检索结果-内蒙古大学图书馆

A CLIENT-SERVER APPROACH FOR distributed FINITE-ELEMENT ANALYSIS

ADVANCES IN ENGINEERING SOFTWARE 1993年第2期17卷 69-78页

作者： SHARMA, SK BAUGH, JW CHADHA, HS N CAROLINA STATE UNIV DEPT CIVIL ENGN RALEIGH NC 27695 USA

The prevalence of local area networks has made the combined processing power of interconnected workstations a compelling alternative to mainframe computers for computer-intensive analyses. We describe a methodology for developing finite element algorithms that distributes workload over an arbitrary number of network-connected computers. The approach employs a client server model in which conventional Unix processes execute concurrently on a number of workstations and exchange information by sending messages over an Ethernet. The simplicity and flexibility of the model sets it apart from other approaches for distributed programming. Our approach shows impressive overall speedup for finite element analysis, even for small problem sizes.

关键词： distributed programming SOFTWARE ARCHITECTURES COMPUTER NETWORKS FINITE ELEMENT ANALYSIS

来源：评论

学校读者我要写书评

暂无评论

The urbanet revolution: Sensor power to the people!

引用

IEEE PERVASIVE COMPUTING 2007年第2期6卷 41-49页

作者： Riva, Oriana Borcea, Cristian Helsinki Inst Informat Technol Helsinki Finland New Jersey Inst Technol Newark NJ 07102 USA

With mobile devices becoming ubiquitous, the time is ripe to bring sensor data out of close-loop networks into the center of daily urban life.

关键词： Mobile Computing Mobile Applications Ubiquitous Computing distributed Systems distributed programming Sensor Networks

来源：评论

学校读者我要写书评

暂无评论

MACLP: multi agent constraint logic programming

引用

INFORMATION SCIENCES 2002年第1-4期144卷 127-142页

作者： Vlahavas, I Aristotle Univ Thessaloniki Dept Informat GR-54006 Thessaloniki Greece

Multi Agent Systems (MAS) have become the key technology for decomposing complex problems in order to solve them more efficiently, or for problems distributed in nature. However, many industrial applications besides their distributed nature, also involve a large number of parameters and constraints among them, i.e. they are combinatorial. Solving such particularly hard problems efficiently requires programming tools that combine MAS technology with a programming schema that facilitates the modeling and solution of constraints. This paper presents MACLP (Multi Agent Constraint Logic programming), a logic-programming platform for building, in a declarative way, multi agent systems with constraint-solving capabilities. MACLP extends CSPCONS, a logic programming system that permits distributed program execution through communicating sequential Prolog processes with constraints, by providing all the necessary facilities for communication between agents. These facilities abstract from the programmer all the low-level details of the communication and allow him to focus on the development of the agent itself. (C) 2002 Elsevier Science Inc. All rights reserved.

关键词： multi agent systems prolog constraint logic programming distributed programming

来源：评论

学校读者我要写书评

暂无评论

Toward Efficient and Simplified distributed Data Intensive Computing

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2011年第6期22卷 974-984页

作者： Gu, Yunhong Grossman, Robert Univ Illinois Lab Adv Comp Chicago IL 60607 USA Open Data Grp Chicago IL 60607 USA

While the capability of computing systems has been increasing at Moore's Law, the amount of digital data has been increasing even faster. There is a growing need for systems that can manage and analyze very large data sets, preferably on shared-nothing commodity systems due to their low expense. In this paper, we describe the design and implementation of a distributed file system called Sector and an associated programming framework called Sphere that processes the data managed by Sector in parallel. Sphere is designed so that the processing of data can be done in place over the data whenever possible. Sometimes, this is called data locality. We describe the directives Sphere supports to improve data locality. In our experimental studies, the Sector/Sphere system has consistently performed about 2-4 times faster than Hadoop, the most popular system for processing very large data sets.

关键词： distributed programming distributed file systems performance frameworks

来源：评论

学校读者我要写书评

暂无评论

PySy: a Python package for enhanced concurrent programming

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2014年第2期26卷 309-335页

作者： Williamson, Todd Olsson, Ronald A. Univ Calif Davis Dept Comp Sci Davis CA 95616 USA

Over the last decade, the popularity of Python has increased considerably. Python is widely used and has been demonstrated to be effective over many problem domains including scripting, prototyping, and simulation. Python's easy to use and concise syntax is highly expressive and allows a developer to create considerably shorter and easier to understand programs than semantically equivalent programs written in languages like C, C++, or Java. An important aspect of any language's flexibility is a highly parallelizable environment that allows its users to write concurrent programs. However, Python is still lacking a high-level, expressive concurrent and distributed programming environment. This paper presents our experience creating PySy, a Python package (on the basis of the SR and JR concurrent programming languages), which provides an easy to use and expressive concurrent environment and allows for the distributed sharing of resources. This paper discusses our design decisions, describes our implementation, and shows qualitative and quantitative analyses of well-known concurrent programs written in PySy. Overall, PySy is reasonable to use for expressing the more common programming scenarios, while it provides acceptable performance. Copyright (c) 2012 John Wiley & Sons, Ltd.

关键词： Python concurrency distributed programming

来源：评论

学校读者我要写书评

暂无评论

Behavioral specification of distributed software component interfaces

引用

COMPUTER 1999年第7期32卷 46-+页

作者： Della Torre, C Rotenstreich, S George Washington Univ Dept Comp Sci & Elect Engn Washington DC 20052 USA

Networked computers are finding their way into a broader range of environments, from corporate offices to schools, homes, and shirt pockets. This new computing model fosters the development of distributed software components that communicate with one another across the underlying networked infrastructure. A distributed software component can be plugged into distributed applications that may not have existed when it was created. The intention is that many developers will reuse distributed software components to build new systems. An interface definition language usually is used to describe a distributed software component's interface. However, a notable limitation of current IDLs is that they generally only describe the names and type signatures of the component's attributes and operations. Current IDLs don't formally specify the behavior of the software component's operations. To help solve these problems, the authors have developed Biscotti (behavioral specification of distributed software component interfaces), a Java extension that enhances Java remote method invocation interfaces with Eiffel-style preconditions, postconditions, and invariants.

关键词： Biscotti Eiffel-style invariants Eiffel-style postconditions Eiffel-style preconditions Java Java extension Java remote method invocation interfaces application program interfaces behavioral specification distributed applications distributed programming distributed software component interfaces distributed software component reuse formal specification networked computers object-oriented programming remote procedure calls software reusability

来源：评论

学校读者我要写书评

暂无评论

Joust: A platform for liquid software

引用

COMPUTER 1999年第4期32卷 50-+页

作者： Hartman, JJ Bigot, PA Bridges, P Montz, B Piltz, R Spatscheck, O Proebsting, TA Peterson, LL Bavier, A Univ Arizona Dept Comp Sci Tucson AZ 85721 USA Microsoft Res Programming Language Syst Grp Redmond WA 98052 USA Princeton Univ Dept Comp Sci Tech Staff Princeton NJ 08544 USA

Computer network research has recently focused on the feasibility of running mobile code on the intermediate nodes that forward packets through a network. A network that exploits mobile code in this way is called an active network because the network's packet delivery service is programmable, rather than fixed. Active networking is just one example of a class of systems that exploit liquid software-low-level, communication-oriented code that easily flows from machine to machine. This article describes a Java-based platform for liquid software, called Joust, that is specifically designed to support low-level, communication-oriented systems and to avoid the limitations of general-purpose OSs. The authors contrast the platform requirements for communication-oriented liquid software with those of computation-oriented software, identify the limitations of current platforms, and outline the benefits of Joust. They also offer an overview of Scout (the underlying OS upon which Joust is built), its runtime system,and its just-in-time (JIT) compiler.

关键词： Java Java Joust Scout active networks communication-oriented systems computation-oriented software distributed programming just-in-time compiler liquid software mobile code network operating systems operating system program compilers run-time system

来源：评论

学校读者我要写书评

暂无评论

Resolving race conditions in asynchronous partial order scenarios

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2005年第9期31卷 767-784页

作者： Mitchell, B Univ Surrey Dept Comp Surrey GU2 7XH England

Scenario-based requirements specifications are the industry norm for defining communication protocols. However, such scenarios often contain race conditions. A race condition occurs when events are specified to occur in a particular order, but in practice, this order cannot be guaranteed. The paper considers UML/MSC scenarios that can be described with standard partial order theoretic asynchronous behavioral semantics. We define these to be partial order scenarios. The paper proves there is a unique minimal generalization of a partial order scenario that is race free. The paper also proves there is a unique minimal race free refinement of the behavioral semantics of a partial order scenario. Unlike the generalization, the refinement cannot be realized in the form of a partial order scenario, although it can always be embedded in one. The paper also proves the results can be generalized to a subclass of iterative scenarios.

关键词： requirements analysis formal methods distributed programming

来源：评论

学校读者我要写书评

暂无评论

distributed garbage collection algorithms for timestamped data

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2006年第10期17卷 1057-1071页

作者： Ramachandran, Umakishore Knobe, Kathleen Harel, Nissim Mandviwala, Hasnain A. Georgia Inst Technol Coll Comp Atlanta GA 30332 USA Intel Micropro Technol Labs Cambridge Ctr 1 Cambridge MA 02142 USA

There is an important class of interactive multimedia applications that deals with stream data from distributed sources. Indexing the data temporally facilitates ordering individual streams as well as correlating items from different streams. The Stampede programming system organizes stream data into channels that are distributed and synchronized data structures that contain timestamped items. A Stampede program is a data flow graph of threads and channels. Stampede semantics for channels allow concurrent access from multiple threads for input and output. While a channel holds timestamped items, the semantics do not place any restriction on either the production or consumption order of these items. Furthermore, timestamps of items in a channel need not be contiguous. These flexibilities are required due to the dynamic and parallel structure of stream- oriented applications targeted by the Stampede system. Under such circumstances, a key issue is the "garbage collection" (GC) of channel items. In this paper, we present and compare three different GC algorithms: 1) REF is a simple algorithm that keeps a reference count on individual items;2) TGC is a distributed algorithm for computing a global low watermark for timestamp values of interest in the entire application;3) DGC is another distributed algorithm that uses information about the dependencies between the producers and consumers of data streams to compute a low water mark local to each node of the data flow graph. DGC can simultaneously eliminate garbage from channels and unneeded computations from threads. In tests performed using an interactive application, DGC enjoys nearly 30 percent reduction in the application memory footprint compared to TGC and REF. DGC and REF are also shown to be more scalable compared to TGC.

关键词： garbage collection distributed programming logical timestamps virtual time soft real-time systems performance evaluation cluster computing multimedia systems ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

A WEAKEST PRECONDITION SEMANTICS FOR COMMUNICATING PROCESSES

引用

THEORETICAL COMPUTER SCIENCE 1984年第3期29卷 231-250页

作者： ELRAD, T FRANCEZ, N IBM CORP THOMAS J WATSON RES CTRYORKTOWN HTSNY 10598

A weakest precondition semantics for communicating processes is presented, based on a centralized, one-level approach. Semantic equations are given for the CSP constructs and their continuity is proved. The equivalence of two weakest precondition definitions, one with certain order preferences, and another one, preference-free, is shown. The representation of various operational concepts, including delay, is discussed. Several examples of applying the rules are given.

关键词： Weakest precondition semantics communicating processes distributed programming nondeterminism termination deadlock

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：