检索结果-内蒙古大学图书馆

International Conference on High Performance Computing

作者： Xin-Min Tian S. Nemawarkar G.R. Gao H. Hum O. Maquelin A. Sodan K. Theobald IBM Toronto Software Laboratory Toronto Canada Department of Electrical Engineering McGill University Montreal Canada School of Computer Science McGill University Montreal Canada Intel Corporation Portland USA GMD FIRST Research Center Berlin Germany

Multithreading has been promoted as an effective mechanism to hide inter-processor communications and remote data access latencies by quickly switching among a set of ready threads. In this paper, we show that multitreading provides an immunity to the performance variations due to changes in data distributions in a distributed-memory multiprocessor. First, toe propose two performance metrics to quantify the sensitivity of performance to data-locality. Second, we perform a quantitative comparison of data-locality sensitivity with both single-threaded and multithreaded computations. These experiments are performed on a 20-node EARTH-MANNA system. Our results show that not only does a multithreaded computation yields higher performance than the single-threaded version, but also that its performance is more robust (less affected) by variations in data-locality.

关键词： Earth Yarn Multithreading Delay Distributed computing High performance computing computer architecture Communication switching Benchmark testing Laboratories

来源：评论

学校读者我要写书评

暂无评论

Data and information architectures for large-scale distributed data intensive information systems

Data and information architectures for large-scale distribut...

引用

International Working Conference on Scientific and Statistical Database Management

作者： L. Kerschberg H. Gomaa D. Menasce Jong Pil Yoon Center for Information Systems Integration and Evolution George Mason University Fairfax VA USA Department of Information and Software Systems Engineering George Mason University Fairfax VA USA Department of Computer Science George Mason University Fairfax VA USA Sookmyung Woman's University South Korea

The Earth Observing System (EOS) Data and Information System (EOSDIS) is perhaps one of the most important examples of large-scale, geographically distributed, and data intensive systems. The paper presents various facets of a data and information architecture for EOSDIS. EOS data is organized by means of an object-oriented schema, while EOS knowledge is organized through multiple domain-specific thesauri, complemented by domain knowledge and rules. The information holdings are organized into the source data archives, a data warehouse which provides an integrated view of the information holdings, and information marts which generate value-added information products for specialized user communities. Finally a federated client-server architecture is proposed to allow non-EOSDIS systems to become members of the EOSDIS community, allowing them to access EOSDIS holdings, and sharing their own data with EOSDIS.

关键词： Large-scale systems Information systems Earth Observing System Satellites computer architecture NASA Large scale integration Planets Instruments Atmosphere

来源：评论

学校读者我要写书评

暂无评论

A model for decision maintenance in the WinWin collaboration framework

A model for decision maintenance in the WinWin collaboration...

引用

Knowledge-Based software engineering Conference

作者： P. Bose Center for Software Engineering Department of Computer Science University of Southern California USA

Cost-effective engineering and evolution of complex software must involve the different stakeholders concurrently and collaboratively. The hard problem is providing computer support for such collaborative activities. The WinWin approach being developed and experimented at the USC center for software engineering provides a domain independent solution for the stakeholders to cooperate in the requirements engineering phase of the software lifecycle. A major problem confronted in the WinWin framework is aiding decision coordination-coordinating the decision making activities of the stakeholders. A key element in supporting decision coordination is decision maintenance. As decisions undergo evolution, the effects of such changes on existing decision elements must be determined and the decision structure appropriately revised. The paper presents an approach to addressing the problem of supporting decision maintenance. The key ideas involve a) defining an extended ontology for decision rationale, that models the WinWin decision space and their states, b) formally describing a theory based on that ontology that specify conditions for states to hold, and c) defining an agent that utilizes the theory to determine revisions and coordinate with other agents to propagate revisions in a distributed support framework.

关键词： Collaboration Collaborative software software engineering Decision making Ontologies Concurrent engineering computer science software design software maintenance Contracts

来源：评论

学校读者我要写书评

暂无评论

Humans and process frameworks: some critical process elements

Humans and process frameworks: some critical process element...

引用

International Workshop on software Process

作者： B. Boehm P. Bose USC Center for Software Engineering Department of Computer Science University of Southern California USA

Successful engineering of complex software systems require humans to engage collaboratively in multiple critical process elements. This paper identifies those necessary process elements and defines WinWin, a collaborative process model that addresses the process elements. It briefly describes a process support system for the WinWin model.

关键词： Humans Spirals Collaboration Collaborative software Chemical elements software engineering computer science Calendars Joining processes Monitoring

来源：评论

学校读者我要写书评

暂无评论

A performance oriented design methodology for large-scale distributed data intensive information systems

A performance oriented design methodology for large-scale di...

引用

IEEE International Conference on engineering of Complex computer Systems

作者： D.A. Menasce H. Gomaa L. Kerschberg Department of Computer Science Center of the New Engineer USA Department of Information and Software Systems Engineering Center for Information Systems Integration and Evolution George Mason University Fairfax VA USA

The Earth Observing System (EOS) Data and Information System (EOSDIS) is perhaps one of the most important examples of a large-scale, geographically distributed, and data-intensive systems. Designing such systems in a way that ensures that the resulting design will satisfy all functional and performance requirements is not a trivial task. This paper presents a performance oriented methodology to design large-scale distributed data intensive information systems. The methodology is then applied to the design of the EOSDIS Core System (ECS). Performance results, based on queueing network models of ECS are also presented.

关键词： Design methodology Large-scale systems Information systems Earth Observing System Large scale integration Data engineering Design engineering Satellites Atmosphere computer science

来源：评论

学校读者我要写书评

暂无评论

Critical success factors for knowledge-based software engineering applications

Critical success factors for knowledge-based software engine...

引用

Knowledge-Based software engineering Conference

作者： B. Boehm P. Bose Department of Computer Science USC Center슠for슠Software Engineering USA

A key problem in KBSE is evaluating the utility of KBSA tools. This paper analyzes the utility of ten KBSA prototype applications that were developed as part of an advanced course. Based on this analysis, we hypothesis three new critical success factors for explaining their utility. The factors identify key elements of KBSA tools that contribute towards their utility.< >

关键词： software engineering Application software software prototyping Context modeling Prototypes Guidelines Expert systems Job shop scheduling Robustness computer science

来源：评论

学校读者我要写书评

暂无评论

A collaborative spiral software process model based on Theory W

A collaborative spiral software process model based on Theor...

引用

International Conference on the software Process

作者： B. Boehm P. Bose USC Center for Software Engineering Computer Science Department University of Southern California USA

A primary difficulty in applying the spiral model has been the lack of explicit process guidance in determining the prospective system's objectives, constraints, and alternatives that get elaborated in each cycle. This paper presents an extension of the spiral model, called the Next Generation Process Model (NGPM), which uses the Theory W(win-win) approach (Boehm-Ross, 1989) to converge on a system's next-level objectives, constraints, and alternatives. The refined Spiral Model explicitly addresses the need for concurrent analysis, risk resolution definition, and elaboration of both the software product and the software process in a collaborative manner. This paper also describes some of the key elements of the support system developed based on the model and refined through experiments with it. It reports on experiences in applying NGPM to a large department of Defense program.< >

关键词： Collaborative software Spirals Constraint theory Risk analysis Collaborative work software engineering Collaboration software maintenance computer science Programming

来源：评论

学校读者我要写书评

暂无评论

software technology risk advisor

Software technology risk advisor

引用

Knowledge-Based software engineering Conference

作者： G.A. Toth USC Center For Software Engineering Department of Computer Science University of Southern California Los Angeles CA USA Electronics Systems Division Northrop Grumman Corporation Hawthorne CA USA

This paper describes the software Technology Risk Advisor (STRA), a knowledge-based software engineering tool that provides assistance in identifying and managing software technology risks. The STRA contains a knowledge base of software product and process needs, satisfying capabilities and capability maturity factors. After a user ranks the importance of relevant needs to his or her project, the STRA automatically infers risk areas by evaluating disparities between project needs and technology maturities. Identified risks are quantitatively prioritized and the user is given risk reduction advice and rationale for each conclusion. This paper presents methods used in the STRA, along with discussions of knowledge acquisition experimental results, current status, and related work.< >

关键词： Risk management software tools software engineering Knowledge management Programming Technology management Expert systems Application software computer science engineering management

来源：评论

学校读者我要写书评

暂无评论

A standard simulation environment: a review of preliminary requirements 94

A standard simulation environment: a review of preliminary r...

引用

Simulation Winter Conference

作者： M.A.F. Wagner S. Sevinc O. Tanir P.L. Haigh J.D. Arthur R.E. Nance H.D. Schwetman SysTech Software Solutions Annandale VA USA Knowledge Systems Group Basser University of Sydney Australia Quality Engineering and Research (QER) Group Longueuil QUE Canada High Performance Software Inc. Dayton OH USA Systems Research Center Department of Computer Science Virginia Polytechnic Institute and State University Blacksburg VA USA Mesquite Software Inc. Austin TX USA

ISBN: (纸本)9780780321090

The concept of a simulation environment combines different aspects of the simulation process into one complete powerful tool. The environment should provide the necessary state-of-the-art advances and concepts that a modeler may require during the simulation development and execution process. The "environment" requirements must address the end user needs while minimizing the necessity of learning a new language. The requirements must specify the useful features, independent of different platforms and implementation languages. Hence the opportunity exists for standardization of environments. The paper opens a discussion on challenges and rewards awaiting the simulation community with the advent of a standard environment.

关键词： Power system modeling Computational modeling computer simulation Standardization Knowledge based systems Australia Knowledge engineering software performance Drives computer science

来源：评论

学校读者我要写书评

暂无评论

Comments on "Temporal logic-based deadlock analysis for Ada" by G.M. Karam and R.J.A. Burh

引用

IEEE Transactions on software engineering 1993年第2期19卷 198-199页

作者： M. Young D.L. Levine R.N. Taylor Software Engineering Research Center Department of Computer Science Purdue University West Lafayette IN USA Department of Information and Computer Science University of California Irvine CA USA

The commenters discuss several flaws they found in the above-titled paper by G.M. Koran and R.J.A. Burh (see ibid., vol.17, no.10, p.109-1125, (1991)). The commenters argue that the characterization of operational and axiomatic proof method is modified and inaccurate; the classification of modeling techniques for concurrent systems confuses the distinction between state-based and event-based models with the essential distinction between explicit enumeration of behaviors and symbolic manipulation of properties; the statements about the limitations of linear-time temporal logic in relation to nondeterminism are inaccurate; and the characterization of the computational complexity of the analysis technique is overly optimistic.< >

关键词： System recovery Logic Computational complexity computer science Interleaved codes Testing Heart software engineering Safety Reachability analysis

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：