检索结果-内蒙古大学图书馆

2nd International Conference on Scalable Information Systems, InfoScale 2007

作者： Tao, Yongcai Jin, Hai Shi, Xuanhua Cluster and Grid Computing Lab Services Computing Technology and System Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781595937575

grid workflow is a complex and typical grid application, but owing to the highly dynamic feature of grid environments, resource unavailability is increasingly becoming severe and poses great challenges to grid workflow scheduling. Though fault recovery mechanism adopted in grid system guarantee the completion of jobs to some extent, but wasting system resources. To overcome the shortcoming, this paper proposes a Markov Chain based grid node availability prediction model which can efficiently predict grid nodes' availability in the future without adding significant overhead. Based on this model, the paper presents a grid workflow scheduling based on reliability cost (RCGS). The performance evaluation results demonstrate that RCGS improves the dependability of workflow execution and success ratio of tasks with low reliability cost.

关键词： grid computing

来源：评论

学校读者我要写书评

暂无评论

Container-Based Customization Approach for Mobile Environments on Clouds 13th

Container-Based Customization Approach for Mobile Environmen...

引用

13th International Conference on Green, Pervasive, and Cloud computing, GPC 2018

作者： Hu, Jiahuan Wu, Song Jin, Hai Chen, Hanhua Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783030150921

Recently, mobile cloud which utilizes the elastic resources of clouds to provide services for mobile applications, is becoming more and more popular. When building a mobile cloud platform (MCP), one of the most important things is to provide an execution environment for mobile applications, e.g., the Android mobile operating system (OS). Many efforts have been made to build Android environments on clouds, such as Android virtual machines (VMs) and Android containers. However, the need of customizable Android execution environments for MCP has been ignored for many years, since the existing OS customization solutions are only designed for hardware-specific platforms or driver-specific applications, and taking little account of frequently-changing scenarios on clouds. Moreover, they lack a unified method of customization, as well as an effective upgrade and maintenance mechanism. As a result, they are not suitable for varied and large-scale scenarios on clouds. Therefore, in this paper, we propose a unified and effective approach for customizing Android environments on clouds. The approach provides a container-based solution to custom-tailor Android OS components, as well as a way to run Android applications for different scenarios. Under the guidance of this approach, we develop an automatic customization toolkit named AndroidKit for generating specific Android OS components. Through this toolkit, we are able to boot new Android VM instances called AndroidXs. These AndroidXs are composed of OS images generated by AndroidKit, which can be easily customized and combined for varied demands on clouds. © 2019, Springer Nature Switzerland AG.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Dev store: Distributed storage system for desktop virtualization

Dev store: Distributed storage system for desktop virtualiza...

引用

8th International Conference on Computer Science and Education, ICCSE 2013

作者： Jiang, Yue Jin, Hai Liao, Xiaofei Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781467344623

With the development of desktop virtualization technology, more and more companies begins to deploy virtual desktop. Traditional NAS and SAN storages can only support small-scale users due to network bandwidth limit and poor scalability. Another disadvantage is that NAS and SAN storages are very expensive. The distributed file systems such as GFS, PVFS, and Lustre are with low cost, high scalability and mass storage, but they are only designed for specific scenarios and can not meet the need of desktop virtualization storage. The characteristics of virtual desktop I/O are small random I/O, high IOPS, snapshot needed and frequent access of the root image. Based on these I/O characteristics, DevStore is designed for desktop virtualization, and aims to be low cost, good scalability and performance. Experiments show that DevStore image's write performance is 70MB/s and read performance is 60MB/s in gigabit Ethernet. The snapshot time of DevStore is less than 1ms. DevStore is also easy to expand. Experiments also show that DevStore is better than QCOW in NFS environment and meets the desktop virtualization storage need. © 2013 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Evaluating RISC-V Vector Instruction Set Architecture Extension with Computer Vision Workloads

引用

Journal of Computer Science & technology 2023年第4期38卷 807-820页

作者：李若时彭平邵志远金海郑然 National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Wuhan 430074China Services Computing Technology and System Laboratory Huazhong University of Science and TechnologyWuhan 430074 China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China

Computer vision(CV)algorithms have been extensively used for a myriad of applications *** the multimedia data are generally well-formatted and regular,it is beneficial to leverage the massive parallel processing power of the underlying platform to improve the performances of CV *** Instruction Multiple Data(SIMD)instructions,capable of conducting the same operation on multiple data items in a single instruction,are extensively employed to improve the efficiency of CV *** this paper,we evaluate the power and effectiveness of RISC-V vector extension(RV-V)on typical CV algorithms,such as Gray Scale,Mean Filter,and Edge *** our examinations,we show that compared with the baseline OpenCV implementation using scalar instructions,the equivalent implementations using the RV-V(version 0.8)can reduce the instruction count of the same CV algorithm up to 24x,when processing the same input ***,the actual performances improvement measured by the cycle counts is highly related with the specific implementation of the underlying RV-V *** our evaluation,by using the vector co-processor(with eight execution lanes)of Xuantie C906,vector-version CV algorithms averagely exhibit up to 2.98x performances speedups compared with their scalar counterparts.

关键词： RISC-V vector extension single instruction multiple data(SIMD) computer vision OpenCV

来源：评论

学校读者我要写书评

暂无评论

A Novel routing scheme for paired peers in P2P network

A Novel routing scheme for paired peers in P2P network

引用

2007 Asian technology Information Program's (ATIP's) 3rd Workshop on High Performance computing in China - Solution Approaches to Impediments for High Performance computing, CHINA HPC'07

作者： Liao, Xiaofei Services Computing Technology and System Lab Cluster and Grid Computing Lab. Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781595939036

Peer-to-Peer (P2P) networks have been shown to be a promising approach to provide instant voice services over the Internet for its potential high scalability. However, for one paired peers, how to efficiently transmit voice data among peers in such networks remains a major challenge. Hereby this paper proposed some hybrid routing schemes for P2P transmitting system, which include improved random detection algorithm, delay binary tree search algorithm, AS-aware discovery algorithm. With the help of these novel routing schemes, we can choose the correct algorithm to transfer media data, in small size but low delay, among peers in P2P network. Simulations show that these new routing strategies achieve obvious effect. © 2008 ACM.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

RTRM: A response time-based replica management strategy for cloud storage system

引用

8th International Conference on grid and Pervasive computing, GPC 2013

作者： Bai, Xiaohu Jin, Hai Liao, Xiaofei Shi, Xuanhua Shao, Zhiyuan Services Computing Technology and System Lab. Cluster and Grid Computing Lab. Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9783642380266

Replica management has become a hot research topic in storage systems. This paper presents a dynamic replica management strategy based on response time, named RTRM. RTRM strategy consists of replica creation, replica selection, and replica placement mechanisms. RTRM sets a threshold for response time, if the response time is longer than the threshold, RTRM will increase the number of replicas and create new replica. When a new request comes, RTRM will predict the bandwidth among the replica servers, and make the replica selection accordingly. The replica placement refers to search new replica placement location, and it is a NP-hard problem. Based on graph theory, this paper proposes a reduction algorithm to solve this problem. The simulation results show that RTRM strategy performs better than the five built-in replica management strategies in terms of network utilization and service response time. © 2013 Springer-Verlag.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

XGCN:a library for large-scale graph neural network recommendations

引用

Frontiers of Computer Science 2024年第3期18卷 247-249页

作者： Xiran SONG Hong HUANG Jianxun LIAN Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Microsoft Research Asia Beijing 100080China

1 Introduction Graph Neural Networks(GNNs)have gained widespread adoption in recommendation systems,and nowadays there is a pressing need to effectively manage large-scale graph data[1].When it comes to large graphs,GNNs may encounter the scalability issue stemming from their multi-layer messagepassing ***,scaling GNNs has emerged as a crucial research area in recent years,with numerous scaling strategies being proposed.

关键词： scaling gained operations

来源：评论

学校读者我要写书评

暂无评论

SAND: semi-automated adaptive network defense via programmable rule generation and deployment

引用

Science China(Information Sciences) 2022年第7期65卷 121-138页

作者： Haoyu CHEN Deqing ZOU Hai JIN Shouhuai XU Bin YUAN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabHubei Engineering Research Center on Big Data Security School of Cyber Science and EngineeringHuazhong University of Science and Technology Department of Computer Science University of Colorado at Colorado Springs

Cyber security is dynamic as defenders often need to adapt their defense postures. The state-ofthe-art is that the adaptation of network defense is done manually(i.e., tedious and error-prone). The ideal solution is to automate adaptive network defense, which is however a difficult problem. As a first step towards automation, we propose investigating how to attain semi-automated adaptive network defense(SAND). We propose an approach extending the architecture of software-defined networking, which is centered on providing defenders with the capability to program the generation and deployment of dynamic defense rules enforced by network defense tools. We present the design and implementation of SAND, as well as the evaluation of the prototype implementation. Experimental results show that SAND can achieve agile and effective dynamic adaptations of defense rules(less than 15 ms on average for each operation), while only incurring a small performance overhead.

关键词： network defense adaptive defense automated defense programmable defense security services software-defined networking security management

来源：评论

学校读者我要写书评

暂无评论

VAST: Automatically combining keywords and visual features for web image retrieval

VAST: Automatically combining keywords and visual features f...

引用

2008 10th International Conference on Advanced Communication technology

作者： Hai, Jin Ruhan, He Wenbing, Tao Aobing, Sun Services Computing Technology and System Lab. Cluster and Grid Computing Lab. Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9788955191356

A large-scale image retrieval system for the WWW, named VAST (VisuAl & SemanTic image search), is presented in this paper. Based on the existing inverted file and visual feature clusters, we form a semantic network on top of the keyword association on the visual feature clusters. The system is able to automatically combine keyword and visual features for retrieval by the semantic network The combination is automatic, simple, and very fast, which is suitable for large-scale web dataset Meanwhile, the retrieval takes advantage of the semantic contents of the images in addition to the low-level features, which remarkably improves the retrieval precision. The experimental results demonstrate the superiority of the system.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

DDASTM: Ensuring conflict serializability efficiently in distributed STM

引用

8th International Conference on grid and Pervasive computing, GPC 2013

作者： Zhang, Yu Jin, Hai Liao, Xiaofei Services Computing Technology and System Lab. Cluster and Grid Computing Lab. Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9783642380266

CS (Conflict Serializability) is a recently proposed relaxer correctness criterion that can increase transactional memory's parallelism. DDA (Distributed Dependency-Aware) model is currently proposed to implement CS in distributed STM (Software Transactional Memory) for the first time. However, its transactions detect conflicts individually via detecting cycles in PG (Precedence Graph) and cause extra runtime overhead, especially at the condition that the transactions access lots of objects or the PG is large. In this paper, we propose an approach to make each cycle in PG detected by those transactions, which construct this cycle, together in parallel way, instead of detecting cycle individually. Experimental results show that the average execution time and communication cost of all transactions, including aborted ones, in our approach, can be decreased to 76% and 78% of those in DDA respectively. Its speedup is up to 2.56x against baseDSTM, employing two-phase locking. © 2013 Springer-Verlag.

关键词： Locks (fasteners)

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：