Article(id=1327018203877847576, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327017934683222337, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440612, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1720972800000, receivedDateStr=2024-07-15, revisedDate=1736352000000, revisedDateStr=2025-01-09, acceptedDate=1737820800000, acceptedDateStr=2025-01-26, onlineDate=1794315394609, onlineDateStr=2026-11-10, pubDate=1759248000000, pubDateStr=2025-10-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794315394609, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794315394609, creator=13701087609, updateTime=1794315394609, updator=13701087609, issue=Issue{id=1327017934683222337, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='10', pageStart='2397', pageEnd='2650', issueExtLink='null', onlineDate='null', pubDate='1759248000000', pubDateStr='2025-10-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794315330429, creator='13701087609', updateTime=1794376951272, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327276391986475384, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327017934683222337, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327276391986475385, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327017934683222337, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=2622, endPage=2634, ext={EN=ArticleExt(id=1327018204121117209, articleId=1327018203877847576, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Generalized Stencil Auto-Tuning Framework on GPU Platform, columnId=1327010930744996407, journalTitle=Journal of Computer Research and Development, columnName=Software Technology, runingTitle=null, highlight=null, articleAbstract=
Stencil computations are widely adopted in scientific applications. Many HPC platforms utilize the high computation capability of GPUs to accelerate Stencil computations. In recent years, Stencils have become more complex in terms of Stencil order, memory accesses, and computation patterns. To adapt Stencil computations to GPU architectures, the academic community has proposed a variety of optimization techniques based on streaming and tiling. Due to the diversity of Stencil computational patterns and GPU architectures, no single optimization technique fits all Stencil instances. Therefore, researchers have proposed Stencil auto-tuning mechanisms to conduct parameter searches for a given combination of optimization techniques. However, existing mechanisms introduce huge offline profiling costs and online prediction overhead, unable to be flexible to arbitrary Stencil patterns. To address the above problems, we propose a generalized Stencil auto-tuning framework GeST, which achieves the ultimate performance optimization of Stencil computations on GPU platforms. Specifically, GeST constructs the global search space through the zero-padding format, quantifying parameter correlations via the coefficient of variation to generate parameter groups. After that, GeST iteratively selects parameter values from the parameter groups, adjusting the sampling ratio according to the reward policy and avoiding redundant execution through Hash coding. The experimental results show that GeST can identify better-performing parameter settings in a short time compared with other state-of-the-art auto-tuning work.
, authors=Qingxiao Sun
1, Hailong Yang
2, authorsList=Qingxiao Sun, Hailong Yang, authorCompany=null, correspAuthors=null, authorNote=
born in 1996. PhD, associate professor. Member of CCF. His main research interests include heterogeneous runtime system and performance optimization
born in 1985. PhD, professor. Distinguished member of CCF. His main research interests include high performance computing and intelligent computing system
, 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=1327018207740801588, articleId=1327018203877847576, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=面向GPU平台的通用Stencil自动调优框架, columnId=1327010930908574265, journalTitle=计算机研究与发展, columnName=软件技术, runingTitle=null, highlight=null, articleAbstract=
Stencil计算在科学应用中得到了广泛采用. 许多高性能计算(HPC)平台利用GPU的高计算能力来加速Stencil计算. 近年来,Stencil计算在阶数、内存访问和计算模式等方面变得更加复杂. 为了使Stencil计算适配GPU架构,学术界提出了各种基于流处理和分块的优化技术. 由于Stencil计算模式和GPU架构的多样性,没有单一的优化技术适合所有Stencil实例. 因此,研究人员提出了Stencil自动调优机制来对给定优化技术组合进行参数搜索. 然而,现有机制引入了庞大的离线分析成本和在线预测开销,并且无法灵活地推广到任意Stencil模式. 为了解决上述问题,提出了通用Stencil自动调优框架GeST,其在GPU平台上实现Stencil计算的极致性能优化. 具体来说,GeST通过零填充格式构建全局搜索空间,利用变异系数量化参数相关性并生成参数组;之后,GeST迭代地从参数组选取参数值,根据奖励策略调整采样比例并通过哈希编码避免冗余执行. 实验结果表明,与其他先进的自动调优工作相比,GeST能够在短时间内识别出性能更优的参数设置.
, authors=孙庆骁
1, 杨海龙
2, authorsList=孙庆骁, 杨海龙, authorCompany=null, correspAuthors=null, authorNote=
 |
1996年生. 博士,副教授. CCF会员. 主要研究方向为异构运行时系统、性能优化 |
 |
1985年生. 博士,教授. CCF杰出会员. 主要研究方向为高性能计算、智能计算系统 |
, correspAuthorsNote=null, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=OUL2jtLuCWk+jQWqvnem8A==, magXml=eoUi6gO3l7onfDR2p5Auag==, pdfUrl=null, pdf=kBoHcPrpTjZ9VpB3z+sOkg==, pdfFileSize=1356232, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=rCg+YwDvU/FWf2KTZMSj5w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=34/jErnVfvC0YBgMfCW/Cg==, mapNumber=null, fund=null)}, authors=[Author(id=1327018966234542097, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=qingxiao.sun@cup.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018966310039571, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, authorId=1327018966234542097, language=EN, stringName=Qingxiao Sun, firstName=Qingxiao, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing 102249, bio={"content":"
born in 1996. PhD, associate professor. Member of CCF. His main research interests include heterogeneous runtime system and performance optimization
"}, bioImg=null, bioContent=
born in 1996. PhD, associate professor. Member of CCF. His main research interests include heterogeneous runtime system and performance optimization
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018966398119956, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, authorId=1327018966234542097, language=CN, stringName=孙庆骁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1中国石油大学(北京)人工智能学院 北京 102249, bio={"img":"w3OPF3+ntt+82m8vg7C7Tg==","content":"
1996年生. 博士,副教授. CCF会员. 主要研究方向为异构运行时系统、性能优化
"}, bioImg=w3OPF3+ntt+82m8vg7C7Tg==, bioContent=
1996年生. 博士,副教授. CCF会员. 主要研究方向为异构运行时系统、性能优化
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018965974495242, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, xref=1, ext=[AuthorCompanyExt(id=1327018965982883851, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018965974495242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing 102249), AuthorCompanyExt(id=1327018965991272460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018965974495242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国石油大学(北京)人工智能学院 北京 102249)])]), Author(id=1327018966465228822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=1327018966544920600, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, authorId=1327018966465228822, language=EN, stringName=Hailong Yang, firstName=Hailong, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2School of Computer Science and Engineering, Beihang University, Beijing 100191, bio={"content":"
born in 1985. PhD, professor. Distinguished member of CCF. His main research interests include high performance computing and intelligent computing system
"}, bioImg=null, bioContent=
born in 1985. PhD, professor. Distinguished member of CCF. His main research interests include high performance computing and intelligent computing system
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018966612029465, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, authorId=1327018966465228822, language=CN, stringName=杨海龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2北京航空航天大学计算机学院 北京 100191, bio={"img":"puYQEYzmALWdoBXgL4scGw==","content":"
1985年生. 博士,教授. CCF杰出会员. 主要研究方向为高性能计算、智能计算系统
"}, bioImg=puYQEYzmALWdoBXgL4scGw==, bioContent=
1985年生. 博士,教授. CCF杰出会员. 主要研究方向为高性能计算、智能计算系统
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018966091935757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, xref=2, ext=[AuthorCompanyExt(id=1327018966142267406, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018966091935757, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Engineering, Beihang University, Beijing 100191), AuthorCompanyExt(id=1327018966150656015, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018966091935757, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2北京航空航天大学计算机学院 北京 100191)])])], keywords=[Keyword(id=1327018966813356058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, orderNo=1, keyword=Stencil computation), Keyword(id=1327018966905630747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, orderNo=2, keyword=GPU), Keyword(id=1327018966989516828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, orderNo=3, keyword=auto-tuning), Keyword(id=1327018967073402909, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, orderNo=4, keyword=performance optimization), Keyword(id=1327018967148900382, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, orderNo=5, keyword=parameter search), Keyword(id=1327018967299895327, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, orderNo=1, keyword=Stencil计算), Keyword(id=1327018967392170016, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, orderNo=2, keyword=GPU), Keyword(id=1327018967463473185, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, orderNo=3, keyword=自动调优), Keyword(id=1327018967526387746, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, orderNo=4, keyword=性能优化), Keyword(id=1327018967585108003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, orderNo=5, keyword=参数搜索)], refs=[Reference(id=1327018971687137344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Mullapudi R T, Vasista V, Bondhugula U. PolyMage: Automatic optimization for image processing pipelines[C]//Proc of the 20th Int Conf on Architectural Support for Programming Languages and Operating Systems. New York: ACM, 2015: 429−443, articleTitle=null, refAbstract=null), Reference(id=1327018971791994945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Gamell M, Teranishi K, Heroux M A, et al. Local recovery and failure masking for Stencil-based applications at extreme scales[C/OL]//Proc of the 27th Int Conf for High Performance Computing, Networking, Storage and Analysis. New York: ACM, 2015[2024-07-15]. https://dl.acm.org/doi/abs/10.1145/2807591.2807672, articleTitle=null, refAbstract=null), Reference(id=1327018971972350018, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Sano K, Hatsuda Y, Yamamoto S. Multi-FPGA accelerator for scalable Stencil computation with constant memory bandwidth[J]. IEEE Transactions on Parallel and Distributed Systems, 2013, 25(3): 695−705, articleTitle=null, refAbstract=null), Reference(id=1327018972039458883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Ravishankar M, Holewinski J, Grover V. Forma: A DSL for image processing applications to target GPUs and multi-core CPUs[C]//Proc of the 8th Workshop on General Purpose Processing Using GPUs. New York: ACM, 2015: 109−120, articleTitle=null, refAbstract=null), Reference(id=1327018972123344964, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Hagedorn B, Stoltzfus L, Steuwer M, et al. High performance stencil code generation with LIFT[C]//Proc of the 16th ACM/IEEE Int Symp on Code Generation and Optimization. New York: ACM, 2018: 100−112, articleTitle=null, refAbstract=null), Reference(id=1327018972240785477, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Rawat P S, Vaidya M, Sukumaran-Rajam A, et al. On optimizing complex Stencils on GPUs[C]//Proc of the 33rd IEEE Int Parallel and Distributed Processing Symp. Piscataway, NJ: IEEE, 2019: 641–652, articleTitle=null, refAbstract=null), Reference(id=1327018972303700038, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Grosser T, Cohen A, Holewinski J, et al. Hybrid hexagonal/classical tiling for GPUs[C]//Proc of the 12th ACM/IEEE Int Symp on Code Generation and Optimization. New York: ACM, 2014: 66−75, articleTitle=null, refAbstract=null), Reference(id=1327018972370808903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Ragan-Kelley J, Barnes C, Adams A, et al. Halide: A language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines[J]. ACM SIGPLAN Notices, 2013, 48(6): 519−530, articleTitle=null, refAbstract=null), Reference(id=1327018972437917768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Matsumura K, Zohouri H R, Wahib M, et al. AN5D: Automated stencil framework for high-degree temporal blocking on GPUs[C]//Proc of the 18th ACM/IEEE Int Symp on Code Generation and Optimization. New York: ACM, 2020: 199–211, articleTitle=null, refAbstract=null), Reference(id=1327018972500832329, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Sun Qingxiao, Liu Yi, Yang Hailong, et al. csTuner: Scalable auto-tuning framework for complex Stencil computation on GPUs[C]//Proc of the 23rd IEEE Int Conf on Cluster Computing. Piscataway, NJ: IEEE, 2021: 192−203, articleTitle=null, refAbstract=null), Reference(id=1327018972576329802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Sun Qingxiao, Liu Yi, Yang Hailong, et al. Adaptive auto-tuning framework for global exploration of Stencil optimization on GPUs[J]. IEEE Transactions on Parallel and Distributed Systems, 2024, 35(1): 20−33, articleTitle=null, refAbstract=null), Reference(id=1327018972651827275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Sun Qingxiao, Liu Yi, Yang Hailong, et al. QoS-aware dynamic resource allocation with improved utilization and energy efficiency on GPU[J]. Parallel Computing, 2022, 113: 102958, articleTitle=null, refAbstract=null), Reference(id=1327018972714741836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Rawat P S, Rastello F, Sukumaran-Rajam A, et al. Register optimizations for Stencils on GPUs[C]//Proc of the 23rd ACM SIGPLAN Symp on Principles and Practice of Parallel Programming. New York: ACM, 2018: 168−182, articleTitle=null, refAbstract=null), Reference(id=1327018972786045005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Sun Qingxiao, Liu Yi, Yang Hailong, et al. StencilMART: Predicting optimization selection for Stencil computations across GPUs[C]//Proc of the 36th IEEE Int Parallel and Distributed Processing Symp. Piscataway, NJ: IEEE, 2022: 875–885, articleTitle=null, refAbstract=null), Reference(id=1327018972869931086, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Yuan Liang, Cao Hang, Zhang Yunquan, et al. Temporal vectorization for Stencils[C/OL]//Proc of the 33rd Int Conf for High Performance Computing, Networking, Storage and Analysis. New York: ACM, 2021[2024-07-15]. https://dl.acm.org/doi/abs/10.1145/3458817.3476149, articleTitle=null, refAbstract=null), Reference(id=1327018972924457039, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Li Kun, Yuan Liang, Zhang Yunquan, et al. Reducing redundancy in data organization and arithmetic calculation for Stencil computations[C/OL]//Proc of the 33rd Int Conf for High Performance Computing, Networking, Storage and Analysis. New York: ACM, 2021[2024-07-15]. https://dl.acm.org/doi/abs/10.1145/3458817.3476154, articleTitle=null, refAbstract=null), Reference(id=1327018972983177296, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Garvey J D, Abdelrahman T S. Automatic performance tuning of Stencil computations on GPUs[C]//Proc of the 44th Int Conf on Parallel Processing. Piscataway, NJ: IEEE, 2015: 300−309, articleTitle=null, refAbstract=null), Reference(id=1327018973046091857, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Stock K, Kong M, Grosser T, et al. A framework for enhancing data reuse via associative reordering[C]//Proc of the 35th ACM SIGPLAN Conf on Programming Language Design and Implementation. New York: ACM, 2014: 65−76, articleTitle=null, refAbstract=null), Reference(id=1327018973117395026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Oh C, Zheng Zhen, Shen Xipeng, et al. GoPipe: A granularity-oblivious programming framework for pipelined Stencil executions on GPU[C]//Proc of the 29th Int Conf on Parallel Architectures and Compilation Techniques. New York: ACM, 2020: 43−54, articleTitle=null, refAbstract=null), Reference(id=1327018973188698195, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Yulong, Tan Guangming, Mo Zeyao, et al. FAST: A fast Stencil autotuning framework based on an optimal solution space model[C]//Proc of the 29th Int Conf on Supercomputing. New York: ACM, 2015: 187−196, articleTitle=null, refAbstract=null), Reference(id=1327018974887391316, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Ansel J, Kamil S, Veeramachaneni K, et al. OpenTuner: An extensible framework for program autotuning[C]//Proc of the 23rd Int Conf on Parallel Architectures and Compilation Techniques. New York: ACM, 2014: 303−316, articleTitle=null, refAbstract=null), Reference(id=1327018974962888789, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Trümper L, Ben-Nun T, Schaad P, et al. Performance embeddings: A similarity-based transfer tuning approach to performance optimization[C]//Proc of the 37th Int Conf on Supercomputing. New York: ACM, 2023: 50−62, articleTitle=null, refAbstract=null), Reference(id=1327018975029997654, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Martínez V, Dupros F, Castro M, et al. Performance improvement of stencil computations for multi-core architectures based on machine learning[J]. Procedia Computer Science, 2017, 108: 305−314, articleTitle=null, refAbstract=null), Reference(id=1327018975105495127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Cosenza B, Durillo J J, Ermon S, et al. Autotuning Stencil computations with structural ordinal regression learning[C]//Proc of the 31st IEEE Int Parallel and Distributed Processing Symp. Piscataway, NJ: IEEE, 2017: 287−296, articleTitle=null, refAbstract=null), Reference(id=1327018975160021080, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Nesterenko B, Yi Qing, Lin P H, et al. Modeling optimization of stencil computations via domain-level properties[C]//Proc of the 13th Int Workshop on Programming Models and Applications for Multicores and Manycores. New York: ACM, 2022: 35−44, articleTitle=null, refAbstract=null), Reference(id=1327018975218741337, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Roy R B, Patel T, Gadepally V, et al. BLISS: Auto-tuning complex applications using a pool of diverse lightweight learning models[C]//Proc of the 42nd ACM SIGPLAN Int Conf on Programming Language Design and Implementation. New York: ACM, 2021: 1280−1295, articleTitle=null, refAbstract=null), Reference(id=1327018975285850202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Christen M, Schenk O, Burkhart H. PATUS: A code generation and autotuning framework for parallel iterative stencil computations on modern microarchitectures[C]//Proc of the 25th IEEE Int Parallel and Distributed Processing Symp. Piscataway, NJ: IEEE, 2011: 676−687, articleTitle=null, refAbstract=null), Reference(id=1327018975352959067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Maruyama N, Nomura T, Sato K, et al. Physis: An implicitly parallel programming model for Stencil computations on large-scale GPU-accelerated supercomputers[C/OL]//Proc of the 23rd Int Conf for High Performance Computing, Networking, Storage and Analysis. New York: ACM, 2011[2024-07-15]. https://dl.acm.org/doi/abs/10.1145/2063384.2063398, articleTitle=null, refAbstract=null), Reference(id=1327018975411679324, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Rawat P S, Vaidya M, Sukumaran-Rajam A, et al. Domain-specific optimization and generation of high-performance GPU code for Stencil computations[J]. Proceedings of the IEEE, 2018, 106(11): 1902−1920, articleTitle=null, refAbstract=null), Reference(id=1327018975491371101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=de Fine Licht J, Kuster A, De Matteis T, et al. StencilFlow: Mapping large Stencil programs to distributed spatial computing systems[C]//Proc of the 19th IEEE/ACM Int Symp on Code Generation and Optimization. Piscataway, NJ: IEEE, 2021: 315−326, articleTitle=null, refAbstract=null), Reference(id=1327018975554285662, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=曹杭, 袁良, 黄珊, 等. 一种基于空间密铺的星型Stencil并行算法[J]. 计算机研究与发展, 2020, 57(12): 2621−2634, articleTitle=null, refAbstract=null), Reference(id=1327018975625588831, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Cao Hang, Yuan Liang, Huang Shan, et al. A parallel star Stencil algorithm based on tessellating[J]. Journal of Computer Research and Development, 2020, 57(12): 2621−2634 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018975709474912, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=Bisbas G, Lydike A, Bauer E, et al. A shared compilation stack for distributed-memory parallelism in Stencil DSLs[C]//Proc of the 29th ACM Int Conf on Architectural Support for Programming Languages and Operating Systems. New York: ACM, 2024: 38−56, articleTitle=null, refAbstract=null), Reference(id=1327018975776583777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, 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=孙相征, 张云泉, 王婷, 等. 对角线稀疏矩阵的SpMV自适应性能优化[J]. 计算机研究与发展, 2013, 50(3): 648−656, articleTitle=null, refAbstract=null), Reference(id=1327018975847886946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Xiangzheng, Zhang Yunquan, Wang Ting, et al. Auto-tuning of SpMV for diagonal sparse matrices[J]. Journal of Computer Research and Development, 2013, 50(3): 648−656 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018975919190115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Ang, Song S L, Kumar A, et al. Critical points based register-concurrency autotuning for GPUs[C]//Proc of the 53rd Design, Automation & Test in Europe Conf & Exhibition. Piscataway, NJ: IEEE, 2016: 1273−1278, articleTitle=null, refAbstract=null), Reference(id=1327018975994687588, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Pfaffe P, Grosser T, Tillmann M. Efficient hierarchical online-autotuning: A case study on polyhedral accelerator mapping[C]//Proc of the 33rd Int Conf on Supercomputing. New York: ACM, 2019: 354−366, articleTitle=null, refAbstract=null), Reference(id=1327018976074379365, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng Lianmin, Jia Chengfan, Sun Minmin, et al. Ansor: Generating high-performance tensor programs for deep learning[C]//Proc of the 14th USENIX Symp on Operating Systems Design and Implementation. Berkeley, CA: USENIX Association, 2020: 863−879, articleTitle=null, refAbstract=null), Reference(id=1327018976145682534, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Romero F, Zhao M, Yadwadkar N J, et al. LLaMA: A heterogeneous & serverless framework for auto-tuning video analytics pipelines[C/OL]//Proc of the 12th ACM Symp on Cloud Computing. New York: ACM, 2021[2024-07-15]. https://dl.acm.org/doi/abs/10.1145/3472883.3486972, articleTitle=null, refAbstract=null), Reference(id=1327018976212791399, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Qi, Zhang Xinyun, Geng Hao, et al. GTuner: Tuning DNN computations on GPU via graph attention network[C]//Proc of the 59th ACM/IEEE Design Automation Conf. New York: ACM, 2022: 1045−1050, articleTitle=null, refAbstract=null), Reference(id=1327018976275705960, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=曹坤, 龙赛琴, 李哲涛. CPU-GPU MPSoC中使用寿命驱动的OpenCL应用调度方法[J]. 计算机研究与发展, 2023, 60(5): 976−991, articleTitle=null, refAbstract=null), Reference(id=1327018976342814825, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Kun, Long Saiqin, Li Zhetao. Lifetime-driven OpenCL application scheduling on CPU-GPU MPSoC[J]. Journal of Computer Research and Development, 2023, 60(5): 976−991 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018976409923690, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Anastasiadis P, Papadopoulou N, Goumas G, et al. PARALiA: A performance aware runtime for auto-tuning linear algebra on heterogeneous systems[J]. ACM Transactions on Architecture and Code Optimization, 2023, 20(4): 1−25, articleTitle=null, refAbstract=null), Reference(id=1327018976493809771, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Jinchen, Song Guanghui, Zhou Bei, et al. A holistic approach to automatic mixed-precision code generation and tuning for affine programs[C]//Proc of the 29th ACM SIGPLAN Annual Symp on Principles and Practice of Parallel Programming. New York: ACM, 2024: 55−67, articleTitle=null, refAbstract=null), Reference(id=1327018976569307244, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Chendi, Xu Yufan, Saravani S M, et al. Accelerated auto-tuning of GPU kernels for tensor computations[C]//Proc of the 38th ACM Int Conf on Supercomputing. New York: ACM, 2024: 549−561, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327018965974495242, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, xref=1, ext=[AuthorCompanyExt(id=1327018965982883851, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018965974495242, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Artificial Intelligence, China University of Petroleum-Beijing, Beijing 102249), AuthorCompanyExt(id=1327018965991272460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018965974495242, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1中国石油大学(北京)人工智能学院 北京 102249)]), AuthorCompany(id=1327018966091935757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, xref=2, ext=[AuthorCompanyExt(id=1327018966142267406, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018966091935757, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Computer Science and Engineering, Beihang University, Beijing 100191), AuthorCompanyExt(id=1327018966150656015, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, companyId=1327018966091935757, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2北京航空航天大学计算机学院 北京 100191)])], figs=[ArticleFig(id=1327018967778045988, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 1, caption=
Basic hardware architecture of GPU, figureFileSmall=7uWSNQZ9zOz+HAXZbv67rw==, figureFileBig=rCg+YwDvU/FWf2KTZMSj5w==, tableContent=null), ArticleFig(id=1327018967845154853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图1, caption=
GPU基础硬件架构, figureFileSmall=7uWSNQZ9zOz+HAXZbv67rw==, figureFileBig=rCg+YwDvU/FWf2KTZMSj5w==, tableContent=null), ArticleFig(id=1327018967941623846, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 2, caption=
The design overview of GeST framework, figureFileSmall=ly64gM1mJe8NPb6bocktOw==, figureFileBig=n3kafqDriGSue1Cc7XE3Qw==, tableContent=null), ArticleFig(id=1327018968138756135, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图2, caption=
GeST框架的设计概要, figureFileSmall=ly64gM1mJe8NPb6bocktOw==, figureFileBig=n3kafqDriGSue1Cc7XE3Qw==, tableContent=null), ArticleFig(id=1327018968222642216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 3, caption=
Workflow of parameter grouping, figureFileSmall=yIKSIKFcEwg359Raqm2gMg==, figureFileBig=x5s6CoY2uPC5hST62d0n4A==, tableContent=null), ArticleFig(id=1327018968298139689, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图3, caption=
参数分组的工作流程, figureFileSmall=yIKSIKFcEwg359Raqm2gMg==, figureFileBig=x5s6CoY2uPC5hST62d0n4A==, tableContent=null), ArticleFig(id=1327018968377831466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 4, caption=
Quota-based reward policy, figureFileSmall=bGlIy/1ukfs/Q45H7msWeg==, figureFileBig=W8jv7UWoWrmUrEcCBqQUmg==, tableContent=null), ArticleFig(id=1327018968457523243, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图4, caption=
基于配额的奖励策略, figureFileSmall=bGlIy/1ukfs/Q45H7msWeg==, figureFileBig=W8jv7UWoWrmUrEcCBqQUmg==, tableContent=null), ArticleFig(id=1327018968524632108, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 5, caption=
Auto-tuning efficiency comparison of typical Stencil patterns on V100 GPU, figureFileSmall=EjIvlNnBg1yS3SzGxxzYkQ==, figureFileBig=8leffoI96OpLTCu0s1ei8g==, tableContent=null), ArticleFig(id=1327018968591740973, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图5, caption=
V100 GPU上典型Stencil模式的自动调优效率对比, figureFileSmall=EjIvlNnBg1yS3SzGxxzYkQ==, figureFileBig=8leffoI96OpLTCu0s1ei8g==, tableContent=null), ArticleFig(id=1327018968671432750, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 6, caption=
Auto-tuning performance comparison of parameters on V100 GPU, figureFileSmall=bAHC6rXcLHhr/knDyWHtpw==, figureFileBig=rBQrSKg7Zy38F4UEUJvbDw==, tableContent=null), ArticleFig(id=1327018970344960047, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图6, caption=
V100 GPU上的参数自动调优性能对比, figureFileSmall=bAHC6rXcLHhr/knDyWHtpw==, figureFileBig=rBQrSKg7Zy38F4UEUJvbDw==, tableContent=null), ArticleFig(id=1327018970420457520, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 7, caption=
Auto-tuning performance comparison of parameters on A100 GPU, figureFileSmall=X8tvheFAHqTgtINrr5VgWg==, figureFileBig=TN/tjQ4z0/3BTAEs47WwUg==, tableContent=null), ArticleFig(id=1327018970500149297, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图7, caption=
A100 GPU上的参数自动调优性能对比, figureFileSmall=X8tvheFAHqTgtINrr5VgWg==, figureFileBig=TN/tjQ4z0/3BTAEs47WwUg==, tableContent=null), ArticleFig(id=1327018970600812594, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 8, caption=
Auto-tuning performance comparison of parameters under other grid sizes, figureFileSmall=De6yI390WjNG8aIvQFlc5w==, figureFileBig=cCQpVDbgJdLu7Kds8m5lEw==, tableContent=null), ArticleFig(id=1327018970688892979, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图8, caption=
其他网格大小下的参数自动调优性能对比, figureFileSmall=De6yI390WjNG8aIvQFlc5w==, figureFileBig=cCQpVDbgJdLu7Kds8m5lEw==, tableContent=null), ArticleFig(id=1327018970756001844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 9, caption=
Auto-tuning performance comparison of parameters with different Stencil dataset sizes, figureFileSmall=3R3qFPXy28Fy1LiHiPvbMA==, figureFileBig=xTUtejfz4VN0tZBmrf8UwQ==, tableContent=null), ArticleFig(id=1327018970827305013, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图9, caption=
不同Stencil数据集规模的参数调优性能对比, figureFileSmall=3R3qFPXy28Fy1LiHiPvbMA==, figureFileBig=xTUtejfz4VN0tZBmrf8UwQ==, tableContent=null), ArticleFig(id=1327018970902802486, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 10, caption=
Auto-tuning performance comparison with different numbers of parameter groups, figureFileSmall=z+Q8nslBlKzK97kyEqaoNw==, figureFileBig=O8im7BC2ZLQrzV8JSyTQJQ==, tableContent=null), ArticleFig(id=1327018970969911351, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图10, caption=
不同参数组数量的自动调优性能对比, figureFileSmall=z+Q8nslBlKzK97kyEqaoNw==, figureFileBig=O8im7BC2ZLQrzV8JSyTQJQ==, tableContent=null), ArticleFig(id=1327018971032825912, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Figure 11, caption=
Time breakdown of processing overhead, figureFileSmall=56h2W0ldBIblBUhRKB2eTw==, figureFileBig=uVTkNYGyQcdh5tHyELoxAQ==, tableContent=null), ArticleFig(id=1327018971087351865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=图11, caption=
处理开销的时间分解, figureFileSmall=56h2W0ldBIblBUhRKB2eTw==, figureFileBig=uVTkNYGyQcdh5tHyELoxAQ==, tableContent=null), ArticleFig(id=1327018971150266426, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Table 1, caption=
Stencil Performance Optimizations Technology on GPU Platforms, figureFileSmall=null, figureFileBig=null, tableContent=
| 优化技术 | 约束 |
|---|
| 注:“—”表示没有约束. |
| 流处理(ST) | — |
| 块合并(BM) | 启用CM时无效 |
| 循环合并(CM) | 启用BM时无效 |
| 重定时(RT) | 仅在启用ST时有效 |
| 预取(PR) | 仅在启用ST时有效 |
| 时间分块(TL) | — |
), ArticleFig(id=1327018971217375291, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=表1, caption=
面向GPU平台的Stencil性能优化技术
, figureFileSmall=null, figureFileBig=null, tableContent=
| 优化技术 | 约束 |
|---|
| 注:“—”表示没有约束. |
| 流处理(ST) | — |
| 块合并(BM) | 启用CM时无效 |
| 循环合并(CM) | 启用BM时无效 |
| 重定时(RT) | 仅在启用ST时有效 |
| 预取(PR) | 仅在启用ST时有效 |
| 时间分块(TL) | — |
), ArticleFig(id=1327018971305455676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Table 2, caption=
Optimization Space of Stencil’s Parameters on GPU Platform, figureFileSmall=null, figureFileBig=null, tableContent=
| 优化技术 | 参数 | 范围 |
|---|
| 线程块维度 | TBx, TBy, TBz | [1,1 024], [1,2 024], [1,64] |
| 共享内存 | useShared | {1,2} |
| 固定内存 | useConstant | {1,2} |
| 流处理 | useStreaming | {1,2} |
| 流处理维度 | SD | {1,2,3} |
| 并发流处理 | SB | [1,MSD] |
| 循环展开 | UFx, UFy, UFz | [1,M1], [1,M2], [1,M3] |
| 循环合并 | CMx, CMy, CMz | [1,M1], [1,M2], [1,M3] |
| 块合并 | BMx, BMy, BMz | [1,M1], [1,M2], [1,M3] |
| 重定时 | useRetiming | {1,2} |
| 预取 | usePrefetching | {1,2} |
| 时间分块 | useTB | {1,2} |
), ArticleFig(id=1327018971376758845, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=表2, caption=
面向GPU平台的Stencil参数优化空间
, figureFileSmall=null, figureFileBig=null, tableContent=
| 优化技术 | 参数 | 范围 |
|---|
| 线程块维度 | TBx, TBy, TBz | [1,1 024], [1,2 024], [1,64] |
| 共享内存 | useShared | {1,2} |
| 固定内存 | useConstant | {1,2} |
| 流处理 | useStreaming | {1,2} |
| 流处理维度 | SD | {1,2,3} |
| 并发流处理 | SB | [1,MSD] |
| 循环展开 | UFx, UFy, UFz | [1,M1], [1,M2], [1,M3] |
| 循环合并 | CMx, CMy, CMz | [1,M1], [1,M2], [1,M3] |
| 块合并 | BMx, BMy, BMz | [1,M1], [1,M2], [1,M3] |
| 重定时 | useRetiming | {1,2} |
| 预取 | usePrefetching | {1,2} |
| 时间分块 | useTB | {1,2} |
), ArticleFig(id=1327018971448062014, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=EN, label=Table 3, caption=
Hardware Specifications, figureFileSmall=null, figureFileBig=null, tableContent=
| 服务器参数 | CPU | GPU |
|---|
| 型号 | Intel Xeon E5-2680 v4 | NVIDIA Tesla V100 |
| 频率/GHz | 2.4 | 1.5 |
| 核心 | 28 | 13 440 (80 SMs) |
| 缓存 | 32 KB L1, 256KB L2, 35 MB L3 | 6 MB L2 |
| 内存 | 378 GB DDR4 | 32 GB HBM2 |
| 带宽/GBps | 76.8 | 900 |
), ArticleFig(id=1327018971519365183, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018203877847576, language=CN, label=表3, caption=
硬件规格
, figureFileSmall=null, figureFileBig=null, tableContent=
| 服务器参数 | CPU | GPU |
|---|
| 型号 | Intel Xeon E5-2680 v4 | NVIDIA Tesla V100 |
| 频率/GHz | 2.4 | 1.5 |
| 核心 | 28 | 13 440 (80 SMs) |
| 缓存 | 32 KB L1, 256KB L2, 35 MB L3 | 6 MB L2 |
| 内存 | 378 GB DDR4 | 32 GB HBM2 |
| 带宽/GBps | 76.8 | 900 |
)], 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/issn1000-1239.202440612, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440612, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440612, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440612, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1759248000000, fullTextJson=null, articleText=null, reference=null)