检索结果-内蒙古大学图书馆

Skeleton Particle-in-Cell Codes on Emerging Computer Architectures

COMPUTING IN SCIENCE & ENGINEERING 2015年第2期17卷 47-52页

作者： Decyk, Viktor K. Univ Calif Los Angeles Los Angeles CA 90089 USA

If we define each supercomputer node as a parameterized abstract machine, then it's possible to design algorithms independently of hardware. Such an abstract machine could consist of a collection of vector processors, each with a small fast memory communicating via a larger global memory. programming this type of machine will require ideas from the past as well as new concepts.

关键词： graphics processing units multiprocessing systems parallel architectures parallel machines program compilers SIMD processor computer architecture next generation processor parallel computer parameterized abstract machine skeleton particle-in-cell codes supercomputers Algorithm design and analysis Computer architecture High performance computing Parallel processing Program processors Scientific computing Supercomputers HPC concurrent programming distributed programming high-performance computing physics computer applications scientific computing

来源：评论

学校读者我要写书评

暂无评论

High performance genetic algorithm for land use planning

引用

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS 2013年第Jan.期37卷 45-58页

作者： Porta, Juan Parapar, Jorge Doallo, Ramon Rivera, Francisco F. Sante, Ines Crecente, Rafael Univ A Coruna Comp Architecture Grp La Coruna Spain Univ Santiago de Compostela D Elect & Comp Santiago De Compostela Spain Univ Santiago de Compostela Land Lab Santiago De Compostela Spain

This study uses genetic algorithms to formulate and develop land use plans. The restrictions to be imposed and the variables to be optimized are selected based on current local and national legal rules and experts' criteria. Other considerations can easily be incorporated in this approach. Two optimization criteria are applied: land suitability and the shape-regularity of the resulting land use patches. We consider the existing plots as the minimum units for land use allocation. As the number of affected plots can be large, the algorithm execution time is potentially high. The work thus focuses on implementing and analyzing different parallel paradigms: multi-core parallelism, cluster parallelism and the combination of both. Some tests were performed that show the suitability of genetic algorithms to land use planning problems. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Land use planning Genetic algorithms Parallel programming distributed programming Clusters of multi-core systems GIS

来源：评论

学校读者我要写书评

暂无评论

A formal nethod (a networked formal method)

引用

INNOVATIONS IN SYSTEMS AND SOFTWARE ENGINEERING 2010年第4期6卷 255-268页

作者： Breuer, Peter T. Pickin, Simon Univ Birmingham Dept Comp Sci Birmingham W Midlands England Univ Carlos III Dept Ing Telemat Madrid Spain

A year-long trial has seen a large lightweight verification problem treated by an ad hoc distributed network of identical solvers. The trialled problem is the semantic analysis of the C code in the Linux kernel to exclude a common deadlock possibility. The aim of the programme behind the experiment is to develop a viable loosely coupled distributed formal method which a community of interested part-time helpers on the net can lend their computing cycles to as they will, or send their own verification problems to for solving.

关键词： Formal methods programming logic Static analysis Linux kernel C Open source distributed programming

来源：评论

学校读者我要写书评

暂无评论

How smart does an agent need to be?

引用

INTERNATIONAL JOURNAL OF MODERN PHYSICS C 2005年第1期16卷 139-155页

作者： Kirkpatrick, S Schneider, JJ Hebrew Univ Jerusalem Sch Engn & Comp Sci Jerusalem Israel Univ Mainz Dept Phys D-55099 Mainz Germany

The classic distributed computation is done by atoms, molecules or spins in vast numbers, each equipped with nothing more than the knowledge of their immediate neighborhood and the rules of statistical mechanics. These agents, 10(23) or more, are able to form liquids and solids from gases, realize extremely complex ordered states, such as liquid crystals, and even decode encrypted messages. We will describe a study done for a sensor-array "challenge problem" in which we have based our approach on old-fashioned simulated annealing to accomplish target acquisition and tracking under the rules of statistical mechanics. We believe the many additional constraints that occur in the real problem can be folded, step by step, into this stochastic approach. The results have applicability to other network management problems on scales where a distributed solution will be mandatory.

关键词： stochastic optimization sensor arrays multi-agent systems distributed programming

来源：评论

学校读者我要写书评

暂无评论

Multilevel Parallelism for the Exploration of Large-Scale Graphs

引用

IEEE TRANSACTIONS ON MULTI-SCALE COMPUTING SYSTEMS 2018年第3期4卷 204-216页

作者： Bernaschi, Massimo Bisson, Mauro Mastrostefano, Enrico Vella, Flavio NVIDIA Corp Santa Clara CA 95051 USA Natl Res Council Italy Ist Applicaz Calcolo I-00185 Rome Italy

We present the most recent release of our parallel implementation of the BFS and BC algorithms for the study of large scale graphs. Although our reference platformis a high-end cluster of new generation Nvidia GPUs and some of our optimizations are CUDA specific, most of our ideas can be applied to other platforms offering multiple levels of parallelism. We exploit multi level parallel processing through a hybrid programming paradigm that combines highly tuned CUDA kernels, for the computations performed by each node, and explicit data exchange through the Message Passing Interface (MPI), for the communications among nodes. The results of the numerical experiments show that the performance of our code is comparable or better with respect to other state-of-the-art solutions. For the BFS, for instance, we reach a peak performance of 200 Giga Teps on a single GPU and 5.5 Terateps on 1024 Pascal GPUs. We release our source codes both for reproducing the results and for facilitating their usage as a building block for the implementation of other algorithms.

关键词： Large graphs graph algorithms parallel algorithms parallel programming distributed programming GPU CUDA

来源：评论

学校读者我要写书评

暂无评论

distributed APPLICATION SUPPORT - SURVEY AND SYNTHESIS OF EXISTING APPROACHES

引用

INFORMATION AND SOFTWARE TECHNOLOGY 1990年第8期32卷 545-558页

作者： SCHILL, A UNIV KARLSRUHE INST TELEMATW-7500 KARLSRUHEGERMANY

The distributed application support area for distributed systems is surveyed. The focus is on: 1. distributed programming and configuration techniques, 2. use of object-oriented techniques, and 3. development support. Several important communication approaches are classified and compared, including extended message passing and remote procedure call facilities, as well as new distributed object-oriented interaction mechanisms and multiparty communication support. Important distributed configuration management issues covered are placement and structure support for distributed applications, dynamic configuration change support, and associated configuration languages. An outline is provided of an object-oriented environment's architecture for distributed application development support.

关键词： development environments distributed applications distributed configuration management distributed programming distributed systems multiparty communication object-oriented systems remote procedure call tool integration

来源：评论

学校读者我要写书评

暂无评论

Real-World distributed Computer with Ibis

引用

COMPUTER 2010年第8期43卷 54-62页

作者： Bal, Henri E. Maassen, Jason van Nieuwpoort, Rob V. Drost, Niels Kemp, Roelof van Kessel, Timo Palmer, Nick Wrzesinska, Gosia Kielmann, Thilo van Reeuwijk, Kees Seinstra, Frank J. Jacobs, Ceriel J. H. Verstoep, Kees Vrije Univ Amsterdam Dept Comp Sci High Performance Distributed Syst Res Grp Amsterdam Netherlands

The use of parallel and distributed computing systems is essential to meet the ever-increasing computational demands of many scientific and industrial applications. Ibis allows easy programming and deployment of compu... 详细信息

关键词： distributed programming distributed systems Ibis Java Scientific computing Systems engineering computational demands distributed computing systems industrial applications parallel computing systems parallel programming real-world distributed computer scientific applications

来源：评论

学校读者我要写书评

暂无评论

TERMINATION DETECTION FOR distributed COMPUTATIONS

引用

INFORMATION PROCESSING LETTERS 1984年第1期18卷 33-36页

作者： TOPOR, RW Department of Computer Science University of Melbourne Parkville Victoria 3052 Australia

An important problem in distributed programming is identifying the termination of a distributed computation in which a main computation process signals other processes to become active. Once all processes have become idle, the computation is terminated. An effective detection procedure requires: 1. that processes be modified independently of their definitions, 2. that the procedure does not delay the main computation, and 3. that no new communication channels be established between processes. A termination detection algorithm for distributed computations is presented to satisfy these requirements. With the algorithm, signals are generated throughout the spanning tree, initially inward from leaves to root; then, if termination is not detected, signals are generated outward from root to leaves. This process is repeated until termination is detected.

关键词： distributed computation distributed programming concurrency CSP termination detection program derivation

来源：评论

学校读者我要写书评

暂无评论

COM+: The evolution of component services

引用

COMPUTER 1999年第7期32卷 104-106页

作者： Eddon, G Learning Tree Int Los Angeles CA 90045 USA

COM+ encompasses two areas: a fundamental programming architecture for building software components (first defined by the original COM specification) and an integrated suite of component services replete with an associated runtime environment. For many developers, however, the fundamental COM model is insufficient. In the typical corporation, developers build business components that operate as part of a larger application. Developers expend a great deal of effort to build even the simplest of components. They must also create a robust and secure framework for it and ensure that only clients with the proper authorization can perform certain privileged operations using the component. The problem with the bare-bones component model is that developers are left to implement an enormous amount of functionality that has little to do with the goals of the application itself. To reduce the amount of work required to build a complex distributed application, Microsoft developed the Microsoft Transaction Server (MTS), the first Windows-based implementation of a runtime environment to provide component services. These component services operate within a general set of tools and technologies that, together with COM+, form what Microsoft calls the distributed Internet Applications (DNA) architecture

关键词： COM+ distributed Internet Applications architecture Microsoft Transaction Server Windows-based runtime environment business components business data processing client-server systems complex distributed application building distributed object management distributed programming integrated component services suite programming architecture runtime environment software component building software reusability

来源：评论

学校读者我要写书评

暂无评论

Pengines: Web Logic programming Made Easy

引用

THEORY AND PRACTICE OF LOGIC programming 2014年第4-5期14卷 539-552页

作者： Lager, Torbjorn Wielemaker, Jan Gothenburg Univ S-41124 Gothenburg Sweden Vrije Univ Amsterdam Amsterdam Netherlands

When developing a (web) interface for a deductive database, functionality required by the client is provided by means of HTTP handlers that wrap the logical data access predicates. These handlers are responsible for converting between client and server data representations and typically include options for paginating results. Designing the web accessible API is difficult because it is hard to predict the exact requirements of clients. Pengines changes this picture. The client provides a Prolog program that selects the required data by accessing the logical API of the server. The pengine infrastructure provides general mechanisms for converting Prolog data and handling Prolog non-determinism. The Pengines library is small (2000 lines Prolog, 150 lines JavaScript). It greatly simplifies defining an AJAX based client for a Prolog program and provides non-deterministic RPC between Prolog processes as well as interaction with Prolog engines similar to Paul Tarau's engines. Pengines are available as a standard package for SWI-Prolog 7.(1)

关键词： web programming query languages agent programming distributed programming

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：