检索结果-内蒙古大学图书馆

GridFoRCE: A comprehensive resource kit for teaching grid computing

IEEE TRANSACTIONS ON EDUCATION 2007年第1期50卷 10-16页

作者： Ramamurthy, Bina SUNY Buffalo Comp Sci & Engn Dept Buffalo NY 14260 USA

A comprehensive suite of pedagogical resources is presented that will enable an instructor to embed grid computing concepts in a traditional distributed system course. Rapidly advancing Internet technologies and ever expanding application domains have created excitement in teaching distributed systems. Many fundamental concepts developed decades earlier, such as remote procedure calls and multithreading, have come to play key roles in modern distributed systems. Standards such as eXtensible Markup Language (XML) and Simple Object Access Protocol (SOAP) have been developed to enable interoperability among heterogeneous distributed systems. However, a plethora of new paradigms, a wide variety of technological choices, and short cycles of technological obsolescence challenge the introduction of these important concepts into a distributed systems course. this paper describes how the author addressed these challenges in teaching grid computing. the paper also provides details of the resources developed during this process. the pedagogical resource kit developed includes course curriculum, lecture notes, a set of laboratory assignments, a Globus Toolkit-based experimental grid adapted to classroom assignments, and valuable lessons learned from the course offerings during the past two years. the material provided in this paper is expected to help to "jumpstart" educators considering the introduction of grid computing into their curricula.

关键词： computer science education curriculum distributed systems distributed architectures distributed programming distributed/Internet based software engineering tools and techniques grid computing web-based services

来源：评论

学校读者我要写书评

暂无评论

Modeling the effects of contention on the performance of heterogeneous applications

Modeling the effects of contention on the performance of het...

引用

5th IEEE international symposium on High Performance distributed computing

作者： Figueira, SM Berman, F UNIV CALIF SAN DIEGO DEPT COMP ENGN & SCISAN DIEGOCA 92103

ISBN: (纸本)0818675829

Fast networks have made it possible to coordinate distributed heterogeneous CPU, memory, and storage resources to provide a powerful platform for executing high-performance applications. However, the performance of these applications on such systems is highly dependent on the allocation and efficient coordination of application tasks. A key component for a performance-efficient allocation strategy is a predictive model which provides a realistic estimate of application performance under varying resource loads. In this paper, we present a model for predicting the effects of contention on application behavior in heterogeneous systems. In particular, our model calculates the slowdown imposed on communication and computation for non-dedicated two-machine heterogeneous platforms. We describe the model for the Sun/CM2 and Sun/Paragon coupled heterogeneous systems. We present experiments on production systems with emulated contention which show the predicted communication and computation costs to be within 15% on average of actual costs.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

A dynamic load balancing tool for one and two dimensional parallel loops

A dynamic load balancing tool for one and two dimensional pa...

引用

5th international symposium on parallel and distributed computing

作者： Carino, Ricolindo L. Banicescu, Ioana Mississippi State Univ Ctr Computat Sci HPCC POB 9627 Mississippi State MS 39762 USA Mississippi State Univ Dept Comp Sci & Engn Mississippi State MS 39762 USA

ISBN: (纸本)0769526381

this paper describes a dynamic load balancing tool intended for computational investigators who have little familiarity with programming for a message-passing environment. Motivated by the PAR DOALL directive available in. some compilers for shared-memory systems, the tool is designed to simplify the manual conversion of sequential programs containing computationally intensive loops with independent iterates into parallel programs that execute with high efficiency on general-purpose clusters. the tool implemerrts a dynamic loop scheduling strategy to address load imbalance which may be induced by the non-uniformity of loop iterate times, and by the heterogeneity of processors. the tool is based on the Message Passing Interface library for wide availability. Timings of a nontrivial application. that utilize the tool on, a Linux cluster are presented to demonstrate sample achievable performance.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

A novel workload migration scheme for heterogeneous distributed computing

A novel workload migration scheme for heterogeneous distribu...

引用

5th IEEE international symposium on Cluster computing and the Grid (CCGrid 2005)

作者： Li, YW Lan, ZL IIT Dept Comp Sci Chicago IL 60616 USA

ISBN: (纸本)0780390741

Dynamically partitioning of adaptive applications and migration of excess workload from overloaded processors to underloaded processors during execution are critical techniques needed for distributed computing. distributed systems differ from traditional parallel systems in that they consist of heterogeneous resources connected with shared networks, thereby preventing existing schemes from benefiting large-scale applications. In particular, the cost entailed by workload migration is significant when the excess workload is transferred across heterogeneous distributed platforms. this paper introduces a novel distributed data migration scheme for large-scale adaptive applications. the major contributions of the paper include: (1) a novel hierarchical data migration scheme is proposed by considering the heterogeneous and dynamic features of distributed computing environments;and (2) a linear programming algorithm is presented to effectively reduce the overhead entailed in migrating excess workload across heterogeneous distributed platforms. Experiment results show that the proposed migration scheme outperforms common-used schemes with respect to reducing the communication cost and the application execution time.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

A Survey Paper on Task Scheduling Methods in Cluster computing Environment for High Performance 5

A Survey Paper on Task Scheduling Methods in Cluster Computi...

引用

5th international Conference on Advanced computing & Communication Technologies (ACCT)

作者： Singh, Harvinder Singh, Gurdev PTU Kapurthala Kapurthala Punjab India PTU Kapurthala Gurukul Vidyapeeth Inst Engn & Tech Kapurthala Punjab India

ISBN: (纸本)9781479984886

parallel computing perform concurrently execution tasks on distributed nodes. Large application split up into tasks and run on number on nodes for high performance computing. Cluster environment composed with heterogeneous devices and software components capable of cost effective and high performance computing on parallel application. In heterogeneous cluster environment proper scheduling of tasks and allocation to nodes is important for high performance computing. Many task scheduling algorithms proposed for achieving high performance computing on heterogeneous computing. We proposed swarm technique methodology for task scheduling on heterogeneous cluster environment, which can perform better results for minimize makespan, high performance and resource utilization compared to others.

关键词： Heterogeneous cluster parallel computing task scheduling high performance makespan swarm technology

来源：评论

学校读者我要写书评

暂无评论

Simulation-based evaluation of distributed mesh allocation algorithms

Simulation-based evaluation of distributed mesh allocation a...

引用

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

作者： Koszalka, Leszek Wroclaw Univ Technol Fac Elect Chair Syst & Comp Networks PL-50370 Wroclaw Poland

ISBN: (纸本)9783540747666

In recent years, grid and mesh structures have received increasing attention. the mesh based multicomputers are the future of processing. As we slowly reach natural limits of semi-conductor spatial density supercomputer design depends more heavily on parallel and distributed processing. this paper concerns mesh allocation algorithms effectiveness assessment and the experimentation system that was developed to provide testing environment. Most focus was put on creation of such a system that would represent the highest scope of real supercomputers inner working routines and at the same time supply a way to input measured processing data as a base of allocation algorithm load computation. In investigations reported different allocation algorithms, including own WSBA, and various task parameters are considered.

关键词： Grid computing

来源：评论

学校读者我要写书评

暂无评论

Research on Harmony Search BFGS Hybrid parallel Algorithm Based on Cloud computing 18

Research on Harmony Search BFGS Hybrid Parallel Algorithm Ba...

引用

18th international symposium on distributed computing and Applications for Business Engineering and Science (DCABES)

作者： Lu, Jianbo Li, Wenjing Liu, Chunxia Nanning Normal Univ Sch Comp & Informat Engn Nanning 530299 Peoples R China Guangxi Technol Coll Machinery & Elect Dept Comp & Informat Engn Nanning 530001 Peoples R China

ISBN: (纸本)9781728128658

In order to solve the problems of traditional harmony search algorithm such as slow convergence speed and low solution precision, this paper proposes the harmony search BFGS (Broyden-Fletcher-Goldfarb-Shanno) hybrid parallel algorithm based on cloud computing. the generated evolutionary harmony solution vector is used as the initial vector of BFGS algorithm, which then goes through the refining and optimization computing by BFGS algorithm, thus the hybrid parallel algorithm combining the harmony search and BFGS algorithm is constructed, the Map Reduce parallel programming model is used to design the Map and Reduce parallel functions of optimization computing on the cloud platform to construct the hybrid search BFGS hybrid optimization algorithm based on the cloud platform. It performs the programming and comparative experiment on Hadoop platform. the experimental results show that the proposed algorithm outperforms the harmony search algorithm in optimization precision, convergence speed and acceleration ratio, and its parallel computing is close to the linear acceleration ratio.

关键词： Harmony Search BFGS Algorithm brid parallelism cloud computing

来源：评论

学校读者我要写书评

暂无评论

A Verified Accumulate Algorithmic Skeleton 5

A Verified Accumulate Algorithmic Skeleton

引用

5th international symposium on computing and Networking (CANDAR)

作者： Loulergue, Frederic No Arizona Univ Sch Informat Comp & Cyber Syst Flagstaff AZ 86011 USA

ISBN: (纸本)9781538620878

this paper presents an extension of a library for the Coq interactive theorem prover that enables the development of correct functional parallel programs based on sequential program transformation and automatic parallelization using an algorithmic skeleton named accumulate. Such an algorithmic skeleton is a pattern of a parallel algorithm that is provided as a high-order function implemented in parallel. the use of this framework is illustrated with the bracket matching problem, including experiments on a parallel machine.

关键词： Data parallel programming functional programming formal verification interactive theorem proving Coq bulk synchronous parallelism

来源：评论

学校读者我要写书评

暂无评论

Realization of a distributed OS component for internal clock synchronization in a LAN environment 5

Realization of a distributed OS component for internal clock...

引用

5th IEEE international symposium on Object-Oriented Real-Time distributed computing (ISORC 2002)

作者： Kim, KHK Im, C Athreya, P Univ Calif Irvine Irvine CA 92717 USA

ISBN: (纸本)0769515584

A key challenge in keeping distributed clocks well synchronized in a LAN environment via OS- or middleware-level mechanisms is to create an interference-free condition in a network channel(s) and a nonpreemptible on-alert condition in the responsible thread in each node during each resynchronization round while keeping the length of each round as short as possible. An approach for meeting this challenge which is based on the middleware architecture TMOSM, has been presented. A prototype implementation and its measurements indicated that with a typical network of PCs connected via a 10 Mbps Ethernet, the PC nodes can be kept synchronized within the deviation bound of 0.5 milliseconds. the organizing principle is believed to be applicable to many real-time OSs or middleware used to support distributed computing applications.

关键词： real time clock synchronization deviation embedded TMO time triggered message object middleware distributed parallel programming

来源：评论

学校读者我要写书评

暂无评论

Supporting HPDC applications over ATM networks with cell-based transport mechanisms

Supporting HPDC applications over ATM networks with cell-bas...

引用

5th IEEE international symposium on High Performance distributed computing

作者： VilaSallent, J SolePareta, J UNIV POLITECN CATALUNYA DEPT COMP ARCHITECTUREBARCELONACATALONIASPAIN

ISBN: (纸本)0818675829

In this paper, we address the problem of supporting High Performance distributed computing (HPDC) applications running over ATM networks. For this purpose, we consider a logically separate subnetwork for these applications. After presenting an architectural reference model for the HPDC subnetwork and distinguishing which functions should be installed over the ATM network in order to satisfy the needs of HPDC applications, we propose two mechanisms that aim at optimizing communications by taking advantage of both the special properties of HPDC traffic and the cell-based nature of ATM. the performance of these mechanisms is evaluated and compared with that achieved by the SSCOP protocol. the results show that when the ATM network experiences high load and the HPDC applications make an intensive use of arrays, cell-based mechanisms become more robust than standard SSCOP and provide low latency and efficient cell loss recovery. Since both situations are very likely to occur in HPDC environments, we conclude that the introduction of cell-based retransmission mechanisms does contribute to enhance performance of HPDC systems over ATM networks.

关键词： distributed computer 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：