检索结果-内蒙古大学图书馆

Journal of Software 2011年第12 SPEC. ISSUE期6卷 2331-2340页

作者： Zhu, Erzhou Guan, Haibing Dong, Guoxing Yang, Yindong Yang, Hongbo Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiaotong University Shanghai China

The method of using DBT (dynamic binary translation) to execute the source ISAs binary code on target platforms has been perplexed by low overhead for many years. GPU as a many-core processor has tremendous computational power. Employing GPU as a coprocessor to parallel execute the hot spot of binary code hold a great promise of substantially reduce the overhead of DBT. This paper presents a novel translation framework for constructing the virtual execution environment aiming at accelerating the process of DBT on CPU/GPU based architectures. With parallelizable parts (hot spots) of binary code and their related information, the framework converts the sequential code into PTX form and executes them on GPUs. Under the framework, we need not to rewrite the source code, and the binary compatibility issues between different GPUs are also resolved properly. Experimental results on several programs from CUDA SDK Code Samples and Parboil Benchmark Suite show that the framework can significantly improve the performance, usually have 10X speedup on average compared to X86 native platforms. Especially, when the scale of input become larger, the performance becomes even better. © 2011 Academy Publisher.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A dynamic-static combined code layout reorganization approach for dynamic binary translation

Journal of Software

引用

Journal of Software 2011年第12 SPEC. ISSUE期6卷 2341-2349页

作者： Guan, Haibing Zhu, Erzhou Chen, Kai Ma, Ruhui He, Yunchao Deng, Haipeng Yang, Hongbo Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiaotong University Shanghai China

Dynamic binary translation (DBT) has attracted much attention as a powerful technique for the runtime adaptation of software among different ISAs. It offers unprecedented flexibility in the control and modification of a program during the runtime. However, its inherent high overhead has perplexed researchers for many years. In order to reduce the overhead of DBT, this paper presents a dynamic-static combined approach to reorganize the layout of software cache. Under this approach, we first employ an emulating execution to collect the profile information and the translated target code. Especially, the path of execution flow will be tracked. In the static phase, based on the profile information collected in the previous stage, we first use the method of code replicating to build the traces, and then reorganize the layout of the target code by putting the hottest traces at the top of the software cache. Because of exact prediction and improved locality, the execution stream will concentrate on a small area with less control transfer. This approach can greatly reduce the overhead of DBT on the condition that the program runs repeatedly. Experimental results on executing the SPEC 2000 benchmarks show that our approach can reduce more than 30% run time on average. © 2011 Academy Publisher.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

A strategy-proof combinatorial heterogeneous channel auction framework in noncooperative wireless networks

引用

IEEE Transactions on Mobile computing 2015年第6期14卷 1123-1137页

作者： Zheng, Zhenzhe Wu, Fan Chen, Guihai Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China

Auction is believed to be an effective way to solve or relieve the problem of radio spectrum shortage, by dynamically redistributing idle wireless channels of primary users to secondary users. However, to design a practical channel auction mechanism, we have to consider five challenges, including strategy-proofness, channel spatial reusability, channel heterogeneity, bid diversity, and social welfare maximization. Unfortunately, none of the existing works fully considered the five design challenges. In this paper, we present the first in-depth study on the problem of dynamic channel redistribution jointly considering the five design challenges, and present SMASHER, which is a family of Strategy-proof coMbinatorial A uction mechaniSms for HEterogeneous channel R edistribution. SMASHER contains two strategy-proof auction mechanisms, namely SMASHER-AP and SMASHER-GR. SMASHER-AP is a strategy-proof, approximately efficient combinatorial auction mechanism for indivisible channel redistribution. We further consider the case, in which channels can be shared by the users in a paradigm of time-division multiplexing and propose SMASHER-GR, which is a strategy-proof channel allocation and scheduling mechanism. We have extensively evaluated our designs. The evaluation results show that our designs achieve much better performance than existing works. © 2014 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

STAR: Strategy-Proof Double Auctions for Multi-Cloud, Multi-Tenant Bandwidth Reservation

引用

IEEE Transactions on Computers 2015年第7期64卷 2071-2083页

作者： Zheng, Zhenzhe Gui, Yang Wu, Fan Chen, Guihai Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University China

Bandwidth reservation has been recognized as a value-added service to the cloud provider in recent years. We consider an open market of cloud bandwidth reservation, in which cloud providers offer bandwidth reservation services to cloud tenants, especially online streaming service providers, who have strict requirements on the amount of bandwidth to guarantee their quality of services. In this paper, we model the open market as a double-sided auction, and propose the first family of STrategy-proof double Auctions for multi-cloud, multi-tenant bandwidth Reservation (STAR). STAR contains two auction mechanisms. The first one, STAR-Grouping, divides the tenants into groups by a bid-independent way, and carefully matches the cloud providers with the tenant groups to form good trades. The second one, STAR-Padding, greedily matches the cloud providers with the tenants, and fills the partially reserved cloud provider(s) with a novel virtual padding tenant who can be a component of the auctioneer. Our analysis shows that both of the two auction mechanisms achieve strategy-proofness and ex-post budget balance. Our evaluation results show that they achieve good performance in terms of social welfare, cloud bandwidth utilization, and tenant satisfaction ratio. © 1968-2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Recovering Performance for Vector-based Machine Learning on Managed Runtime

引用

ACM SIGPLAN Notices 2017年第8期52卷 457-458页

作者： Wu, Mingyu Guan, Haibing Zang, Binyu Chen, Haibo Shanghai Key Laboratory of Scalable Computing and Systems Institute of Parallel and Distributed Systems Shanghai Jiao Tong University China

来源：评论

学校读者我要写书评

暂无评论

An ant colony system algorithm for the problem of server consolidation in virtualized data centers

引用

Journal of Computational Information systems 2012年第16期8卷 6631-6640页

作者： Gao, Yongqiang Guan, Haibing Qi, Zhengwei Wang, Bin Shanghai Key Laboratory of Scalable Computing and Systems Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China

The problem of server sprawl is common in today's data centers. Virtualization-based server consolidation is a vital mechanism to solve the server sprawl problem in modern data centers by consolidating multiple virtualized servers onto a few physical servers leading to improved resource utilization. In this paper we propose an ant colony optimization metaheuristic to solve the problem of server consolidation in virtualized data centers. For evaluating the proposed algorithm we apply it to ten classes of instances proposed in the literature, and compare the results to three competing algorithms including a first-fit decreasing (FFD) algorithm, a genetic algorithm, and a max-min ant system algorithm. The results show that the algorithm proposed in this paper is an effective and efficient methodology to solve the problem of server consolidation in virtualized data centers. © 2012 Binary Information Press.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Privacy and quality preserving multimedia data aggregation for participatory sensing systems

引用

IEEE Transactions on Mobile computing 2015年第6期14卷 1287-1300页

作者： Qiu, Fudong Wu, Fan Chen, Guihai Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai200240 China

With the popularity of mobile wireless devices equipped with various kinds of sensing abilities, a new service paradigm named participatory sensing has emerged to provide users with brand new life experience. However, the wide application of participatory sensing has its own challenges, among which privacy and multimedia data quality preservations are two critical problems. Unfortunately, none of the existing work has fully solved the problem of privacy and quality preserving participatory sensing with multimedia data. In this paper, we propose SLICER , which is the first k -anonymous privacy preserving scheme for participatory sensing with multimedia data. SLICER integrates a data coding technique and message transfer strategies, to achieve strong protection of participants' privacy, while maintaining high data quality. Specifically, we study two kinds of data transfer strategies, namely transfer on meet up (TMU) and minimal cost transfer (MCT). For MCT, we propose two different but complimentary algorithms, including an approximation algorithm and a heuristic algorithm, subject to different strengths of the requirement. Furthermore, we have implemented SLICER and evaluated its performance using publicly released taxi traces. Our evaluation results show that SLICER achieves high data quality, with low computation and communication overhead. © 2014 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Genetic Programming Using Dynamic Population Variation for Computational Efforts Reduction in System Modeling

引用

Journal of shanghai Jiaotong university(Science) 2012年第2期17卷 190-196页

作者：陶砚蕴曹健李明禄 Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai Key Laboratory of Scalable Computing and System

In this paper,we propose genetic programming(GP) using dynamic population variation(DPV) with four innovations for reducing computational efforts.A new stagnation phase definition and characteristic measure are defined for our *** exponential pivot function is proposed to our DPV method in conjunction with the new stagnation phase *** appropriate population variation formula is suggested to accelerate *** efficacy of these innovations in our DPV is examined using six benchmark *** among the difierent characteristic measures has been conducted for regression problems and the new proposed measure outperformed other *** is proved that our DPV has the capacity to provide solutions at a lower computational effort compared with previously proposed DPV methods and standard genetic programming in most ***,our DPV approach introduced in GP could also rapidly find an excellent solution as well as standard GP in system modeling problems.

关键词： dynamic population variation(DPV) stagnation phase exponential pivot function computational effort average number of evaluation diversity

来源：评论

学校读者我要写书评

暂无评论

Suspend-to-PCM: a new power-aware strategy for operating system's rapid suspend and resume

Suspend-to-PCM: a new power-aware strategy for operating sys...

引用

2012 International Conference on Emerging Technologies for Information systems, computing, and Management, ICM 2012

作者： Zi, Chenyang Zhang, Chao Lin, Qian Qi, Zhengwei Gao, Shang Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781461470090

Modern data centers provide good performance and many kinds of services accompanying considerable power consumption. Reducing power consumption becomes essential for decreasing the operating costs. Unlike conventional ways, authors propose the novel Suspend-to-PCM hibernation strategy to provide rapid suspending and resuming of the operating system (OS). Characterized by its low access latency and low energy consumption, Phase change memory (PCM) is a kind of non-volatile flash media. Strategy in the paper is to suspend OS from memory to PCM rather than disk, and vice versa for the resuming. Since PCM owns much better property of access speed and power utilization than traditional storage media, the Suspend-to-PCM strategy is able to achieve improved performance of system suspending and low power consumption. © 2013 Springer Science+Business Media New York.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Distributed Model Interpretation for Vertical Federated Learning with Feature Discrepancy 31

Distributed Model Interpretation for Vertical Federated Lear...

引用

31st IEEE/ACM International Symposium on Quality of Service, IWQoS 2023

作者： Xing, Rui Zheng, Zhenzhe Li, Qinya Wu, Fan Chen, Guihai Shanghai Jiao Tong University Shanghai Key Laboratory of Scalable Computing and Systems China

ISBN: (纸本)9798350399738

Vertical federated learning (VFL) allows multiple clients with misaligned feature spaces to collaboratively accomplish the global model training. Applying VFL to high stakes decision scenarios greatly requires model interpretation for decision reliability and diagnosis. However, the feature discrepancy in VFL raises new issues for model interpretation in distributed setting: one is from the local-global perspective, where the local importance of features is not equal to the global importance;and the other is from the local-local perspective, where information asymmetry among clients causes difficulty in identifying overlapped features. In this work, we propose a new distributed Model Interpretation method for Vertical Federated Learning with feature discrepancy, namely MI-VFL. In particular, to deal with the local-global discrepancy, MI-VFL leverages the law of total probability to adjust the local importance of features and ensures the completeness of the selected features using adversarial game. To handle the local-local discrepancy, MI-VFL builds a federated adversarial learning model to efficiently identify the overlapped features once, rather than performing client-to-client intersections multiple times. We extensively evaluate MI-VFL on six synthetic datasets and five real-world datasets. The evaluation results reveal that MI-VFL can accurately identify the important features, suppress the overlapped features, and thus improve the model performance. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：