检索结果-内蒙古大学图书馆

Performance implications of task routing and task scheduling strategies for multiprocessor systems 1

Performance implications of task routing and task scheduling...

1st international conference on Massively Parallel computing Systems: The Challenges of General-Purpose and Special-Purpose computing, MPCS 1994

作者： Dandamudi, S. School of Computer Science Carleton University OttawaONK1S 5B6 Canada

ISBN: (纸本)0818663227

In distributed task ready queue organizations, task routing refers to how ready tasks are assigned to processors in the system and task scheduling refers to how these tasks are scheduled on the assigned processor. In this paper, we consider the interaction between task routing and task scheduling strategies and their impact on the performance of the distributed task queue organization. We consider four task routing strategies two adaptive and two non-adaptive-and five task scheduling policies-two preemptive and three run-to-completion policies. We show that, when adaptive task routing is employed, the scheduling policy has only a marginal impact on performance and preemptive round robin policies tend to perform worse than the FCFS policy. © 1994 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Massively parallel computing systems with real time constraints: The "algorithm Architecture Adequation" methodology 1

Massively parallel computing systems with real time constrai...

引用

1st international conference on Massively Parallel computing Systems: The Challenges of General-Purpose and Special-Purpose computing, MPCS 1994

作者： Sorel, Y. INRIA Domaine de Voluceau Rocquencourt B.P.105 Le Chesnay Cedex78153 France

ISBN: (纸本)0818663227

Massively Parallel computing Systems (MPCS) provide high performance computing generally used to accelerate numerical computation applications. We present a methodology called "Algorithm Architecture Adequation" used to take advantage of the computation power of these systems in the case of real-time applications. With this methodology, the application algorithm as well as the MPCS are specified with graphs, then the implementation of an algorithm on a MPCS in respect with real-time constraints may be formalized in terms of graph transformations. This allows one to optimize the real-time performances of the implementation taking into account critical inter-processor communications. As a result, real-time distributed executives are produced automatically without dead-lock and with minimum overhead. This reduces drastically the development cycle for real-time applications running on MPCS. © 1994 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Communication in distributed computing environments 1

Communication in distributed computing environments

引用

1st international conference on Massively Parallel computing Systems: The Challenges of General-Purpose and Special-Purpose computing, MPCS 1994

作者： Sjöström, A.M. Department of Mechanical Engineering Colorado State University Fort CollinsCO United States

ISBN: (纸本)0818663227

computing is often viewed as a tool and a computing system is typically treated as a toolbox of applications for performing operations such as calculations and data storage and transfer. Currently, humans develop these application tools and apply, or specify how to apply, them. Recognizing that computing is a fundamental discipline challenges us to accept the notion that a computing system could play other roles than merely serving as a toolbox. An active player will require massive parallelism and mechanisms for abstracting over interactions. © 1994 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Design of the matching unit of a massively parallel dataflow computing system 1

Design of the matching unit of a massively parallel dataflow...

引用

1st international conference on Massively Parallel computing Systems: The Challenges of General-Purpose and Special-Purpose computing, MPCS 1994

作者： Marques, E. Kirner, C. Universidade de São Paulo - USP São Carlos - SP13560-970 Brazil Univ. Federal de São Carlos - UFSCar São Carlos - SP13565-905 Brazil

ISBN: (纸本)0818663227

This paper describes a Massively Parallel computing System, named Recursively structured Parallel Computer-RSPC, designed to work as a dataflow distributed computer, and presents the design of the matching store of each node. That machine, structured as a multicomputer based on hierarchical buses, can have thousands of nodes. Each node, acting as a dataflow processor, can execute a part of a dataflow program, cooperating to solve the overall problem. Several strategies for the matching store implementation are discussed and the analysis of the techniques for highly efficient memory search is presented. © 1994 IEEE.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Conservative and optimistic distributed simulation in massively parallel computers: A comparative study 1

Conservative and optimistic distributed simulation in massiv...

引用

1st international conference on Massively Parallel computing Systems: The Challenges of General-Purpose and Special-Purpose computing, MPCS 1994

作者： Alonso, J.M. Frutos, A.A. Palacio, R.B. Dep. Arquitectura y Tecnología de Computadores UPV/EHU Apdo. 649 San-Sebastián Spain Dep. Electrónica Univ. de Cantabria AV. de los Castros s/n Santander39005 Spain

ISBN: (纸本)0818663227

The main algorithms for sequential and parallel discrete event simulations are introduced. A set of different simulators is evaluated and compared using a transputer-based multicomputer: sequential, parallel conservative and parallel optimistic. For the proposed model, the conservative simulator shows better speedups. The obtained results show that a significant improvement on execution time can be obtained using parallel systems, but only if the model under simulation have some properties like coarse grain size and high degree of self-synchronisation. © 1994 IEEE.

关键词： Transputers

来源：评论

学校读者我要写书评

暂无评论

1st international Workshop on Parallel Scientific computing, PARA 1994

引用

1st international Workshop on Parallel Scientific computing, PARA 1994

ISBN: (纸本)9783540587125

The proceedings contain 53 papers. The special focus in this conference is on Parallel Scientific computing. The topics include: Computational fluid dynamics on workstation clusters in industrial environments;PVM implementations of advection-chemistry modules of air pollution models;a parallel tree N-body code for heterogeneous clusters;parallel computation of the eigenstructure of toeplitz-plus-hankel matrices on multleomputers;computing eigenvalues of sparse matrices on the connection machine;preliminary experiences with extrapolation methods for parallel solution of differential algebraic equations;a transform approach to fast matrix multiplication;quantum mechanical treatment of reactive scattering problems;load-balancing procedure for distributed short- range molecular dynamics;parallel distributed 2-D short-range molecular dynamics on networked workstations;implementation of parallel lattice gas program on workstations under PVM;constructing numerical software libraries for high-performance computing environments;the CERFACS experience;towards an automatic portation of programs from nCUBE2 to KSR1;a new algorithm for the traveling salesman problem on networked workstations;nonlinear finite element problems on parallel computers;the challenge of portable libraries for high performance machines;two enhancements in a partitioned sparse code;nonlinear dynamics in biochemical control systems;scientific software libraries for scalable architectures;parallel interval methods for perturbed linear systems;limiting factors in high performance computing;programming the convex exemplar series SPP system;parallelization of HIRLAM on MIMD platforms;simulation of fluid dynamical flow problems;real time simulation in a cluster computing environment and parallel computations in molecular dynamics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A NEW METHODOLOGY OF SIMULATED ANNEALING FOR THE OPTIMIZATION PROBLEMS

引用

PHYSICA A 1994年第1-3期205卷 367-374页

作者： LIN, SC HSUEH, JHC Computing Centre Academia Sinica Taipei Taiwan 11529 ROC

Complex optimisation problems with many degrees of freedom are often characterised by the enormously large configuration space, typically O(e(N)) or O(N!). The idea of simulated annealing (SA) proposed by Kirkpatrick has been applied to the complex optimisation problems, which can be treated as annealing a statistical mechanical system from high temperature to low temperature;however, the SA is terribly slow for large problem sizes in typically O(N3 In N) time. We discover the hybrid algorithm (HA), which is based on a hybrid mechanism which combines conventional heuristics with low temperature simulated annealing (LTSA), which could be parallelised easily. The HA is a new approach of resolving optimisation problems with O(N) complexity where information propagation can be inhibited by restraining the range of searches in the configuration space. We use the HA to resolve several famous combinatorial optimisation problems, including the travelling salesman problem (TSP) of large sizes up to 1 000 000 cities within 3 to 5 percent of the optimal value in linear time and other nonuniformly distributed TSPs as well. We shall also discuss the applicability of the HA to the optimisation problems in general.

关键词：

来源：评论

学校读者我要写书评

暂无评论

APPLICATION OF THE OSF distributed computing ENVIRONMENT TO GLOBAL PACS

APPLICATION OF THE OSF DISTRIBUTED COMPUTING ENVIRONMENT TO ...

引用

conference on PACS: Design and Evaluation

作者： MARTINEZ, R ALSAFADI, Y KIM, JM UNIV ARIZONA DEPT ELECT & COMP ENGNCOMP ENGN RES LABTUCSONAZ 85719

ISBN: (纸本)0819414603

The Open Software Foundation (OSF) distributed computing Environment (DCE) is an integrated set of services that facilitates the construction, use and maintenance of distributed applications in a heterogeneous computing environment. This heterogeneous computing environment is comprised of various hardware and software architectures on different computing platforms and communications networks. To date, we have developed time Global PACS environment for remote consultation and diagnosis and distributed file management in radiology using socket communications and a distributed file management system. Global PACS applications currently run on a variety of machines using different operating systems, file systems and communication protocols over time internet and NSFNET. In this paper, we present our approach to developing Global Picture Archiving and Communication System (GPACS) applications using the OSF DCE services and toolkits. Time OSF DCE services include remote procedure calls, naming service, threads service, tine service, file management services, and security service. Several OSF DCE toolkits are currently available from computer and software vendors. Designing distributed Global PACS applications using the OSF DCE approach will feature an open architecture. heterogeneity, and technology independence for GPACS remote consultation atid diagnosis applications, including synchronized image annotation, and system privacy and security. Time applications can communicate though various transport services and communications networks in a Global PACS environment. The use of OSF DCE services for Global PACS will enabel us to develop a robust distributed structure and new user services which feature reliability and scalability for Global PACS environments. © 1994 SPIE. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A distributed FILE MANAGEMENT-SYstEM FOR REMOTE CONSULTATION AND DIAGNOSIS IN GLOBAL PACS

A DISTRIBUTED FILE MANAGEMENT-SYSTEM FOR REMOTE CONSULTATION...

引用

conference on PACS: Design and Evaluation

作者： MARTINEZ, R SUTARIA, B UNIV ARIZONA DEPT ELECT & COMP ENGNTUCSONAZ 85721

ISBN: (纸本)0819414603

Continuous advancements in the field of high speed computer networks and real-time distributed database technology have made new applications in the field of medical imaging possible. The Global PACS prototype is one such application which has been implemented on a national scale via wide area networks. It integrates different system components, such as imaging equipment, viewing workstations, database management and the archive system, fiber optic networks and a high-speed backbone network. Global PACS includes a distributed database archive system spread throughout wide geographical areas and interconnected via the internet and NSFNET. This paper presents a new approach using a file management system for a Global PACS distributed database management and archive system. The file management system allows collaboration between Local and Remote viewing workstations in Global PACS. The image GIF files are stored and retrieved under a UNIX file management system on several servers on the internet. The file management system is used to access different multimedia files, such as image, voice and video data, from Global PACS servers on the internet. The file management approach reduces unnecessary DBMS overhead and supports real-time applications for Global PACS. The UNIX RPC (Remote Procedure Call) facility is used for real-time query and FTP (File Transfer Protocol) is used for image file transfer. This system has been integrated with the remote consultation and diagnosis system in Global PACS. The distributed file management system has been tested over the local Ethernet at the University Medical Center and over the internet/NSFNET to Wake Forest University, on distributed Global PACS servers. Query and image retrieval tests using the file management system have shown excellent performance. Future features of this system will include the use of the Open Software Foundation distributed computing Environment services. This research is sponsored by the National Science Fou

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

DeViouS: a distributed environment for vision tasks

DeViouS: a distributed environment for vision tasks

引用

IEEE international conference on Image Processing

作者： P.R. Romig A. Samal Department of Computer Science and Engineering University of Nebraska Lincoln Lincolnshire NE USA

We present a system for the integration of computer vision tasks in a distributed environment. This system, called DeViouS, is based on the client/server model and runs in a heterogeneous environment of Unix workstations. It takes advantage of the free cycles in modern workstation environments to distribute and speed up the execution of vision tasks. Two primary goals of DeViouS are to provide a practical distributed system and a research environment for vision computing. DeViouS is based on a modular design that allows experimentation in various aspects of algorithm design, scheduling and network programming. It can make use of any existing computer vision package with very minor changes to DeViouS. DeViouS has been tested in an environment of SUN and Digital workstations and has shown substantial improvements in speed over sequential computing with negligible overhead.< >

关键词： Computer vision Workstations distributed computing Algorithm design and analysis Scheduling algorithm Processor scheduling Packaging Sequential analysis Object recognition Machine vision

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：