检索结果-内蒙古大学图书馆

A modeling study of the TPC-C benchmark

SIGMOD Record 1993年第2期22卷 22-31页

作者： Leutenegger, Scott T. Dias, Daniel ICASE: Institute for Computer Applications in Science and Engineering Mail Stop 132c Nasa Langley Research Center HamptonVA23681-0001 United States Ibm Research Division T.J. Watson Research Center P.O. Box 704 Yorktown HeightsNY10598 United States

The TPC-C benchmark is a new benchmark approved by the TPC council intended for comparing database platforms running a medium complexity transaction processing workload. Some key aspects in which this new benchmark differs from the TPC-A benchmark are in having several transaction types, some of which are more complex than that in TPC-A, and in having data access skew. In this paper we present results from a modelling study of the TPC-C benchmark for both single node and distributed database management systems. We simulate the TPC-C workload to determine expected buffer miss rates assuming an LRU buffer management policy. These miss rates are then used as inputs to a throughput model. From these models we show the following: (i) We quantify the data access skew as specified in the benchmark and show what fraction of the accesses go to what fraction of the data. (ii) We quantify the resulting buffer hit ratios for each relation as a function of buffer size. (iii) We show that close to linear scale-up (about 3% from the ideal) can be achieved in a distributed system, assuming replication of a read-only table. (iv) We examine the effect of packing hot tuples into pages and show that significant price/performance benefit can be thus achieved. (v) Finally, by coupling the buffer simulations with the throughput model, we examine typical disk/memory configurations that maximize the overall price/performance. © 1993 ACM.

关键词： Distributed database systems

来源：评论

学校读者我要写书评

暂无评论

PARALLELIZATION OF A CLASS OF IMPLICIT FINITE DIFFERENCE SCHEMES IN COMPUTATIONAL FLUID DYNAMICS

引用

International Journal of High Speed Computing 1993年第1期5卷 1-50页

作者： NAOMI H. NAIK VIJAY K. NAIK MICHEL NICOULES Lamont-Doherty Earth Observatory Columbia University Palisades NY 10964 USA Research supported by the National Aeronautics and Space Administration under NASA Contract No. NAS1-18605 while in residence at the Institute for Computer Applications in Science and Engineering (ICASE) NASA Langley Research Center Hampton VA 23665– 5225. IBM T.J. Watson Research Center P.O. Box 218 Yorktown Heights NY 10598 USA Current address: Institut National Des Telecommunications 91011 Evry France.

Implicit finite difference schemes are often the preferred numerical methods in computational fluid dynamics, requiring less stringent stability bounds than the explicit schemes. Each iteration in an implicit scheme, however, involves global data dependencies in the form of second and higher order recurrences. Efficient parallel implementations of such methods, therefore, are more difficult and can be non-intuitive. Moreover, in practical applications, some sections of the computations are explicit while other sections are implicit in nature. Developing techniques that extract maximum parallelism simultaneously from all sections of an application is considerably harder than extracting parallelism from just an implicit section or an explicit section of the computations. In this paper, we consider issues in the parallelization of techniques that are used for solving Euler and thin-layer Navier-Stokes equations and that require, as a part of the computation, solving large linear systems in the form of block tri-diagonal and/or scalar penta-diagonal matrices. We focus our attention on three-dimensional cases and present schemes that minimize the total execution time when implemented on a message passing system. We describe various partitioning and scheduling strategies for alleviating the effects of the global data dependencies. Analyses of the computation, the communication, and the memory requirements of these methods are presented. The ARC-3D code, developed at NASA Ames, is used as an example application. Performance of the proposed methods is verified on the Victor multiprocessor system, a message passing architecture developed at the IBM T.J. Watson Research Center.

关键词： Parallel CFD implicit finite difference schemes partitioning methods for block tri-diagonal and scalar penta-diagonal solvers ARC-3D message passing systems

来源：评论

学校读者我要写书评

暂无评论

UTILIZING RESERVE ASSETS - MUTUAL SUPPORT AT SUPSHIP BATH

引用

NAVAL ENGINEERS JOURNAL 1993年第6期105卷 39-42页

作者： GOLDA, EM PORPORA, GA Cdr. Eugene Michael Golda:is a Naval Reserve engineering duty officer and is commanding officer of NR NavSea PMS Det 302. He has developed and directed mutual support programs assisting the Supervisor of Shipbuilding Brooklyn and has participated in the training and mutual support programs at the Supervisor of Shipbuilding Bath. He received a Ph.D. and M.S. in materials science and engineering from Stevens Institute of Technology Hoboken N.J. A 1977 graduate of the United States Naval Academy Cdr. Golda has been a member of ASNE since 1974. Cdr. Golda is a materials engineer at the Annapolis Detachment Carderock Division Naval Surface Warfare Center working on naval applications of superconducting technology. LCdr. Gregory A. Porpora:is an IBM market support representative who provides technical consulting support in application development with computer aided software engineering (CASE) tools. Prior to joining IBM he was a senior design engineer for a defense contractor involved in design and development of radar and ASW systems including the AN/BSY-1 combat system trainer. LCdr. Porpora is a member of IEEE the Naval Institute and the Naval Reserve Association. He holds a BSEE and MSEE from the Polytechnic Institute of Technology New York. LCdr. Porpora is currently assigned to NR SupShip Det 502 which provides extensive mutual support for the Supervisor of Shipbuilding Bath and the resident office in Brooklyn New York.

来源：评论

学校读者我要写书评

暂无评论

Interactive tools for signal processing education. The signal processing instructional facility (SPIF lab) at Washington State University

引用

computer applications in engineering Education 1993年第6期1卷 517-517页

作者： Bamberger, R.H. Signal Processing Instructional Facility School of Electrical Engineering and Computer Science Washington State University Pullman WA 99164-2752 Dr. Roberto H. Bamberger:was born on January 30 1965 in Buenos Aires Argentina. He received his B.E.E and PhD from the Georgia Institute of Technology in 1986 and 1990 respectively. Currently Dr. Bamberger is an assistant professor in the School of Electrical Engineering and Computer Science at Washington State University. Dr. Bamberger's research program is focused on the design implementation and application of multidimensional multirate filter banks subband image and video compression analysis of nonstationary data and application of digital signal processing techniques in the design of analog and mixed-mode integrated circuits. Dr. Bamberger is the founder and director of the Signal Processing Instructional Facility (SPIF Lab) at Washington State University. The SPIF Lab features interactive multimedia-based tools for teaching concepts related to linear systems theory. Dr. Bamberger is active in developing multimedia-based instructional laboratories for a variety of other topics as well. In addition to his teaching and research programs Dr. Bamberger is an associate editor for theIEEE Transactions on Signal Processingand a member of the editorial board forComputer Applications in Engineering Education. Dr. Bamberger is also advisor to the WSU Student Branch of the IEEE and assistant director of the WSU Cougar Marching Band. Dr. Bamberger is a member of Phi Eta Sigma Eta Kappa Nu Tau Beta Pi and Kappa Kappa Psi.

The Signal Processing Instructional Facility (SPIF Lab) is an experiment in using in interactive multimedia for teaching concepts related to linear systems theory and signal processing. The goals of the SPIF lab are to augment, enhance, and interconnect sophomore, junior, and senior level courses with the common thread of linear systems and transforms by unifying the experimentation medium. In this fashion, physical phenomenon is returned to the forefront of engineering education. The laboratory features powerful Mathematica Notebooks (a form of hypertext) and interactive applications that use dedicated DSP microprocessors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An approach to the direct analysis of transient stability

引用

European Transactions on Electrical Power 1993年第3期3卷 241-248页

作者： Djukanovic, M.B. Sobajic, D.J. Pao, Y.‐H. Miodrag B. Djukanovic (1959) received his B.S. M.Sc. and Ph.D. degrees in Electrical Engineering from the University of Belgrade/Yugoslavia in 1982 1985 and 1992 respectively specializing in electric power systems. In 1984 he joined the Electrical Engineering Institute “Nikola Tesla” in Belgrade where he was working on the scientific studies in the field of power systems planning operation and control. In 1985 and 1990 he was appointed as a research scholar at the Royal Institute of Technology Stockholm and Case Western Reserve University Cleveland Ohio. His major in- terests are in the area of power system analysis steady-state and dynamic security and application of neural networks in electric power systems. (Electrical Engineering Institute “Nicola Tesla” ul. Koste Glavinica 8A YU-11000 Belgrad T +3811/2351-619 Fax + 3811/2351-823) Dejan J. Sobajic (1949) received the B.S.E.E. and the M.S.E.E. degrees from the University of Belgrade/Yugoslavia in 1972 and 1976 respectively and the Ph.D. degree from Case Western Reserve University Cleveland Ohio in 1988. At present he is with the Department of Electrical Engineering and Applied Physics Case Western Reserve University Cleveland. He is also the Engineering Manager of A1 WARE Inc. Cleveland. His current research interests include power system operation and control neuralnet systems and adaptive control. He is a member of the IEEE Task Force on Neural-Network Applications in Power Systems and of the IEEE Intelligent Controls Committee. He is the Chairman of the International Neural-Networks Society Special Interest Group on Power Engineering. (Case Western Reserve University Department of Electrial Engineering and Computer Sciences Glennan Building Ohio 44 106 USA T + 1216/421-2380 Fax +1216/368-8776) Yoh-Han Pao (1922) has been a Professor of Electrical Engineering and Computer Science at Case Westem Reserve University (CWRU) Cleveland Ohio since 1967. He has served as chairman of the University's Electrical Engineering Department

The Transient Energy Function (TEF) method has been intensely investigated over the last decade as a reliable and accurate tool for transient stability assessment of multimachine power systems. In this paper we propose the Potential Energy Boundary Surface (PEBS) based method for direct analysis of transient stability. The critical value of transient energy and the Critical Clearing Time (T_CCT) are evaluated without the need for successive calculation and memorization of the system kinetic and potential energy values along the sustained fault trajectory. The method is used for determination of output features in the training phase of the neural‐net based transient security assessment. The proposed approach is tested on the well‐known ten‐generator New England test system demonstrating the validity and accuracy of obtained results. Copyright © 1993 John Wiley & Sons, Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CONCURRENT BOUNDARY-ELEMENT COMPUTATION

引用

INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS 1993年第2期6卷 83-98页

作者： MCDOWALL, DS LEE, TW FUSCO, VF Microwave Research Group Department of Electrical and Electronic Engineering The Queen's University of Belfast Ashby Building Stranmillis Road Belfast BT9 5AH Northern Ireland U.K. D. Stewart McDowall was born in Dublin epublic of Ireland in 1967. He received the M. Eng. degree in Electrical and Electronic Engineering from the Queen's University of Belfast in 1990. In the same year he was presented with a Distinction Award from the Department of Education of Northern Ireland and he is currently pursuing his Ph.D. in the Microwave Research Group at Q.U.B. His principal research area is the electromagnetic field mapping of microwave systems using concurrient programming. He is an Associate Member of the Institute of Electrical Engineers. Lee Thaim Wee was awarded the degree of B. Eng. in Electronics from the Queen's University of Belfast in July 1991. He is currently serving in the Malaysian Armed Forces. Vincent F. Fusco was educated at the Queen's Univeristy of Belfast where he obtained the degree of Ph.D. in 1982. He has worked as a research engineer on short-range radar and radio telementry systems. Currently he is a reader in Microwave Communications in the School of Electrical Engineering and Computer Science the Queen's Univeristy of Belfast. His current research interests include non-linear microwave circuit simulation and concurrent programming techniques for electromagnetic field problems with particular emphasis on EMC applications. He has published numerous research papers in these areas. He is the author of the bookMicrowave Circuits Analysis and Computer Aided Design Prentice-Hall 1987. Dr Fusco is a Chartered Electrical Engineer and a Member of the Institute of Electrical Engineers.

A major limitation of the boundary element method (BEM) for the solution of electrical potential problems is the long computational time required. However, a large portion of the calculations involved can be viewed as being parallel in nature and can therefore be computed concurrently. This paper makes an effort to increase the efficiency of the BEM process using transputer-based multiprocessor computing techniques. The algorithms developed may equally well be applied to any multiprocessor system. The application selected to demonstrate the technique is the solution of an electrostatic problem governed by a two-dimensional Laplace equation. A parallel algorithm for problem setup and field extraction using BEM is designed and implemented on a transputer array. Special attention is directed to the utilization of the parallel processors to achieve maximum efficiency. The analysis in this work concentrates on the communication strategies for passing data between processors as well as a consideration of the workload attributed to each processor. The parallel algorithms were implemented using 3L Parallel Fortran;however, the choice of topology for the overall BEM implementation was limited by the fact that certain parts of the algorithm could only utilize a pipeline configuration of processors. Comprehensive results for the parallel BEM algorithm are given and they are encouraging, indicating that parallel processing has much to offer when applied to the boundary element method.

关键词： Boundary element method

来源：评论

学校读者我要写书评

暂无评论

Stabilizers enhancing the frequency regulation action of HVDC links supplying weak AC systems

引用

European Transactions on Electrical Power 1993年第3期3卷 201-212页

作者： Maris, T.I. Lygdis, A.D. Vovos, N.A. Giannakopoulos, G.B. Theodoros I. Maris (1961) received the Diploma in Electrical Engineering from the University of Patras/Greece in 1984. In 1985 he joined the Power Systems Laboratory at the Electrical Engineering Department of the University of Patras as research assistant where he is currently working for his Ph.D. degree. His area of interest is HVDC transmission. (University of Patras Dep. of Electrical Engineering Power Systems Laboratory GR-26 500 Rion. Patras/Greece T +3061/997350 Fax +3061/997362) Athanassios D. Lygdis (1954) received the Diploma in Electrical Engineering from the University of Patras/Greece in 1979. From 1979 until 1982 he worked at the Nuclear Technology Laboratory of the University of Patras as research assistant. In 1983 he joined the Power Systems Laboratory at the Electrical Engineering Department of the University of Patras as scientific collaborator. He is now working for his Ph.D. degree in this Department. His main field of interest is power transmission by HVDC systems. (University of Patras Dep. of Electrical Engineering Power Systems Labora- tory GR-26 500 Rion Patras/Greece T + 3061/997350 Fax + 3061/997361) Nickolas A. Vovos (1951) received the Diploma degree from the University of Patras/Greece the M.Sc. degree from the University of Manchester/England Institute of Science and Technology. and the Ph.D. degree from the University of Patras in 1974 1975 1978 respectively all in Electrical Engineering. In 1976 he joined the Power Systems Laboratory at the Electrical Engineering Department of the University of Patras where he is now Associate Professor. His main fields of interest are the modeiling and the transient stability study of integrated AC/DC systems. He is a member of the IEEE Power Engineering Society and CIGRE and a registered professional Engineer and member of the Technical Chamber of Greece (University of Patras Dep. of Electrical Engineering Power Systems laboratory GR-26500 Rion Patras/Greece. T +3061/997369 Fax +3061/997362) Gabriel B. Giannakopoulos (1

Power System Stabilizers (PSS) superimposed to the basic control system of an HVDC link supplying a weak AC system, in order to enhance its frequency regulation action, are proposed. To decrease the AC voltage sensitivity at the inverter side, the basic control system of the HVDC link is proposed to operate with the rectifier under Minimum Ignition Angle (MIA) control and the inverter under Constant Current (CC) control. Inputs to the PSS are the frequency and the AC voltage deviations at the inverter side and their constant parameters are calculated using modal control technique. Detailed simulation results for a practical integrated AC/DC system are presented to evaluate the performance of the proposed control scheme. Copyright © 1993 John Wiley & Sons, Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

THE PRESSURE DILATION CORRELATION IN COMPRESSIBLE FLOWS

引用

PHYSICS OF FLUIDS A-FLUID DYNAMICS 1992年第12期4卷 2674-2682页

作者： SARKAR, S Institute for Computer Applications in Science and Engineering NASA Langley Research Center Hampton Virginia 23665

Simulations of simple compressible flows have been performed to enable the direct estimation of the pressure-dilatation correlation. The generally accepted belief that this correlation may be important in high-speed flows has been verified by the simulations. The pressure-dilatation correlation is theoretically investigated by considering the equation for fluctuating pressure in an arbitrary compressible flow. This leads to the isolation of a component of the pressure-dilatation that exhibits temporal oscillations on a fast time scale. Direct numerical simulations of homogeneous shear turbulence and isotropic turbulence show that this fast component has a negligible contribution to the evolution of turbulent kinetic energy. Then, an analysis for the case of homogeneous turbulence is performed to obtain a formal solution for the nonoscillatory pressure-dilatation. Simplifications lead to a model that algebraically relates the pressure-dilatation to quantities traditionally obtained in incompressible turbulence closures. The model is validated by direct comparison with the simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of a parallel unstructured Euler solver on shared and distributed memory architectures

Implementation of a parallel unstructured Euler solver on sh...

引用

1992 ACM/IEEE conference on Supercomputing, Supercomputing 1992

作者： Mavriplis, D.J. Das, Raja Saltz, Joel Vermeland, R.E. Institute for Computer Applications in Science and Engineering United States Cray Research Inc. United States

ISBN: (纸本)0818626305

An efficient three dimensional unstructured Euler solver is parallelized on a Cray Y-MP C90 shared memory computer and on an Intel Touchstone Delta distributed memory computer. This paper relates the experiences gained and describes the software tools and hardware used in this study. Performance comparisons between the two differing architectures are made. © 1992 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Complete exchange on a circuit switched mesh

Complete exchange on a circuit switched mesh

引用

Scalable High Performance Computing Conference

作者： S.H. Bokhari H. Berryman Department of Electrical Engineering University of Engineering and Technology Lahore Pakistan Institute for Computer Applications in Science & Engineering NASA-Langley Research Center Hampton VA USA

The complete exchange ('all-to-all personalized') communication pattern is at the heart of numerous important multicomputer algorithms. Recent research has shown how this pattern can efficiently be performed on circuit-switched hypercubes. However, on circuit-switched meshes, this pattern is difficult to perform efficiently because the sparsity of the mesh interconnect leads to severe link contention. The authors develop a family of algorithms that proceed by recursively carrying out a series of contention-free exchanges on subdivisions of the mesh. Each member of this family is useful for some range of the parameters: mesh size, message size, startup time, and data transmission and permutation rates. The authors describe the performance of their algorithms on the Touchstone Delta mesh.< >

关键词： Switching circuits Hypercubes Communication switching Programming profession Power engineering computing NASA Distributed computing Power engineering and energy Hardware Integrated circuit interconnections

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：