of CPU[C/OL]//Proc of the 60th ACM/IEEE Design Automation Conf. Piscataway, NJ: IEEE, 2023[2023-12-18]. https://ieeexplore.ieee.org/document/10247790, articleTitle=null, refAbstract=null), Reference(id=1327011949293973990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=182, rfOrder=183, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Duo, Yan Mingyu, Teng Yihan, et al. A high-accurate multi-objective ensemble exploration framework for design space of CPU microarchitecture[C]//Proc of the 33rd Great Lakes Symp on VLSI 2023. New York: ACM, 2023: 379–383, articleTitle=null, refAbstract=null), Reference(id=1327011950946529767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=183, rfOrder=184, authorNames=null, journalName=null, refType=null, unstructuredReference=Beltrame G, Fossati L, Sciuto D. Decision-theoretic design space exploration of multiprocessor platforms[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2010, 29(7): 1083−1095, articleTitle=null, refAbstract=null), Reference(id=1327011951005250024, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=184, rfOrder=185, authorNames=null, journalName=null, refType=null, unstructuredReference=Beltrame G, Nicolescu G. A multi-objective decision-theoretic exploration algorithm for platform-based design[C]//Proc of the 14th Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2011: 1192−1195, articleTitle=null, refAbstract=null), Reference(id=1327011951068164585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=185, rfOrder=186, authorNames=null, journalName=null, refType=null, unstructuredReference=Sheldon D, Vahid F, Lonardi S. Soft-core processor customization using the design of experiments paradigm[C]//Proc of the 10th Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2007: 821−826, articleTitle=null, refAbstract=null), Reference(id=1327011951164633578, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=186, rfOrder=187, authorNames=null, journalName=null, refType=null, unstructuredReference=Mariani G, Palermo G, Silvano C, et al. Meta-model assisted optimization for design space exploration of multi-processor systems-on-chip[C]//Proc of the 12th Euromicro Conf on Digital System Design, Architectures, Methods and Tools. Los Alamitos, CA: IEEE Computer Society, 2009: 383–389, articleTitle=null, refAbstract=null), Reference(id=1327011951235936747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=187, rfOrder=188, authorNames=null, journalName=null, refType=null, unstructuredReference=Palermo G, Silvano C, Zaccaria V. Multi-objective design space exploration of embedded systems[J]. Journal of Embedded Computing, 2005, 1(3): 305−316, articleTitle=null, refAbstract=null), Reference(id=1327011951382737388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=188, rfOrder=189, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Nan, Xie Yuan, Hao Cong. IronMan: GNN-assisted design space exploration in high-level synthesis via reinforcement learning[C]//Proc of the 31st Great Lakes Symp on VLSI. New York: ACM, 2021: 39–44, articleTitle=null, refAbstract=null), Reference(id=1327011951458234861, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=189, rfOrder=190, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Nan, Xie Yuan, Hao Cong. IronMan-Pro: Multiobjective design space exploration in HLS via reinforcement learning and graph neural network-based modeling[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023, 42(3): 900−913, articleTitle=null, refAbstract=null), Reference(id=1327011951537926638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=190, rfOrder=191, authorNames=null, journalName=null, refType=null, unstructuredReference=Kao S C, Jeong G, Krishna T. ConfuciuX: Autonomous hardware resource assignment for DNN accelerators using reinforcement learning[C]//Proc of the 53rd Annual IEEE/ACM Int Symp on Microarchitecture. Piscataway, NJ: IEEE, 2020: 622–636, articleTitle=null, refAbstract=null), Reference(id=1327011951626007023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=191, rfOrder=192, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Lang, Liu Wenjian, Guo Chuliang, et al. GANDSE: Generative adversarial network based design space exploration for neural network accelerator design[J]. ACM Transactions on Design Automation of Electronic Systems, 2023, 28(3): 35: 1−35: 20, articleTitle=null, refAbstract=null), Reference(id=1327011951756030448, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=192, rfOrder=193, authorNames=null, journalName=null, refType=null, unstructuredReference=Akram A, Sawalha L. A survey of computer architecture simulation techniques and tools[J]. IEEE Access, 2019, 7: 78120−78145, articleTitle=null, refAbstract=null), Reference(id=1327011951923802609, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=193, rfOrder=194, authorNames=null, journalName=null, refType=null, unstructuredReference=Manjikian N. Multiprocessor enhancements of the simplescalar tool set[J]. SIGARCH Computer Architecture News, 2001, 29(1): 8−15, articleTitle=null, refAbstract=null), Reference(id=1327011952016077298, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=194, rfOrder=195, authorNames=null, journalName=null, refType=null, unstructuredReference=Qureshi Y M, Simon W A, Zapater M, et al. Gem5-X: A many-core heterogeneous simulation platform for architectural exploration and optimization[J]. ACM Transactions on Architecture and Code Optimization, 2021, 18(4): 44: 1–44: 27, articleTitle=null, refAbstract=null), Reference(id=1327011952099963379, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=195, rfOrder=196, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlson T E, Heirman W, Eyerman S, et al. An evaluation of high-level mechanistic core models[J]. ACM Transactions on Architecture and Code Optimization, 2014, 11(3): 28: 1–28: 25, articleTitle=null, refAbstract=null), Reference(id=1327011952288707060, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=196, rfOrder=197, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Zhangxi, Waterman A, Cook H, et al. A case for fame: FPGA architecture model execution[C]//Proc of the 37th Annual Int Symp on Computer Architecture. New York: ACM, 2010: 290–301, articleTitle=null, refAbstract=null), Reference(id=1327011952380981749, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=197, rfOrder=198, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee Y, Waterman A, Cook H, et al. An agile approach to building RISC-V microprocessors[J]. IEEE Micro, 2016, 36(2): 8−20, articleTitle=null, refAbstract=null), Reference(id=1327011952515199478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=198, rfOrder=199, authorNames=null, journalName=null, refType=null, unstructuredReference=Di Biagio A, Davis M. llvm-mca: A static performance analysis tool[EB/OL]. (2018−03−01)[2023-12-01]. https://lists.llvm.org/pipermail/llvm-dev/2018-March/121490.html, articleTitle=null, refAbstract=null), Reference(id=1327011952699748855, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=199, rfOrder=200, authorNames=null, journalName=null, refType=null, unstructuredReference=Mendis C, Renda A, Amarasinghe D S, et al. Ithemal: Accurate, portable and fast basic block throughput estimation using deep neural networks[C]//Proc of the 36th Int Conf on Machine Learning. New York: PMLR, 2019: 4505–4515, articleTitle=null, refAbstract=null), Reference(id=1327011952766857720, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=200, rfOrder=201, authorNames=null, journalName=null, refType=null, unstructuredReference=Blocklove J, Garg S, Karri R, et al. Chip-Chat: Challenges and opportunities in conversational hardware design[C/OL]//Proc of the 5th ACM/IEEE Workshop on Machine Learning for CAD. Piscataway, NJ: IEEE, 2023[2023-12-18]. https://ieeexplore.ieee.org/document/10299874, articleTitle=null, refAbstract=null), Reference(id=1327011952838160889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=201, rfOrder=202, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang Kaiyan, Wang Ying, Ren Haimeng, et al. ChipGPT: How far are we from natural language hardware design[J]. arXiv preprint, arXiv: 2305.14019, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011952909464058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=202, rfOrder=203, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Yao, Liu Shang, Zhang Qijun, et al. RTLLM: An open-source benchmark for design RTL generation with large language model[J]. arXiv preprint, arXiv: 2308.05345, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011953052070395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=203, rfOrder=204, authorNames=null, journalName=null, refType=null, unstructuredReference=Balkind J, Chang Tingjung, Jackson P J, et al. OpenPiton at 5: A nexus for open and agile hardware design[J]. IEEE Micro, 2020, 40(4): 22−31, articleTitle=null, refAbstract=null), Reference(id=1327011953156927996, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=204, rfOrder=205, authorNames=null, journalName=null, refType=null, unstructuredReference=Bachrach J, Vo H, Richards B, et al. Chisel: Constructing hardware in a scala embedded language[C]//Proc of the 49th Annual Design Automation Conf. New York: ACM, 2012: 1216–1225, articleTitle=null, refAbstract=null), Reference(id=1327011953354060285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=205, rfOrder=206, authorNames=null, journalName=null, refType=null, unstructuredReference=Patel H D, Shukla S K. Tackling an abstraction gap: Co-simulating SystemC DE with Bluespec ESL[C]//Proc the of 10th Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2007: 279−284, articleTitle=null, refAbstract=null), Reference(id=1327011953429557758, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=206, rfOrder=207, authorNames=null, journalName=null, refType=null, unstructuredReference=Bourgeat T, Pit-Claudel C, Chlipala A, et al. The essence of Bluespec: A core language for rule-based hardware design[C]//Proc of the 41st ACM SIGPLAN Conf on Programming Language Design and Implementation. New York: ACM, 2020: 243–257, articleTitle=null, refAbstract=null), Reference(id=1327011953630884351, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=207, rfOrder=208, authorNames=null, journalName=null, refType=null, unstructuredReference=Käyrä M, Hämäläinen T D. A survey on system-on-a-chip design using Chisel HW construction language[C/OL]//Proc of the 47th Annual Conf of the IEEE Industrial Electronics Society. Piscataway, NJ: IEEE, 2021[2023-12-18]. https://ieeexplore.ieee.org/document/9589614, articleTitle=null, refAbstract=null), Reference(id=1327011953819628032, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=208, rfOrder=209, authorNames=null, journalName=null, refType=null, unstructuredReference=王凯帆,徐易难,余子濠,等. 香山开源高性能RISC-v处理器设计与实现[J]. 计算机研究与发展,2023,60(3):476−493, articleTitle=null, refAbstract=null), Reference(id=1327011955430240769, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=208, rfOrder=210, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Kaifan, Xu Yinan, Yu Zihao, et al. XiangShan open-source high performance RISC-V processor design and implementation[J]. Journal of Computer Research and Development, 2023, 60(3): 476−493(in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011955501543939, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=209, rfOrder=211, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee B C, Brooks D M, Supinski B R de, et al. Methods of inference and learning for performance modeling of parallel applications[C]//Proc of the 12th ACM SIGPLAN Sympon Principles and Practice of Parallel Programming. New York: ACM, 2007: 249–258, articleTitle=null, refAbstract=null), Reference(id=1327011955560264197, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=210, rfOrder=212, authorNames=null, journalName=null, refType=null, unstructuredReference=Hallschmid P, Saleh R. Fast design space exploration using local regression modeling with application to ASIPs[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2008, 27(3): 508−515, articleTitle=null, refAbstract=null), Reference(id=1327011955627373063, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=211, rfOrder=213, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Changshu, Ravindran A, Datta K, et al. A machine learning approach to modeling power and performance of chip multiprocessors[C]//Proc of the 29th Int Conf on Computer Design. Los Alamitos, CA: IEEE Computer Society, 2011: 45–50, articleTitle=null, refAbstract=null), Reference(id=1327011955698676232, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=212, rfOrder=214, authorNames=null, journalName=null, refType=null, unstructuredReference=Beg A, Prasad P W C, Singh A K, et al. A neural model for processor-throughput using hardware parameters and software’s dynamic behavior[C]//Proc of the 12th Int Conf on Intelligent Systems Design and Applications. Piscataway, NJ: IEEE, 2012: 821–825, articleTitle=null, refAbstract=null), Reference(id=1327011955782562313, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=213, rfOrder=215, authorNames=null, journalName=null, refType=null, unstructuredReference=Paone E, Vahabi N, Zaccaria V, et al. Improving simulation speed and accuracy for many-core embedded platforms with ensemble models[C]//Proc of the 16th Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2013: 671–676, articleTitle=null, refAbstract=null), Reference(id=1327011955858059786, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=214, rfOrder=216, authorNames=null, journalName=null, refType=null, unstructuredReference=Castillo P A, Mora A M, Guervós J J M, et al. Architecture performance prediction using evolutionary artificial neural networks[C]//Proc of the Applications of Evolutionary Computing. Berlin: Springer, 2008: 175–183, articleTitle=null, refAbstract=null), Reference(id=1327011955954528781, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=215, rfOrder=217, authorNames=null, journalName=null, refType=null, unstructuredReference=Khan S, Xekalakis P, Cavazos J, et al. Using predictive modeling for cross-program design space exploration in multicore systems[C]//Proc of the 16th Int Conf on Parallel Architecture and Compilation Techniques. Los Alamitos, CA: IEEE Computer Society, 2007: 327–338, articleTitle=null, refAbstract=null), Reference(id=1327011956017443342, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=216, rfOrder=218, authorNames=null, journalName=null, refType=null, unstructuredReference=Dubach C, Jones T M, O’Boyle M F P. Rapid early-stage microarchitecture design using predictive models[C]//Proc of the 27th Int Conf on Computer Design. Los Alamitos, CA: IEEE Computer Society, 2009: 297–304, articleTitle=null, refAbstract=null), Reference(id=1327011956097135119, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=217, rfOrder=219, authorNames=null, journalName=null, refType=null, unstructuredReference=Özisikyilmaz B, Memik G, Choudhary A N. Machine learning models to predict performance of computer system design alternatives[C]//Proc of the 37th Int Conf on Parallel Processing. Los Alamitos, CA: IEEE Computer Society, 2008: 495–502, articleTitle=null, refAbstract=null), Reference(id=1327011956160049680, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=218, rfOrder=220, authorNames=null, journalName=null, refType=null, unstructuredReference=Özisikyilmaz B, Memik G, Choudhary A N. Efficient system design space exploration using machine learning techniques[C]//Proc of the 45th Design Automation Conf. New York: ACM, 2008: 966–969, articleTitle=null, refAbstract=null), Reference(id=1327011956227158545, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=219, rfOrder=221, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghosh A, Givargis T. Cache optimization for embedded processor cores: An analytical approach[J]. ACM Transactions on Design Automation of Electronic Systems, 2004, 9(4): 419−440, articleTitle=null, refAbstract=null), Reference(id=1327011956294267410, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=220, rfOrder=222, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Sheng, Chen Ke, Ahn J H, et al. CACTI-p: Architecture-level modeling for SRAM-based structures with advanced leakage reduction techniques[C]//Proc of the 30th Int Conf on Computer-Aided Design. Los Alamitos, CA: IEEE Computer Society, 2011: 694–701, articleTitle=null, refAbstract=null), Reference(id=1327011956369764883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=221, rfOrder=223, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Sheng, Ahn J H, Strong R D, et al. McPAT: An integrated power, area, and timing modeling framework for multicore and manycore architectures[C]//Proc of the 42nd Annual IEEE/ACM Int Symp on Microarchitecture. New York: ACM, 2009: 469–480, articleTitle=null, refAbstract=null), Reference(id=1327011956474622484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=222, rfOrder=224, authorNames=null, journalName=null, refType=null, unstructuredReference=Karkhanis T S, Smith J E. A first-order superscalar processor model[C]//Proc of the 31st Annual Int Symp on Computer Architecture. Piscataway, NJ: IEEE, 2004: 338–349, articleTitle=null, refAbstract=null), Reference(id=1327011956541731349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=223, rfOrder=225, authorNames=null, journalName=null, refType=null, unstructuredReference=Genbrugge D, Eyerman S, Eeckhout L. Interval simulation: Raising the level of abstraction in architectural simulation[C/OL]//Proc of the 16th Int Symp on High-Performance Computer Architecture. Piscataway, NJ: IEEE, 2010[2023-12-18]. https://ieeexplore.ieee.org/document/5416636, articleTitle=null, refAbstract=null), Reference(id=1327011956604645910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=224, rfOrder=226, authorNames=null, journalName=null, refType=null, unstructuredReference=Breughe M, Eyerman S, Eeckhout L. A mechanistic performance model for superscalar in-order processors[C]//Proc of the 2012 IEEE Int Symp on Performance Analysis of Systems & Software. Los Alamitos, CA: IEEE Computer Society, 2012: 14–24, articleTitle=null, refAbstract=null), Reference(id=1327011956659171863, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=225, rfOrder=227, authorNames=null, journalName=null, refType=null, unstructuredReference=Van den Steen S, Eyerman S, De Pestel S, et al. Analytical processor performance and power modeling using micro-architecture independent characteristics[J]. IEEE Transactions on Computers, 2016, 65(12): 3537−3551, articleTitle=null, refAbstract=null), Reference(id=1327011956722086424, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=226, rfOrder=228, authorNames=null, journalName=null, refType=null, unstructuredReference=De Pestel S, Van den Steen S, Akram S, et al. RPPM: Rapid performance prediction of multithreaded workloads on multicore processors[C]//Proc of the 2019 IEEE Int Symp on Performance Analysis of Systems and Software. Piscataway, NJ: IEEE, 2019: 257–267, articleTitle=null, refAbstract=null), Reference(id=1327011956797583897, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=227, rfOrder=229, authorNames=null, journalName=null, refType=null, unstructuredReference=Jongerius R, Mariani G, Anghel A, et al. Analytic processor model for fast design-space exploration[C]//Proc of the 33rd IEEE Int Conf on Computer Design. Los Alamitos, CA: IEEE Computer Society, 2015: 411–414, articleTitle=null, refAbstract=null), Reference(id=1327011956852109850, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=228, rfOrder=230, authorNames=null, journalName=null, refType=null, unstructuredReference=Jongerius R, Anghel A, Dittmann G, et al. Analytic multi-core processor model for fast design-space exploration[J]. IEEE Transactions on Computers, 2018, 67(6): 755−770, articleTitle=null, refAbstract=null), Reference(id=1327011956919218715, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=229, rfOrder=231, authorNames=null, journalName=null, refType=null, unstructuredReference=Kwon J, Carloni L P. Transfer learning for design-space exploration with high-level synthesis[C]//Proc of the 2nd ACM/IEEE Workshop on Machine Learning for CAD. New York: ACM, 2020: 163–168, articleTitle=null, refAbstract=null), Reference(id=1327011956986327580, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=230, rfOrder=232, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zheng, Chen Tinghuan, Huang Jiaxin, et al. A fast parameter tuning framework via transfer learning and multi-objective Bayesian optimization[C]//Proc of the 59th ACM/IEEE Design Automation Conf. New York: ACM, 2022: 133–138, articleTitle=null, refAbstract=null), Reference(id=1327011957045047837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=231, rfOrder=233, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Keyi, Asgar Z, Horowitz M. Bringing source-level debugging frameworks to hardware generators[C]//Proc of the 59th ACM/IEEE Design Automation Conf. New York: ACM, 2022: 1171–1176, articleTitle=null, refAbstract=null), Reference(id=1327011957107962398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=232, rfOrder=234, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Qingcheng, Zheng Size, Wu Bingzhe, et al. HASCO: Towards agile hardware and software co-design for tensor computation[C]//Proc of the 48th Annual Int Symp on Computer Architecture. Piscataway, NJ: IEEE, 2021: 1055–1068, articleTitle=null, refAbstract=null), Reference(id=1327011957208625695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=233, rfOrder=235, authorNames=null, journalName=null, refType=null, unstructuredReference=Esmaeilzadeh H, Ghodrati S, Kahng A B, et al. Physically accurate learning-based performance prediction of hardware-accelerated ML algorithms[C]//Proc of the 4th ACM/IEEE Workshop on Machine Learning for CAD. New York: ACM, 2022: 119–126, articleTitle=null, refAbstract=null), Reference(id=1327011957267345952, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=234, rfOrder=236, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Qi, Chen Tinghuan, Liu Siting, et al. Correlated multi-objective multi-fidelity optimization for HLS directives design[C]//Proc of the 24th Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2021: 46–51, articleTitle=null, refAbstract=null), Reference(id=1327011957359620641, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=235, rfOrder=237, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Y N, Tsai P A, Parashar A, et al. Sparseloop: An analytical approach to sparse tensor accelerator modeling[C]//Proc of the 55th IEEE/ACM Int Symp on Microarchitecture. Piscataway, NJ: IEEE, 2022: 1377–1395, articleTitle=null, refAbstract=null), Reference(id=1327011957422535202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=236, rfOrder=238, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Qijing, Kang M, Dinh G, et al. CoSA: Scheduling by constrained optimization for spatial accelerators[C]//Proc of the 48th Annual Int Symp on Computer Architecture. Piscataway, NJ: IEEE, 2021: 554–566, articleTitle=null, refAbstract=null), Reference(id=1327011957493838371, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=237, rfOrder=239, authorNames=null, journalName=null, refType=null, unstructuredReference=Mei Linyan, Houshmand P, Jain V, et al. ZigZag: Enlarging joint architecture-mapping design space exploration for DNN accelerators[J]. IEEE Transactions on Computers, 2021, 70(8): 1160−1174, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327011915253002423, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=1, ext=[AuthorCompanyExt(id=1327011915282362552, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Lab of Processors (Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190), AuthorCompanyExt(id=1327011915311722681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915253002423, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190)]), AuthorCompany(id=1327011915387220154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=2, ext=[AuthorCompanyExt(id=1327011915391414459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049), AuthorCompanyExt(id=1327011915412385980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915387220154, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院大学计算机科学与技术学院 北京 100049)]), AuthorCompany(id=1327011915508854973, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, xref=3, ext=[AuthorCompanyExt(id=1327011915517243582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915508854973, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3China Mobile Communications Research Institute, Beijing 100053), AuthorCompanyExt(id=1327011915521437887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, companyId=1327011915508854973, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3中国移动研究院 北京 100053)])], figs=[ArticleFig(id=1327011919979983092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Figure 1, caption=
Design space exploration after acceleration, figureFileSmall=GHmDoZZCTR6gIaZhWuaCZA==, figureFileBig=0vo/5ihQEAYbB0QvoN7SqA==, tableContent=null), ArticleFig(id=1327011920038703349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=图1, caption=
加速后的设计空间探索, figureFileSmall=GHmDoZZCTR6gIaZhWuaCZA==, figureFileBig=0vo/5ihQEAYbB0QvoN7SqA==, tableContent=null), ArticleFig(id=1327011920164532470, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Figure 2, caption=
Statistical sample simulation, figureFileSmall=mV0pt7lCM2aSe0WGEaLOJQ==, figureFileBig=V4EMC2opFdbDpkcLzM6upw==, tableContent=null), ArticleFig(id=1327011920294555895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=图2, caption=
统计采样模拟, figureFileSmall=mV0pt7lCM2aSe0WGEaLOJQ==, figureFileBig=V4EMC2opFdbDpkcLzM6upw==, tableContent=null), ArticleFig(id=1327011920382636280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Figure 3, caption=
Synthetic simulation flow (SFG[69]), figureFileSmall=0xTpEICeXi8YJAmvxJXRGg==, figureFileBig=ZLqABcTJIC+SIjxri6O7Ng==, tableContent=null), ArticleFig(id=1327011920554602746, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=图3, caption=
综合模拟的流程(SFG [69]), figureFileSmall=0xTpEICeXi8YJAmvxJXRGg==, figureFileBig=ZLqABcTJIC+SIjxri6O7Ng==, tableContent=null), ArticleFig(id=1327011920684626171, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Figure 4, caption=
Interval analysis analyzes performance on an interval basis determined by disruptive miss events[104], figureFileSmall=sPVm5QS4hlpEdvqGiyLEbg==, figureFileBig=DiBL2v4Q/EbJMBQWdYtyZw==, tableContent=null), ArticleFig(id=1327011920781095164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=图4, caption=
区间分析对破坏性缺失事件确定的区间基性能进行了分析[104], figureFileSmall=sPVm5QS4hlpEdvqGiyLEbg==, figureFileBig=DiBL2v4Q/EbJMBQWdYtyZw==, tableContent=null), ArticleFig(id=1327011920948867325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Figure 5, caption=
A graph-based processor performance model[180], figureFileSmall=/NSzviY+W1X4HeQh52zEgw==, figureFileBig=DCN69CQKFkuMqbZ0PdBVyw==, tableContent=null), ArticleFig(id=1327011921083085054, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=图5, caption=
基于图的处理器性能模型[180], figureFileSmall=/NSzviY+W1X4HeQh52zEgw==, figureFileBig=DCN69CQKFkuMqbZ0PdBVyw==, tableContent=null), ArticleFig(id=1327011921196331263, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 1, caption=
Category of Acceleration Methods for Processor Microarchitecture Design Space Exploration, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 子类型 | 典型方法 |
|---|
| 负载选择 | 基于微架构相关特征的方法 | 文献[15, 27] |
| 基于微架构无关特征的方法 | MinneSPEC[28]、文献[29–32]、BenchSubset[33]、CASH[34] |
| 基于微架构相关与无关特征的方法 | 文献[29, 35–37]、BenchPrime[38] |
| 部分模拟 | 统计采样模拟 | 采样单线程[39-43]、采样多线程[44-48]、采样访存[49-51] |
| 综合模拟 | 综合单线程[52-55]、综合多线程[56-58]、综合访存[59-62] |
| 设计点选择 | 采样方法 | 基于参数敏感度的方法[15,63-67]、基于实验设计的方法[6,25,34,67] |
| 迭代搜索方法 | 启发式方法[68-70]、组合优化方法[68,71-74]、统计推理方法[14,25-26,67,75] |
| 模拟工具 | 软件模拟 | SimpleScalar[76],SESC[77],gem5[78] |
| 硬件模拟 | FAST[79], PROTOFLEX[80-81], RAMP Gold[82], HAsim[83], FireSim[84] |
| 敏捷开发 | 基于低级语言的平台[85-87]、基于高级语言的平台[50,88-89] |
| 性能模型 | 特定负载预测模型 | 参数化模型[2,4,90]、核函数模型[13,68,91]、神经网络模型[3,92-93]、树模型[94-96]、集成学习模型[67,97-98] |
| 跨负载预测模型 | 基于负载特征[8,99-100]、基于硬件响应[9,23,101]、基于迁移学习[7,10-11] |
| 机械模型 | 分析模型[102-103]、区间模型[104-106]、图模型[107-109]、概率统计模型[110-112]、混合模型[113-115] |
), ArticleFig(id=1327011921280217345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表1, caption=
处理器微架构设计空间探索的加速方法分类
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 子类型 | 典型方法 |
|---|
| 负载选择 | 基于微架构相关特征的方法 | 文献[15, 27] |
| 基于微架构无关特征的方法 | MinneSPEC[28]、文献[29–32]、BenchSubset[33]、CASH[34] |
| 基于微架构相关与无关特征的方法 | 文献[29, 35–37]、BenchPrime[38] |
| 部分模拟 | 统计采样模拟 | 采样单线程[39-43]、采样多线程[44-48]、采样访存[49-51] |
| 综合模拟 | 综合单线程[52-55]、综合多线程[56-58]、综合访存[59-62] |
| 设计点选择 | 采样方法 | 基于参数敏感度的方法[15,63-67]、基于实验设计的方法[6,25,34,67] |
| 迭代搜索方法 | 启发式方法[68-70]、组合优化方法[68,71-74]、统计推理方法[14,25-26,67,75] |
| 模拟工具 | 软件模拟 | SimpleScalar[76],SESC[77],gem5[78] |
| 硬件模拟 | FAST[79], PROTOFLEX[80-81], RAMP Gold[82], HAsim[83], FireSim[84] |
| 敏捷开发 | 基于低级语言的平台[85-87]、基于高级语言的平台[50,88-89] |
| 性能模型 | 特定负载预测模型 | 参数化模型[2,4,90]、核函数模型[13,68,91]、神经网络模型[3,92-93]、树模型[94-96]、集成学习模型[67,97-98] |
| 跨负载预测模型 | 基于负载特征[8,99-100]、基于硬件响应[9,23,101]、基于迁移学习[7,10-11] |
| 机械模型 | 分析模型[102-103]、区间模型[104-106]、图模型[107-109]、概率统计模型[110-112]、混合模型[113-115] |
), ArticleFig(id=1327011921359909122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 2, caption=
Comparison of Acceleration Methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 典型方法 | 加速比 | 准确率/% |
|---|
| 负载选择 | 文献[37] | 5.2 | 93.0 |
| 部分模拟 | 文献[116] | 520 | 94.9 |
| 设计点选择 | 文献[117] | 23000 | 99.0 |
| 模拟工具 | 文献[76] | 1000 | 95.0 |
| 性能模型 | 文献[118] | 180000 | 98.2 |
), ArticleFig(id=1327011921422823683, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表2, caption=
加速方法对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 典型方法 | 加速比 | 准确率/% |
|---|
| 负载选择 | 文献[37] | 5.2 | 93.0 |
| 部分模拟 | 文献[116] | 520 | 94.9 |
| 设计点选择 | 文献[117] | 23000 | 99.0 |
| 模拟工具 | 文献[76] | 1000 | 95.0 |
| 性能模型 | 文献[118] | 180000 | 98.2 |
), ArticleFig(id=1327011921494126852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 3, caption=
Comparison of Workload Selecting Methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法类型 | 方法来源 | 使用微架构相关特征的方式 | 使用微架构无关特征的方式 | 聚类算法 | 负载选择比 | 误差/% |
|---|
| 注:“负载选择比”列中的“/”表示选择的负载数量和全部负载数量之比,“-”表示文献中无数据. “✘”表示无该项. |
基于微架构相关 特征的方法 | 文献[15] | 参数显著性排名 | ✘ | 阈值聚类 | 7/12 | - |
| 文献[27] | 执行时间向量 | ✘ | 层次聚类 | 6/11 | 5 |
基于微架构无关 特征的方法 | 文献[28] | ✘ | 卡方检验 | ✘ | -/23 | - |
| 文献[29] | ✘ | 主成分分析 | 层次聚类 | 7/79 | - |
| 文献[30] | ✘ | 基本块向量 | 距离最大 | 60/20 000 | - |
| 文献[31] | ✘ | 主成分分析 | k均值聚类 | 9/21 | 15 |
| 文献[32] | ✘ | 基本块向量+主成分分析 | 层次聚类 | 4/47 | - |
| 文献[33] | ✘ | 分组主成分分析 | 共识聚类 | - | - |
| 文献[34] | ✘ | 独立成分分析 | 多种聚类 | 5/27 | 3 |
| 文献[120] | ✘ | 主成分分析/遗传算法 | k质心聚类 | 50/118 | 5 |
| 文献[121−122] | ✘ | 凸壳体积、主成分分析 | 遗传算法 | 6/22 | - |
基于微架构相关与 无关特征的方法 | 文献[29,35] | 主成分分析 | 层次聚类 | 14/29 | - |
| 文献[36] | 主成分分析 | 层次聚类 | 10/23 | - |
| 文献[37] | 主成分分析 | 层次聚类 | 12/43 | 7 |
| 文献[123] | 多元因素分析 | 层次聚类 | 10/23 | - |
| 文献[38] | 主成分分析+线性判别 | 多种聚类 | 20/54 | - |
), ArticleFig(id=1327011921565430021, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表3, caption=
负载选择方法的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法类型 | 方法来源 | 使用微架构相关特征的方式 | 使用微架构无关特征的方式 | 聚类算法 | 负载选择比 | 误差/% |
|---|
| 注:“负载选择比”列中的“/”表示选择的负载数量和全部负载数量之比,“-”表示文献中无数据. “✘”表示无该项. |
基于微架构相关 特征的方法 | 文献[15] | 参数显著性排名 | ✘ | 阈值聚类 | 7/12 | - |
| 文献[27] | 执行时间向量 | ✘ | 层次聚类 | 6/11 | 5 |
基于微架构无关 特征的方法 | 文献[28] | ✘ | 卡方检验 | ✘ | -/23 | - |
| 文献[29] | ✘ | 主成分分析 | 层次聚类 | 7/79 | - |
| 文献[30] | ✘ | 基本块向量 | 距离最大 | 60/20 000 | - |
| 文献[31] | ✘ | 主成分分析 | k均值聚类 | 9/21 | 15 |
| 文献[32] | ✘ | 基本块向量+主成分分析 | 层次聚类 | 4/47 | - |
| 文献[33] | ✘ | 分组主成分分析 | 共识聚类 | - | - |
| 文献[34] | ✘ | 独立成分分析 | 多种聚类 | 5/27 | 3 |
| 文献[120] | ✘ | 主成分分析/遗传算法 | k质心聚类 | 50/118 | 5 |
| 文献[121−122] | ✘ | 凸壳体积、主成分分析 | 遗传算法 | 6/22 | - |
基于微架构相关与 无关特征的方法 | 文献[29,35] | 主成分分析 | 层次聚类 | 14/29 | - |
| 文献[36] | 主成分分析 | 层次聚类 | 10/23 | - |
| 文献[37] | 主成分分析 | 层次聚类 | 12/43 | 7 |
| 文献[123] | 多元因素分析 | 层次聚类 | 10/23 | - |
| 文献[38] | 主成分分析+线性判别 | 多种聚类 | 20/54 | - |
), ArticleFig(id=1327011921640927494, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 4, caption=
Summary of Common Benchmark Suits, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 工作负载 | 简称 |
|---|
| 多媒体和通信 | MediaBench[124] | MediaBench |
| 嵌入式 | MiBench[125] | MiBench |
| 单线程 | SPEC CPU 2000[126] | SPEC2k |
| 单线程 | SPEC CPU 2006[127] | SPEC2k6 |
| 单/多线程 | SPEC CPU 2017[18] | SPEC2k17 |
| 多线程 | Princeton Application Repository for Shared-Memory Computers[128] | PARSEC |
| 多线程 | Stanford Parallel Applications for Shared Memory[129] | SPLASH |
), ArticleFig(id=1327011921716424967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表4, caption=
常用基准套件汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 工作负载 | 简称 |
|---|
| 多媒体和通信 | MediaBench[124] | MediaBench |
| 嵌入式 | MiBench[125] | MiBench |
| 单线程 | SPEC CPU 2000[126] | SPEC2k |
| 单线程 | SPEC CPU 2006[127] | SPEC2k6 |
| 单/多线程 | SPEC CPU 2017[18] | SPEC2k17 |
| 多线程 | Princeton Application Repository for Shared-Memory Computers[128] | PARSEC |
| 多线程 | Stanford Parallel Applications for Shared Memory[129] | SPLASH |
), ArticleFig(id=1327011921787728136, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 5, caption=
Microarchitecture-Dependent Features, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 特征 |
|---|
| 注:MPKI表示每千条指令缺失. |
| 整体聚合 | 执行时间、CPI、功率 |
| 控制流 | 分支预测MPKI、BTB命中率 |
| cache行为(Icache/Dcache/L2/L3) | 访问数量、命中数量、MPKI |
| TLB行为(ITLB/DTLB/L2TLB) | 访问数量、命中数量、MPKI |
), ArticleFig(id=1327011921963888905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表5, caption=
微架构相关特征
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 特征 |
|---|
| 注:MPKI表示每千条指令缺失. |
| 整体聚合 | 执行时间、CPI、功率 |
| 控制流 | 分支预测MPKI、BTB命中率 |
| cache行为(Icache/Dcache/L2/L3) | 访问数量、命中数量、MPKI |
| TLB行为(ITLB/DTLB/L2TLB) | 访问数量、命中数量、MPKI |
), ArticleFig(id=1327011922026803466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 6, caption=
Microarchitecture-Independent Features, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 子类型 | 特征 |
|---|
| 注:SIMD表示单指令多数据流. |
| 指令流 | 指令混合 | 整型、浮点、SIMD等 |
| 控制分支 |
| 存储读/写 |
| 寄存器通信 | 平均操作数数量 |
| 平均使用次数 |
| 重用距离 |
| 指令级并行性 | 不同窗口大小的并行度 |
| 基本块大小 |
| 指令局部性 | 指令工作集大小 |
| 时间、空间重用距离 |
| 数据流 | 数据局部性 | 数据工作集大小 |
| 时间、空间重用距离 |
| 通信特征 | 私有数据读写次数 |
| 生产者写/消费者读次数 |
), ArticleFig(id=1327011922089718027, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表6, caption=
微架构无关特征
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 子类型 | 特征 |
|---|
| 注:SIMD表示单指令多数据流. |
| 指令流 | 指令混合 | 整型、浮点、SIMD等 |
| 控制分支 |
| 存储读/写 |
| 寄存器通信 | 平均操作数数量 |
| 平均使用次数 |
| 重用距离 |
| 指令级并行性 | 不同窗口大小的并行度 |
| 基本块大小 |
| 指令局部性 | 指令工作集大小 |
| 时间、空间重用距离 |
| 数据流 | 数据局部性 | 数据工作集大小 |
| 时间、空间重用距离 |
| 通信特征 | 私有数据读写次数 |
| 生产者写/消费者读次数 |
), ArticleFig(id=1327011922165215500, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 7, caption=
Comparison of Partial Simulation Acceleration Methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 目标 | 子类型 | 方法来源 | 指令流 | 数据流 | 微架构相关特征 | 加速比 | 误差/% |
|---|
| 注:“-”表示文献无该数据. “✔”表示有使用该类数据,“✘”表示没有使用该类数据. |
| 统计采样模拟 | 采样单线程 | 随机采样 | 文献[134] | ✘ | ✘ | ✘ | - | 7~17 |
| 均匀采样 | 文献[39] | ✘ | ✘ | ✘ | 35~60 | 0.6 |
| 文献[40] | ✘ | ✘ | ✘ | ~4 000 | 3.5 |
| 代表性采样 | 文献[41−42,135−136] | ✔ | ✘ | ✘ | 62~107 | 3.7 |
| 文献[43] | ✔ | ✘ | ✘ | 1~1.4 | 0.5 |
| 文献[137] | ✔ | ✘ | IPC, cache | ~100 | 3 |
| 文献[138] | ✔ | ✘ | IPC, cache | - | 2~8 |
| 采样多线程 | 基于时间 | 文献[44] | ✔ | ✘ | IPC | 10 | 5 |
| 文献[139] | ✔ | ✘ | IPC | 5.8 | 3.5 |
| 文献[45] | ✔ | ✘ | IPC | 20 | 5.3 |
| 基于负载和特定同步 | 文献[47] | ✔ | ✘ | ✘ | 25 | 0.9 |
| 文献[48] | ✔ | ✘ | ✘ | 220 | 0.5 |
| 基于循环迭代 | 文献[46] | ✔ | ✘ | ✘ | 801 | 2.3 |
| 采样访存 | 基于检查点 | 文献[49] | ✘ | ✔ | cache, BP | 8 000~15 000 | ~0.6 |
| 文献[51] | ✘ | ✔ | cache, BP | 50~100 | ~0.6 |
| 文献[50,140−141] | ✘ | ✔ | cache, BP | - | - |
| 基于预热 | 文献[142] | ✔ | ✔ | cache, BP | 8 000~15 000 | ~0.6 |
| 文献[143] | ✔ | ✔ | cache, BP | ~100 | 1.5 |
| 文献[144] | ✔ | ✔ | cache, BP | ~70 | 0.3 |
| 文献[145−147] | ✔ | ✔ | cache, BP | - | - |
| 综合模拟 | 综合单线程 | | 文献[54] | ✔ | ✘ | cache, BP | - | 5~7 |
| 文献[148] | ✔ | ✘ | cache, BP | - | 4.1 |
| 文献[149] | ✔ | ✘ | cache, BP | - | - |
| 文献[52−53] | ✔ | ✘ | cache, BP | - | 8 |
| 文献[150] | ✔ | ✘ | cache, BP | ~1 000 | 6.6 |
| 文献[55,151] | ✔ | ✔ | cache, BP | ~1 000 | 2.4 |
| 文献[116] | ✔ | ✔ | cache, BP | 520 | 5.1 |
| 文献[152] | ✔ | ✔ | cache, BP | - | 3.2 |
| 文献[153−155] | ✔ | ✔ | ✘ | - | - |
| 综合多线程 | | 文献[58] | ✔ | ✔ | ✘ | 9~385 | 3.8~9.8 |
| 文献[156] | ✔ | ✔ | ✘ | 1 000~10 000 | 4.9 |
| 文献[56−57] | ✔ | ✔ | cache, BP | 40~70 | 5.5 |
| 文献[157] | ✔ | ✔ | cache, BP | 21 | 8 |
| 综合访存 | | 文献[59] | ✘ | ✔ | ✘ | - | 0.4~3.1 |
| 文献[60−61] | ✘ | ✔ | ✘ | - | - |
| 文献[158−160] | ✔ | ✔ | ✘ | 31 | 4.8 |
| 文献[161] | ✔ | ✔ | ✘ | 20 | 2.8 |
| 文献[62] | ✔ | ✔ | ✘ | 20~50 | 4.2 |
| 文献[162] | ✔ | ✔ | ✘ | - | 9 |
), ArticleFig(id=1327011922253295885, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表7, caption=
部分模拟加速方法的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 目标 | 子类型 | 方法来源 | 指令流 | 数据流 | 微架构相关特征 | 加速比 | 误差/% |
|---|
| 注:“-”表示文献无该数据. “✔”表示有使用该类数据,“✘”表示没有使用该类数据. |
| 统计采样模拟 | 采样单线程 | 随机采样 | 文献[134] | ✘ | ✘ | ✘ | - | 7~17 |
| 均匀采样 | 文献[39] | ✘ | ✘ | ✘ | 35~60 | 0.6 |
| 文献[40] | ✘ | ✘ | ✘ | ~4 000 | 3.5 |
| 代表性采样 | 文献[41−42,135−136] | ✔ | ✘ | ✘ | 62~107 | 3.7 |
| 文献[43] | ✔ | ✘ | ✘ | 1~1.4 | 0.5 |
| 文献[137] | ✔ | ✘ | IPC, cache | ~100 | 3 |
| 文献[138] | ✔ | ✘ | IPC, cache | - | 2~8 |
| 采样多线程 | 基于时间 | 文献[44] | ✔ | ✘ | IPC | 10 | 5 |
| 文献[139] | ✔ | ✘ | IPC | 5.8 | 3.5 |
| 文献[45] | ✔ | ✘ | IPC | 20 | 5.3 |
| 基于负载和特定同步 | 文献[47] | ✔ | ✘ | ✘ | 25 | 0.9 |
| 文献[48] | ✔ | ✘ | ✘ | 220 | 0.5 |
| 基于循环迭代 | 文献[46] | ✔ | ✘ | ✘ | 801 | 2.3 |
| 采样访存 | 基于检查点 | 文献[49] | ✘ | ✔ | cache, BP | 8 000~15 000 | ~0.6 |
| 文献[51] | ✘ | ✔ | cache, BP | 50~100 | ~0.6 |
| 文献[50,140−141] | ✘ | ✔ | cache, BP | - | - |
| 基于预热 | 文献[142] | ✔ | ✔ | cache, BP | 8 000~15 000 | ~0.6 |
| 文献[143] | ✔ | ✔ | cache, BP | ~100 | 1.5 |
| 文献[144] | ✔ | ✔ | cache, BP | ~70 | 0.3 |
| 文献[145−147] | ✔ | ✔ | cache, BP | - | - |
| 综合模拟 | 综合单线程 | | 文献[54] | ✔ | ✘ | cache, BP | - | 5~7 |
| 文献[148] | ✔ | ✘ | cache, BP | - | 4.1 |
| 文献[149] | ✔ | ✘ | cache, BP | - | - |
| 文献[52−53] | ✔ | ✘ | cache, BP | - | 8 |
| 文献[150] | ✔ | ✘ | cache, BP | ~1 000 | 6.6 |
| 文献[55,151] | ✔ | ✔ | cache, BP | ~1 000 | 2.4 |
| 文献[116] | ✔ | ✔ | cache, BP | 520 | 5.1 |
| 文献[152] | ✔ | ✔ | cache, BP | - | 3.2 |
| 文献[153−155] | ✔ | ✔ | ✘ | - | - |
| 综合多线程 | | 文献[58] | ✔ | ✔ | ✘ | 9~385 | 3.8~9.8 |
| 文献[156] | ✔ | ✔ | ✘ | 1 000~10 000 | 4.9 |
| 文献[56−57] | ✔ | ✔ | cache, BP | 40~70 | 5.5 |
| 文献[157] | ✔ | ✔ | cache, BP | 21 | 8 |
| 综合访存 | | 文献[59] | ✘ | ✔ | ✘ | - | 0.4~3.1 |
| 文献[60−61] | ✘ | ✔ | ✘ | - | - |
| 文献[158−160] | ✔ | ✔ | ✘ | 31 | 4.8 |
| 文献[161] | ✔ | ✔ | ✘ | 20 | 2.8 |
| 文献[62] | ✔ | ✔ | ✘ | 20~50 | 4.2 |
| 文献[162] | ✔ | ✔ | ✘ | - | 9 |
), ArticleFig(id=1327011922324599054, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 8, caption=
Comparison of Design of Experiments, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 实验设计 | 样本数 |
|---|
| 注:M为所需的样本数,N为参数个数. |
| 随机 | 均匀随机[3,170] | M |
| 基于参数级别 | 2级全阶乘[25] | 2N |
| 中心复合设计[25] | 1+2N+2N |
| Box-Behnken[25] | 1+2N |
| PB设计[15] | 2N |
| 正交设计[6-7] | 相对固定 |
拉丁超立方体[92,97]、 均匀拉丁超立方体[34,171] | M |
| 基于距离 | 智能采样[3] | M |
| 最小的成对距离最大[169] | M |
| 最大化距离矩阵的迹[14] | M |
| k均值[172-173] | N |
), ArticleFig(id=1327011923989737744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表8, caption=
实验设计的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 实验设计 | 样本数 |
|---|
| 注:M为所需的样本数,N为参数个数. |
| 随机 | 均匀随机[3,170] | M |
| 基于参数级别 | 2级全阶乘[25] | 2N |
| 中心复合设计[25] | 1+2N+2N |
| Box-Behnken[25] | 1+2N |
| PB设计[15] | 2N |
| 正交设计[6-7] | 相对固定 |
拉丁超立方体[92,97]、 均匀拉丁超立方体[34,171] | M |
| 基于距离 | 智能采样[3] | M |
| 最小的成对距离最大[169] | M |
| 最大化距离矩阵的迹[14] | M |
| k均值[172-173] | N |
), ArticleFig(id=1327011924073623826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 9, caption=
Comparison of Iterative Searching Acceleration Methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 子类型 | 方法来源 | 代理模型 | 搜索/获取函数 | 硬件设计空间 |
|---|
| 注:“-”表示该方法只以软件模拟或基于RTL的电路评估的方式获取性能指标,其余方法可通过训练代理模型替代软件模拟来获取指标或指标之间的关系. |
| 启发式 | | 文献[174] | - | 参数聚类、贪心 | 单核片上系统 |
| 文献[64] | - | 敏感度、贪心 | cache微架构 |
| 文献[66] | - | 敏感度、贪心 | FPGA软核 |
| 文献[175] | - | 二进制搜索树 | VLIW |
| 文献[176] | - | 贪心、单目标化 | CMP |
| 组合优化 | 遗传算法 | 文献[71] | - | GA | 单核片上系统 |
| 文献[72] | 2层次模拟 | 局部搜索+GA | 单核CPU |
| 文献[73,177] | 模糊系统 | GA | VLIW |
| 文献[171] | 多项式回归 | GA | 单核CPU |
| 文献[117] | - | 爬山/GA/蚁群 | CMP |
| 文献[74] | ANN预测级别 | NSGA-II | CMP |
| 文献[69] | ANN | NSGA-II | CMP |
| 文献[178] | ANN | NSGA-II | VLIW |
| 文献[68] | ACOSSO | NSGA-II | CMP |
| 模拟退火 | 文献[178] | ANN预测级别 | 模拟退火 | VLIW |
| 文献[179] | 多种模型之一[25] | 多种搜索算法 | CMP |
| 统计推理 | 不确定度 | 文献[67,97] | AdaBoost.ANN | CoV | 单核CPU |
| 文献[172−173] | XGBoost | 距离的最小值 | 单核CPU |
| 预期改善 | 文献[75,180] | 克里金模型预测级别 | EI(+GA) | CMP |
| 文献[34] | 随机深林 | EI | CMP |
| 超体积改善 | 文献[13] | ACOSSO | EHVI | CMP |
| 文献[14] | 高斯过程 | EHVI | 单核CPU |
| 文献[181] | AdaGBRT | HVI+均匀性 | 单核CPU |
| 文献[182] | BagGBRT | HVI+UCB | 单核CPU |
| 帕累托 | 文献[25] | 多种模型之一 | 候选帕累托最优解集 | CMP |
| 文献[183−184] | 马尔可夫决策 | 帕累托覆盖 | CMP |
| 文献[26,168] | 马尔可夫网预测分布 | 帕累托最优解集 | CMP |
), ArticleFig(id=1327011924258173203, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表9, caption=
迭代搜索加速方法的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 子类型 | 方法来源 | 代理模型 | 搜索/获取函数 | 硬件设计空间 |
|---|
| 注:“-”表示该方法只以软件模拟或基于RTL的电路评估的方式获取性能指标,其余方法可通过训练代理模型替代软件模拟来获取指标或指标之间的关系. |
| 启发式 | | 文献[174] | - | 参数聚类、贪心 | 单核片上系统 |
| 文献[64] | - | 敏感度、贪心 | cache微架构 |
| 文献[66] | - | 敏感度、贪心 | FPGA软核 |
| 文献[175] | - | 二进制搜索树 | VLIW |
| 文献[176] | - | 贪心、单目标化 | CMP |
| 组合优化 | 遗传算法 | 文献[71] | - | GA | 单核片上系统 |
| 文献[72] | 2层次模拟 | 局部搜索+GA | 单核CPU |
| 文献[73,177] | 模糊系统 | GA | VLIW |
| 文献[171] | 多项式回归 | GA | 单核CPU |
| 文献[117] | - | 爬山/GA/蚁群 | CMP |
| 文献[74] | ANN预测级别 | NSGA-II | CMP |
| 文献[69] | ANN | NSGA-II | CMP |
| 文献[178] | ANN | NSGA-II | VLIW |
| 文献[68] | ACOSSO | NSGA-II | CMP |
| 模拟退火 | 文献[178] | ANN预测级别 | 模拟退火 | VLIW |
| 文献[179] | 多种模型之一[25] | 多种搜索算法 | CMP |
| 统计推理 | 不确定度 | 文献[67,97] | AdaBoost.ANN | CoV | 单核CPU |
| 文献[172−173] | XGBoost | 距离的最小值 | 单核CPU |
| 预期改善 | 文献[75,180] | 克里金模型预测级别 | EI(+GA) | CMP |
| 文献[34] | 随机深林 | EI | CMP |
| 超体积改善 | 文献[13] | ACOSSO | EHVI | CMP |
| 文献[14] | 高斯过程 | EHVI | 单核CPU |
| 文献[181] | AdaGBRT | HVI+均匀性 | 单核CPU |
| 文献[182] | BagGBRT | HVI+UCB | 单核CPU |
| 帕累托 | 文献[25] | 多种模型之一 | 候选帕累托最优解集 | CMP |
| 文献[183−184] | 马尔可夫决策 | 帕累托覆盖 | CMP |
| 文献[26,168] | 马尔可夫网预测分布 | 帕累托最优解集 | CMP |
), ArticleFig(id=1327011924354642196, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 10, caption=
Comparison of Simulation Tools, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 准确率 | 模拟速度 | 灵活性 | 开发难度 |
|---|
| 软件模拟 | 低 | 中(~10 MHz) | 高 | 低 |
| 硬件模拟 | 中 | 快(~100 MHz) | 低 | 中 |
| 敏捷设计 | 高 | 慢(1~5 kHz) | 中 | 高 |
), ArticleFig(id=1327011924438528277, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表10, caption=
模拟工具的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 准确率 | 模拟速度 | 灵活性 | 开发难度 |
|---|
| 软件模拟 | 低 | 中(~10 MHz) | 高 | 低 |
| 硬件模拟 | 中 | 快(~100 MHz) | 低 | 中 |
| 敏捷设计 | 高 | 慢(1~5 kHz) | 中 | 高 |
), ArticleFig(id=1327011924505637142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 11, caption=
Comparison of Hardware Simulation Platforms, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 平台 | 功能模拟 | 时序模拟 | 核心数 | 速率/ (MIPS/核) |
|---|
| 注:速率的单位为MIPS/核. “-”表示文献无该数据. |
| 2007 | FAST[79] | QEMU | FPGA | 1 | 1.20 |
| 2009 | ProtoFlex[80-81] | FPGA | 软件 | 16 | - |
| 2010 | RAMP Gold[82] | FPGA | FPGA | 64 | 0.78 |
| 2011 | HAsim[83] | FPGA | FPGA | 15 | 8.47 |
| 2018 | FireSim[84] | FPGA | FPGA | 4096 | 3.42 |
), ArticleFig(id=1327011924602106135, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表11, caption=
硬件模拟平台的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 年份 | 平台 | 功能模拟 | 时序模拟 | 核心数 | 速率/ (MIPS/核) |
|---|
| 注:速率的单位为MIPS/核. “-”表示文献无该数据. |
| 2007 | FAST[79] | QEMU | FPGA | 1 | 1.20 |
| 2009 | ProtoFlex[80-81] | FPGA | 软件 | 16 | - |
| 2010 | RAMP Gold[82] | FPGA | FPGA | 64 | 0.78 |
| 2011 | HAsim[83] | FPGA | FPGA | 15 | 8.47 |
| 2018 | FireSim[84] | FPGA | FPGA | 4096 | 3.42 |
), ArticleFig(id=1327011924677603608, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 12, caption=
Comparison of Agile Development Platforms, figureFileSmall=null, figureFileBig=null, tableContent=
| 语言类型 | 平台 | 设计语言 | 指令集 | 年份 |
|---|
| 注:“-”表示文献无该项. |
| 低级语言 | OpenPiton[85] | Verilog HDL | SPARCv9 | 2016 |
| LiveHD[86] | Verilog HDL | RISC-V | 2020 |
| BlackParrot [87] | SystemVerilog | RISC-V | 2020 |
| 高级语言 | CMD[88] | BlueSpec | RISC-V | 2018 |
| Agile[197] | Chisel | RISC-V | 2016 |
| Chipyard[89] | Chisel | RISC-V | 2020 |
| MINJIE[50] | Chisel | RISC-V | 2022 |
| 语言模型 | llvm-mca[198] | - | - | 2018 |
| Ithemal[199] | - | CISC | 2019 |
| Chip-Chat[200] | 自然语言 | - | 2023 |
| ChipGPT[201] | 自然语言 | RISC | 2023 |
| RTLLM[202] | 自然语言 | RISC | 2023 |
), ArticleFig(id=1327011924757295385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表12, caption=
敏捷开发平台的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 语言类型 | 平台 | 设计语言 | 指令集 | 年份 |
|---|
| 注:“-”表示文献无该项. |
| 低级语言 | OpenPiton[85] | Verilog HDL | SPARCv9 | 2016 |
| LiveHD[86] | Verilog HDL | RISC-V | 2020 |
| BlackParrot [87] | SystemVerilog | RISC-V | 2020 |
| 高级语言 | CMD[88] | BlueSpec | RISC-V | 2018 |
| Agile[197] | Chisel | RISC-V | 2016 |
| Chipyard[89] | Chisel | RISC-V | 2020 |
| MINJIE[50] | Chisel | RISC-V | 2022 |
| 语言模型 | llvm-mca[198] | - | - | 2018 |
| Ithemal[199] | - | CISC | 2019 |
| Chip-Chat[200] | 自然语言 | - | 2023 |
| ChipGPT[201] | 自然语言 | RISC | 2023 |
| RTLLM[202] | 自然语言 | RISC | 2023 |
), ArticleFig(id=1327011924908290330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 13, caption=
Comparison of Performance Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 准确性 | 复杂度 | 可解释性 |
|---|
| 预测模型 | 低 | 低 | 低 |
| 机械模型 | 高 | 高 | 高 |
), ArticleFig(id=1327011924983787803, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表13, caption=
性能模型的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 准确性 | 复杂度 | 可解释性 |
|---|
| 预测模型 | 低 | 低 | 低 |
| 机械模型 | 高 | 高 | 高 |
), ArticleFig(id=1327011925059285276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 14, caption=
Comparison of Performance Prediction Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 准确性 | 复杂度 | 可解释性 |
|---|
| 参数化 | 低 | 低 | 高 |
| 核函数 | 中 | 中 | 低 |
| 神经网络 | 中 | 高 | 低 |
| 树模型 | 中 | 中 | 高 |
| 集成学习 | 高 | 高 | 中 |
), ArticleFig(id=1327011925130588445, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表14, caption=
性能预测模型的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 准确性 | 复杂度 | 可解释性 |
|---|
| 参数化 | 低 | 低 | 高 |
| 核函数 | 中 | 中 | 低 |
| 神经网络 | 中 | 高 | 低 |
| 树模型 | 中 | 中 | 高 |
| 集成学习 | 高 | 高 | 中 |
), ArticleFig(id=1327011925206085918, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 15, caption=
Comparison of Workload-Specific Prediction Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 预测模型 | 硬件设计空间 | 预测指标 | 负载 | 误差/% | R2 | 采样/设计空间 |
|---|
| 注:硬件设计空间中单核主要包括单核处理器微架构,多核指基于总线或片上网络的同构多核处理器. “T”指时间,“E”指功率,“P”指对多个性能指标探索帕累托最优解集,误差以CPI的百分比绝对误差衡量(越接近0越好),R2为相关系数(越接近1越好),“-”表示该工作无显式标注数据. |
| 参数化 | 线性回归[90] | 单核 | CPI | MinnerSPEC | 0.8 | - | 200/67×106 |
| 受限三次样条回归[2,4] | 单核、异构核 | CPI, E, P | SPEC2k | 4.9 | - | 4×103/22×109 |
| 三次样条回归模型[5] | 单核、多核 | T | 18项负载 | 1.4 | - | 300/4.3×109 |
| 埃尔米特多项式插值[210] | PHT, cache | E | SPEC2k, MediaBench | - | - | 243/19×103 |
| 核函数 | 支持向量机[170] | 单核 | T, E | SPEC2k | 0.5 | - | 12/4608 |
| 内核典型相关分析[211] | 多核 | T, E | ENePBench | 6.2 | 0.88 | 450/2.8×106 |
| ACOSSO[68] | 单核、多核 | T, E, P | SPEC2k, SPLASH-2 | - | - | 450/128×103 |
| ACOSSO[13] | 多核 | T, E, P | SPLASH-2 | - | - | 100/332×103 |
| 高斯过程[91] | 核数 | T | SPLASH-3, PARSEC-3 | - | 0.82 | 67/68 |
| 高斯过程[14] | 单核 | T, E, P | 27项负载 | - | - | 14/994 |
| 神经网络 | 径向基函数网络[92] | 单核 | CPI | MinnerSPEC | 2.8 | - | 200/512 |
| 小波神经网络[93] | 单核 | CPI, E, P | SPEC2k | - | - | 1024/246×103 |
| 神经网络[3,209,212-213] | 单核、多核 | CPI | MinneSPEC等 | 2.3 | - | 221/23×103 |
| 神经网络+遗传算法[214] | 单核 | CPI | SPEC2k | 3.3 | | 230/23×103 |
| 树模型 | 模型树[94] | 性能计数器 | CPI | SPEC2k6 | 7.8 | 0.98 | - |
| 模型树[95] | 单核 | T, E | 图像压缩负载 | 1.3 | 0.95 | 3211/3288 |
| 决策树[138] | 性能计数器 | CPI | SPEC2k6,SysMark07等 | 2 | - | - |
| 决策树[96] | 异构核 | T, E | SD-VBS, MiBench | 2.1 | - | 664/830 |
| 集成学习 | 自适应提升+神经网络[67,97] | 单核 | CPI | SPEC2k6 | - | - | 264/8.4×106 |
| 梯度提升回归树[169] | 单核、多核 | T | SPEC2k, SPLASH-2 | 1.1 | - | 3×103/15×106 |
| XGBoost[172] | 单核 | E | riscv-tests | 3.4 | 0.99 | 1120/1200 |
| 提升法+梯度提升回归树[181] | 单核 | CPI, E, P | SPEC2k17 | - | - | 100/2×103 |
| 装袋法+模型树[98] | 单核 | CPI, E | SPEC2k | - | - | 320/71×106 |
| 装袋法+梯度提升回归树[182] | 单核 | CPI, E, P | SPEC2k17 | - | - | 100/37×103 |
| 堆叠法+决策树[22] | 单核、多核 | T, E | SPEC2k6,SPLASH-2 | - | - | 100/605×103 |
| 堆叠法+异类模型[118] | 单核 | CPI, E | SPEC2k | 1.8 | - | 3×103/2.5×109 |
), ArticleFig(id=1327011925310943519, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表15, caption=
特定负载预测模型的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 预测模型 | 硬件设计空间 | 预测指标 | 负载 | 误差/% | R2 | 采样/设计空间 |
|---|
| 注:硬件设计空间中单核主要包括单核处理器微架构,多核指基于总线或片上网络的同构多核处理器. “T”指时间,“E”指功率,“P”指对多个性能指标探索帕累托最优解集,误差以CPI的百分比绝对误差衡量(越接近0越好),R2为相关系数(越接近1越好),“-”表示该工作无显式标注数据. |
| 参数化 | 线性回归[90] | 单核 | CPI | MinnerSPEC | 0.8 | - | 200/67×106 |
| 受限三次样条回归[2,4] | 单核、异构核 | CPI, E, P | SPEC2k | 4.9 | - | 4×103/22×109 |
| 三次样条回归模型[5] | 单核、多核 | T | 18项负载 | 1.4 | - | 300/4.3×109 |
| 埃尔米特多项式插值[210] | PHT, cache | E | SPEC2k, MediaBench | - | - | 243/19×103 |
| 核函数 | 支持向量机[170] | 单核 | T, E | SPEC2k | 0.5 | - | 12/4608 |
| 内核典型相关分析[211] | 多核 | T, E | ENePBench | 6.2 | 0.88 | 450/2.8×106 |
| ACOSSO[68] | 单核、多核 | T, E, P | SPEC2k, SPLASH-2 | - | - | 450/128×103 |
| ACOSSO[13] | 多核 | T, E, P | SPLASH-2 | - | - | 100/332×103 |
| 高斯过程[91] | 核数 | T | SPLASH-3, PARSEC-3 | - | 0.82 | 67/68 |
| 高斯过程[14] | 单核 | T, E, P | 27项负载 | - | - | 14/994 |
| 神经网络 | 径向基函数网络[92] | 单核 | CPI | MinnerSPEC | 2.8 | - | 200/512 |
| 小波神经网络[93] | 单核 | CPI, E, P | SPEC2k | - | - | 1024/246×103 |
| 神经网络[3,209,212-213] | 单核、多核 | CPI | MinneSPEC等 | 2.3 | - | 221/23×103 |
| 神经网络+遗传算法[214] | 单核 | CPI | SPEC2k | 3.3 | | 230/23×103 |
| 树模型 | 模型树[94] | 性能计数器 | CPI | SPEC2k6 | 7.8 | 0.98 | - |
| 模型树[95] | 单核 | T, E | 图像压缩负载 | 1.3 | 0.95 | 3211/3288 |
| 决策树[138] | 性能计数器 | CPI | SPEC2k6,SysMark07等 | 2 | - | - |
| 决策树[96] | 异构核 | T, E | SD-VBS, MiBench | 2.1 | - | 664/830 |
| 集成学习 | 自适应提升+神经网络[67,97] | 单核 | CPI | SPEC2k6 | - | - | 264/8.4×106 |
| 梯度提升回归树[169] | 单核、多核 | T | SPEC2k, SPLASH-2 | 1.1 | - | 3×103/15×106 |
| XGBoost[172] | 单核 | E | riscv-tests | 3.4 | 0.99 | 1120/1200 |
| 提升法+梯度提升回归树[181] | 单核 | CPI, E, P | SPEC2k17 | - | - | 100/2×103 |
| 装袋法+模型树[98] | 单核 | CPI, E | SPEC2k | - | - | 320/71×106 |
| 装袋法+梯度提升回归树[182] | 单核 | CPI, E, P | SPEC2k17 | - | - | 100/37×103 |
| 堆叠法+决策树[22] | 单核、多核 | T, E | SPEC2k6,SPLASH-2 | - | - | 100/605×103 |
| 堆叠法+异类模型[118] | 单核 | CPI, E | SPEC2k | 1.8 | - | 3×103/2.5×109 |
), ArticleFig(id=1327011925403218208, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 16, caption=
Comparison of Cross-Workload Prediction Model Work, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 来源 | 预测模型 | 跨负载方法核心 | 性能指标 | 设计点数 | 误差/% | R2 |
|---|
| 注:“-”表示文献无该数据. “设计点数”列中的表达形式为源样本数量×源负载数量+目标样本数量. |
| 负载特征 | 文献[99] | 归一化、PCA+GA、线性回归 | 负载特征、平均相似负载的结果 | 时间 | 35×25+0 | - | - |
| 文献[8] | 多项式回归+遗传算法 | 负载特征 | CPI | 360×7+0 | 8~10 | >0.90 |
| 文献[100] | 模型树 | 负载特征 | CPI、功率 | 500×25+0 | - | 0.90 |
| 文献[34] | 多种模型之一 | 负载特征、最近邻归类模型 | CPI、功率 | 3 000×10+0 | - | 0.98 |
| 硬件响应 | 文献[9] | 神经网络 | 模型本身泛化 | 时间 | 639×27+50 | - | - |
| 文献[23] | 矩阵补全算法 | 模型本身泛化 | CPI、功率 | 128×20+20 | 10.0 | - |
| 文献[101] | 线性回归 | 响应边际关系、最近邻归类 | CPI | 60×23+600 | 6.3 | 0.92 |
| 文献[215] | 神经网络 | 响应签名、模型本身泛化 | 时间、EDP | 1000×8+0 | 4.2 | - |
| 迁移学习 | 文献[11] | 神经网络 | 线性回归 | CPI、功率 | 512×5+32 | 7.0 | 0.95 |
| 文献[10,216] | 神经网络 | 贪心选择负载、线性回归 | CPI、功率 | 512×5+32 | 3.0 | - |
| 文献[7] | 模型树+自适应提升 | 负载聚类、样本迁移TrAdaBoost | CPI | 10×5+10 | 7.0 | 0.91 |
| 文献[6] | 神经网络+自适应提升 | 支持向量机 | CPI | 128×3+40 | 5.5 | 0.93 |
), ArticleFig(id=1327011925482909985, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表16, caption=
跨负载预测模型工作的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 来源 | 预测模型 | 跨负载方法核心 | 性能指标 | 设计点数 | 误差/% | R2 |
|---|
| 注:“-”表示文献无该数据. “设计点数”列中的表达形式为源样本数量×源负载数量+目标样本数量. |
| 负载特征 | 文献[99] | 归一化、PCA+GA、线性回归 | 负载特征、平均相似负载的结果 | 时间 | 35×25+0 | - | - |
| 文献[8] | 多项式回归+遗传算法 | 负载特征 | CPI | 360×7+0 | 8~10 | >0.90 |
| 文献[100] | 模型树 | 负载特征 | CPI、功率 | 500×25+0 | - | 0.90 |
| 文献[34] | 多种模型之一 | 负载特征、最近邻归类模型 | CPI、功率 | 3 000×10+0 | - | 0.98 |
| 硬件响应 | 文献[9] | 神经网络 | 模型本身泛化 | 时间 | 639×27+50 | - | - |
| 文献[23] | 矩阵补全算法 | 模型本身泛化 | CPI、功率 | 128×20+20 | 10.0 | - |
| 文献[101] | 线性回归 | 响应边际关系、最近邻归类 | CPI | 60×23+600 | 6.3 | 0.92 |
| 文献[215] | 神经网络 | 响应签名、模型本身泛化 | 时间、EDP | 1000×8+0 | 4.2 | - |
| 迁移学习 | 文献[11] | 神经网络 | 线性回归 | CPI、功率 | 512×5+32 | 7.0 | 0.95 |
| 文献[10,216] | 神经网络 | 贪心选择负载、线性回归 | CPI、功率 | 512×5+32 | 3.0 | - |
| 文献[7] | 模型树+自适应提升 | 负载聚类、样本迁移TrAdaBoost | CPI | 10×5+10 | 7.0 | 0.91 |
| 文献[6] | 神经网络+自适应提升 | 支持向量机 | CPI | 128×3+40 | 5.5 | 0.93 |
), ArticleFig(id=1327011925566796066, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 17, caption=
Comparison of Cross-Workload Prediction Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 核心 | 准确性 | 复杂度 |
|---|
| 负载特征 | 特征空间的相似性 | 低 | 低 |
| 硬件响应 | 硬件响应作为新维度 | 中 | 中 |
| 迁移学习 | 元模型的知识迁移 | 高 | 高 |
), ArticleFig(id=1327011925659070755, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表17, caption=
跨负载预测模型的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 核心 | 准确性 | 复杂度 |
|---|
| 负载特征 | 特征空间的相似性 | 低 | 低 |
| 硬件响应 | 硬件响应作为新维度 | 中 | 中 |
| 迁移学习 | 元模型的知识迁移 | 高 | 高 |
), ArticleFig(id=1327011925738762532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 18, caption=
Comparison of Mechanism Model Work, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 来源 | 目标架构 | 组件 | 预测指标 | 仅微架构无关特征 | 误差/% | 速率/(MIPS/核) |
|---|
| 注:“-”表示文献无该数据. |
| 分析模型 | 文献[219] | cache | cache | cache缺失 | ✘ | - | - |
| 文献[102] | 乱序、单核 | 指令窗口、BP、cache | IPC | ✘ | 5.5 | 100 |
| 文献[103] | cache、多核 | cache | IPC | ✘ | 1.57 | - |
| 文献[220] | cache | cache | 功率、面积 | ✘ | 5 | - |
| 文献[221] | 按/乱序、多核 | BP、cache、NoC等 | 功率、面积 | ✘ | 11~23 | - |
| 区间模型 | 文献[222] | 乱序、单核 | BP, cache | IPC | ✘ | 5.8 | - |
| 文献[104] | 乱序、单核 | BP, cache | IPC | ✘ | 7 | - |
| 文献[223] | 乱序、多核 | BP, cache | IPC | ✘ | 4.6 | ~1 |
| 文献[105,224] | 按序、单核 | 指令依赖、BP, cache | CPI、功率 | ✘ | 2.5 | ~6 |
| 文献[225] | 乱序、单核 | BP, cache | IPC、功率 | ✔ | 9.3 | 1.9 |
| 文献[226] | 乱序、多核 | BP, cache | CPI | ✔ | 11.2 | - |
| 文献[227] | 乱序、单核 | SIMD、cache、带宽 | CPI、功率 | ✔ | 25 | - |
| 文献[228] | 乱序、多核 | SIMD、cache、带宽 | 时间、功率 | ✔ | 36 | - |
| 图模型 | 文献[107] | 乱序、单核 | BP, cache | CPI | ✘ | - | - |
| 文献[108] | 乱序、单核 | BP, cache | CPI | ✘ | - | - |
| 文献[109] | 乱序、多核 | BP, cache, NoC | IPC | ✘ | 7.2 | ~12 |
| 概率统计模型 | 文献[110] | 乱序、单核 | BP, cache | IPC | ✘ | 2~10 | - |
| 文献[111] | 乱序、多核 | BP, cache | IPC | ✘ | 7.9 | ~9 |
| 文献[112] | cache | cache | cache缺失 | ✘ | 0.2 | - |
| 混合模型 | 文献[113] | 乱序、单核 | 流水线深度 | IPC | ✘ | - | - |
| 文献[114] | 乱序、单核 | cache、MSHR、预取 | CPI、cache缺失 | ✘ | 9.4 | ~15 |
| 文献[115] | 乱序、单核 | 执行单元 | CPI | ✘ | 5.6 | 15.1 |
), ArticleFig(id=1327011925839425829, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表18, caption=
机械模型工作的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 来源 | 目标架构 | 组件 | 预测指标 | 仅微架构无关特征 | 误差/% | 速率/(MIPS/核) |
|---|
| 注:“-”表示文献无该数据. |
| 分析模型 | 文献[219] | cache | cache | cache缺失 | ✘ | - | - |
| 文献[102] | 乱序、单核 | 指令窗口、BP、cache | IPC | ✘ | 5.5 | 100 |
| 文献[103] | cache、多核 | cache | IPC | ✘ | 1.57 | - |
| 文献[220] | cache | cache | 功率、面积 | ✘ | 5 | - |
| 文献[221] | 按/乱序、多核 | BP、cache、NoC等 | 功率、面积 | ✘ | 11~23 | - |
| 区间模型 | 文献[222] | 乱序、单核 | BP, cache | IPC | ✘ | 5.8 | - |
| 文献[104] | 乱序、单核 | BP, cache | IPC | ✘ | 7 | - |
| 文献[223] | 乱序、多核 | BP, cache | IPC | ✘ | 4.6 | ~1 |
| 文献[105,224] | 按序、单核 | 指令依赖、BP, cache | CPI、功率 | ✘ | 2.5 | ~6 |
| 文献[225] | 乱序、单核 | BP, cache | IPC、功率 | ✔ | 9.3 | 1.9 |
| 文献[226] | 乱序、多核 | BP, cache | CPI | ✔ | 11.2 | - |
| 文献[227] | 乱序、单核 | SIMD、cache、带宽 | CPI、功率 | ✔ | 25 | - |
| 文献[228] | 乱序、多核 | SIMD、cache、带宽 | 时间、功率 | ✔ | 36 | - |
| 图模型 | 文献[107] | 乱序、单核 | BP, cache | CPI | ✘ | - | - |
| 文献[108] | 乱序、单核 | BP, cache | CPI | ✘ | - | - |
| 文献[109] | 乱序、多核 | BP, cache, NoC | IPC | ✘ | 7.2 | ~12 |
| 概率统计模型 | 文献[110] | 乱序、单核 | BP, cache | IPC | ✘ | 2~10 | - |
| 文献[111] | 乱序、多核 | BP, cache | IPC | ✘ | 7.9 | ~9 |
| 文献[112] | cache | cache | cache缺失 | ✘ | 0.2 | - |
| 混合模型 | 文献[113] | 乱序、单核 | 流水线深度 | IPC | ✘ | - | - |
| 文献[114] | 乱序、单核 | cache、MSHR、预取 | CPI、cache缺失 | ✘ | 9.4 | ~15 |
| 文献[115] | 乱序、单核 | 执行单元 | CPI | ✘ | 5.6 | 15.1 |
), ArticleFig(id=1327011925952672038, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=EN, label=Table 19, caption=
Comparison of Mechanism Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 核心思想 | 准确性 | 复杂度 |
|---|
| 分析模型 | 数学公式 | 低 | 低 |
| 区间模型 | 事件分隔的区间 | 中 | 高 |
| 图模型 | 依赖图的关键路径 | 中 | 中 |
| 概率统计模型 | 事件发生的概率 | 中 | 中 |
| 混合模型 | 分析模型+预测模型 | 中 | 低 |
), ArticleFig(id=1327011926057529639, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011732247130887, language=CN, label=表19, caption=
机械模型的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 核心思想 | 准确性 | 复杂度 |
|---|
| 分析模型 | 数学公式 | 低 | 低 |
| 区间模型 | 事件分隔的区间 | 中 | 高 |
| 图模型 | 依赖图的关键路径 | 中 | 中 |
| 概率统计模型 | 事件发生的概率 | 中 | 中 |
| 混合模型 | 分析模型+预测模型 | 中 | 低 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202330348, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330348, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330348, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330348, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1735660800000, fullTextJson=null, articleText=null, reference=null)