Article(id=1329458250841436325, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329458094792356805, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330164, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1678982400000, receivedDateStr=2023-03-17, revisedDate=1692028800000, revisedDateStr=2023-08-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1794897147140, onlineDateStr=2026-11-17, pubDate=1732982400000, pubDateStr=2024-12-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794897147140, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794897147140, creator=13701087609, updateTime=1794897147140, updator=13701087609, issue=Issue{id=1329458094792356805, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='12', pageStart='2937', pageEnd='3187', issueExtLink='null', onlineDate='null', pubDate='1732982400000', pubDateStr='2024-12-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794897109934, creator='13701087609', updateTime=1794897109934, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=2985, endPage=3004, ext={EN=ArticleExt(id=1329458251051151526, articleId=1329458250841436325, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=MC
2 Energy Consumption Model for Massively Distributed Data Parallel Training of Deep Neural Network, columnId=1325489901852041729, journalTitle=Journal of Computer Research and Development, columnName=Computer Architecture, runingTitle=null, highlight=null, articleAbstract=
Deep neural network (DNN) have achieved state-of-the-art accuracy in many modern artificial intelligence (AI) tasks. In recent years, it has become increasingly popular to use high performance computing platforms for massively distributed parallel training of DNN. Energy consumption models have been crucial in designing and optimizing DNN for massively parallel training and restraining excessive energy consumption on HPC (high performance computing) platforms. Currently, most energy consumption models model the energy consumption of a single device or a cluster of multiple devices from a hardware perspective. From an energy consumption perspective, the need for disaggregated analysis of distributed parallel DNN applications has resulted in a dearth of energy consumption models that model the characteristics of distributed DNN applications. In this paper, we propose the “materials preprocessing-computing-communicating” three-stage MC2 model from the perspective of the essential features of DNN model training for the most commonly used DNN distributed data parallel training model. The model is validated by training the classical VGG16, ResNet50 networks and the latest Vision Transformer network using up to 128 MT nodes and 32 FT nodes on the domestic E-class prototype Tianhe-3. The experimental results show that the difference between MC2 and the actual energy measurements is only 2.84%. Compared with the four linear proportional energy models and the AR, SES, and ARIMA time prediction models, the accuracy of the model proposed is improved by 69.12%, 69.50%, 34.58%, 13.47%, 5.23%, 22.13%, and 10.53%, respectively. By using the models proposed in this paper, the energy consumption of DNN models at each stage and the overall energy consumption can be obtained on a supercomputer platform, which provides a basis for evaluating the efficiency of DNN energy-aware massively distributed parallel training and inference, as well as optimizing the strategies of task scheduling, job scheduling, model partitioning, and model pruning.
, authors=Jia Wei, Xingjun Zhang*, Longxiang Wang, Mingqiang Zhao, Xiaoshe Dong, authorsList=Jia Wei, Xingjun Zhang, Longxiang Wang, Mingqiang Zhao, Xiaoshe Dong, authorCompany=null, correspAuthors=Xingjun Zhang, authorNote=
born in 1997. PhD candidate. His research interests include computer architecture, high performance computing, and deep learning
born in 1969. PhD, professor, PhD, supervisor. Senior member of CCF. His main research interests include computer architecture, high performance computing, big data storage system, and computer networks
born in 1988. PhD. Member of CCF. His main research interests include data deduplication, big data storage system, and artificial intelligence
born in 1998. Master candidate. His main research interests include job scheduling, high performance computing, and reinforcement learning
born in 1963. PhD, professor, PhD supervisor. Member of CCF. His main research interests include high performance computer system, storage system, and cloud computing
, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 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=1329458255262232773, articleId=1329458250841436325, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=面向深度神经网络大规模分布式数据并行训练的MC
2能耗模型, columnId=1325489904427344387, journalTitle=计算机研究与发展, columnName=体系结构, runingTitle=null, highlight=null, articleAbstract=
深度神经网络(deep neural network,DNN)在许多现代人工智能(artificial intelligence,AI)任务中取得了最高的精度. 近年来,使用高性能计算平台进行大规模分布式并行训练DNN越来越普遍. 能耗模型在设计和优化DNN大规模并行训练和抑制高性能计算平台过量能耗方面起着至关重要的作用. 目前,大部分的能耗模型都是从设备的角度出发对单个设备或多个设备构成的集群进行能耗建模,由于缺乏从能耗角度对分布式并行DNN应用进行分解剖析,导致罕有针对分布式DNN应用特征进行建模的能耗模型. 针对目前最常用的DNN分布式数据并行训练模式,从DNN模型训练本质特征角度出发,提出了“数据预处理(materials preprocessing)–前向与反向传播(computing)–梯度同步与更新(communicating)”三阶段MC2能耗模型,并通过在国产E级原型机天河三号上使用最多128个MT节点和32个FT节点训练经典的VGG16和ResNet50网络以及最新的Vision Transformer网络验证了模型的有效性和可靠性. 实验结果表明,MC2与真实能耗测量结果相差仅为2.84%,相较4种线性比例能耗模型以及AR,SES,ARIMA时间预测模型准确率分别提升了69.12个百分点,69.50个百分点,34.58个百分点,13.47个百分点,5.23个百分点,22.13个百分点,10.53个百分点. 通过使用的模型可以在超算平台得到DNN模型的各阶段能耗和总体能耗结果,为评估基于能耗感知的DNN大规模分布式数据并行训练及推理各阶段任务调度、作业放置、模型分割、模型裁剪等优化策略的效能提供了基础.
, authors=魏嘉, 张兴军*, 王龙翔, 赵明强, 董小社, authorsList=魏嘉, 张兴军, 王龙翔, 赵明强, 董小社, authorCompany=null, correspAuthors=张兴军, authorNote=
 |
1997年生. 博士研究生. 主要研究方向为计算机体系结构、高性能计算、深度学习 |
 |
1969年生. 博士,教授,博士生导师,CCF高级会员. 主要研究方向为计算机体系结构、高性能计算、大数据存储系统、计算机网络 |
 |
1988年生. 博士. CCF会员. 主要研究方向为数据去重、大数据存储系统、人工智能 |
 |
1998年生. 硕士研究生. 主要研究方向为作业调度、高性能计算、强化学习 |
 |
1963年生. 博士,教授,博士生导师,CCF会员. 主要研究方向为高性能计算系统、存储系统、云计算 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=UK+L1O8/Ge71FNeUW01zuw==, magXml=rcyKvPvJBIFpcvROKtNCpw==, pdfUrl=null, pdf=jgNpU/iMJIa5HgToySXnNw==, pdfFileSize=2988801, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=e+mLYMBpxXqqd5O3GaOeWA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=3QLMQC7/T2vAwGPab4AZFw==, mapNumber=null, fund=null)}, authors=[Author(id=1329458255568416970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=weijia4473@stu.xjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458255639720140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458255568416970, language=EN, stringName=Jia Wei, firstName=Jia, middleName=null, lastName=Wei, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127, bio={"content":"
born in 1997. PhD candidate. His research interests include computer architecture, high performance computing, and deep learning
"}, bioImg=null, bioContent=
born in 1997. PhD candidate. His research interests include computer architecture, high performance computing, and deep learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458255698440397, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458255568416970, language=CN, stringName=魏嘉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安交通大学计算机科学与技术学院 西安 710127, bio={"img":"N1O3OnPbjru2JDAIPftPQg==","content":"
1997年生. 博士研究生. 主要研究方向为计算机体系结构、高性能计算、深度学习
"}, bioImg=N1O3OnPbjru2JDAIPftPQg==, bioContent=
1997年生. 博士研究生. 主要研究方向为计算机体系结构、高性能计算、深度学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458255467753670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, xref=null, ext=[AuthorCompanyExt(id=1329458255476142279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127), AuthorCompanyExt(id=1329458255501308104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安交通大学计算机科学与技术学院 西安 710127)])]), Author(id=1329458255786520783, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xjzhang@xjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329458255857823953, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458255786520783, language=EN, stringName=Xingjun Zhang, firstName=Xingjun, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127, bio={"content":"
born in 1969. PhD, professor, PhD, supervisor. Senior member of CCF. His main research interests include computer architecture, high performance computing, big data storage system, and computer networks
"}, bioImg=null, bioContent=
born in 1969. PhD, professor, PhD, supervisor. Senior member of CCF. His main research interests include computer architecture, high performance computing, big data storage system, and computer networks
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458255920738514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458255786520783, language=CN, stringName=张兴军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=西安交通大学计算机科学与技术学院 西安 710127, bio={"img":"R4p0E925O1h99DRWuHN7GA==","content":"
1969年生. 博士,教授,博士生导师,CCF高级会员. 主要研究方向为计算机体系结构、高性能计算、大数据存储系统、计算机网络
"}, bioImg=R4p0E925O1h99DRWuHN7GA==, bioContent=
1969年生. 博士,教授,博士生导师,CCF高级会员. 主要研究方向为计算机体系结构、高性能计算、大数据存储系统、计算机网络
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458255467753670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, xref=null, ext=[AuthorCompanyExt(id=1329458255476142279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127), AuthorCompanyExt(id=1329458255501308104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安交通大学计算机科学与技术学院 西安 710127)])]), Author(id=1329458255975264468, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, orderNo=2, 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=1329458256038179030, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458255975264468, language=EN, stringName=Longxiang Wang, firstName=Longxiang, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127, bio={"content":"
born in 1988. PhD. Member of CCF. His main research interests include data deduplication, big data storage system, and artificial intelligence
"}, bioImg=null, bioContent=
born in 1988. PhD. Member of CCF. His main research interests include data deduplication, big data storage system, and artificial intelligence
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458256113676503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458255975264468, language=CN, stringName=王龙翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安交通大学计算机科学与技术学院 西安 710127, bio={"img":"SPt6ieZDGCseWRwS/Q9l6w==","content":"
1988年生. 博士. CCF会员. 主要研究方向为数据去重、大数据存储系统、人工智能
"}, bioImg=SPt6ieZDGCseWRwS/Q9l6w==, bioContent=
1988年生. 博士. CCF会员. 主要研究方向为数据去重、大数据存储系统、人工智能
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458255467753670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, xref=null, ext=[AuthorCompanyExt(id=1329458255476142279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127), AuthorCompanyExt(id=1329458255501308104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安交通大学计算机科学与技术学院 西安 710127)])]), Author(id=1329458256189173977, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=1329458256252088539, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458256189173977, language=EN, stringName=Mingqiang Zhao, firstName=Mingqiang, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127, bio={"content":"
born in 1998. Master candidate. His main research interests include job scheduling, high performance computing, and reinforcement learning
"}, bioImg=null, bioContent=
born in 1998. Master candidate. His main research interests include job scheduling, high performance computing, and reinforcement learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458256310808796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458256189173977, language=CN, stringName=赵明强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安交通大学计算机科学与技术学院 西安 710127, bio={"img":"iGdCO5s5eVsDq9IHueZYrw==","content":"
1998年生. 硕士研究生. 主要研究方向为作业调度、高性能计算、强化学习
"}, bioImg=iGdCO5s5eVsDq9IHueZYrw==, bioContent=
1998年生. 硕士研究生. 主要研究方向为作业调度、高性能计算、强化学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458255467753670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, xref=null, ext=[AuthorCompanyExt(id=1329458255476142279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127), AuthorCompanyExt(id=1329458255501308104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安交通大学计算机科学与技术学院 西安 710127)])]), Author(id=1329458256369529054, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=1329458256440832224, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458256369529054, language=EN, stringName=Xiaoshe Dong, firstName=Xiaoshe, middleName=null, lastName=Dong, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127, bio={"content":"
born in 1963. PhD, professor, PhD supervisor. Member of CCF. His main research interests include high performance computer system, storage system, and cloud computing
"}, bioImg=null, bioContent=
born in 1963. PhD, professor, PhD supervisor. Member of CCF. His main research interests include high performance computer system, storage system, and cloud computing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458256507941089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, authorId=1329458256369529054, language=CN, stringName=董小社, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安交通大学计算机科学与技术学院 西安 710127, bio={"img":"+n0XbrXwq0sWKvJQGnGFSg==","content":"
1963年生. 博士,教授,博士生导师,CCF会员. 主要研究方向为高性能计算系统、存储系统、云计算
"}, bioImg=+n0XbrXwq0sWKvJQGnGFSg==, bioContent=
1963年生. 博士,教授,博士生导师,CCF会员. 主要研究方向为高性能计算系统、存储系统、云计算
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458255467753670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, xref=null, ext=[AuthorCompanyExt(id=1329458255476142279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127), AuthorCompanyExt(id=1329458255501308104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安交通大学计算机科学与技术学院 西安 710127)])])], keywords=[Keyword(id=1329458256734433506, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, orderNo=1, keyword=deep neural network (DNN)), Keyword(id=1329458256797348067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, orderNo=2, keyword=energy consumption model), Keyword(id=1329458256881234148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, orderNo=3, keyword=massively distributed training), Keyword(id=1329458256956731621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, orderNo=4, keyword=data parallel), Keyword(id=1329458257019646182, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, orderNo=5, keyword=supercomputer), Keyword(id=1329458257082560743, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, orderNo=1, keyword=深度神经网络), Keyword(id=1329458257153863912, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, orderNo=2, keyword=能耗模型), Keyword(id=1329458257216778473, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, orderNo=3, keyword=大规模分布式训练), Keyword(id=1329458257288081642, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, orderNo=4, keyword=数据并行), Keyword(id=1329458257342607595, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, orderNo=5, keyword=超级计算机)], refs=[Reference(id=1329458263806030101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Orhan A E. Robustness properties of Facebook’s ResNeXt WSL models[J]. arXiv preprint, arXiv: 1907.07640, 2019, articleTitle=null, refAbstract=null), Reference(id=1329458263894110486, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Gao Yongqiang, Guan Haibing, Qi Zhengwei, et al. Quality of service aware power management for virtualized data centers[J]. Journal of Systems Architecture, 2013, 59(4/5): 245−259, articleTitle=null, refAbstract=null), Reference(id=1329458263986385175, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Bilal K, Malik S U R, Khan S U, et al. Trends and challenges in cloud datacenters[J]. IEEE Cloud Computing, 2014, 1(1): 10−20, articleTitle=null, refAbstract=null), Reference(id=1329458264049299736, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Whitehead B, Andrews D, Shah A, et al. Assessing the environmental impact of data centres part 1: Background, energy use and metrics[J]. Building and Environment, 2014, 82(4): 151−159, articleTitle=null, refAbstract=null), Reference(id=1329458264116408601, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Rivoire S M. Designing Energy-Efficient Computer Systems[M]//Models and Metrics for Energy-Efficient Computer Systems. Ann Arbor, MI: ProQuest, 2008: 29−65, articleTitle=null, refAbstract=null), Reference(id=1329458264183517466, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=vor dem Berge M, Da Costa G, Kopecki A, et al. Modeling and simulation of data center energy-efficiency in coolemall[C]//Proc of the 1st Int Workshop on Energy Efficient Data Centers. Berlin: Springer, 2012: 25−36, articleTitle=null, refAbstract=null), Reference(id=1329458264250626331, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Floratou A, Bertsch F, Patel J M, et al. Towards building wind tunnels for data center design[J]. Proceedings of the VLDB Endowment, 2014, 7(9): 781−784, articleTitle=null, refAbstract=null), Reference(id=1329458264351289628, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Dean J, Corrado G S, Monga R, et al. Large scale distributed deep networks[C]//Proc of the 26th Neural Information and Processing System. Cambridge, MA: MIT, 2012: 1223−1231, articleTitle=null, refAbstract=null), Reference(id=1329458264426787101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Raina R, Madhavan A, Ng A Y. Large-scale deep unsupervised learning using graphics processors[C]//Proc of the 26th Int Conf on Machine Learning. New York: ACM, 2009: 873−88, articleTitle=null, refAbstract=null), Reference(id=1329458264493895966, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Li Teng, Dou Yong, Jiang Jingfei, et al. Optimized deep belief networks on CUDA GPUs[C]//Proc of the 27th Int Joint Conf on Neural Networks. Piscataway, NJ: IEEE, 2015: 1688−1696, articleTitle=null, refAbstract=null), Reference(id=1329458264556810527, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Bottleson J, Kim S Y, Andrews J, et al. clCaffe: OpenCL accelerated Caffe for convolutional neural networks[C]//Proc of the 30th IEEE Int Parallel and Distributed Processing Symp Workshops. Piscataway, NJ: IEEE, 2016: 50−57, articleTitle=null, refAbstract=null), Reference(id=1329458264649085216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Kaler T, Stathas N, Ouyang A, et al. Accelerating training and inference of graph neural networks with fast sampling and pipelining[C]//Proc of the 5th Machine Learning and Systems. New York: ACM, 2022: 172−189, articleTitle=null, refAbstract=null), Reference(id=1329458264741359905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Tan Sijun, Knott B, Tian Yuan, et al. CryptGPU: Fast privacy-preserving machine learning on the GPU[C]//Proc of the 42nd IEEE Symp on Security and Privacy. Piscataway, NJ: IEEE, 2021: 1021−1038, articleTitle=null, refAbstract=null), Reference(id=1329458264795885858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Viebke A, Memeti S, Pllana S, et al. CHAOS: A parallelization scheme for training convolutional neural networks on Intel Xeon Phi[J]. The Journal of Supercomputing, 2019, 75(1): 197−227, articleTitle=null, refAbstract=null), Reference(id=1329458264854606115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Liu Junjie, Wang Haixia, Wang Dongsheng, et al. Parallelizing convolutional neural networks on Intel many integrated core architecture[C]//Proc of the 28th Int Conf on Architecture of Computing Systems. Berlin: Springer, 2015: 71−82, articleTitle=null, refAbstract=null), Reference(id=1329458264921714980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Zlateski A, Lee K, Seung H S. Scalable training of 3D convolutional networks on multi-and many-cores[J]. Journal of Parallel and Distributed Computing, 2017, 106(7): 195−204, articleTitle=null, refAbstract=null), Reference(id=1329458264988823845, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Suda N, Chandra V, Dasika G, et al. Throughput-optimized OpenCL-based FPGA accelerator for large-scale convolutional neural networks[C]//Proc of the 24th ACM/SIGDA Int Symp on Field-Programmable Gate Arrays. New York: ACM, 2016: 16−25, articleTitle=null, refAbstract=null), Reference(id=1329458265055932710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Zhang Jialiang, Li Jing. Improving the performance of OpenCL-based FPGA accelerator for convolutional neural network[C]//Proc of the 25th ACM/SIGDA Int Symp on Field-Programmable Gate Arrays. New York: ACM, 2017: 25−34, articleTitle=null, refAbstract=null), Reference(id=1329458265127235879, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Aydonat U, O’Connell S, Capalija D, et al. An OpenCL™ deep learning accelerator on Arria 10[C]//Proc of the 25th ACM/SIGDA Int Symp on Field-Programmable Gate Arrays. New York: ACM, 2017: 55−64, articleTitle=null, refAbstract=null), Reference(id=1329458265194344744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=朱传家,刘鑫,方佳瑞. 基于“神威太湖之光”的Caffe分布式扩展研究[J]. 计算机应用与软件,2020,37(1):15−20, articleTitle=null, refAbstract=null), Reference(id=1329458265261453609, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Zhu Chuanjia, Liu Xin, Fang Jiarui. Research on distributed extension of Caffe based on “Light of Taihu Lake” in Shenwei[J]. Computer Applications and Software, 2020, 37(1): 15−20 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458265336951082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=魏嘉,张兴军,纪泽宇,等. 天河三号原型机分布式并行深度神经网络性能评测及调优[J]. 计算机工程与科学,2021,43(5):782−791, articleTitle=null, refAbstract=null), Reference(id=1329458265446002987, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei Jia, Zhang Xingjun, Ji Zeyu, et al. Performance evaluation and optimization of distributed parallel deep neural networks on the Tianhe-3 prototype[J]. Computer Engineering and Science, 2021, 43(5): 782−791, articleTitle=null, refAbstract=null), Reference(id=1329458265504723244, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Shihao, Satish N, Li Sheng, et al. Parallelizing Word2Vec in shared and distributed memory[J]. IEEE Transactions on Parallel and Distributed Systems, 2019, 30(9): 2090−2100, articleTitle=null, refAbstract=null), Reference(id=1329458265571832109, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Das D, Avancha S, Mudigere D, et al. Distributed deep learning using synchronous stochastic gradient descent[J]. arXiv preprint, arXiv: 1602.06709, 2016, articleTitle=null, refAbstract=null), Reference(id=1329458265638940974, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Roy P, Song S L, Krishnamoorthy S, et al. Numa-caffe: Numa-aware deep learning neural networks[J]. ACM Transactions on Architecture and Code Optimization, 2018, 15(2): 1−26, articleTitle=null, refAbstract=null), Reference(id=1329458265693466927, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Mittal S, Rajput P, Subramoney S. A survey of deep learning on CPUs: Opportunities and co-optimizations[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(10): 5095−5115, articleTitle=null, refAbstract=null), Reference(id=1329458265907376432, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Awan A A, Hamidouche K, Hashmi J M, et al. S-Caffe: Co-designing MPI runtimes and Caffe for scalable deep learning on modern GPU clusters//Proc of the 22nd ACM SIGPLAN Symp on Principles and Practice of Parallel Programming. New York: ACM, 2017: 193−205, articleTitle=null, refAbstract=null), Reference(id=1329458266075148593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin J, Gahlot S, Laanait N, et al. Strategies to deploy and scale deep learning on the summit supercomputer[C]//Proc of the 3rd IEEE/ACM Workshop on Deep Learning on Supercomputers. Piscataway, NJ: IEEE, 2019: 84−94, articleTitle=null, refAbstract=null), Reference(id=1329458266150646066, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Duan Qingyang, Wang Zeqin, Xu Yuedong, et al. Mercury: A simple transport layer scheduler to accelerate distributed DNN training[C]//Proc of the 41st IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2022: 350−359, articleTitle=null, refAbstract=null), Reference(id=1329458266230337843, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yanping, Cheng Youlong, Bapna A, et al. Gpipe: Efficient training of giant neural networks using pipeline parallelism[J]. Advances in Neural Information Processing Systems, 2019, 32(1): 103−112, articleTitle=null, refAbstract=null), Reference(id=1329458266305835316, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Narayanan D, Harlap A, Phanishayee A, et al. PipeDream: Generalized pipeline parallelism for DNN training[C]//Proc of the 27th ACM Symp on Operating Systems Principles. New York: ACM, 2019: 1−15, articleTitle=null, refAbstract=null), Reference(id=1329458266364555573, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Rajbhandari S, Ruwase O, Rasley J, et al. Zero-infinity: Breaking the gpu memory wall for extreme scale deep learning[C]//Proc of the 34th Int Conf for High Performance Computing, Networking, Storage and Analysis. Piscataway, NJ: IEEE, 2021: 826−840, articleTitle=null, refAbstract=null), Reference(id=1329458266465218870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Dayarathna M, Wen Yonggang, Fan Rui. Data center energy consumption modeling: A survey[J]. IEEE Communications Surveys & Tutorials, 2015, 18(1): 732−794, articleTitle=null, refAbstract=null), Reference(id=1329458268075831607, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Ge Rong, Feng Xizhou, Cameron K W. Performance-constrained distributed dvs scheduling for scientific applications on power-aware clusters[C]//Proc of the 18th ACM/IEEE Conf on Supercomputing. Piscataway, NJ: IEEE, 2005: 34−34, articleTitle=null, refAbstract=null), Reference(id=1329458268306518329, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Yeo S, Lee H H S. Peeling the Power Onion of Data Centers[M]//Energy Efficient Thermal Management of Data Centers. Berlin: Springer, 2012: 137−168, articleTitle=null, refAbstract=null), Reference(id=1329458268574953786, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Gao Yongqiang, Guan Haibing, Qi Zhengwei, et al. Quality of service aware power management for virtualized data centers[J]. Journal of Systems Architecture, 2013, 59(4): 245−259, articleTitle=null, refAbstract=null), Reference(id=1329458268658839867, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Shin D, Kim J, Chang N, et al. Energy-optimal dynamic thermal management for green computing[C]//Proc of the 22nd IEEE/ACM Int Conf on Computer-Aided Design-Digest of Technical Papers. Piscataway, NJ: IEEE, 2009: 652−657, articleTitle=null, refAbstract=null), Reference(id=1329458268826612028, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Merkel A, Bellosa F. Balancing power consumption in multiprocessor systems[J]. ACM SIGOPS Operating Systems Review, 2006, 40(4): 403−414, articleTitle=null, refAbstract=null), Reference(id=1329458268897915197, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Bertran R, Becerra Y, Carrera D, et al. Accurate energy accounting for shared virtualized environments using pmc-based power modeling techniques[C/OL]//Proc of the 11th IEEE/ACM Int Conf on Grid Computing. Piscataway, NJ: IEEE, 2010[2023-07-20].https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5697889, articleTitle=null, refAbstract=null), Reference(id=1329458268977606974, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, 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=Li Hui, Casale G, Ellahi T. SLA-driven planning and optimization of enterprise applications[C]//Proc of the 1st Joint WOSP/SIPEW Int Conf on Performance Engineering. New York: ACM, 2010: 117−128, articleTitle=null, refAbstract=null), Reference(id=1329458269074075967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Keqin. Optimal configuration of a multicore server processor for managing the power and performance tradeoff[J]. The Journal of Supercomputing, 2012, 61(1): 189−214, articleTitle=null, refAbstract=null), Reference(id=1329458269149573440, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim S, Roy I, Talwar V. Evaluating integrated graphics processors for data center workloads[C]//Proc of the 46th Workshop on Power-Aware Computing and Systems. New York: ACM, 2013: 41−45, articleTitle=null, refAbstract=null), Reference(id=1329458269208293697, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Jouppi N P, Young C, Patil N, et al. In-datacenter performance analysis of a tensor processing unit[C]//Proc of the 44th Annual Int Symp on Computer Architecture. New York: ACM, 2017: 1−12, articleTitle=null, refAbstract=null), Reference(id=1329458269275402562, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Boyu, Davoodi A, Hu Yuhen. Exploring energy and accuracy tradeoff in structure simplification of trained deep neural networks[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2018, 8(4): 836−848, articleTitle=null, refAbstract=null), Reference(id=1329458269367677251, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Ellison B, Minas L. The problem of power consumption in servers[J]. Energy Efficiency for Information Technology, 2009, 41(2): 1−17, articleTitle=null, refAbstract=null), Reference(id=1329458269447369028, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Giridhar B, Cieslak M, Duggal D, et al. Exploring DRAM organizations for energy-efficient and resilient exascale memories[C]//Proc of the 26th Int Conf on High Performance Computing, Networking, Storage and Analysis. Piscataway, NJ: IEEE, 2013: 277−289, articleTitle=null, refAbstract=null), Reference(id=1329458269514477893, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Jiang, Zheng Hongzhong, Zhu Zhichun, et al. Thermal modeling and management of DRAM memory systems[C]//Proc of the 34th Annual Int Symp on Computer Architecture. New York: ACM, 2007: 312−322, articleTitle=null, refAbstract=null), Reference(id=1329458269581586758, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Vijaykrishnan N, Kandemir M, Irwin M J, et al. Energy-driven integrated hardware-software optimizations using SimplePower[J]. ACM SIGARCH Computer Architecture News, 2000, 28(2): 95−106, articleTitle=null, refAbstract=null), Reference(id=1329458269644501319, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Shiue W T, Chakrabarti C. Memory exploration for low power, embedded systems[C]//Proc of the 36th Design Automation Conf. Piscataway, NJ: IEEE, 1999: 140−145, articleTitle=null, refAbstract=null), Reference(id=1329458269745164616, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Roy S, Rudra A, Verma A. An energy complexity model for algorithms[C]//Proc of the 4th Conf on Innovations in Theoretical Computer Science. New York: ACM, 2013: 283−304, articleTitle=null, refAbstract=null), Reference(id=1329458269812273481, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Poess M, Othayoth Nambiar R. A power consumption analysis of decision support systems[C]//Proc of the 1st Joint WOSP/SIPEW Int Conf on Performance Engineering. New York: ACM, 2010: 147−152, articleTitle=null, refAbstract=null), Reference(id=1329458269870993738, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Boliang, Lu Jiaheng, Zhou Yongluan, et al. Energy efficiency for MapReduce workloads: An in-depth study[C]//Proc of the 33rd Australasian Database Conf. Canberra, Australian: ACS, 2012: 61−70, articleTitle=null, refAbstract=null), Reference(id=1329458269933908299, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang T, Chen Y, Sze V. Designing energy-efficient convolutional neural networks using energy-aware pruning[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 5687−5695, articleTitle=null, refAbstract=null), Reference(id=1329458270017794380, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Ruibo, Lu Kai, Chen Juan, et al. Brief introduction of TianHe exascale prototype system[J]. Tsinghua Science and Technology, 2020, 26(3): 361−369, articleTitle=null, refAbstract=null), Reference(id=1329458270097486157, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei Jia, Zhang Xingjun, Ji Zeyu, et al. Deploying and scaling distributed parallel deep neural networks on the Tianhe-3 prototype system[J]. Scientific Reports, 2021, 11(1): 1−14, articleTitle=null, refAbstract=null), Reference(id=1329458270160400718, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint, arXiv:1409.1556, 2014, articleTitle=null, refAbstract=null), Reference(id=1329458270223315279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 770−778, articleTitle=null, refAbstract=null), Reference(id=1329458270298812752, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[J]. arXiv preprint, arXiv: 2010.11929, 2021, articleTitle=null, refAbstract=null), Reference(id=1329458270378504529, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Marcel S, Rodriguez Y. Torchvision the machine-vision package of torch[C]//Proc of the 18th ACM Int Conf on Multimedia. New York: ACM, 2010: 1485−1488, articleTitle=null, refAbstract=null), Reference(id=1329458270487556434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(1): 1097−1105, articleTitle=null, refAbstract=null), Reference(id=1329458270558859603, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Akaike H. Autoregressive model fitting for control[M]//Selected Papers of Hirotugu Akaike. Berlin: Springer, 1998: 153−170, articleTitle=null, refAbstract=null), Reference(id=1329458270617579860, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Gardner Jr E S. Exponential smoothing: The state of the art[J]. Journal of Forecasting, 1985, 4(1): 1−28, articleTitle=null, refAbstract=null), Reference(id=1329458270697271637, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Box G E P, Pierce D A. Distribution of residual autocorrelations in autoregressive-integrated moving average time series models[J]. Journal of the American statistical Association, 1970, 332(65): 1509−1526, articleTitle=null, refAbstract=null), Reference(id=1329458270755991895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Hanusz Z, Tarasinska J, Zielinski W. Shapiro-Wilk test with known mean[J]. REVSTAT-Statistical Journal, 2016, 14(1): 89−100, articleTitle=null, refAbstract=null), Reference(id=1329458270827295065, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Henning J L. SPEC CPU2000: Measuring CPU performance in the new millennium[J]. Computer, 2000, 33(7): 28−35, articleTitle=null, refAbstract=null), Reference(id=1329458270932152666, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Nishtala R, Petrucci V, Carpenter P, et al. Twig: Multi-agent task management for colocated latency-critical cloud services[C]//Proc of the 26th IEEE Int Symp on High Performance Computer Architecture. Piscataway, NJ: IEEE, 2020: 167−179, articleTitle=null, refAbstract=null), Reference(id=1329458270990872923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Jahanshahi A, Yu Nanpeng, Wong D. PowerMorph: QoS-aware server power reshaping for data center gegulation service[J]. ACM Transactions on Architecture and Code Optimization, 2022, 19(3): 1−27, articleTitle=null, refAbstract=null), Reference(id=1329458272601485660, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Laiping, Yang Yanan, Zhang Kaixuan, et al. Rhythm: Component-distinguishable workload deployment in datacenters[C]//Proc of the 15th European Conf on Computer Systems. New York: ACM, 2020: 153−170, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329458255467753670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, xref=null, ext=[AuthorCompanyExt(id=1329458255476142279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710127), AuthorCompanyExt(id=1329458255501308104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, companyId=1329458255467753670, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安交通大学计算机科学与技术学院 西安 710127)])], figs=[ArticleFig(id=1329458257464242412, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 1, caption=
System structure of HPC platform, figureFileSmall=216CbpeEcB1TgcCGEHeN4w==, figureFileBig=e+mLYMBpxXqqd5O3GaOeWA==, tableContent=null), ArticleFig(id=1329458257543934189, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图1, caption=
高性能计算平台系统结构, figureFileSmall=216CbpeEcB1TgcCGEHeN4w==, figureFileBig=e+mLYMBpxXqqd5O3GaOeWA==, tableContent=null), ArticleFig(id=1329458259238433006, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 2, caption=
Illustration of data parallel training of DNN model, figureFileSmall=UT7cnXLOi/7kMcwaG8NNHw==, figureFileBig=5W/4Kvgx1RbozuX8lbFPpA==, tableContent=null), ArticleFig(id=1329458259297153263, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图2, caption=
深度神经网络模型数据并行训练示意图, figureFileSmall=UT7cnXLOi/7kMcwaG8NNHw==, figureFileBig=5W/4Kvgx1RbozuX8lbFPpA==, tableContent=null), ArticleFig(id=1329458259355873520, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 3, caption=
Structure of MC2 energy consumption model, figureFileSmall=F+6CieKIaqppTszjUkLN7g==, figureFileBig=+1buC/FdMr6EbsMi63R/XA==, tableContent=null), ArticleFig(id=1329458259410399473, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图3, caption=
MC2能耗模型结构, figureFileSmall=F+6CieKIaqppTszjUkLN7g==, figureFileBig=+1buC/FdMr6EbsMi63R/XA==, tableContent=null), ArticleFig(id=1329458259473314034, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 4, caption=
Structure of VGG16 neural network model[55], figureFileSmall=8LCLQUiYFQ27WUaJ+nBhfA==, figureFileBig=ISbwMyZjhMAkJzChXW+0pg==, tableContent=null), ArticleFig(id=1329458259540422899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图4, caption=
VGG16神经网络模型结构[55], figureFileSmall=8LCLQUiYFQ27WUaJ+nBhfA==, figureFileBig=ISbwMyZjhMAkJzChXW+0pg==, tableContent=null), ArticleFig(id=1329458259599143156, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 5, caption=
Building blocks in ResNet[56], figureFileSmall=lJ9DdfLdPQuZmjZkIoiVKg==, figureFileBig=+eaG+Nck+7nTTVBQe+ScQg==, tableContent=null), ArticleFig(id=1329458259666252021, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图5, caption=
ResNet中的构建块[56], figureFileSmall=lJ9DdfLdPQuZmjZkIoiVKg==, figureFileBig=+eaG+Nck+7nTTVBQe+ScQg==, tableContent=null), ArticleFig(id=1329458259716583670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 6, caption=
Structures of ResNet34 and ResNet50[56], figureFileSmall=cClOUeWN6cbVcvM9C2pSFw==, figureFileBig=TTVAD/gaH7PqN62tnk7mNA==, tableContent=null), ArticleFig(id=1329458259771109623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图6, caption=
ResNet34与ResNet50结构[56], figureFileSmall=cClOUeWN6cbVcvM9C2pSFw==, figureFileBig=TTVAD/gaH7PqN62tnk7mNA==, tableContent=null), ArticleFig(id=1329458259850801400, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 7, caption=
Principle diagram of ViT model[54], figureFileSmall=X4XKNGMcw/3VexTN0p3FYw==, figureFileBig=IUhKK+rmNA5XOkEa/FTykA==, tableContent=null), ArticleFig(id=1329458259917910265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图7, caption=
ViT模型原理图[54], figureFileSmall=X4XKNGMcw/3VexTN0p3FYw==, figureFileBig=IUhKK+rmNA5XOkEa/FTykA==, tableContent=null), ArticleFig(id=1329458259989213434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 8, caption=
Time for MTP 128 calculation, communication, and data I/O, figureFileSmall=YCppiDPQursT2YBk4U5itg==, figureFileBig=0c3uxDIQcSl1YBcOk4GQAA==, tableContent=null), ArticleFig(id=1329458260068905211, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图8, caption=
MTP 128计算、通信和数据读取时间, figureFileSmall=YCppiDPQursT2YBk4U5itg==, figureFileBig=0c3uxDIQcSl1YBcOk4GQAA==, tableContent=null), ArticleFig(id=1329458260123431164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Figure 9, caption=
CPU frequencies change with time during training, figureFileSmall=Foj3f7ObDfBN3Ij5vLKXaQ==, figureFileBig=cpQShQ7mQzTqwyHgmavF5g==, tableContent=null), ArticleFig(id=1329458260253454589, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=图9, caption=
训练过程中CPU频率随时间变化, figureFileSmall=Foj3f7ObDfBN3Ij5vLKXaQ==, figureFileBig=cpQShQ7mQzTqwyHgmavF5g==, tableContent=null), ArticleFig(id=1329458260328952062, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 1, caption=
Key Variables in Related Work
, figureFileSmall=null, figureFileBig=null, tableContent=
| 符号 | 含义 |
|---|
| $ W $ | 神经网络权值 |
| $ {\lambda }_{\mathrm{l}\mathrm{r}} $ | 神经网络学习率 |
| n | 批大小 |
| E | 能耗 |
| P | 功率 |
| T | 时间 |
| t | 时刻 |
| $ {P}_{\mathrm{t}\mathrm{o}\mathrm{t}\mathrm{a}\mathrm{l}} $ | 总功率 |
| $ {P}_{\mathrm{d}\mathrm{y}\mathrm{n}\mathrm{a}\mathrm{m}\mathrm{i}\mathrm{c}} $ | 动态功率 |
| $ {P}_{\mathrm{s}\mathrm{t}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{c}} $ | 静态功率 |
| A | 每个时钟周期内的开关数 |
| V | 电压 |
| C | 电容 |
| $ {I}_{\mathrm{s}\mathrm{t}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{c}} $ | 漏电电流 |
| $ {T}_{\mathrm{d}} $ | 温度 |
| $ {K}_{i} $ | 技术常数 |
| $ {\alpha }_{i} $ | 某个事件发生的次数 |
| $ {C}_{i} $ | 某个事件所花费的能耗 |
| m | 处理器核数 |
| $ \rho $ | 处理器核利用率 |
| $ {P}_{s} $ | 速度为s时的处理器功率 |
| λ | 任务到达率 |
| $ R $ | 每个任务平均执行指令数目 |
| $ {\alpha }_{\mathrm{a}i} $ | 活动因子 |
| $ {f}_{\mathrm{m}\mathrm{a}\mathrm{x}i} $ | 处理器组件最大频率 |
| $ {P}_{\mathrm{i}\mathrm{d}\mathrm{l}\mathrm{esm}} $ | 空闲流处理组件功率 |
| $ E_{\rm DRAM\;to\;SRAM} $ | 从DRAM读写数据到SRAM的能耗 |
| $ {E}_{\rm SRAM} $ | SRAM实现激活和权值缓冲区的能耗 |
| $ {E}_{\mathrm{r}\mathrm{e}\mathrm{s}\mathrm{t}} $ | TPU其余组件能耗 |
| $ {P}_{\rm DRAM} $ | 动态随机存储器(DRAM)功率 |
| $ {\mu }_{\mathrm{w}\mathrm{r}\mathrm{i}\mathrm{t}\mathrm{e}} $ | 写吞吐量 |
| $ {\mu }_{\mathrm{r}\mathrm{e}\mathrm{a}\mathrm{d}} $ | 读吞吐量 |
| $ {E}_{\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{c}\mathrm{h}\mathrm{e}} $ | 指令高速缓存能耗 |
| $ {E}_{\mathrm{d}\mathrm{c}\mathrm{a}\mathrm{c}\mathrm{h}\mathrm{e}} $ | 数据高速缓存能耗 |
| $ {E}_{\mathrm{b}\mathrm{u}\mathrm{s}\mathrm{e}\mathrm{s}} $ | 高速缓存指令开销 |
| $ {E}_{\mathrm{p}\mathrm{a}\mathrm{d}\mathrm{s}} $ | 主存与外设间总线能耗 |
| $ {E}_{\mathrm{m}\mathrm{e}\mathrm{m}} $ | 内存能耗 |
| $ \alpha \left(A\right) $ | 算法A激活阶段指令周期数 |
| R(A) | 算法A激活阶段指令读次数 |
| W(A) | 算法A激活阶段指令写次数 |
| $ {P}_{\mathrm{c}\mathrm{k}\mathrm{e}} $ | 内存静态功率 |
| $ {P}_{\mathrm{s}\mathrm{t}\mathrm{b}\mathrm{y}} $ | 激活存储组件和等待指令功率 |
| $ {E}_{\mathrm{a}\mathrm{c}\mathrm{t}} $ | 激活时能耗 |
| $ {P}_{\mathrm{r}\mathrm{d}\mathrm{w}\mathrm{r}} $ | 内存读写功率 |
| $ {P}_{\mathrm{ser}} $ | 整个服务器的功率 |
| $ {P}_{\mathrm{c}\mathrm{p}\mathrm{u}} $ | 服务器中CPU功率 |
| $ {C}_{\mathrm{c}\mathrm{p}\mathrm{u}} $ | 每台服务器CPU的数量 |
| $ {C}_{\mathrm{m}\mathrm{e}\mathrm{m}} $ | 每个服务器中内存DIMMs的数量 |
| $ {C}_{\mathrm{d}} $ | 每个服务器磁盘数量 |
| $ {P}_{\mathrm{d}} $ | 每个磁盘的功率 |
| ($ {P}_{\mathrm{i}}{,T}_{\mathrm{i}} $) | MapReduce初始化阶段 |
| ($ {P}_{\mathrm{m}}{,T}_{\mathrm{m}} $) | MapReduce映射阶段 |
| $ {(P}_{\mathrm{shu}},{T}_{\mathrm{shu}}) $ | MapReduce洗牌阶段 |
| $ \left({P}_{\mathrm{r}},{T}_{\mathrm{r}}\right) $ | MapReduce规约阶段 |
| $ {E}_{\mathrm{l}\mathrm{a}\mathrm{y}\mathrm{e}\mathrm{r}} $ | 每一层的能耗 |
| $ {E}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{p}} $ | 计算开销 |
| $ {E}_{\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 数据输入、数据输出以及卷积核的访存开销 |
), ArticleFig(id=1329458260458975487, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表1, caption=
相关工作中的关键变量
, figureFileSmall=null, figureFileBig=null, tableContent=
| 符号 | 含义 |
|---|
| $ W $ | 神经网络权值 |
| $ {\lambda }_{\mathrm{l}\mathrm{r}} $ | 神经网络学习率 |
| n | 批大小 |
| E | 能耗 |
| P | 功率 |
| T | 时间 |
| t | 时刻 |
| $ {P}_{\mathrm{t}\mathrm{o}\mathrm{t}\mathrm{a}\mathrm{l}} $ | 总功率 |
| $ {P}_{\mathrm{d}\mathrm{y}\mathrm{n}\mathrm{a}\mathrm{m}\mathrm{i}\mathrm{c}} $ | 动态功率 |
| $ {P}_{\mathrm{s}\mathrm{t}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{c}} $ | 静态功率 |
| A | 每个时钟周期内的开关数 |
| V | 电压 |
| C | 电容 |
| $ {I}_{\mathrm{s}\mathrm{t}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{c}} $ | 漏电电流 |
| $ {T}_{\mathrm{d}} $ | 温度 |
| $ {K}_{i} $ | 技术常数 |
| $ {\alpha }_{i} $ | 某个事件发生的次数 |
| $ {C}_{i} $ | 某个事件所花费的能耗 |
| m | 处理器核数 |
| $ \rho $ | 处理器核利用率 |
| $ {P}_{s} $ | 速度为s时的处理器功率 |
| λ | 任务到达率 |
| $ R $ | 每个任务平均执行指令数目 |
| $ {\alpha }_{\mathrm{a}i} $ | 活动因子 |
| $ {f}_{\mathrm{m}\mathrm{a}\mathrm{x}i} $ | 处理器组件最大频率 |
| $ {P}_{\mathrm{i}\mathrm{d}\mathrm{l}\mathrm{esm}} $ | 空闲流处理组件功率 |
| $ E_{\rm DRAM\;to\;SRAM} $ | 从DRAM读写数据到SRAM的能耗 |
| $ {E}_{\rm SRAM} $ | SRAM实现激活和权值缓冲区的能耗 |
| $ {E}_{\mathrm{r}\mathrm{e}\mathrm{s}\mathrm{t}} $ | TPU其余组件能耗 |
| $ {P}_{\rm DRAM} $ | 动态随机存储器(DRAM)功率 |
| $ {\mu }_{\mathrm{w}\mathrm{r}\mathrm{i}\mathrm{t}\mathrm{e}} $ | 写吞吐量 |
| $ {\mu }_{\mathrm{r}\mathrm{e}\mathrm{a}\mathrm{d}} $ | 读吞吐量 |
| $ {E}_{\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{c}\mathrm{h}\mathrm{e}} $ | 指令高速缓存能耗 |
| $ {E}_{\mathrm{d}\mathrm{c}\mathrm{a}\mathrm{c}\mathrm{h}\mathrm{e}} $ | 数据高速缓存能耗 |
| $ {E}_{\mathrm{b}\mathrm{u}\mathrm{s}\mathrm{e}\mathrm{s}} $ | 高速缓存指令开销 |
| $ {E}_{\mathrm{p}\mathrm{a}\mathrm{d}\mathrm{s}} $ | 主存与外设间总线能耗 |
| $ {E}_{\mathrm{m}\mathrm{e}\mathrm{m}} $ | 内存能耗 |
| $ \alpha \left(A\right) $ | 算法A激活阶段指令周期数 |
| R(A) | 算法A激活阶段指令读次数 |
| W(A) | 算法A激活阶段指令写次数 |
| $ {P}_{\mathrm{c}\mathrm{k}\mathrm{e}} $ | 内存静态功率 |
| $ {P}_{\mathrm{s}\mathrm{t}\mathrm{b}\mathrm{y}} $ | 激活存储组件和等待指令功率 |
| $ {E}_{\mathrm{a}\mathrm{c}\mathrm{t}} $ | 激活时能耗 |
| $ {P}_{\mathrm{r}\mathrm{d}\mathrm{w}\mathrm{r}} $ | 内存读写功率 |
| $ {P}_{\mathrm{ser}} $ | 整个服务器的功率 |
| $ {P}_{\mathrm{c}\mathrm{p}\mathrm{u}} $ | 服务器中CPU功率 |
| $ {C}_{\mathrm{c}\mathrm{p}\mathrm{u}} $ | 每台服务器CPU的数量 |
| $ {C}_{\mathrm{m}\mathrm{e}\mathrm{m}} $ | 每个服务器中内存DIMMs的数量 |
| $ {C}_{\mathrm{d}} $ | 每个服务器磁盘数量 |
| $ {P}_{\mathrm{d}} $ | 每个磁盘的功率 |
| ($ {P}_{\mathrm{i}}{,T}_{\mathrm{i}} $) | MapReduce初始化阶段 |
| ($ {P}_{\mathrm{m}}{,T}_{\mathrm{m}} $) | MapReduce映射阶段 |
| $ {(P}_{\mathrm{shu}},{T}_{\mathrm{shu}}) $ | MapReduce洗牌阶段 |
| $ \left({P}_{\mathrm{r}},{T}_{\mathrm{r}}\right) $ | MapReduce规约阶段 |
| $ {E}_{\mathrm{l}\mathrm{a}\mathrm{y}\mathrm{e}\mathrm{r}} $ | 每一层的能耗 |
| $ {E}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{p}} $ | 计算开销 |
| $ {E}_{\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 数据输入、数据输出以及卷积核的访存开销 |
), ArticleFig(id=1329458260584804608, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 2, caption=
Basic Information of Tianhe-3 Prototype
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 属性 | FT-2000+ | MT-2000+ |
|---|
| 硬件 | 节点数 | 128 | 512 |
| 单节点核数 | 32 | 32 |
| 频率/GHz | 2.4 | 2.0 |
| 内存容量/GB | 64 | 16 |
| 网络互联带宽/Gbps | 200 | |
| 软件 | 操作系统 | kylin 4.0-1a OS with kernel v4.4.0 |
| 文件系统 | lustre |
| MPI版本 | mpich v3.2.1 |
| 编译器 | gcc v4.9.1/v4.9.3 |
| 库 | Boost,BLAS,openBLAS,scalapack等 |
), ArticleFig(id=1329458260651913473, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表2, caption=
天河三号原型机基本信息
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 属性 | FT-2000+ | MT-2000+ |
|---|
| 硬件 | 节点数 | 128 | 512 |
| 单节点核数 | 32 | 32 |
| 频率/GHz | 2.4 | 2.0 |
| 内存容量/GB | 64 | 16 |
| 网络互联带宽/Gbps | 200 | |
| 软件 | 操作系统 | kylin 4.0-1a OS with kernel v4.4.0 |
| 文件系统 | lustre |
| MPI版本 | mpich v3.2.1 |
| 编译器 | gcc v4.9.1/v4.9.3 |
| 库 | Boost,BLAS,openBLAS,scalapack等 |
), ArticleFig(id=1329458260706439426, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 3, caption=
Power Consumption of Each Component
, figureFileSmall=null, figureFileBig=null, tableContent=
| 组件类型 | 功率/W |
|---|
| MT-$ {P}_{\mathrm{c}\mathrm{a}} $ | 60 |
| MT-$ {P}_{\mathrm{c}\mathrm{i}} $ | 15 |
| MT-$ {P}_{\mathrm{m}\mathrm{a}} $ | 75 |
| MT-$ {P}_{\mathrm{m}\mathrm{i}} $ | 18.75 |
| FT-$ {P}_{\mathrm{c}\mathrm{a}} $ | 50 |
| FT-$ {P}_{\mathrm{c}\mathrm{i}} $ | 12.5 |
| FT-$ {P}_{\mathrm{m}\mathrm{a}} $ | 46 |
| FT-$ {P}_{\mathrm{m}\mathrm{i}} $ | 11.5 |
), ArticleFig(id=1329458260794519811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表3, caption=
各组件功耗
, figureFileSmall=null, figureFileBig=null, tableContent=
| 组件类型 | 功率/W |
|---|
| MT-$ {P}_{\mathrm{c}\mathrm{a}} $ | 60 |
| MT-$ {P}_{\mathrm{c}\mathrm{i}} $ | 15 |
| MT-$ {P}_{\mathrm{m}\mathrm{a}} $ | 75 |
| MT-$ {P}_{\mathrm{m}\mathrm{i}} $ | 18.75 |
| FT-$ {P}_{\mathrm{c}\mathrm{a}} $ | 50 |
| FT-$ {P}_{\mathrm{c}\mathrm{i}} $ | 12.5 |
| FT-$ {P}_{\mathrm{m}\mathrm{a}} $ | 46 |
| FT-$ {P}_{\mathrm{m}\mathrm{i}} $ | 11.5 |
), ArticleFig(id=1329458260907766020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 4, caption=
Training Time of Each Stage in VGG16-MT128
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 训练时间/s |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 4.5603 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 0.1891 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 0.7302 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.5636 |
| $ {T}_{\mathrm{f}} $ | 21.2910 |
| $ {T}_{\mathrm{b}} $ | 28.6782 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 2.1815 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 0.2425 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 1.8468 |
), ArticleFig(id=1329458261004235013, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表4, caption=
VGG16-MT128各阶段训练时间
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 训练时间/s |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 4.5603 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 0.1891 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 0.7302 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.5636 |
| $ {T}_{\mathrm{f}} $ | 21.2910 |
| $ {T}_{\mathrm{b}} $ | 28.6782 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 2.1815 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 0.2425 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 1.8468 |
), ArticleFig(id=1329458261088121094, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 5, caption=
Training Time of Each Stage in ViT-MT128
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 训练时间/s |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 13.6556 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 1.0237 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 1.8221 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.9213 |
| $ {T}_{\mathrm{f}} $ | 140.0465 |
| $ {T}_{\mathrm{b}} $ | 323.5359 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 21.2551 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 16.7213 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 20.0640 |
), ArticleFig(id=1329458261159424263, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表5, caption=
ViT-MT128各阶段训练时间
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 训练时间/s |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 13.6556 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 1.0237 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 1.8221 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.9213 |
| $ {T}_{\mathrm{f}} $ | 140.0465 |
| $ {T}_{\mathrm{b}} $ | 323.5359 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 21.2551 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 16.7213 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 20.0640 |
), ArticleFig(id=1329458261247504648, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 6, caption=
Training Time of Each Stage in VGG16-FT32
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 训练时间/s |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 3.2940 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 0.1932 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 0.4508 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.2546 |
| $ {T}_{\mathrm{f}} $ | 76.4447 |
| $ {T}_{\mathrm{b}} $ | 100.1702 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 6.3135 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 0.6579 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 4.7971 |
), ArticleFig(id=1329458261352362249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表6, caption=
VGG16-FT32各阶段训练时间
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类型 | 训练时间/s |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 3.2940 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 0.1932 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 0.4508 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.2546 |
| $ {T}_{\mathrm{f}} $ | 76.4447 |
| $ {T}_{\mathrm{b}} $ | 100.1702 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 6.3135 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 0.6579 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 4.7971 |
), ArticleFig(id=1329458261419471114, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 7, caption=
Energy Consumption in VGG MT128 Training
, figureFileSmall=null, figureFileBig=null, tableContent=
| 阶段 | 能耗/(kW·h) | 总能耗/(kW·h) |
|---|
| MT128-数据预处理 | 0.0205 | 0.2743 |
| MT128-前向与反向传播 | 0.2399 |
| MT128-梯度同步与更新 | 0.0139 |
| FT32-数据预处理 | 0.0023 | 0.1600 |
| FT32-前向与反向传播 | 0.1507 |
| FT32-梯度同步与更新 | 0.0070 |
), ArticleFig(id=1329458261494968587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表7, caption=
VGG MT128训练中的能耗
, figureFileSmall=null, figureFileBig=null, tableContent=
| 阶段 | 能耗/(kW·h) | 总能耗/(kW·h) |
|---|
| MT128-数据预处理 | 0.0205 | 0.2743 |
| MT128-前向与反向传播 | 0.2399 |
| MT128-梯度同步与更新 | 0.0139 |
| FT32-数据预处理 | 0.0023 | 0.1600 |
| FT32-前向与反向传播 | 0.1507 |
| FT32-梯度同步与更新 | 0.0070 |
), ArticleFig(id=1329458261557883148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 8, caption=
Energy Consumption in ViT MT128 Training
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 能耗/(kW·h) |
|---|
| $ {E}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 0.065546674 |
| $ {E}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 0.003275884 |
| $ {E}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 0.00874608 |
| $ {E}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.00294816 |
| $ {E}_{\mathrm{f}} $ | 0.672223157 |
| $ {E}_{\mathrm{b}} $ | 1.552972412 |
| $ {E}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 0.10202448 |
| $ {E}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 0.080256 |
| Etotal | 2.5120 |
), ArticleFig(id=1329458261687906573, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表8, caption=
ViT MT128训练中的能耗
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 能耗/(kW·h) |
|---|
| $ {E}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 0.065546674 |
| $ {E}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 0.003275884 |
| $ {E}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 0.00874608 |
| $ {E}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 0.00294816 |
| $ {E}_{\mathrm{f}} $ | 0.672223157 |
| $ {E}_{\mathrm{b}} $ | 1.552972412 |
| $ {E}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 0.10202448 |
| $ {E}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 0.080256 |
| Etotal | 2.5120 |
), ArticleFig(id=1329458261755015438, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 9, caption=
Training Time of Each Stage in MT128 ResNet50
, figureFileSmall=null, figureFileBig=null, tableContent=
| 阶段 | 训练时间/min |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 40.1352 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 6.0920 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 4.3322 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 2.2662 |
| $ {T}_{\mathrm{f}} $ | 115.5126 |
| $ {T}_{\mathrm{b}} $ | 157.6198 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 13.0800 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 4.9034 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 17.9000 |
), ArticleFig(id=1329458261826318607, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表9, caption=
MT128 ResNet50各阶段训练时间
, figureFileSmall=null, figureFileBig=null, tableContent=
| 阶段 | 训练时间/min |
|---|
| $ {T}_{\mathrm{s}\mathrm{e}\mathrm{t}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}\mathrm{s}\mathrm{e}\mathrm{t}} $ | 40.1352 |
| $ {T}_{\mathrm{l}\mathrm{o}\mathrm{a}\mathrm{d}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{a}} $ | 6.0920 |
| $ {T}_{\mathrm{p}\mathrm{r}\mathrm{e}\mathrm{p}\mathrm{r}\mathrm{o}\mathrm{c}\mathrm{e}\mathrm{s}\mathrm{s}} $ | 4.3322 |
| $ {T}_{\mathrm{i}\mathrm{n}\mathrm{o}\mathrm{u}\mathrm{t}\mathrm{m}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}} $ | 2.2662 |
| $ {T}_{\mathrm{f}} $ | 115.5126 |
| $ {T}_{\mathrm{b}} $ | 157.6198 |
| $ {T}_{\mathrm{c}\mathrm{o}\mathrm{m}\mathrm{m}\mathrm{u}\mathrm{n}\mathrm{i}\mathrm{c}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}} $ | 13.0800 |
| $ {T}_{\mathrm{u}\mathrm{p}\mathrm{d}\mathrm{a}\mathrm{t}\mathrm{e}} $ | 4.9034 |
| $ {T}_{\mathrm{a}\mathrm{d}\mathrm{d}} $ | 17.9000 |
), ArticleFig(id=1329458261897621776, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 10, caption=
Energy Consumption in ResNet50 Training
, figureFileSmall=null, figureFileBig=null, tableContent=
| 阶段 | 能耗/(kW·h) |
|---|
| MT128-数据预处理 | 6.28 |
| MT128-前向与反向传播 | 64.69 |
| MT128-梯度同步与更新 | 6.47 |
| MT128-总能耗 | 77.44 |
), ArticleFig(id=1329458261968924945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表10, caption=
ResNet50训练能耗
, figureFileSmall=null, figureFileBig=null, tableContent=
| 阶段 | 能耗/(kW·h) |
|---|
| MT128-数据预处理 | 6.28 |
| MT128-前向与反向传播 | 64.69 |
| MT128-梯度同步与更新 | 6.47 |
| MT128-总能耗 | 77.44 |
), ArticleFig(id=1329458262057005330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=EN, label=Table 11, caption=
Comparison of Energy Consumption Model
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 速度 | 成本 | 部署难易程度 | 准确性 |
|---|
| 测量方法 | 慢 | 高 | 困难 | 高 |
| CPU估算 | 慢 | 高 | 简单 | 低 |
| MC2 | 快 | 低 | 中等 | 较高 |
), ArticleFig(id=1329458263663423763, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458250841436325, language=CN, label=表11, caption=
能耗模型对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 速度 | 成本 | 部署难易程度 | 准确性 |
|---|
| 测量方法 | 慢 | 高 | 困难 | 高 |
| CPU估算 | 慢 | 高 | 简单 | 低 |
| MC2 | 快 | 低 | 中等 | 较高 |
)], 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/issn1000-1239.202330164, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330164, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330164, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330164, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1732982400000, fullTextJson=null, articleText=null, reference=null)