检索结果-内蒙古大学图书馆

workshop on Evolutionary Models and Strategies and workshop on parallel Processing: Logic, Organization, and Technology, WOPPLOT 1989

引用

workshop on Evolutionary Models and Strategies and workshop on parallel Processing: Logic, Organization, and Technology, WOPPLOT 1989

ISBN: (纸本)9783540550273

The proceedings contain 30 papers. The special focus in this conference is on Evolutionary Models and Strategies and workshop on parallel Processing: Logic. The topics include: On parallel consciousness;complementarity and non-locality in complex systems;systems and uncertainty;the construction of space and the logics of quantum mechanics;cellular automata and the concept of space;multipurpose and special purpose computers;implementation of divide-and-conquer algorithms on multiprocessors;some remarks on synchronization problems;effective implementation of distributed arbitration in multiprocessor systems;flowshop and travelling salesman problem;architectural considerations for NERV - a general purpose neural network simulation system;connectionist models of utterance production;self-organization of informational systems;distributed semantic representations of word meanings;logic of cognitive representations and their evolution;a modal propositional calculus for quantum facts and dynamical theories;self-organization in computational systems;adaptation and extension;chaotic dynamics of generating markov partitions, and linguistic sequences mimicking zipf's law;understanding evolution as a collective strategy for groping in the dark;parallel genetic algorithms, population genetics, and combinatorial optimization;ASPARAGOS, a parallel genetic algorithm and population genetics;travelling in an imaginary landscape;finding the global minimum of a low-dimensional spin-glass model;ten theses regarding the design of controlled evolutionary strategies;incommensurability of liouvillean dynamics and information dynamics;selforganization by evolutionary strategies in visual systems and on steiner trees and genetic algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel Proto-a prototyping tool for analyzing and validating sequential and parallel processing software requirements

Parallel Proto-a prototyping tool for analyzing and validati...

引用

International workshop on Rapid System Prototyping (RSP)

作者： C. Burns Rome Laboratory NY USA

parallel Proto is a software prototyping tool for analyzing and validating functional requirements which are targeted to either sequential, parallel or distributed architecture environments. Currently, most parallel processing computer-aided software engineering (CASE) tools focus on the identification and simulation of parallelism during the coding stage of the software lifecycle. Such an approach does not take into account any explicit specification of parallelism inherent in the application or an associated parallel-oriented design. Using parallel Proto, parallelism can be explicitly identified and modeled in the requirements and high level design stages of software development. The tool provides facilities for graphically constructing, data-flow-like software functional specifications and parallel and distributed hardware architectures, associating the software functions with the hardware components and interactively executing the functional prototype. Performance modeling statistics are available after prototype execution. Such capabilities support the early analysis of high level software and hardware architecture trade-offs.< >

关键词： Prototypes Software prototyping parallel processing Computer architecture Software tools Hardware Computer aided software engineering Computational modeling Computer simulation Application software

来源：评论

学校读者我要写书评

暂无评论

Topological properties of WK-recursive networks

Topological properties of WK-recursive networks

引用

IEEE workshop on Future Trends of distributed Computing Systems

作者： A.I. Mahdaly H.T. Mouftah N.N. Hanna Department of Electrical Engineering Queen's University Kingston ONT Canada Department of Electronics and Telecommunication Faculty of Engineering and Technology Helwan University Cairo Egypt

The WK-recursive networks are highly concurrent message-passing architectures which belong to a class of regular scalable topologies and can be expanded very easily to any size regardless of the node degree. The authors examine the strength and weakness of WK-recursive topologies from a graph point of view and consider the features that make its connectivity appealing. A set of interconnection metrics is defined. A simulation package is developed and a transputer development system (TDS) is used to evaluate the relation between communication time, size of message, and distance traveled.< >

关键词： Computer networks Telecommunication network topology Message passing Packaging Multiprocessor interconnection networks Network topology Computational modeling Computer simulation Concurrent computing parallel processing

来源：评论

学校读者我要写书评

暂无评论

EURASIP workshop on Neural Networks, 1990

引用

EURASIP workshop on Neural Networks, 1990

ISBN: (纸本)9783540522553

The proceedings contain 23 papers. The special focus in this conference is on Neural Networks. The topics include: Preface;when are k-nearest neighbor and back propagation accurate for feasible sized sets of examples?;rule-injection hints as a means of improving network performance and learning time;inversion in time;cellular neural networks: Dynamic properties and adaptive learning algorithm;improved simulated annealing, Boltzmann machine, and attributed graph matching;artificial dendritic learning;a neural net model of human short-term memory development;large vocabulary speech recognition using neural-fuzzy and concept networks;speech feature extraction using neural networks;neural network based continuous speech recognition by combining self organizing feature maps and hidden markov modeling;ultra-small implementation of a neural halftoning technique;complexity theory of neural networks and classification problems;application of self-organising networks to signal processing;a study of neural network applications to signal processing;simulation machine and integrated implementation of neural networks: A review of methods, problems and realizations;vLSI implementation of an associative memory based on distributed storage of information;generalization performance of overtrained back-propagation networks;stability of the random neural network model;temporal pattern recognition using EBPS;markovian spatial properties of a random field describing a stochastic neural network: Sequential or parallel implementation?;chaos in neural networks;the "moving targets" training algorithm;acceleration techniques for the backpropagation algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Systems whose distributed simulation requires low overhead

Systems whose distributed simulation requires low overhead

引用

International Phoenix Conference on Computers and Communications (IPCCC)

作者： D. Kumar Department of Computer Engineering and Science Case Western Reserve University Cleveland OH USA

The author identifies a class of systems which can be simulated by distributed simulation with low overhead. Many cyclic systems are included in this class. He shows that this class of systems has special properties allowing him to develop schemes specifically tailored for it with lower overhead than a direct application of general-purpose schemes in previous studies. The author shows that in simulating these systems, the scheme in a particular study would have lower overhead than its usual overhead in simulating more general systems.< >

关键词： Computational modeling System recovery Context modeling distributed computing Computer simulation parallel processing Discrete event simulation Synchronization Clocks Degradation

来源：评论

学校读者我要写书评

暂无评论

Indexed, global objects for distributed memory parallel architectures

引用

SIGPLAN Notices (ACM Special Interest Group on Programming Languages) 1989年第4期24卷 95-98页

作者： Bain, William L. Block Island Technologies

distributed memory, message passing (DMMP) parallel architectures, such as the intel iPSC(R) computer system, provide the processing power and memory to solve very large parallel programming problems. However, their large grain process model and distributed memory complicate the programmer's view of the system. Extensions have been created for interwork II's global object name space in order to support arrays of objects;interwork II distributes the element objects among the processing nodes so as to balance the number on each node. Indexed objects simplify the programmer's view of parallel architectures by enabling related data to be automatically partitioned among the processing nodes. They also speedup computations by allowing these data to be operated on in parallel. This mechanism has proved useful as the basis for constructing a large, parallel simulation.

关键词： Computer Systems Programming

来源：评论

学校读者我要写书评

暂无评论

Load sharing in heterogeneous queueing systems

Load sharing in heterogeneous queueing systems

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： S.A. Banawan J. Zahorjan Department of Computer Science University of Houston Houston TX USA Department of Computer Science University of Washington Seattle WA USA

The problem of sharing jobs among a set of parallel queues is discussed. The system is heterogeneous in the sense that different servers may have different speeds. Socially optimal policies that minimize the mean response time of all jobs ar of interest. Using semi-Markov decision processes, it is shown that an optimal policy that uses the instantaneous queue length independent of system utilization does not exist. Rather, the optimal decision of assigning a job to a server depends on the workload intensity. At light loads, the optimal policy tends to assign most jobs to fast servers. At heavy loads, slower servers are used to offload fast ones. simulation results indicate that a simple heuristic, i.e., a generalization of the optimal policy for homogeneous systems derived from the analytic results, yields substantial performance improvement compared with no load sharing and outperforms the join-shortest-queue policy.< >

关键词： Network servers Computer science distributed computing Routing Delay Queueing analysis Communication networks Application software Analytical models Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Future trend on concurrency control in distributed database system design.

Future trend on concurrency control in distributed database ...

引用

proceedings - workshop on the Future Trends of distributed Computing Systems in the 1990s.

作者： Wu, S.M. Pan, D.L. Tamkang Univ Taipei Taiwan

ISBN: (纸本)0818608978

The state of the art of concurrency control is reviewed, and the pros and cons of various approaches are compared. The time-stamp interval approach is emphasized due to its promising features. Critical issues and control strategy are suggested for future studies in the 1990s. A time-stamp interval approach with parallel validation is presented under the proposed guidelines. simulation results are analyzed to compare the related methods.

关键词： DATABASE SYSTEMS

来源：评论

学校读者我要写书评

暂无评论

3rd Aegean workshop on Computing: VLSI Algorithms and Architectures, AWOC 1988

引用

3rd Aegean workshop on Computing: VLSI Algorithms and Architectures, AWOC 1988

ISBN: (纸本)9780387968186

The proceedings contain 46 papers. The special focus in this conference is on Computing: VLSI Algorithms and Architectures. The topics include: Optimal parallel evaluation of tree-structured computations by raking (extended abstract);on finding lowest common ancestors: Simplification and parallelization: Extended summary;A scheduling problem arising from loop parallelization on MIMD machines;scheduling dags to minimize time and communication;computing a perfect matching in a line graph;separation pair detection;graph embeddings 1988: Recent breakthroughs, new directions;simulating binary trees on hypercubes;embedding rectangular grids into square grids;fast parallel and sequential algorithms for edge-coloring planar graphs: extended abstract;Efficient reconfiguration of VLSI arrays: Extended abstract;embedding grids into hypercubes;compaction on the torus: Extended abstract;channel routing with short wires;simple three-layer channel routing algorithms;applying the classification theorem for finite simple groups to minimize pin count in uniform permutation architectures: Extended abstract;a new algorithm for wiring layouts;Input sensitive VLSI layouts for graphs of arbitrary degree;Fast self-reduction algorithms for combinatorial problems of VLSI design;Regular structures and testing: RCC-adders: Extended abstract;optimal parallel algorithms on planar graphs;parallel simulation and test of VLSI array logic;Universal hashing in VLSI;converting affine recurrence equations to quasi-uniform recurrence equations;better computing on the anonymous ring: Extended Abstract;Network complexity of sorting and graph problems and simulating CRCW PRAMS by interconnection networks: Preliminary version;analysis of a distributed scheduler for communication networks;weighted distributed match-making: Preliminary version;a tradeoff between information and communication in broadcast protocols;families of consensus algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Future trend on concurrency control in distributed database system design

Future trend on concurrency control in distributed database ...

引用

IEEE workshop on Future Trends of distributed Computing Systems

作者： S.M. Wu D.L. Pan Tamkang University Taipei Taiwan

关键词： Concurrency control Database systems Data structures Protocols Design optimization Throughput Optimization methods

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：