检索结果-内蒙古大学图书馆

A parallel finite element program on a Beowulf cluster

ADVANCES IN ENGINEERING SOFTWARE 2002年第7-10期33卷 427-443页

作者： Sonzogni, VE Yommi, AM Nigro, NM Storti, MA Univ Nacl Litoral CONICET INTEC Int Ctr Comp Methods EngnCIMEC RA-3000 Santa Fe Argentina

Some experiences on writing a parallel finite element code on a Beowulf cluster are shown. this cluster is made up of seven Pentium III processors connected by Fast Ethernet. the code was written in C++ making use of MPI as message passing library and parallel extensible toolkit for scientific computations. the code presented here is a general framework where specific applications may be written. In particular CFD applications regarding Laplace equations, Navier-Stokes and shallow water flows have been implemented. the parallel performance of this application code is assessed and several numerical results are presented. (C) 2002 Civil-Comp Ltd and Elsevier Science Ltd. All rights reserved.

关键词： Beowulf clusters parallel computing finite element method computational fluid dynamics distributed computations computational mechanics

来源：评论

学校读者我要写书评

暂无评论

Scheduling in a grid computing environment using genetic algorithms 16

Scheduling in a grid computing environment using genetic alg...

引用

16th international parallel and distributed Processing symposium, IPDPS 2002

作者： Di Martino, V. Mililotti, M. CASPUR c/o Univ. of Rome P.le Aldo Mora 5 Rome00185 Italy

ISBN: (纸本)0769515738

We investigate the possibility to use the computing GRID in a flexible way to permit the maximum usage of resources. In our simulation the jobs submitted by the users provide a characterization of themself to help the system scheduler to do an optimal scheduling in case of resources contention. We use a genetic algorithms to select an optimal or suboptimal scheduling of the jobs. In this preliminary tests we show how the solution founded may maximize the total machine throughput considering not only the single job request but all the job requests during the scheduling process. In this work we show that it is possible to resolve conflicts in the usage of the total computing power and in the data locality for a reasonable number of jobs. © 2002 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A modular and extensible simulator for performance evaluation of adaptive applications in heterogeneous computing environments 5

A modular and extensible simulator for performance evaluatio...

引用

5th international Conference on Algorithms and Architectures for parallel Processing, ICA3PP 2002

作者： Hong, Bo Prasanna, V.K. Department of Electrical Engineering - Systems University of Southern California Los AngelesCA90089-2562 United States

ISBN: (纸本)0769515126

We propose a modular and extensible simulator that can be used to evaluate the performance of applications in a dynamic heterogeneous environment. Our simulator has built-in support for evaluating the performance of adaptive applications in dynamic heterogeneous environments. the simulator provides the user with flexibility in configuring the applications and resources and evaluating various adaptation algorithms. We illustrate the features of the simulator by simulating algorithms for distributed matrix multiplication and LU decomposition in various computing environments. © 2002 IEEE.

关键词： Simulators

来源：评论

学校读者我要写书评

暂无评论

Using group communication to support mobile augmented reality applications 5

Using group communication to support mobile augmented realit...

引用

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

作者： Reijers, N Cunningham, R Meier, R Hughes, B Gaertner, G Cahill, V Univ Dublin Trinity Coll Distributed Syst Grp Dublin 2 Ireland

ISBN: (纸本)0769515584

Augmented reality and group communication in wireless ad-hoc networks form relatively, new fields of research. When using group communication ordering and timeliness requirements are important. Moreover, when using wireless ad-hoc networks, the possibility of network partition is a serious consideration. In this paper we explore these three issues in the context of using group communication to support mobile augmented reality applications. We describe a policy that enables us to handle partitions and failures, while allowing the members in a partition to make progress, although limited by the application's consistency requirements. We introduce an approach to determining the message ordering requirements needed to maintain a desired level of consistency and timeliness requirements that should be met in order to have the application state correspond to the sequence of events perceived in the real world.

关键词： Ad hoc networks Augmented reality Context Educational institutions Global Positioning System Laser beams Mobile communication Sensor systems Wearable sensors Wire

来源：评论

学校读者我要写书评

暂无评论

Aspect-oriented programming with C# and .NET 5

Aspect-oriented programming with C# and .NET

引用

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

作者： Schult, W Polze, A Univ Potsdam Hasso Plattner Inst Potsdam Germany

ISBN: (纸本)0769515584

Almost a year ago, Microsoft has introduced the .NET architecture as a new component-based programming environment, which allows for easy integration of classical distributed programming techniques with Web computing. NET defines a type system and introduces notions such as component, object, and interface, which are building blocks for distributed multi-language component-based applications. As many other component frameworks, NET mainly focuses on functional interfaces of components. Nonfunctional aspects of components, such as resource usage (CPU, memory), timing behavior, fault-tolerance, or security requirements are currently not expressed in NET's component interfaces. Within this paper, we discuss the usage of aspect-oriented programming techniques in context of the NET framework. We focus on the fault-tolerance aspect and discuss the expression of non-functional component properties (aspects) as C# custom attributes. Our approach uses reflection to generate replicated objects based on settings of a special "fault-tolerance" attribute for C# components(perpendicular to). We have implemented an aspect-weaver for integration of aspect-code and component-code, which uses the mechanisms of the language-neutral NET type system. therefore, our approach is not restricted to the C# language but works for an), of the NET programming languages.

关键词： Computer architecture Computer languages distributed computing Fault tolerance Object oriented modeling Programming environments Reflection Security Service oriented architecture Timing

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 5th international Conference on Algorithms and Architectures for parallel Processing, ICA3PP 2002

Proceedings - 5th International Conference on Algorithms and...

引用

5th international Conference on Algorithms and Architectures for parallel Processing, ICA3PP 2002

ISBN: (纸本)0769515126

the proceedings contain 78 papers. the topics discussed include: efficient weighted multiselection in parallel architectures;local block factorization and its parallelization to block tridiagonal matrices;parity declustering data layout for tolerating dependent disk failures in network raid systems;an analysis of update ordering in a cluster of replicated servers;performance of dynamic load balancing algorithm on cluster of workstations and PCs;universal parallel numerical computing for 3d convection-diffusion equation with variable coefficients;efficient loop partitioning for parallel codes of irregular scientific computations;an evolutionary algorithm of contracting search space based on partial ordering relation for constrained optimization problems;a new divide and conquer algorithm for real symmetric band generalized eigenvalue problem;a framework of using cooperating mobile agents to achieve load sharing in distributed web server groups;and design and analysis of finite difference domain decomposition algorithms for the two-dimensional heat equation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IKE 2 - Implementing the stateful distributed object paradigm 5

IKE 2 - Implementing the stateful distributed object paradig...

引用

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

作者： Noseworthy, JR Object Sciences Corporation United States

ISBN: (纸本)0769515584

this paper describes IKE 2, which is distributed object computing middleware that supports the creation of interoperable real-time distributed applications. these applications appear in many domains, such as telecom, aerospace, military testing and training ranges, and financial services. IKE 2 combines the concepts of CORBA distributed objects and anonymous publish-subscribe data dissemination to provide a programming abstraction known as a stateful distributed object (SDO). Every SDO can have both a remote method interface and publication state. the remote method interface allows client applications to invoke methods on target objects efficiently without concern for their location, programming language, OS platform, communication protocols and interconnects, or hardware. the publication state of a given SDO is disseminated to applications that have expressed their interest by subscribing to certain characteristics, such as the type of the SDO. Subscribers can read the publication state of an SDO as if it were a local object. the SDOs provided by the IKE 2 metaobject model support inheritance from other SDOs, containment of other SDOs, and references to other SDOs. IKE 2 is implemented in C++. the API relies heavily on compile-time type-safety to help ensure reliable behavior at run-time-a critical feature of any real-time system. Automatic code generation is used to provide the high-level abstractions without unduly burdening application programmers.

关键词： distributed object middleware distributed object middleware publish-subscribe middleware SDO stateful distributed object CORBA event service

来源：评论

学校读者我要写书评

暂无评论

On mapping RT-UML specifications to RT-Java API:: Bridging the gap 5

On mapping RT-UML specifications to RT-Java API:: Bridging t...

引用

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

作者： Becker, LB Höltz, RH Pereira, CE Univ Fed Rio Grande Sul Inst Comp Sci BR-90046900 Porto Alegre RS Brazil

ISBN: (纸本)0769515584

Two recent standards have a great potential to impulse the use of object orientation in the development of real-time applications. the first is the Real-Time Specification for Java, consisting in an Application Programming Interface (API) for real-time object-oriented programming. the other is the emerging RT-UML standard, which addresses the specification of real-time requirements and time using extended UML diagrams. this work-proposes an approach for bridging the gap between the two emerging standards, aiming to provide a clear link between the modeled real-time constraints and the programming entities that provide their implementation. the main idea is to enhance the traceability as well as readability of timing constraints from a model-based requirements model to implementation. Relationships between the stereotypes and tags used to decorate the UML diagrams and their code representation are explained. An assessment of the benefits achieved using both standards as well are as some proposed enhancements are also discussed.

关键词： Application software Computer science distributed computing Java Object oriented modeling Object oriented programming Productivity Standards development Timing Unified modeling language

来源：评论

学校读者我要写书评

暂无评论

Enhancing real-time event service for synchronization in object oriented distributed systems 5

Enhancing real-time event service for synchronization in obj...

引用

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

作者： Singh, G Maddula, B Zeng, Q Kansas State Univ Manhattan KS 66506 USA

ISBN: (纸本)0769515584

distributed object computing a middleware such as CORBA, RMI, and DCOM have gained wide acceptance and has shielded programmers from many tedious and error-prone aspects of distributed programming. In particular, CORBA Event Service has been used extensively in embedded systems. In this paper, we propose an aspect oriented approach to develop synchronization code for distributed systems that use event service as the underlying communication middleware. Our approach is to factor out synchronization as a separate aspect, synthesize synchronization code and then compose it with the functional code. We use high-level "global invariants" to specify the synchronization policies which are then automatically translated into synchronization code for the underlying event service. To implement synchronization efficiently using, the event service, we propose enhancements to the semantics of the event service. Specifically, we define the notion of condition events and exactly, k semantics. Given these enhancements, we describe a synthesis procedure to translate global invariants into synchronization code based on events. We describe the implementation of the enhancements on the Tao's Real-Time Event Service. We present experimental results to demonstrate that the enhanced event service leads to more efficient implementation of synchronization. We feel that our methodology and the enhanced Real-Time Event Service will lead to more confident use of sophisticated synchronization policies in distributed object oriented systems.

关键词： distributed computing Embedded software Embedded system Middleware Object oriented programming Programming profession Real time systems Unified modeling language Vehicle safety Yarn

来源：评论

学校读者我要写书评

暂无评论

A framework of using cooperating mobile agents to achieve load sharing in distributed Web server groups 5

A framework of using cooperating mobile agents to achieve lo...

引用

5th international Conference on Algorithms and Architectures for parallel Processing, ICA3PP 2002

作者： Cao, Jiannong Wang, Xianbing Das, S.K. Internet Computing and E-Commerce Lab. Dept. of Computing Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Computer Center School of Computer Wuhan University WuhanHubei China Center for Research in Wireless Mobility and Networking Dept. of Computer Science and Engineering University of Texas at Arlington ArlingtonTX76019 United States

ISBN: (纸本)0769515126

this paper studies the issues of using mobile agents to achieve load sharing for network services in a wide-area network environment such as the Internet. Traditionally, load sharing algorithms are based on the message-passing paradigm. In this paper, we propose the use of mobile agents as an aid to design fully distributed and dynamic load-sharing mechanisms for wide-area network services, which provide several advantages over the pure message passing-based approach. A framework (called MALS-mobile agent-enabled load sharing) for structuring and designing load sharing in wide-area network services is presented. In particular, we describe the design of a mobile agent-enabled distributed dynamic load sharing scheme within the MALS framework. A simulation environment of the load sharing protocol is being implemented using Aglet™, a Java-compliant mobile agent platform from IBM. Preliminary experimental results demonstrated that the proposed framework is effective. © 2002 IEEE.

关键词： Mobile agents

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：