检索结果-内蒙古大学图书馆

2010 1st International Workshop on the Web and Requirements engineering, WeRE 2010 2010年 i-ii页

作者： Garrigós, Irene Mazón, Jose-Norberto Escalona, Maria José Koch, Nora Mylopoulos, John Dept. of Software and Computing Systems University of Alicante Spain Dept. of Computer Languages and Systems University of Seville Spain Programming and Software Engineering Dept. University of Munich Germany Information Engineering and Computer Science Dept. University of Trento Italy

来源：评论

学校读者我要写书评

暂无评论

High-Performance Reverse Time Migration on GPU

High-Performance Reverse Time Migration on GPU

引用

computer Science Society (SCCC) International Conference Chilean FLAGGED

作者： Javier Cabezas Mauricio Araya-Polo Isaac Gelado Nacho Navarro Enric Morancho José M. Cela Computer Sciences - Programming Models Barcelona Supercomputing Center (BSC) Barcelona Spain Computer Applications in Science and Engineering dept. Barcelona Supercomputing Center (BSC) Barcelona Spain Department of Computer Architecture Universitat Politècnica de Catalunya Spain Computer Applications in Science and Engineering Department Barcelona Supercomputing Center Barcelona Spain

Partial Differential Equations (PDE) are the heart of most simulations in many scientific fields, from Fluid Mechanics to Astrophysics. One the most popular mathematical schemes to solve a PDE is Finite Difference (FD). In this work we map a PDE-FD algorithm called Reverse Time Migration to a GPU using CUDA. This seismic imaging (Geophysics) algorithm is widely used in the oil industry. GPUs are natural contenders in the aftermath of the clock race, in particular for High-performance Computing (HPC). Due to GPU characteristics, the parallelism paradigm shifts from the classical threads plus SIMD to Single Program Multiple Data (SPMD). The NVIDIA GTX 280 implementation outperforms homogeneous CPUs up to 9x (Intel Harpertown E5420) and up to 14x (IBM PPC 970). These preliminary results confirm that GPUs are a real option for HPC, from performance to programmability.

关键词： Finite difference methods Geophysics computing computer architecture Parallel processing Graphics processing unit Clocks Hardware Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Robust initialization of differential algebraic equations

Robust initialization of differential algebraic equations

引用

1st International Workshop on Equation-Based Object-Oriented Languages and Tools, EOOLT 2007 - In Conjunction with the ECOOP 2007 Conference

作者： Bachmann, Bernhard Aronsson, Peter Fritzson, Peter Dept. Mathematics and Engineering University of Applied Sciences D-33609 Bielefeld Germany MathCore Engineering AB Teknikringen 1F SE-583 30 Linköping Sweden Department of Computer Science PELAB Programming Environments Lab Linköping University SE-581 83 Linköping Sweden

This paper describes a new solution method applied to the problem initializing DAEs using the Modelica language. Modelica is primarily an object- oriented equ-tion-based modeling language that allows specification of mathematical models of complex natural or man-made systems. Major features of Modelica are the multidomain modeling capability and the reusability of model components corresponding to physical objects, which allow to build and simulate highly complex systems. However, initializing such models has been quite cumbersome, since initial equations have to be pro-vided at the system level, where the user needs to know details on the underlying transformation and index-reduction algorithms, that in general are applied to simulate a Modelica model.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Biochemical mathematical modeling with Modelica and the BioChem library 6

Biochemical mathematical modeling with Modelica and the BioC...

引用

6th International Conference APLIMAT 2007

作者： Fritzson, Peter Ulfhielm, Erik Belic, Ales Fransson, Martin Grèen, Henrik PELAB - Programming Environment Lab. Dept. of Computer and Information Science Linköpings Universitet LinköpingSE-581 83 Sweden Laboratory for Modeling Simulation and Control Faculty of Electrical Engineering University of Ljubljana LjubljanaSI-1000 Slovenia Clinical Pharmacology Dept. of Medicine and Care Linköpings Universitet LinköpingSE-581 85 Sweden

ISBN: (纸本)9788096956265

Considering the large amounts of data that is nowadays produced in the biochemistry (functional genomics) it is difficult to extract the information from the measurements. There is currently also a great interest in the development of novel analytical technologies for rapid screening of disease symptoms in pharmaceutical and clinical applications. Modeling and simulation can provide a useful help in understanding the relations of the measured substances and to minimize the need for measurements. The BioChem library presented here is the first free Modelica library available for mathematical modeling of biochemical processes. Three examples are shown to illustrate the library. First, a simple insulin model is presented. Then a simplified model of cholesterol together with simulations are shown. Next, a simple drug model together with parameter estimation in NONMEN are presented. The BioChem library allows for fast and end-user friendly modeling of biomedical systems. The graphical user interface provides graphics similar to that used in the description of metabolic pathways in biochemistry.

关键词： Cholesterol

来源：评论

学校读者我要写书评

暂无评论

A dynamic compilation framework for controlling microprocessor energy and performance 38

A dynamic compilation framework for controlling microprocess...

引用

MICRO-38: 38th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Wu, Qiang Reddi, V.J. Wu, Youfeng Lee, Jin Connors, Dan Brooks, David Martonosi, Margaret Clark, Douglas W. Depts. of Computer Science Electrical Engjneering Princeton University Dept. of Electrical and Computer Engineering U. of Colorado Boulder Programming Systems Lab. Corporate Tech. Group Intel Corporation Division of Engineering and Applied Science Harvard University

ISBN: (纸本)0769524400

Dynamic voltage and frequency scaling (DVFS) is an effective technique for controlling microprocessor energy and performance. Existing DVFS techniques are primarily based on hardware, OS timeinterrupts, or static-compiler techniques. However, substantially greater gains can be realized when control opportunities are also explored in a dynamic compilation environment. There are several advantages to deploying DVFS and managing energy/performance tradeoffs through the use of a dynamic compiler. Most importantly, dynamic compiler driven DVFS is fine-grained, code-aware, and adaptive to the current microarchitecture environment. This paper presents a design framework of the run-time DVFS optimizer in a general dynamic compilation system. A prototype of the DVFS optimizer is implemented and integrated into an industrialstrength dynamic compilation system. The obtained optimization system is deployed in a real hardware platform that directly measures CPU voltage and current for accurate power and energy readings. Experimental results, based on physical measurements for over 40 SPEC or Olden benchmarks, show that significant energy savings are achieved with little performance degradation. SPEC2K FP benchmarks benefit with energy savings of up to 70% (with 0.5% performance loss). In addition, SPEC2K INT show up to 44% energy savings (with 5% performance loss), SPEC95 FP save up to 64% (with 4.9% performance loss), and Olden save up to 61% (with 4.5% performance loss). On average, the technique leads to an energy delay product (EDP) improvement that is 3X-5X better than static voltage scaling, and is more than 2X (22% vs. 9%) better than the reported DVFS results of prior static compiler work. While the proposed technique is an effective method for microprocessor voltage and frequency control, the design framework and methodology described in this paper have broader potential to address other energy and power issues such as di/dt and thermal control. © 2005 IEEE.

关键词： Microprocessor chips

来源：评论

学校读者我要写书评

暂无评论

Scalable QoS approach in a core internet network

Scalable QoS approach in a core internet network

引用

International Conference on Web engineering, ICWE 2003

作者： Barenco Abbas, Cláudia J. García Villalba, L. Javier Dept. Electric Engineering University of Brasilia Brazil Dept. Computer Systems and Programming Complutense University of Madrid Spain

ISBN: (纸本)9783540450689

A special attention about scalability has to be paid to QoS solutions for Core Internet Networks as they deal with a lot of flows and demand many resources. This paper analyses and proposes integrated solutions from the physical layer (SDH/SONET and DTM) to the IP layer (IntServ and DiffServ), concentrating not only on scalability, but also QoS guarantees. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Why not RSVP over DTM ?

Why not RSVP over DTM ?

引用

International Conference on Web engineering, ICWE 2003

作者： Barenco Abbas, Cláudia J. García Villalba, L. Javier Dept. Electrical Engineering University of Brasilia Brazil Dept. Computer Systems and Programming Complutense University of Madrid Spain

ISBN: (纸本)9783540450689

This paper suggests the use of the DTM technology as a solution to the transmission of applications with strict need of bandwidth, instead of the use of the traditional ATM technology. The DTM is a broadband network architecture based on synchronous fast circuit switching solution with a constant delay, perfect to the telephony network which is optimized for the characteristics of voice communication, that is, fixed-sized channels and provision of QoS real-time guarantees. Furthermore, the users require access to new services like audio, video and data which is discussed in this paper by proposing the IETF IntServ and the DTM integration supporting dynamic allocation of resources in a circuit switching network. An overview of the integration of the IntServ guaranteed service/RSVP protocol with the DTM technology on the signalling, reservation and management of the allocated bandwidth before the DTM channel establishment is presented. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Almost-certain eventualities and abstract probabilities in quantitative temporal logic

Almost-certain eventualities and abstract probabilities in q...

引用

Computing: The Australasian Theory Symposium (CATS 2001)

作者： McIver, Annabelle Morgan, Carroll Programming Research Group University of Oxford Oxford OX1 3QD United Kingdom Dept. of Engineering and Computer Science University of New South Wales Sydney 2052 Australia Dept. of Computing Macquarie University Sydney 2019 Australia

'Almost-certain eventualities' are liveness properties that hold with probability 1. 'Abstract probabilities' are probabilities in transition systems about which we know only that they are neither 0 nor 1. Vardi [17] showed that almost-certain properties in linear temporal logic depend only on abstract probabilities, rather than on the probabilities' precise values;we discuss the extent to which a similar result holds in quantitative temporal logic [9,10], and we show how to specialise the logic to those cases. The aim is to provide a simpler calculus than the full logic, one that is in a certain sense complete for proving almost-certain eventualities from abstract-probabilistic assumptions. We consider briefly the complexity of the specialised logic. © 2001 Published by Elsevier Science B.V.

关键词： Logic programming

来源：评论

学校读者我要写书评

暂无评论

Almost-Certain Eventualities and Abstract Probabilities in Quantitative Temporal Logic

引用

Electronic Notes in Theoretical computer Science 2001年 42卷 12-40页

作者： Annabelle McIver Carroll Morgan Programming Research Group University of Oxford Oxford OX1 3QD UK Dept. of Engineering and Computer Science University of New South Wales Sydney 2019 Australia

‘Almost-certain eventualities’ are liveness properties that hold with probability 1. ‘Abstract probabilities’ are probabilities in transition systems about which we know only that they are neither 0 nor 1. Vardi [17] showed that almost-certain properties in linear temporal logic depend only on abstract probabilities, rather than on the probabilities' precise values; we discuss the extent to which a similar result holds in quantitative temporal logic [9,10], and we show how to specialise the logic to those cases. The aim is to provide a simpler calculus than the full logic, one that is in a certain sense complete for proving almost-certain eventualities from abstract-probabilistic assumptions. We consider briefly the complexity of the specialised logic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Managed Software Evolution 1

引用

1000年

作者： Ralf Reussner Jan Keim Michael Goedicke Wilhelm Hasselbring Birgit Vogel-Heuser Lukas Märtin

ISBN: (数字)9783030134990

ISBN: (纸本)9783030134983;9783030135010

This open access book presents the outcomes of the “Design for Future – Managed Software Evolution” priority program 1593, which was launched by the German Research Foundation (“Deutsche Forschungsgemeinschaft (DFG)”) to develop new approaches to software engineering with a specific focus on long-lived software systems. The different lifecycles of software and hardware platforms lead to interoperability problems in such systems. Instead of separating the development, adaptation and evolution of software and its platforms, as well as aspects like operation, monitoring and maintenance, they should all be integrated into one overarching process.;Accordingly, the book is split into three major parts, the first of which includes an introduction to the nature of software evolution, followed by an overview of the specific challenges and a general introduction to the case studies used in the project. The second part of the book consists of the main chapters on knowledge carrying software, and cover tacit knowledge in software evolution, continuous design decision support, model-based round-trip engineering for software product lines, performance analysis strategies, maintaining security in software evolution, learning from evolution for evolution, and formal verification of evolutionary changes. In turn, the last part of the book presents key findings and spin-offs. The individual chapters there describe various case studies, along with their benefits, deliverables and the respective lessons learned. An overview of future research topics rounds out the coverage.;The book was mainly written for scientific researchers and advanced professionals with an academic background. They will benefit from its comprehensive treatment of various topics related to problems that are now gaining in importance, given the higher costs for maintenance and evolution in comparison to the initial development, and the fact that today, most software is not developed from scratch, but as part of a c

关键词： Software engineering Software Management Management of Computing and Information Systems Theory of Computation

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：