检索结果-内蒙古大学图书馆

Information management for computational Grids

International Journal of Web Services Research 2005年第3期2卷 69-82页

作者： Jie, Wei Zang, Tianyi Hung, Terence Turner, Stephen J. Cai, Wentong Institute of High Performance Computing Singapore Singapore Nanyang Technological University Singapore Singapore Singapore Singapore Software and Computing Program Institute of High Performance Computing Singapore Singapore School of Computer Engineering Parallel and Distributed Computing Centre Singapore Singapore

Information Service is a key component of a Grid environment and crucial to the operation of a computational Grid. This paper presents an Information Service for a computational Grid Virtual Organization (VO). The main functionality of this Information Service is the provision of information essential for applications running on a computational Grid. This Information Service is a hierarchical structure that consists of VO layer, site layer, and resource layer. We propose different models of information data organization for Information Service, and experiments were conducted to evaluate the performance of these models. Based on the experimental results, we further introduce the data organization model for our Information Service. The implementation of the Information Service is based on the Globus Toolkit and complies with the OGSI (Open Grid Services Infrastructure) specifications. In this paper, some application experiences of using the Information Service are also presented. Copyright © 2005, Idea Group Inc.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Compute Power of Two HPC systems for higher-Dimensional Grid-Based Simulations with the Widely-distributed Sparse Grid Combination Technique 23

Leveraging the Compute Power of Two HPC Systems for Higher-D...

引用

2023 International Conference for high performance Computing, Networking, Storage and Analysis, SC 2023

作者： Pollinger, Theresa Van Craen, Alexander Niethammer, Christoph Breyer, Marcel Pflüger, Dirk Institute for Parallel and Distributed Systems Universität Stuttgart Stuttgart Germany High Performance Computing Center Universität Stuttgart Stuttgart Germany

ISBN: (纸本)9798400701092

Grid-based simulations of hot fusion plasmas are often severely limited by computational and memory resources;the grids live in four- to six-dimensional space and thus suffer the curse of dimensionality. However, high resolutions are required to fully capture the physics of interest. The sparse grid combination technique is a multi-scale method in which many anisotropically coarse resolved grids are used to approximate a fine-scale solution - -and it alleviates the curse of *** paper presents the core concepts of the widely-distributed combination technique, which allows us to use the compute power and memory of more than one HPC system for the same simulation. We apply the sparse grid combination technique to a six-dimensional advection problem serving as a proxy for plasma simulations. The full-grid solution approximated by the combination technique would contain ≈ 5 ZB if computed with conventional grid-based methods. Even the combination technique simulation operates on ≈ 1 × 1011 double-precision degrees of freedom, or 988 GB, plus the supporting sparse grid data structures. We propose a new approach to divide the compute load between the two HPC systems, requiring only 76 GB to be exchanged. Based on this, we have realized the first synchronous combination technique simulation using two HPC systems, in our case the two German Tier-0 supercomputers HAWK and SuperMUC-NG. On two systems, the simulation can be computed at an average overhead of ≈ 35 % (108 s per combination step) for file I/O and transfer. The presented concepts apply to any pair of HPC systems if high-speed data transfer is possible. © 2023 ACM.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Configuring distributed multimedia applications using CINEMA

Configuring distributed multimedia applications using CINEMA

引用

1996 International Workshop on Multimedia Software Development, MMSD 1996

作者： Barth, I. Institute of Parallel and Distributed High-Performance System Stuttgart University Breitwiesenstrafie 20-22 StuttgartD-70565 Germany

ISBN: (纸本)081867511X

We describe the configuration of distributed multimedia applications using the CINEMA system. Components, interconnected by links via ports are used to handle multimedia data. Configuration management controls these interconnections, establishes components in threads on different systems and allows an interactive control of data handling functions. We present an object-oriented interface, that is able to handle different types of components. To demonstrate the flexibility of this approach we explain a generic application of the CINEMA system to do an interactive configuration of applications using a graphical interface. © 1996 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Protocols for Updating Location Information

引用

Cluster Computing 2001年第4期4卷 355-367页

作者： Leonhardi, Alexander Rothermel, Kurt Institute of Parallel and Distributed High-Performance Systems (IPVR) University of Stuttgart Stuttgart Germany

Detailed location information of mobile objects, for example that of a user with a mobile computer or phone, is an important input for many location-aware applications. However, constantly updating the location information for thousands of mobile objects is not feasible. Therefore, special update protocols for location information are required that transmit the information as efficiently as possible, that is requiring only few update messages, while still being effective in returning the location information with the desired accuracy. Different classes of such update protocols are described in this paper and a new combined protocol is proposed. To be able to compare their effectiveness and efficiency, we present an analysis for the minimum and average resulting accuracy of the location information in comparison with the number of messages transmitted. We also present the results of simulations that we have performed to back up our analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal scheduling of iterative data-flow programs onto multiprocessors with non-negligible interprocessor communication 7th

Optimal scheduling of iterative data-flow programs onto mult...

引用

7th International Conference on high-performance Computing and Networking, HPCN Europe 1999

作者： Antony Louis Piriyakumar, D. Levi, Paul Siva Ram Murthy, C. Institute of Parallel and Distributed High-Performance Systems University of Stuttgart Stuttgart70565 Germany Department of Computer Science and Engineering Indian Institute of Technology Chennai600 036 India

ISBN: (纸本)3540658211

The problem of optimal compile-time multiprocessor scheduling of iterative data-flow programs with feedback (delay elements) is addressed in this paper, unlike the earlier studies assumed the availability of a large number of processors and complete interconnection among them along with the interprocessor communication (IPC) to be non-negligible to be more realistic. We first explain the effects of including IPC in non-overlapped, overlapped, fully-static, and cyclo-static multiprocessor schedules with LMS filter as a realistic example. The effect of IPC in the rate-optimal schedules with the transformation techniques viz. unfolding and retiming in scheduling data-flow programs with optimal unfolding is discussed with an example. We then propose an algorithm, based on the well-known A* algorithm, for optimal scheduling of data-flow programs onto multiprocessors, which uses only minimum number of processors. To alleviate the impediments of large requirements of memory space and CPU time for the optimal scheduling algorithm, we present an effective technique, branch join path isomorphism (BJP) which relies on our previously defined processor isomorphism, task isomorphism, and node isomorphism apart from the lower bound theory and upper bound on the completion time. The schedules produced by our algorithm are superior to those obtained by the earlier algorithms despite considering IPC as non-negligible and also not completely connected multiprocessor systems. © Springer-Verlag Berlin Heidelberg 1999.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

A parallel processing technique for electrical tree growth in solid insulating materials using cellular automata

A parallel processing technique for electrical tree growth i...

引用

International Conference on parallel Computing in Electrical Engineering, PARELEC 2000

作者： Piriyakumar, A.L. Levi, P. Jayaganthan, R. Sarathi, R. Institute of Parallel and Distributed High-Performance Systems University of Stuttgart Germany Max-Planck Institute for Metals Research Stuttgart Germany Department of Electrical Engineering Indian Institute of Technology Chennai India

ISBN: (纸本)076950759X

One of the major problems in an electrical insulation structure is its failure while operating at normal voltage stress which is due to electrical treeing. It is well-known that this electrical tree grows progressively and is damaging locally. To analyze the electrical treeing in the laboratory, not being cost effective, computer simulations are used. We have employed a known cellular automata method with new parallel processing techniques to reduce the computation time considering the available parallel processing systems. The major advantage is that the cellular automata algorithm inherently exhibits parallelism paving the way for ample exploitation. Moreover the parallelisation has helped to understand various aspects of electrical treeing also in a simple way. © 2000 IEEE.

关键词： Insulation

来源：评论

学校读者我要写书评

暂无评论

Exploiting inter task dependencies for dynamic load balancing

Exploiting inter task dependencies for dynamic load balancin...

引用

International Symposium on high performance distributed Computing

作者： W. Becker G. Waldmann Institute for Parallel and Distributed High Performance Systems Stuttgart Germany

The major goal of dynamic load balancing is not primarily to equalize the load on the nodes of a parallel computing system, but to optimize the average response time of single requests or the throughput of all applications in the system. Therefore it is often necessary not only to keep all processors busy and all processor ready queue lengths within the same range, but to avoid delays and inefficient computations caused by foreseeable but ignored data flow and precedence constraints between related tasks. We present concepts for dynamic consideration of inter task dependencies within small groups of tasks and evaluate them observing real applications in a load balancing environment on a network of workstations. The concepts are developed from scheduling of single task graphs towards heterogeneous multi user operation scenarios.< >

关键词： Load management Processor scheduling parallel processing Delay Throughput Data communication Dynamic scheduling Concurrent computing distributed computing high performance computing

来源：评论

学校读者我要写书评

暂无评论

Mole – Concepts of a mobile agent system

引用

World Wide Web 1998年第3期1卷 123-137页

作者： Baumann, J. Hohl, F. Rothermel, K. Straßer, M. IPVR (Institute of Parallel and Distributed High-Performance Systems) University of Stuttgart Breitwiesenstraße Stuttgart Germany

Due to its salient properties, mobile agent technology has received a rapidly growing attention over the last few years. Many developments of mobile agent systems are under way in both academic and industrial environments. In addition, there are already various efforts to standardize mobile agent facilities and architectures. Mole is the first mobile agent system that has been developed in the Java language. The first version was finished in 1995, and since then Mole has been constantly improved. Mole provides a stable environment for the development and usage of mobile agents in the area of distributed applications. In this paper we describe the basic concepts of a mobile agent system, i.e., mobility, communication and security, discuss different implementation techniques, present the decisions made in Mole and give an overview of the system services implemented in Mole.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An open commit protocol preserving consistency in the presence of commission failures

An open commit protocol preserving consistency in the presen...

引用

International Conference on distributed Computing systems

作者： K. Rothermel Institute of Parallel and Distributed High Performance Systems University of Stuttgart Germany

Most of the proposed commit protocols assume that all participants of a transaction are sane, i.e., they only fail with omission failures and eventually recover. Unfortunately, this assumption is not realistic for open distributed systems (ODSs), which can be divided into a trusted and a nontrusted domain. While nodes in the trusted domain are assumed to be sane, nontrusted nodes may fail permanently and with commission failures. The open commit protocols presented are based on a model for consistency checking. The protocol also tolerates any number of commission failures in the nontrusted domain of an ODS. It guarantees that the trusted participants of a transaction terminate in a way that preserves consistency in the trusted domain, which generally does not mean that all trusted participants have to terminate consistently. The protocol groups those trusted participants that have to terminate consistently to maintain data consistency, and ensures that in each group the participants terminate in the same way. The advantages of the protocol are a simplified commit processing and a reduced message complexity. The message complexity of this protocol exceeds that of traditional two-phase commit protocols by no more than two messages for most practical cases.< >

关键词： Protocols Banking Terminology Computer crashes Standardization Communication networks Home computing Waste materials

来源：评论

学校读者我要写书评

暂无评论

QoS negotiation and resource reservation for distributed multimedia applications

QoS negotiation and resource reservation for distributed mul...

引用

IEEE International Conference on Multimedia Computing and systems (ICMCS)

作者： K. Rothermel G. Dermler W. Fiederer Institute of Parallel and Distributed High-Performance Systems University of Stuttgart Stuttgart Germany

distributed multimedia applications require negotiation of quality of service (QoS) and resource reservation for application components and communication links. QoS negotiation is a balancing process between the QoS specified by a client, the resource capabilities of the distributed system and the functional capabilities of the distributed application. It requires application level QoS descriptions and an end-to-end view spanning the distributed application. XNRP, introduced in the paper, is a protocol meeting these requirements. XNRP performs negotiation based on client specified QoS value ranges and is independent of application level QoS semantics. It allows QoS negotiation and resource reservation in three phases and supports arbitrarily interconnected flowgraphs of application components. performance analysis of the XNRP implementation shows its applicability to complex settings.

关键词： Quality of service Streaming media Multimedia systems Transport protocols Filters Flow graphs Topology performance analysis Real time systems Delay

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：