检索结果-内蒙古大学图书馆

34th Aerospace sciences Meeting and Exhibit, 1996

作者： McHugh, P.R. Knoll, D.A. Keyes, D.E. Idaho National Engineering Laboratory P.O. Box 1625 Idaho FallsID83415-3808 United States Institute for Computer Applications in Science and Engineering NASA-LaRC HamptonVA23681-0001 United States Department of Computer Science Old Dominion University NorfolkVA23529-0162 United States

Newton-Krylov-Schwarz algorithms solve a system of equations describing low Mach number combustion. Two model problems are considered. The first is a low speed, combusting flow through a channel, representing an idealized laminar diffusion flame. The second problem consists of an expansion channel, representing an idealized combustion chamber. Both problems include three chemical species and one kinetic reaction. Finite-volume discretization on a staggered mesh converts the continuous system of governing equations into a discrete system of nonlinear algebraic equations, which are subsequently linearized using Newton's method. The resulting linearized systems are solved using the preconditioned Generalized Minimal RESidual (GMRES) algorithm. The effectiveness of domainbased additive and multiplicative Schwarz preconditioned is studied with respect to partitioning strategy and subdomain solver selection. Block incomplete factorizations of the subdomain matrices yield effective Schwarz preconditioners with comparatively moderate computer memory requirements. In comparison, point-wise incomplete factorizations are unreliable at low Mach numbers, while complete factorizations often require excessive computer memory. Multiplicative Schwarz preconditioning outperforms additive Schwarz, but not sufficiently so to outweigh the parallel advantages of additive Schwarz. Preconditionng with a low-order discretization reduces both computer memory and CPU time for the Reynolds number of interest. © 1995 by the American institute of Aeronautics and Astronautics, Inc.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Analysis of algorithmic structures with heterogeneous tasks

Analysis of algorithmic structures with heterogeneous tasks

引用

International Phoenix Conference on computers and Communications (IPCCC)

作者： L.F. Wilson Institute for Computer Applications in Science and Engineering NASA-Langley Research Center Hampton VA USA

Developing efficient programs for distributed systems is difficult because computations must be efficiently distributed and managed on multiple processors. In particular, the programmer must partition functions and data in an attempt to find a reasonable balance between parallelism and overhead. Furthermore, it is very expensive to code an algorithm only to find out that the implementation is not efficient. As a result, it is often necessary to determine and examine those characteristics of an algorithm that can be used to predict its suitability for a distributed computing system. In earlier work (Wilson, 1994 and Wilson and Gonzalez, 1994), we presented a framework for the study of synchronization and communication effects on the theoretical performance of common homogeneous algorithmic structures. In particular, we examined the synchronous, asynchronous, nearest-neighbor, and asynchronous master-slave structures in terms of expected execution times. In this paper, we examine the effects of synchronization and communication on the expected execution times of heterogeneous algorithmic structures. Specifically, we consider structures containing two different types of tasks, where the execution times of the tasks follow one of two different uniform distributions or one of two different normal distributions. Furthermore, we compare the expected execution times of the heterogeneous algorithmic structures with times for corresponding homogeneous structures. Finally, we develop bounds for the expected execution times of the heterogeneous structures and compare those bounds to simulated execution times.

关键词： Algorithm design and analysis Master-slave NASA computer applications Distributed computing Partitioning algorithms Concurrent computing Postal services Programming profession Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Towards a thread-based parallel direct execution simulator

Towards a thread-based parallel direct execution simulator

引用

Annual Hawaii International Conference on System sciences (HICSS)

作者： P. Dickens M. Haines P. Mehrotra D. Nicol Institute For Computer Applications in Science and Engineering NASA-Langley Research Center Hampton VA USA Department of Computer Science College of William and Mary VA USA

Parallel direct execution simulation is an important tool for performance and scalability analysis of large message passing parallel programs executing on top of a virtual computer. However, detailed simulation of message-passing codes requires a great deal of computation. We are therefore interested in pursuing implementation techniques which can decrease this cost. One idea is to implement the application virtual processes as lightweight threads rather than traditional Unix processes, reducing both on-processor communication costs and context switching costs. We describe an initial implementation of a thread-based parallel direct execution simulator. We discuss the advantages of such an approach and present preliminary results that indicate a significant improvement over the process-based approach.

关键词： Computational modeling Costs Analytical models computer simulation Scalability Performance analysis Message passing Concurrent computing Application software Yarn

来源：评论

学校读者我要写书评

暂无评论

Experiments in Automated Load Balancing

Experiments in Automated Load Balancing

引用

Workshop on Principles of Advanced and Distributed Simulation (PADS)

作者： L.F. Wilson D.M. Nicol Institute for Computer Applications in Science and Engineering NASA-Langley Research Center Hampton VA USA Department of Computer Science The College of William and Mary Williamsburg VA USA

来源：评论

学校读者我要写书评

暂无评论

Structural analysis and implementation of two distributed algorithms

Structural analysis and implementation of two distributed al...

引用

International Phoenix Conference on computers and Communications (IPCCC)

作者： L.F. Wilson M.J. Gonzalez Institute for Computer Applications in Science and Engineering NASA-Langley Research Center Hampton VA USA Computer Engineering Research Center University of Texas Austin Austin TX USA

In earlier work, we examined the theoretical effects of synchronization and communication on execution times for different categories of algorithmic structures. The paper demonstrates how two candidate problems for distributed systems can be represented by different algorithmic structures. Specifically, we examine different representations of a partial differential equation (PDE) solver and the travelling salesman problem (TSP). Furthermore, we present results from execution of the algorithms on the Pleiades/ESP System and the Intel Paragon. Using the results from problems executed on real systems, we confirm that our theoretical framework for obtaining bounds on execution time can be used to accurately estimate the performance of a distributed algorithm.

关键词： Algorithm design and analysis Distributed algorithms Concurrent computing Partitioning algorithms computer applications NASA Master-slave Postal services Microwave integrated circuits Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Experiments in automated load balancing 96

Experiments in automated load balancing

引用

Proceedings of the tenth workshop on Parallel and distributed simulation

作者： Linda F. Wilson David M. Nicol Institute for Computer Applications Science and Engineering NASA Langley Research Center Hampton VA Department of Computer Science The College of William and Mary P.O. Box 8795 Williamsburg VA

ISBN: (纸本)9780818675393

One of the promises of parallelized discrete-event simulation is that it might provide significant speedups over sequential simulation. In reality, high performance cannot be achieved unless the system is fine-tuned to balance computation, communication, and synchronization requirements. In this paper, we discuss our experiments in automated load balancing using the SPEEDES simulation framework. Specifically, we examine three mapping algorithms that use run-time measurements. Using simulation models of queuing networks and the National Airspace System, we investigate (i) the use of run-time data to guide mapping, (ii) the utility of considering communication costs in a mapping algorithm, (iii) the degree to which computational ``hot-spots'' ought to be broken up in the linearization, and (iv) the relative execution costs of the different algorithms. We compare the performance of the three algorithms using results from the Intel Paragon.

关键词： load balancing discrete-event simulation parallel computing performance analysis

来源：评论

学校读者我要写书评

暂无评论

On computing sound radiation of a temporally evolving mixing layer by vortex method and matched asymptotic expansions 34th

On computing sound radiation of a temporally evolving mixing...

引用

34th Aerospace sciences Meeting and Exhibit, 1996

作者： Hu, F.Q. Martin, J.E. Hussaini, M.Y. Department of Mathematics and Statistics Old Dominion University NorfolkVA23529 United States Department of Mathematics Christopher Newport University Newport NewsVA23606 United States Institute for Computer Applications in Science and Engineering NASA Langley Research Center HamptonVA23681 United States

In this paper, sound radiation associated with a temporally evolving mixing layer is considered. Numerical simulations are carried out by a vortex method in which the mixing layer is modeled by an array of vortex blobs and perturbed with the wavelength of the most amplified wave. Since the vortex method computes an incompressible flow, a methodology of computing the acoustic field based on matched asymptotic expansions is employed. A singular perturbation is developed in which the incompressible solution obtained by the vortex method is the inner solution while the acoustic field is the outer solution. The formal matching process is carried out by introducing intermediate variables. It is shown that in the limit of zero Mach number, the leading terms match smoothly. The inner solution of the incompressible flow..thus provides the boundary condition for the outer solution of radiated sound. Numerical results of the vortex simulation and computed acoustic pressure are presented. © 1996 by the American institute of Aeronautics and Astronautics, Inc. All Rights Reserved.

关键词： Acoustic fields

来源：评论

学校读者我要写书评

暂无评论

3D shock wave visualization on unstructured grids

3D shock wave visualization on unstructured grids

引用

IEEE Symposium on Volume Visualization and Graphics

作者： Kwan-Liu Ma J. Van Rosendale W. Vermeer Institute for Computer Applications in Science and Engineering(ICASE) NASA-Langley Research Center Hampton VA USA NASA Langley Research Center Hampton VA US Department of Applied Mathematics and Informatics Delft University of Technnology Delft Netherlands

A critical issue in understanding high speed flows is the study of shock waves. The paper summarizes our research on techniques for the detection and visualization of shock waves occuring in simulations of three dimensional flows on unstructured grids. Detection algorithms based on Mach number, density gradient and directional derivatives are compared using a data set from calculations of a transonic flow with a weak double shock around an airfoil. Both surface and volume rendering techniques are used to display the shocks. The issues in this research area are very much like those occurring in medical imaging. Since the data themselves (in this case the results of the fluid dynamics simulation) are intrinsically low resolution and noisy, properly extracting and visualizing the shock is very difficult. In this environment, blurry, low resolution techniques, like the splatting volume rendering, seem to do rather well. More complex schemes, using sophisticated numerical shock detectors coupled with polygon rendering, produce visually sharper shocks, but also introduce "graphics artifacts," which complicate understanding of the flow physics. On the other hand, visualization results produced with techniques like splatting are, in effect, relying more on the human visual system to compensate for limited resolution in the simulation.

关键词： Shock waves Electric shock Data visualization Detection algorithms Automotive components Displays Biomedical imaging Fluid dynamics Medical simulation Working environment noise

来源：评论

学校读者我要写书评

暂无评论

Coordinated fuzzy logic control between SVC and PSS to enhance stability of power systems

引用

ELECTRICAL engineering IN JAPAN 1996年第1期116卷 43-54页

作者： Kihara, H Hiyama, T Miyauchi, H Ortmeyer, TH Kumamoto University B.E. and M.S. degrees in Electrical Engineering from Kumamoto University in 1986 and 1988 respectively and is currently in the doctoral program at the university. In 1988 he joined Kyushu Electric Power Co. and is working in the Research Division. B.E. M.S. and Ph.D. degrees in Electrical Engineering from Kyoto University Japan in 1969 1971 and 1980 respectively. He joined Kumamoto University in 1971 and he has been a Professor of Electrical Engineering and Computer Science since 1989. During the period of June 1985 through September 1986 he was at Clarkson University and was involved with power system harmonics research. His current interests include intelligent control of electric power systems using fuzzy logic control scheme and neural network measurement and real time control of photovoltaic systems and harmonic analysis in distribution systems. He is a senior member of IEEE SICE of Japan and Japan Solar Energy Society. B.E. M.S. and Ph.D. degrees in Electrical Engineering from Kyoto University in 1981 1983 and 1991 respectively. He joined Kyoto University in 1985. Since 1993 he has been at Kumamoto University and currently is an Associate Professor of Electrical Engineering and Computer Science. His current interests include stabilizing control of electric power system and applications of the Superconducting Magnetic Energy Storage (SMES) to electric power systems. He is a member of IEEE and Institute of Systems Control and Information Engineers of Japan. B.S.E.E. degree in 1972 his M.S.E.E. degree in 1977 and Ph.D. degree in 1980 all from Iowa State University. From 1972 to 1976 he worked in the Operational Analysis Department Commonwealth Edison Company Chicago Illinois. Since 1979 he has been at Clarkson University Potsdam N.Y. where he is a Professor of Electrical Engineering. During the period of July 1993 to June 1994 he was also a Visiting Professor at Kumamoto University Kumamoto Japan. His current interests include harmonic performance po

This paper presents a new switching control scheme for static var compensator (SVC) using fuzzy logic control rules to enhance the overall stability of electric power systems. In addition, the coordination with power system stabilizers (PSS) is also considered to achieve a wider stable region. An SVC is set on one of the busbars in the transmission system, where the real power flow signal is utilized at the location of the SVC to determine the firing angle of the thyristor switch. The switching control scheme is simple so as not to require heavy computation on the microcomputer based switching controller. The PSSs are also set on the generators in the study system. Simulation results show the effectiveness of the proposed fuzzy logic switching control scheme for the SVC. The coordination between SVC and PSS is also effective to enlarge the stable region.

关键词： fuzzy logic control scheme real time control SVC PSS FACTS

来源：评论

学校读者我要写书评

暂无评论

ON THE SPLINE-BASED WAVELET DIFFERENTIATION MATRIX

引用

APPLIED NUMERICAL MATHEMATICS 1995年第1期17卷 33-45页

作者： JAMESON, L Institute for Computer Applications in Science and Engineering NASA Langley Research Center Hampton VA 23681 USA

The differentiation matrix for a spline-based wavelet basis without decomposition at multiple scales is constructed. It is shown that regardless of the properties that one imposes on a spline basis, the differentiation matrix is always the one encountered when the basis is simply the B-spline basis. The order of accuracy of this differentiation matrix is shown to display superconvergence. Furthermore, it is shown that spline-based bases generate a class of compact finite difference schemes. With this knowledge boundary conditions of the proper order of accuracy can be imposed.

关键词： WAVELET APPROXIMATION DIFFERENTIATION MATRIX SUPERCONVERGENCE COMPACT FINITE DIFFERENCE SCHEMES

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：