检索结果-内蒙古大学图书馆

Key-attributes based optimistic data consistency maintenance method

5th international symposium on parallel and distributed Processing and Applications/ISPA 2007 international Workshops

作者： Zhou, Jing Wang, Yijie Li, Sikun Natl Univ Def Technol Inst Comp Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China

ISBN: (纸本)9783540747413

Peer-to-peer distributed storage systems usually replicate data objects on multi-node to improve the performance and availability. However, updates may be delayed for P2P systems are generally large-scale and strong distributed, and then the performance of resource location in Internet would be depressed. According to that, an optimistic data consistency maintenance method based on key-attributes is proposed. In the method, updates about key-attributes are separated from user request. Key-updates are propagated by latency-overlay update propagation model, that is, updates are always propagated to nodes having maximum or minimal latency, and assured and uncertain propagation paths of updates are all taken into account. Based on classifying key-update conflicts, a double-level reconciling mechanism including the preprocessing of buffer and the processing of update-log is applied to detect and reconcile conflicts, and then conflicts are solved by policies of last-writer-win and divide-and-rule. Lastly, the technique of managing and maintaining update-log is discussed for the above is deployed based on the information storied in update-log. Delaying key-attributes updates cannot occur by the optimistic disposal method, and then it cannot depress efficiency of resource location based on key-attributes, which adapts well to P2P systems in Internet. The simulation results show it is an effective optimistic consistency maintenance method, achieves good consistency overhead, resource location and access overhead, and has strong robustness.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A distributed multicast routing algorithm for real-time applications in wide area networks

引用

JOURNAL OF parallel AND distributed COMPUTING 2007年第5期67卷 516-530页

作者： Huang, Tzu-Lun Lee, D. T. Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei 10764 Taiwan Acad Sinica Inst Informat Sci Taipei 115 Taiwan

The problem of constructing a minimal cost multicast routing tree (MRT) with delay constraints in wide area networks (WAN) is considered. A new distributed token-passing based algorithm that constructs a sub-optimal MRT satisfying given delay constraints for all members in the multicast group is presented. In contrast with the previous works by Jia [A distributed algorithm of delay-bounded multicast routing for multimedia applications in wide area networks, IEEE/ACM Trans. Network. 6 (1998) 828-837] and several others [Y. Im, Y. Lee, S. Wi, Y. Choi, Delay constrained distributed multicast routing algorithm, Comput. Comm. 20 (1997) 60-66;X. Jia, Y. Zhang, N. Pissinou, K. Makki, A distributed multicast routing protocol for real-time multicast applications, Comput. Networks 31 (1999) 101-110;Q Sun, H. Langendorfer, A distributed delay-constrained dynamic multicast routing algorithm, Telecommun. systems 11 (1999) 47-58], in which cycles may occur, we show that the multicast routing network produced by our algorithm is indeed a tree, namely, cycle free. Also the success rate of our algorithm to find a feasible solution, if one exists, is guaranteed to be 100%, while Jia's algorithm is not. Furthermore, our algorithm is fault tolerant and can also adapt to cases where the multicast group members are allowed to join or leave the multicast session dynamically. Simulations have been conducted and the results show that the MRT generated by our algorithm has better performance compared to previous methods. (C) 2007 Elsevier Inc. All rights reserved.

关键词： multicast routing real-time routing distributed algorithm constrained Steiner tree minimum spanning tree fault tolerant NP-completeness heuristics

来源：评论

学校读者我要写书评

暂无评论

Deploying PHYLIP phylogenetic package on a large scale distributed system 07

Deploying <i>PHYLIP</i> phylogenetic package on a large scal...

引用

7th IEEE international symposium on Cluster Computing and the Grid

作者： Abdennadher, Nabil Boesch, Regis Univ Appl Sci Christchurch New Zealand

ISBN: (纸本)9780769528335

This paper describes the parallelization (gridification) of the phylogenetic pack-age PHYLIP on a Large Scale distributed System termed XtremWeb-CH. PHYLIP is a pack-age of programs for inferring phylogenies (evolutionary trees). It is the most widely-distributed phylogeny-package. PHYLIP has been used to build the largest number of published trees. It's known that some modules of PHYLIP are CPU time consuming;their sequential version can not be applied to a large number of sequences. XtremWeb-CH (XWCH) is a software system that makes it easier for scientists and industrials to deploy and execute their parallel and distributed applications on a public-resource computing infrastructure. Universities, research centres and private companies can create their own XWCH platform while anonymous PC owners can participate to these platforms. They can specify how and when their resources could be used. The objective of XWCH is to develop a real High Performance Peer-To-Peer platform with a distributed scheduling and communication system. The main idea is to build a completely symmetric model where nodes can be providers and consumers at the same time. In this paper we describe the porting, deployment, and execution of some PHYLIP modules on the XWCH platform. The parallelized version of PHYLIP is used to generate evolutionary tree related to HIV viruses.

关键词： Phylogeny Packaging Large-scale systems Peer to peer computing Software systems Computer industry Application software Concurrent computing distributed computing Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Sixth international symposium on parallel and distributed Computing-Title

Sixth International Symposium on Parallel and Distributed Co...

引用

international symposium on parallel and distributed Computing

The following topics are dealt with: parallel computing; cluster computing; grid computing; web services and internet computing; cooperative and collaborative computing; peer-to-peer computing; mobile and ubiquitous computing; software agents and multi-agent systems; algorithms, models and formal verification; programming paradigms and APIs; tools and environments for program analysis; resource discovery and management; task and communication scheduling and load balancing; performance management; parallel, distributed and mobile databases; real-time systems; distributed software components; adaptive computing; real-time distributed systems; security; fault tolerance; scientific computing and large scale simulations; applications and case studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

21st international parallel and distributed Processing symposium, IPDPS 2007

作者： Shi, Xiaoqiu Han, Jinsong Liu, Yunhao Ni, Lionel M. Wenzhou University Dept. of Computer Science Wenzhou Zhejiang 325035 China Hong Kong University of Science and Technology Dept. of Computer Science and Engineering Clear Water Bay Kowloon Hong Kong

ISBN: (纸本)1424409101

In a hybrid peer-to-peer (P2P) system, flooding and DHT are both employed for content locating. The decision to use flooding or DHT largely depends on the population of desired data. Previous works either use local information only, or do not consider dynamic factors of P2P systems. In this paper, we propose a Popularity Adaptive Search method for Hybrid (PASH) P2P systems. By dynamically detecting the content popularity, PASH properly selects search methods and efficiently saves query traffic cost and response time. We comprehensively evaluate PASH through synthetic and trace-driven simulations. The results show that PASH outperforms existing approaches and it also scales well. © 2007 IEEE.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Toward an international "Computer Science Grid" 07

Toward an international "Computer Science Grid"

引用

7th IEEE international symposium on Cluster Computing and the Grid

作者： Cappello, Franck Bal, Henri INRIA Vrije Universiteit

ISBN: (纸本)9780769528335

The Computer Science discipline, especially in large scale distributed systems like Grids and P2P systems and in high performance computing areas, tends to address issues related to increasingly complex systems, gathering thousands to millions of non trivial components. Theoretical analysis, simulation and even emulation are reaching their limits. Like in other scientific disciplines such as physics, chemistry and life science, there is a need to develop, run and maintain generations of scientific instruments for the observation of complex distributed systems running at real scale and under reproducible experimental conditions. Grid'5000 and DAS3 are two large scale systems designed as scientific instruments for researchers in the domains of Grid, P2P and networking. More than testbeds, Grid'5000 and DAS3 have been designed as "Computer Science Grids", where researchers share experimental resources spanning over large geographical distances, are able to reserve resources, configure them, run their experiments, realize precise measurements and replay the same experiments with the same experimental conditions. Computer scientists use these two platforms to address issues in the different software lavers between the hardware and the users: networking protocols, OS, middleware, parallel and distributed application runtimes, and applications. In this paper, we will present two Computer Science Grids: Grid'5000 and DAS3. We will describe the motivations, design and current status of these two systems. We will also present some of their key results, not only in terms of scientific results in computer science, but also the impact of these two systems as research tools. The success of the Grid'5000 and DAS platforms is the basis of an international initiative, having the objective to deploy a European level "Computer Science Grid".

关键词： Computer science Large-scale systems Instruments Application software High performance computing Computational modeling Analytical models Emulation Physics Chemistry

来源：评论

学校读者我要写书评

暂无评论

distributed synthesis of fault-tolerant programs in the high atomicity model

Distributed synthesis of fault-tolerant programs in the high...

引用

9th international symposium on Stabilization, Safety and Security of distributed systems (SSS 2007)

作者： Bonakdarpour, Borzoo Kulkarni, Sandeep S. Abujarad, Fuad Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA

ISBN: (纸本)9783540766261

In this paper, we concentrate on distributed algorithms for automated synthesis of fault-tolerant programs in the high atomicity model, where all processes can read and write all program variables in one atomic step. Although there has recently been an increasing interest in using parallel and distributed techniques in the model checking community, these technique have not been investigated in program synthesis. Developing such techniques is crucial as a means to cope with the state explosion problem in the context of program synthesis and transformation as well. We propose two distributed multithreaded algorithms for adding two levels of fault-tolerance, namely failsafe and masking, to existing fault-intolerant programs whose state space is distributed over a network or cluster of workstations.

关键词： program transformation program synthesis distributed algorithms fault-tolerance parallel synthesis

来源：评论

学校读者我要写书评

暂无评论

Coarse-grain parallel execution for 2-dimensional PDE problems

Coarse-grain parallel execution for 2-dimensional PDE proble...

引用

21st international parallel and distributed Processing symposium, IPDPS 2007

作者： Goumas, Georgios Drosinos, Nikolaos Karakasis, Vasileios Koziris, Nectarios National Technical University of Athens School of Electrical and Computer Engineering Computing Systems Laboratory

ISBN: (纸本)1424409101

This paper presents a new approach for the execution of coarse-grain (tiled) parallel SPMD code for applications derived from the explicit discretization of 2-dimensional PDE problems with finite-differencing schemes. Tiling transformation is an efficient loop transformation to achieve coarse-grain parallelism in such algorithms, while rectangular tile shapes are the only feasible shapes that can be manually applied by program developers. However, rectangular tiling transformations are not always valid due to data dependencies, and thus requiring the application of an appropriate skewing transformation prior to tiling in order to enable rectangular tile shapes. We employ cyclic mapping of tiles to processes and propose a method to determine an efficient rectangular tiling transformation for a fixed number of processes for 2-dimensional, skewed PDE problems. Our experimental results confirm the merit of coarse-grain execution in this family of applications and indicate that the proposed method leads to the selection of highly efficient tiling transformations. © 2007 IEEE.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 2007 ACM Workshop on parallel and distributed systems: Testing and Debugging, PADTAD'07

Proceedings of the 2007 ACM Workshop on Parallel and Distrib...

引用

2007 ACM international symposium on Software Testing and Analysis, ISSTA'07 and PADTAD-V Workshop

ISBN: (纸本)159593748X

The proceedings contain 8 papers. The topics discussed include: a debugger for flow graph based parallel applications;organizing processes and threads for debugging;techniques for specifying bug patterns;testing patterns for software transactional memory engines;semantics driven dynamic partial-order reduction of MPI-based parallel programs;and healing data races on-the-fly.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Cost-driven hybrid configuration prefetching for partial reconfigurable coprocessor

Cost-driven hybrid configuration prefetching for partial rec...

引用

21st international parallel and distributed Processing symposium, IPDPS 2007

作者： Chen, Ying Chen, Simon Y. School of Engineering San Francisco State University 1600 Holloway Ave. San Francisco CA 94132 DSP Group Inc. 3120 Scott Blvd. Santa Clara CA 95054

ISBN: (纸本)1424409101

Reconfigurable computing systems have developed the capability of changing the configuration of the reconfigurable coprocessor multiple times during the course of a program. However, in most systems the reconfigurable coprocessor wastes computation cycles while waiting for the reconfiguration to complete. Therefore, the high demand for frequent run-time reconfiguration directly translates into higher reconfiguration overhead. Some studies have introduced the concept of prefetching to reduce the reconfiguration overhead. However, these prefetching algorithms are probability-driven. We believe that including configuration size information in the prediction algorithm directly links the training of the predictor with the performance gain. Therefore we proposed a performanceoriented cost-driven algorithm for coarse-grained configuration prefetching. Our cycle accurate simulation results show that the proposed cost-driven algorithm outperforms the probability-driven predictor by 10.8% to 29.6% in reducing reconfiguration overhead. © 2007 IEEE.

关键词： parallel processing 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：