检索结果-内蒙古大学图书馆

International conference on parallel and distributed Systems (ICPADS)

作者： N. Kalantery University of Westminster London UK

Previous proposals for the application of discrete event methods to parallelization of sequential software have been based on the optimistic execution strategy. We present a new method which avoids optimistic execution. This is motivated by the observation that the control structure of a sequential program constitutes a temporal coordinate system which is exogenous to the program execution. The method employs a logical time mechanism and provides adaptive synchronisation for the distributed execution. Hence data dependent and/or conditional parallelism is released without the risk of coherency violation. The paper begins with a brief introduction to the parallel discrete event simulation paradigm. The efficient coarse grain mapping of conventional programs onto this paradigm is then discussed.

关键词： Concurrent computing Discrete event simulation Synchronization Clocks Communication channels Timing Partial response channels Application software Optimization methods Runtime

来源：评论

学校读者我要写书评

暂无评论

Effects of dynamic task distributions on the performance of a class of irregular computations

Effects of dynamic task distributions on the performance of ...

引用

International conference on parallel Processing (ICPP)

作者： H.V. Shah J.A.B. Fortes School of ECE Purdue University West Lafayette IN USA

In this paper, a modified version of previously proposed quasi-barrier technique is developed. On distributed memory machines, relaxation with modified quasi-barriers can be used to perform basis computations that arise in symbolic polynomial manipulation. In this type of synchronous computation, the set of tasks is distributed across the processors. Each nonzero result of a task reduction dynamically generates a set of new tasks. The distribution of these newly generated tasks can have a significant impact on the overall execution time of the parallel computation. In this paper, four task distribution strategies, named modified block, modified sorted block, modified cyclic, and modified sorted cyclic are developed and their performances are comparatively evaluated. For the experiments performed on an 18-node IBM SP2, the modified cyclic distribution provides the best performance overall.

关键词： distributed computing Polynomials Concurrent computing Distribution strategy Performance evaluation Equations

来源：评论

学校读者我要写书评

暂无评论

A new interconnection network for parallel computer with low diameter

A new interconnection network for parallel computer with low...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Nak-Keun Joo Hyeong-Seok Lim Department of Computer Science Dong-shin University Choongnam South Korea Department of Computer Science Chonnam National University Kwangju South Korea

ISBN: (纸本)0818682272

In this paper, we propose and analyze the new interconnection network for parallel computer, called graycube. The graycube has the same number of nodes and edges as hypercube, but it's diameter is about one half of the equivalent hypercube. It has simple recursive structure, routing and broadcasting algorithms. Since hypercube can be embedded into graycube with dialation 2, algorithms developed based on hypercube are easily simulated in graycube. The basic properties, routing and broadcasting algorithms, and hypercube embedding are presented.

关键词： Multiprocessor interconnection networks Computer networks Concurrent computing Hypercubes Reflective binary codes Network topology Routing Broadcasting Computer science Joining processes

来源：评论

学校读者我要写书评

暂无评论

CrownFS: a clustered continuous media server

CrownFS: a clustered continuous media server

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Young-Sung Son Yu-Seok Bae Oh-Young Kwon Tae-Geun Kim Chang-Soon Park Network Computing Department Systems Engineering Research Institute Taejon South Korea

ISBN: (纸本)0818682272

CrownFS is a file system for continuous media server in the CROWN (Clustering Resources On Workstations' Network) system. Because of the high I/O bandwidth rate and strict real-time constraints, the design issues of CrownFS are that of efficiently balancing user load against limited disk: bandwidth, network and I/O channel bandwidth. CrownFS accomplishes this balancing by striping continuous data file across several workstations and computing at each workstation in the CROWN system. This paper describes the CROWN system architecture and the CrownFS design. CrownFS runs on a cluster of workstations consisted of Kawaiis, AlphaStations and PCs.

关键词： Network servers Workstations Bandwidth Personal communication networks Costs Streaming media File systems Systems engineering and theory File servers Hardware

来源：评论

学校读者我要写书评

暂无评论

Are 2*-trees interesting topologies for the interconnection of a network?

Are 2*-trees interesting topologies for the interconnection ...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： M. Kant Faculte des Sciences Universite de Moncton NB Canada

In this paper, we explore in detail some properties of 2*-trees. A 2*-tree is a connected graph with N nodes, diameter log/sub 2/N, and degree of nodes 10. We propose routing algorithms for the unicasting, the broadcasting and the gossiping on a 2*-tree network. The routing algorithms we present have their time and communication complexities lower than the corresponding complexities for the routing on H/sub n/, i.e., the hypercube of dimension n=log/sub 2/N. Consequently, we think that a 2*-tree is an interesting topology to be considered for a network of processors.

关键词： Network topology Routing Hypercubes Broadcasting Tree graphs Complexity theory Delay Disruption tolerant networking distributed computing distributed databases

来源：评论

学校读者我要写书评

暂无评论

Integrating heterogeneous databases: a distributed model

Integrating heterogeneous databases: a distributed model

引用

IEEE International conference on Algorithms and Architectures for parallel Processing (ICAP)

作者： P.A. Hepner W. Zhou School of Computing and Mathematics Deakin University Geelong VIC Australia

We put forward a distributed model for accessing heterogeneous database systems. Database operations requested by the user are processed in a distributed manner that takes advantage of the inherent parallelism of distributed systems, minimises network traffic and uses almost any general purpose computer on the network. Processing is not confined to DBMS sites but is provided as a distributed service. The design is modular and provides the mechanisms that may be arranged in a variety of ways providing a range of integration paradigms from loosely coupled integrations to more tightly coupled integrations.

关键词： distributed databases Relational databases Database systems distributed computing Tree graphs Mathematical model Computer networks Protocols Mathematics Australia

来源：评论

学校读者我要写书评

暂无评论

Synchronous load balancing in hypercube multicomputers with faulty nodes

Synchronous load balancing in hypercube multicomputers with ...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Jaewon Seo Sunggu Lee Jong Kim Department of Electrical Engineering Information Research Laboratories PIRL Pohang University of Science and Technology Pohang South Korea IBM Thomas J. Watson Research Center Yorktown Heights NY USA Department of Computer Science & Engineering Information Research Laboratories PIRL Pohang University of Science and Technology Pohang South Korea

ISBN: (纸本)0818682272

This paper presents a new dynamic load balancing algorithm for hypercube multicomputers with faulty nodes. The emphasis in our method is on obtaining global load information and performing task migration using "short paths" in a synchronous manner so that a minimal amount of communication overhead is required. To accomplish this, we present an algorithm for constructing a new logical topology from a hypercube topology with faulty nodes. This new topology is used to obtain the global load information and to perform task migration. Simulation results are used to evaluate the performance of our dynamic load balancing method. The proposed strategy shows good performance in the case of a small number of faulty nodes when compared with previous methods.

关键词： Load management Hypercubes Topology Concurrent computing distributed computing Application software Heuristic algorithms parallel processing Computer networks Multiprocessor interconnection networks

来源：评论

学校读者我要写书评

暂无评论

New architectures and I/O scheduling methods for scalable storage products

New architectures and I/O scheduling methods for scalable st...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： D. Raskovic V. Milutinovic Department of Computer Engineering School of Electrical Engineering University of Belgrade Serbia

The paper presents solutions for an element of the cluster that will be primarily used as a scalable storage product for a collection of mainframes. Existing storage solutions either employ server attached disks: where the problem is the number of I/O slots, or are specially designed products where the problem is the lack of standards. The essence of both proposed solutions is the introduction of the file usage locality concept, together with methods and techniques to exploit it. The first solution is based on the standard SMP architecture, while the second one employs the DSM architecture as the basic building block of a cluster product.

关键词： Bandwidth parallel processing Computer architecture Processor scheduling Uniform resource locators Concurrent computing Modems Fault tolerant systems Throughput

来源：评论

学校读者我要写书评

暂无评论

Efficient algorithm for the nearest smallers problem on distributed shared memory systems with applications

Proceedings of the Conference on High Performance Computing ...

引用

proceedings of the conference on High Performance computing on the Information Superhighway, HPC Asia'97 1997年 367-372页

作者： Graf, T. Kamakoti, V. Balakrishnan, N. Research Cent Juelich Juelich Germany

We present a simple and efficient algorithm for the nearest smallers problem (NSP) on a distributed shared memory (DSM) system with applications to problems from diverse areas. We adopt the block distributed memory (BDM) model of computation as described in [2]. To the best of our knowledge this is the first known algorithm for the NSP on DSM systems. Since the NSP is fundamental in many problems, a solution for it on DSM systems implies DSM-based solutions for a variety of problems in diverse areas as discussed in this paper. parallel algorithms known so far for the NSP are based on shared memory systems and are therefore less scalable than our algorithm.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Transaction-based causally ordered protocol for distributed replicated objects

Transaction-based causally ordered protocol for distributed ...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： T. Enokido T. Tachikawa M. Takizawa Department of Computers and Systems Engineering Tokyo Denki University Japan

In group communications, larger computation and communication overhead are considered to causally order all the messages transmitted in the network. Transactions in clients manipulate objects in servers by sending read and write requests to the servers. In this paper, we define significant messages by using the relation among the transactions. We newly propose an object vector to causally order only the significant messages. The scheme of the object vector is invariant in the change of the group membership. We also show a TBCO (transaction-based causally ordered) protocol which adopts the object vector, by which the number of messages to be causally ordered are reduced.

关键词： Protocols Computer networks distributed computing Network servers Clocks Systems engineering and theory Communication networks Telecommunication network reliability 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：