检索结果-内蒙古大学图书馆

1994 Scalable Parallel Libraries Conference, SPLC 1994

作者： Gropp, W. Lusk, E. Div. of Math. and Comput. Sci. Argonne Nat. Lab. IL60439 United States

ISBN: (纸本)0818668954

In September of 1994 a workshop was held at Argonne National Laboratory on implementation issues for MPI. MPI is a standard message-passing library interface developed during 1993 and 1994 by the MPI Forum, a broadly based group of parallel comput.ng vendors, parallel library writers, and application, sci.ntists. The purpose of the Workshop was to gather together those vendors and others actively engaged in implementing the Standard in order to discuss issues raised by the implementation process. A secondary aim was to explore the possibility of pooling some efforts in order to speed and ease the adoption of MPI. we briefly describe the implementation efforts that were presented at the Workshop, summarize the discussions that took place on the Standard itself and implementation issues, and offer some general conclusions about the state of the MPI implementation effort worldwide. © 1994 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

DIAGNOSABILITY OF ENHANCED HYPERCUBES

引用

IEEE TRANSACTIONS ON comput.RS 1994年第9期43卷 1054-1061页

作者： WANG, DJ Dept.of Math. & Comput. Sci. Montclair State Univ. NJ USA Abstract Authors References Cited By Keywords Metrics Similar Download Citation Email Print Request Permissions

An enhanced hypercube is obtained by adding 2n-1 more links to a regular hypercube of 2n processors. It has been shown that enhanced hypercubes have very good improvements over regular hypercubes in many measurements such as mean internode distance, diameter and traffic density. This paper proves that in the aspect of diagnosability, enhanced hypercubes also achieve improvements. Two diagnosis strategies, both using the well-known PMC diagnostic model, are studied: the precise (one-step) strategy proposed by Preparata et al. and the pessimistic strategy proposed by Friedman. Under the precise strategy, the diagnosability is shown to be increased to n + 1 in enhanced hypercubes (in regular hypercubes the diagnosability is n under this strategy). Under the pessimistic strategy, the diagnosability is shown to be increased to 2n (in regular hypercubes the diagnosability under this strategy is 2n -2). Since the failure probability of one node is fairly low nowadays so that the increase of diagnosability by one or two will considerably enhance the system's self-diagnostic capability, and considering the fact that diagnosability does not ''easily'' increase as the links in networks do, these improvements are noticeable.

关键词： DIAGNOSABILITY DIAGNOSIS FAULT TOLERANCE GRAPH THEORY HYPERCUBES MULTIcomput.R NETWORKS

来源：评论

学校读者我要写书评

暂无评论

Parameter estimation and applications of a class of Gaussian image models

Parameter estimation and applications of a class of Gaussian...

引用

1995 IEEE Southwest Symposium on Image Analysis and Interpretation, IAI 1994

作者： Dattatreya, G.R. Fang, Xiaori Comput. Sci. Program Texas Univ. at Dallas RichardsonTX75083-0688 United States

ISBN: (纸本)0818662506

This paper discusses variations of a model of images and develops algorithms for estimation of all the parameters from the raw image data. The model is suitable for some cases of (1) lossy image compression and realistic reconstruction, (2) texture synthesis and identification, (3) classification of remotely sensed data, and (4) analysis of medical images. Each pixel in the image is modeled as an element of a set of very few known intensity levels (henceforth called pixel-classes) plus an independent zero mean Gaussian random variable. Different statistical structures in the two dimensional lattice of pixel-classes lead to variations in the model. The image representation problem corresponds to estimation of the parameters of the discrete random field formed by the pixel classes, and the parameters of the additive Gaussian field. The authors discuss variations of the model and corresponding applications, and develop convergent estimators for all parameters. © 1994 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

INTEGRABLE STIMULATED RAMAN-SCATTERING SYSTEMS WITH DAMPING

引用

JOURNAL OF PHYSICS A-math.MATICAL AND GENERAL 1994年第16期27卷 5623-5635页

作者： BURTSEV, SP KAUP, DJ Dept. of Math. & Comput. Sci. Clarkson Univ. Potsdam NY USA

We construct stimulated Raman scattering systems with damping which can be solved by the inverse scattering transform with a variable spectral parameter, and present the corresponding linear systems. We also analyse the non-standard properties of the damped soliton solution;amplitude, speed, and form change as the soliton propagates through a medium.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gesture recognition: an assessment of the performance of recurrent neural networks versus competing techniques

Gesture recognition: an assessment of the performance of rec...

引用

IEE Colloquium on Applications of Neural Networks to Signal Processing (Digest No. 1994/248)

作者： J. Cracknell A.Y. Cairns P. Gregor C. Ramsay I.W. Ricketts Dept. of Math. & Comput. Sci. Dundee Univ. UK

A gesture is a motion of the body that contains information (e.g. waving goodbye, beckoning with an index finger, signs in a sign language). There are four classes of gestures; signs (substitutes for spoken language); indications (pointing and showing direction); illustration (conveying ideas such as size and shape); and manipulation (for example making something from virtual clay). The first three of these are suitable for both input and output, while the fourth is only suitable for input. Recognition of gestures is still a major problem, and represents a challenge that rivals speech and hand-writing recognition. The paper describes a comparison of some of the competing techniques that have been applied to solving this problem. Three techniques were investigated; dynamic programming (DP), hidden Markov models (HMMs) and recurrent neural networks (RNNs). All of these techniques seek to represent time explicitly, and are therefore better suited than static techniques to the dynamic nature of most gestures. The study has application to a sign language recognition system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A 2 1/2 -dimensional systolic array architecture

A 2 1/2 -dimensional systolic array architecture

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： S.P.S. Lam Sch. of Comput. & Math. Sci. Oxford Brookes Univ. UK

This paper presents a novel 2 1/2 -dimensional systolic array architecture. The novel systolic array has a logical three-dimensional communication network, but it can be realized on a two-dimensional wafer surface by making use of multiple-layer metalization or multiple chip module technology. The architectural details are discussed in terms of graph theory. Based on several case study, the comput.tional efficiency and hardware overheads for the proposed array are summarised with respect to conventional systolic arrays.< >

关键词： Systolic arrays comput.r architecture Topology Signal processing algorithms Communication networks Graph theory Hardware Distributed comput.ng Electronic mail comput.tional efficiency

来源：评论

学校读者我要写书评

暂无评论

A hybrid genetic algorithm application to a genetics sequencing problem

A hybrid genetic algorithm application to a genetics sequenc...

引用

IEE Colloquium on Molecular Bioinformatics

作者： J.D. Walker P.E. File C.J. Miller W.B. Samson Dept. of Math. & Comput. Sci. Dundee Inst. of Technol. UK

Map building is an example of a difficult sequencing problem which requires some form of search to find a good solution from a large problem space of feasible solutions. The authors describe the development of a hybrid genetic algorithm (HGA) suitable for tackling the problem. The results of applying the HGA to a set of map data are presented.< >

关键词： Biomedical comput.ng Biological cells Biophysics DNA Genetic algorithms Learning systems Search methods

来源：评论

学校读者我要写书评

暂无评论

A genetic algorithm for file and task placement in a distributed system

A genetic algorithm for file and task placement in a distrib...

引用

IEEE International Conference on Evolutionary comput.tion

作者： A.L. Corcoran D.A. Schoenefeld Dept. of Math. & Comput. Sci. Tulsa Univ. OK USA Department of Mathematical and Computer Sciences The University of Tulsa Oklahoma

We explore the distributed file and task placement problem, which is intractable. We also discuss genetic algorithms and how they have been used successfully to solve combinatorial problems. Our experimental results show the GA to be far superior to the greedy heuristic in obtaining optimal and near optimal file and task placements for the problem with various data sets.< >

关键词： Genetic algorithms Costs Communication networks Network topology Intelligent networks Maintenance Control systems comput.r security Delay Communication system control

来源：评论

学校读者我要写书评

暂无评论

The reuse of methods

The reuse of methods

引用

EUROMICRO Conference

作者： M.J. Taylor M. Ramachandran Liverpool John Moores University Liverpool Merseyside GB Sch. of Comput. & Math. Sci. Liverpool John Moores Univ. UK

The reuse paradigm is an actively growing research area within the field of information systems development. Much work has been done to create frameworks for code reuse and design reuse. In this article we propose that we can extend the reuse paradigm even further and can enact the reuse of information systems development methods.< >

关键词： Telephony Information systems Management information systems sci.ntific comput.ng Database systems Data structures Object oriented programming Expert systems Reverse engineering Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

A compilation system that integrates High Performance Fortran and Fortran M

A compilation system that integrates High Performance Fortra...

引用

Scalable High Performance comput.ng Conference

作者： I. Foster Ming Xu B. Avalani Argonne National Laboratory Argonne IL US Div. of Math. & Comput. Sci. Argonne Nat. Lab. IL USA

Task parallelism and data parallelism are often seen as mutually exclusive approaches to parallel programming. Yet there are important classes of application, for example in multidisci.linary simulation and in command and control, that would benefit from an integration of the two approaches. In this paper, we describe a programming system that we are developing to explore this sort of integration. This system builds on previous work on task-parallel and data-parallel Fortran compilers to provide an environment in which the task-parallel language Fortran M can be used to coordinate data-parallel High Performance Fortran tasks. We use an image processing problem to illustrate the issues that arise when building an integrated compilation system of this sort.< >

关键词： Parallel processing Parallel programming Prototypes math.matics Laboratories Buildings Data structures comput.tional Intelligence Society Aircraft manufacture Earth

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：