检索结果-内蒙古大学图书馆

Annual Hawaii International Conference on System Sciences (HICSS)

作者： N. Kalantery Centre for Parallel Computing University of Westminster London UK

The paper examines the real time speed of the conservative parallel simulation of a telecommunications network. Real time speed is defined as the ratio of the simulated time to the execution time. A generic simulation model of SS7 networks is executed under the conservative mechanism. A technique used to secure a stable lower bound on the speed of the simulator is introduced and analyzed. Using this technique simulation models ranging in size, from 16 to 64 nodes are executed on similarly sized and configured transputer networks: empirical data on the real time performance of the system are presented. The results confirm that the speed of the simulator is both stable and scalable: independent of work load density and size of the modelled network simulation of a given period of model activity is achieved within a predetermined period of real time.

关键词： Computational modeling Real time systems Communication system control Discrete event simulation Telecommunication control Switching circuits Switches Communication switching Circuit simulation Telecommunication switching

来源：评论

学校读者我要写书评

暂无评论

parallel optimization of interplanetary trajectories 3rd

引用

Proceedings of the 1996 3rd International Workshop on Applied parallel computing, PARA

作者： Hamma, B. Parallel Algorithms Team CERFACS European Centre for Research Advanced Training in Scientific Computing 42 av. Coriolis Toulouse-Cedex F-31057 France

ISBN: (纸本)3540620958

This paper describes the software developed at CNES within the context of the VESTA Franco-Soviet program, for the optimization of interplanetary trajectories. The sequentiel software, intended for the determination of multiple flyby trajectories and their optimization, was developed previously in collaboration with CNES and LAO of Paul Sabatier University, Toulouse, France. In this software, an impulse manoeuvre is performed at each flyby. The possibility to add an intermediate manoeuvre between flybys and the use of the swing-by aim to reduce the total trajectory costs. The optimization routines are parallelized. © Springer-Verlag Berlin Heidelberg 1996.

关键词： Interplanetary trajectories Lambert problem Multiple-flyby parallel optimization Swing-by

来源：评论

学校读者我要写书评

暂无评论

Implementing distributed shared memory on top of MPI: the DSMPI library

Implementing distributed shared memory on top of MPI: the DS...

引用

Euromicro Workshop on parallel and Distributed Processing

作者： L.M. Silva J.G. Silva S. Chapple University of Coimbra Portugal Edinburgh Parallel Computing Centre UK

Distributed shared memory has been recognized as an alternative programming model to exploit the parallelism in distributed memory systems since it provides a higher level of abstraction than simple message passing. DSM combines the simple programming model of shared-memory with the scalability of distributed memory machines. This paper presents DSMPI, a parallel library that runs atop of MPI and provides a distributed shared memory abstraction. It provides an easy-to-use programming interface, is flexible, portable and supports heterogeneity. Moreover, it supports different coherence protocols and models of consistency. We present some performance results taken in a network of workstations and in a Cray T3D which show that DSMPI can be competitive with MPI for some applications.

关键词： Libraries Programming profession parallel programming Message passing Operating systems parallel processing Scalability Workstations Hardware Coherence

来源：评论

学校读者我要写书评

暂无评论

Constrained migration of an atmospheric circulation model

Constrained migration of an atmospheric circulation model

引用

International Conference and Exhibition on High-Performance computing and Networking, HPCN EUROPE 1996

作者： Kandhai, B.D. Sloot, P.M.A. Huot, J.P. University of Amsterdam Computer Science and Physics Parallel Scientific Computing and Simulation Group Kruislaan 403 Amsterdam1098 SJ Netherlands European Space Research and Technology Centre Keplerlaan 1 Noordwijk2201 AZ Netherlands

ISBN: (纸本)9783540611424

In the migration of large production codes from sequential to parallel implementations a total rewriting of the original code is often prohibited. The reason for this is that very complicated codes took years of evolution to reach a stable and reliable state. Exploring the possibilities for parallelization should therefore be done with extreme care rather than by means of a complete rewrite from scratch. In this paper we discuss the migration of an atmospheric simulation program as an example of such ‘constrained migration’. We show that this type of migration allows for a fast and reliable, though not optimal, parallel implementation. Moreover it forces the researcher to identify locality and sequential hot spots in his code, thus guiding him into new strategies for a complete parallelization of the code. © Springer-Verlag Berlin Heidelberg 1996.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

A NEW METHOD FOR GENERATING INTEGER COMPOSITIONS IN parallel

引用

parallel Algorithms and Applications. 1996年第1-2期9卷 101-109页

作者： HONG SHEN DAVID J. EVANS [a] School of Computing and Information Technology Griffith University Nathan QLD 4111 Australia [b] Parallel Algorithms Research Centre Loughborough University of Technology Loughborough Leicestershire UK

A novel method, binary countdown transformation, for generating integer compositions in parallel is proposed. Based on this method, an optimal and highly adaptive parallel algorithm for generating all compositions of integernis presented. The algorithm runs onpprocessors on a simple SIMD model requiring neither shared memory nor interconnection network and has a worst-case time complexity ofO(n2n−1/p), 1 ≤ p ≤ 2n−1. All the compositions generated are in lexicographic order. The proposed algorithm is superior to those built on generating combinations and set partitions.

关键词： Binary countdown transformation integer compositions lexicographic order parallel algorithm processors time complexity C.1.2 F.2.2 G.2.1

来源：评论

学校读者我要写书评

暂无评论

Optimized wave functions for quantum Monte Carlo studies of atoms and solids

引用

Physical Review B 1996年第15期53卷 9640-9640页

作者： A. J. Williamson S. D. Kenny G. Rajagopal A. J. James R. J. Needs L. M. Fraser W. M. C. Foulkes P. Maccullum Edinburgh Parallel Computing Centre James Clerk Maxwell Building The King's Buildings University of Edinburgh Mayfield Road Edinburgh EH9 3JZ Scotland

Wave functions for the homogeneous electron gas, a germanium pseudosolid, and a germanium pseudoatom are optimized using the method of variance minimization. Forms for the Jastrow factor which are convenient to optimize and may be evaluated rapidly are devised and tested and we stress the advantages of using expressions which are linear in the variable parameters. For each system studied we have performed variational and diffusion quantum Monte Carlo calculations to test the accuracy of the optimized wave functions. The results of our study are very promising for future applications of quantum Monte Carlo methods to real materials. © 1996 The American Physical Society.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Framework for developing extensible and reusable parallel and distributed applications

Framework for developing extensible and reusable parallel an...

引用

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

作者： G.R. Ribeiro Justo P.R. Freire Cunha Centre for Parallel Computing University of Westminster London UK Departamento de Informátrica Universidade Federal de Pernambuco Recife Pernambuco Brazil

The number of parallel and distributed programming languages available is enormous. This means that the user faces a difficult task in selecting the language which suits his/her application. Most of the facilities supported by new languages could be, however, introduced as simple extensions of existing languages. In object oriented languages where the concepts of reusability and extensibility are natural parts of the language, extensions can easily take place by creating frameworks which provide the abstraction level required by the user. We present a framework that supports the dynamic reconfiguration of processes. C++CL is a framework developed in C++ and layered above PVM. This means that dynamic reconfigurable systems are easily built in a C++ fashion following the CL approach. At the same time, by using PVM, we improve the portability of the framework over heterogeneous networks and can also use all tools available for tracing and debugging PVM parallel processes. The paper then shows how the framework can be extended to provide special classes of programs.

关键词： Libraries Object oriented modeling Lakes Debugging Costs Skeleton Computer aided analysis Filling RNA Object oriented programming

来源：评论

学校读者我要写书评

暂无评论

Portable transparent checkpointing for distributed shared memory 96

Portable transparent checkpointing for distributed shared me...

引用

International Symposium on High Performance Distributed computing

作者： L.M. Silva J.G. Silva S. Chapple Departamento Engenharia Informática Universidade de Coimbra Polo II Coimbra Portugal Edinburgh Parallel Computing Centre University of Edinburgh Edinburgh UK

ISBN: (纸本)9780818675829

We present a checkpointing mechanism for a DSM system that, in spite of being invisible to the programmer, is quite efficient and portable. It is efficient because it is nonblocking, coordinated and thus domino-effect free. It offers some portability because it is built on top of MPI and uses only the services offered by MPI and a POSIX compliant local file system. As far as we know, this is the first real implementation of such a scheme for DSM. Along with the description of the algorithms used, we present experimental results obtained in a cluster of workstations, and discuss many insights that came out of the implementation effort. We hope that our research shows that efficient, transparent and portable checkpointing is viable for DSM systems.

关键词： Checkpointing Workstations parallel machines Fault tolerant systems Programming profession File systems Clustering algorithms Scalability Computer crashes Distributed computing

来源：评论

学校读者我要写书评

暂无评论

parallel solution of sparse problems by using a sequence of large dense blocks 3rd

引用

Proceedings of the 1996 3rd International Workshop on Applied parallel computing, PARA

作者： Ostromsky, Tz. Salvini, S. Wasniewski, J. Zlatev, Z. Central Laboratory for Parallel Information Processing Bulgarian Academy of Sciences Acad. G.Bonchev str. bl. 25-A Sofia 1113 Bulgaria The Numerical Algorithms Group Ltd. (NAG) Wilkinson House Jordan Hill Road Oxford OX2 8DR United Kingdom Danish Computing Centre for Research and Education (UNI-C) DTU Bldg. 304 Lyngby DK-2800 Denmark National Environmental Research Institute Frederiksborgvej 399 P. O. Box 358 Roskilde DK-4000 Denmark

ISBN: (纸本)3540620958

Linear least squares problems arise in many important fields of science and engineering (such as econometry, geodesy, statistics, structural analysis, fluid dynamics, etc.). Applications from all these fields are to be handled numerically in the solution of various models used in the development of new industrial products. At the National Environmental Research Institute (Denmark), linear least squares problems have been applied in the efforts to determine optimal values of some of the parameters involved in air pollution models. Large and sparse least squares problems can be handled by treating a sequence of dense blocks. Standard parallel subroutines, which perform orthogonal decomposition of dense matrices (as, for example, subroutines from LAPACK, SCALAPACK or NAG), can be used to handle successively the dense blocks. A preliminary reordering procedure, LORA, is to be applied at the beginning of the computational process. The size of the blocks can be adjusted to the particular computer used. Results obtained on a Silicon Graphics POWER CHALLENGE are given. The same method can also be used in the solution of large and sparse systems of linear algebraic equations. © Springer-Verlag Berlin Heidelberg 1996.

关键词： Linear algebra

来源：评论

学校读者我要写书评

暂无评论

CHIMP AND PUL - SUPPORT FOR PORTABLE parallel computing

引用

FUTURE GENERATION COMPUTER SYSTEMS 1995年第2期11卷 211-219页

作者： BRUCE, RAA CHAPPLE, S MACDONALD, NB TREW, AS TREWIN, S Edinburgh Parallel Computing Centre The University of Edinburgh James Clerk Maxwell Building The King's Buildings May field Road Edinburgh EH9 3JZ UK

The lack of a portable programming interface for parallel computers has inhibited the development of applications for such systems, and thus restricted the exploitation of this technology. In this paper we discuss various efforts to provide a portable interface to parallel computers, and present the Edinburgh CHIMP (Common High-level Interface to Message-Passing), and PUL (parallel Utilities Library) activities in this context. The concepts behind these projects are described, with details of the range of parallel systems on which they are available. An important consequence of the portability offered by the CHIMP message passing layer is the ability for applications programmers to reuse entire programs, as well as code modules. PUL assists this by providing a set of reusable components for implementing parallel applications. Developed on top of CHIMP, the PUL utilities are themselves portable across a range of platforms. Finally, this paper summarises experience using CHIMP and PUL to implement parallel applications in collaboration with both industrial and academic groups.

关键词： MESSAGE PASSING parallel LIBRARIES PORTABILITY REUSABILITY SCALABILITY

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：