A step-by-step guide to parallelizing cem codes

The future of computational electromagnetics is changing drastically as the new generation of computer chips evolves from single-core to multi-core. The burden now falls on software programmers to revamp existing codes and add new functionality to enable computational codes to run efficiently on this new generation of multi-core CPUs. In this book, you'll learn everything you need to know to deal with multi-core advances in chip design by employing highly efficient parallel electromagnetic code. Focusing only on the Method of Moments (MoM), the book covers:

In-Core and Out-of-Core LU Factorization for Solving a Matrix Equation

A Parallel MoM Code Using RWG Basis Functions and ScaLAPACK-Based In-Core and Out-of-Core Solvers

A Parallel MoM Code Using Higher-Order Basis Functions and ScaLAPACK-Based In-Core and Out-of-Core Solvers

Turning the Performance of a Parallel Integral Equation Solver

Refinement of the Solution Using the Conjugate Gradient Method

A Parallel MoM Code Using Higher-Order Basis Functions and Plapack-Based In-Core and Out-of-Core Solvers

Applications of the Parallel Frequency Domain Integral Equation Solver

Appendices are provided with detailed information on the various computer platforms used for computation; a demo shows you how to compile ScaLAPACK and PLAPACK on the Windows(R) operating system; and a demo parallel source code is available to solve the 2D electromagnetic scattering problems.

Parallel Solution of Integral Equation-Based EM Problems in the Frequency Domain is indispensable reading for computational code designers, computational electromagnetics researchers, graduate students, and anyone working with CEM software.

Microsystems are an important success factor in the automobile industry. In order to fulfil the customers requests for safety convenience and vehicle economy, and to satisfy environmental requirements, microsystems are becoming indispensable. Thus a large number of microsystem applications came into the discussion. With the international conference AMAA 2002, VDI/VDE-IT provides a platform for the discussion of all MST relevant components for automotive applications. The conference proceedings gather the papers by authors from automobile suppliers and manufacturers.

The authors, writing with the experience and technological background of Electricite de France, an organisation at the forefront of simulation methods, provide a comprehensive and comprehensible treatment of the modelling and simulation techniques currently in use. The text emphasises model design applied to power plants producing energy, generators and motors carrying out energy transformations and networks transmitting energy. The systems are analysed considering each process, from steady state to fast transients, with detailed explanation of the problem to be solved, the choice of models and methods for optimising efficiency. Many examples and references are provided. The book is essential reading for anyone involved in power system engineering, from practising design and development engineers to researchers and postgraduate and advanced graduate students.

Experts address some of the main issues and uncertainties associated with the design and deployment of Automated Highway Systems (AHS). They discuss new AHS concepts, technology, and benefits, as well as institutional, environmental, and social issues - concerns that will affect dramatically the operation of the current highway system from both the vehicle and infrastructure points of view.

The Compact Disc (CD), as a standardized information carrier, has become one of the most successful consumer products ever marketed. Although the original disc was intended for audio playback, its specific advantages opened very quickly the way towards various computer applications. The standardization of the Compact Disc Read-Only Memory (CD-ROM) and of all succeeding similar products, like Compact Disc interactive (CD-i), Photo and Video CD, CD Recordable (CD-R), and CD Rewritable (CD R/W), has substantially enlarged the range of possible applications. The plastic disc represented from the very beginning a removable medium of large storage capacity. The advent of the personal computer accompa nied by the increasing demand for both data distribution and exchange have strongly marked the evolution of the CD-ROM drive. The number of sold CD-ROM units exceeded 60 millions in 1997 when compared to about 2.5 millions in 1992. As computing power continuously improved over the years, computer pe ripherals have also targeted better performance specifications. In particular, the speed of CD-ROM drives increased from the so-called 1X in 1984 to dou ble speed in 1992, and further to 32X at the beginning of 1998. The average time needed to access data on disc has dropped from about 300 ms to less than 90 ms within the same period of time."

Handbook of Thin Film Technology covers all aspects of coatings preparation, characterization and applications. Different deposition techniques based on vacuum and plasma processes are presented. Methods of surface and thin film analysis including coating thickness, structural, optical, electrical, mechanical and magnetic properties of films are detailed described. The several applications of thin coatings and a special chapter focusing on nanoparticle-based films can be found in this handbook. A complete reference for students and professionals interested in the science and technology of thin films.

Adaptive radio transceivers require a comprehensive theoretical framework in order to optimize their performance. Adaptive Low-Power Circuits for Wireless Communications provides this framework with a discussion of joint optimization of Noise Figure and Input Intercept Point in receiver systems. Original techniques to optimize voltage controlled oscillators and low-noise amplifiers to minimize their power consumption while maintaining adequate system performance are also provided. The experimental results presented at the end of the book confirm the utility of the proposed techniques.

Advances in information technology provide opportunities for the development of computer systems that support risk managers in complex tasks. Leading experts report on the potentials and limitations concerning the use of computer systems in risk management. Their reports are based on many years of experience in their fields which include: risk analysis, systems engineering, geographic information systems, decision support systems, human--machine systems, and psychology. The book addresses four major issues in computer supported risk management: Conceptual aspects: the role, design, and use of computers in risk management Planning and policy analysis: transportation, equity analysis, emergency management, group decision making Operational decision making: nuclear power monitoring, emergency response, public safety warning, satellite tracking Commercial applications: GIS from IIASA, InterClair from IAEA, EPA software, cleanup decision support software survey. This book is meant for researchers, who will find the emerging issues in risk management that are motivated by the encounter of new tasks and novel technology; practitioners who will have descriptions and references of the state-of-the-art models and software; and students who will learn the basic concepts needed to develop advanced information and decision support systems in risk management.

Microfluidics and Microfabrication discusses the interconnect between microfluidics, microfabrication and the life sciences. Specifically, this includes fundamental aspects of fluid mechanics in micro-scale and nano-scale confinements and microfabrication. Material is also presented discussing micro-textured engineered surfaces, high-performance AFM probe-based, micro-grooving processes, fabrication with metals and polymers in bio-micromanipulation and microfluidic applications. Editor Suman Chakraborty brings together leading minds in both fields who also:

• Cover the fundamentals of microfluidics in a manner accessible to multi-disciplinary researchers, with a balance of mathematical details and physical principles
• Discuss the explicit interconnection between microfluiodics and microfabrication from an application perspective
• Detail the amalgamation of microfluidics with logic circuits and applications in micro-electronics

Microfluidics and Microfabrication is an ideal book for researchers, engineers and senior-level graduate students interested in learning more about the two fields.

This handbook provides design considerations and rules-of-thumb to ensure the functionality you want will work. It brings together all the information needed by systems designers to develop applications that include configurability, from the simplest implementations to the most complicated.

This book provides an overview of current Intellectual Property (IP) based System-on-Chip (SoC) design methodology and highlights how security of IP can be compromised at various stages in the overall SoC design-fabrication-deployment cycle. Readers will gain a comprehensive understanding of the security vulnerabilities of different types of IPs. This book would enable readers to overcome these vulnerabilities through an efficient combination of proactive countermeasures and design-for-security solutions, as well as a wide variety of IP security and trust assessment and validation techniques. This book serves as a single-source of reference for system designers and practitioners for designing secure, reliable and trustworthy SoCs.

This useful book addresses electrothermal problems in modern VLSI systems. It discusses electrothermal phenomena and the fundamental building blocks that electrothermal simulation requires. The authors present three important applications of VLSI electrothermal analysis: temperature-dependent electromigration diagnosis, cell-level thermal placement, and temperature-driven power and timing analysis.

The papers published in these proceedings represent the latest developments in the nondestructive characterization of materials and were presented at the Eleventh International Symposium on Nondestructive Characterization of Materials held in June 24-28, 2002, in Berlin, Germany.

The death of Professor Arthur Wright in the summer of 1996 deprived me of a friend and a colleague whose judgement and experience shaped this book. I pay tribute to his contributions to protection and electrical engineering education. In the five years since the first edition appeared, many developments have taken place and it is now necessary to update the book. The use of digital communications and advanced signal processing techniques is now widespread and several fully numeric relays are available from manu facturers. Two new Chapters 13 and 14 have been added to introduce readers to these concepts and associated techniques. Artificial intelligence is making its impact in all engineering applications and power system protection is no exception. Expert systems, fuzzy logic, artificial neural networks, adaptive and integrated protection, synchronized measurements using the global positioning system, genetic algorithms, flexible a.c. transmission systems, are some of the techniques considered in connection with protection. Although many of these techniques have not yet found major application in protection, it is nevertheless essential for the educated protection engineer to have a basic understanding of the underlying principles and methodology so that he, or she, can evaluate their suitability for new relaying problems and applications. Chapter 15 was therefore added to guide readers through this developing area. I have also added some new material in other chapters to reflect changes over the past years."

Oversampling techniques based on sigma-delta modulation are widely used to implement the analog/digital interfaces in CMOS VLSI technologies. This approach is relatively insensitive to imperfections in the manufacturing process and offers numerous advantages for the realization of high-resolution analog-to-digital (A/D) converters in the low-voltage environment that is increasingly demanded by advanced VLSI technologies and by portable electronic systems. In The Design of Low-Voltage, Low-Power Sigma-Delta Modulators, an analysis of power dissipation in sigma-delta modulators is presented, and a low-voltage implementation of a digital-audio performance A/D converter based on the results of this analysis is described. Although significant power savings can typically be achieved in digital circuits by reducing the power supply voltage, the power dissipation in analog circuits actually tends to increase with decreasing supply voltages. Oversampling architectures are a potentially power-efficient means of implementing high-resolution A/D converters because they reduce the number and complexity of the analog circuits in comparison with Nyquist-rate converters. In fact, it is shown that the power dissipation of a sigma-delta modulator can approach that of a single integrator with the resolution and bandwidth required for a given application. In this research the influence of various parameters on the power dissipation of the modulator has been evaluated and strategies for the design of a power-efficient implementation have been identified. The Design of Low-Voltage, Low-Power Sigma-Delta Modulators begins with an overview of A/D conversion, emphasizing sigma-delta modulators. It includes a detailed analysis of noise in sigma-delta modulators, analyzes power dissipation in integrator circuits, and addresses practical issues in the circuit design and testing of a high-resolution modulator. The Design of Low-Voltage, Low-Power Sigma-Delta Modulators will be of interest to practicing engineers and researchers in the areas of mixed-signal and analog integrated circuit design.

Feed-Forward Neural Networks: Vector Decomposition Analysis, Modelling and Analog Implementation presents a novel method for the mathematical analysis of neural networks that learn according to the back-propagation algorithm. The book also discusses some other recent alternative algorithms for hardware implemented perception-like neural networks. The method permits a simple analysis of the learning behaviour of neural networks, allowing specifications for their building blocks to be readily obtained. Starting with the derivation of a specification and ending with its hardware implementation, analog hard-wired, feed-forward neural networks with on-chip back-propagation learning are designed in their entirety. On-chip learning is necessary in circumstances where fixed weight configurations cannot be used. It is also useful for the elimination of most mis-matches and parameter tolerances that occur in hard-wired neural network chips. Fully analog neural networks have several advantages over other implementations: low chip area, low power consumption, and high speed operation. Feed-Forward Neural Networks is an excellent source of reference and may be used as a text for advanced courses.

The world of microelectronics is filled with cusses measurement systems, manufacturing many success stories. From the use of semi control techniques, test, diagnostics, and fail ure analysis. It discusses methods for modeling conductors for powerful desktop computers to their use in maintaining optimum engine per and reducing defects, and for preventing de formance in modem automobiles, they have fects in the first place. The approach described, clearly improved our daily lives. The broad while geared to the microelectronics world, has useability of the technology is enabled, how applicability to any manufacturing process of similar complexity. The authors comprise some ever, only by the progress made in reducing their cost and improving their reliability. De of the best scientific minds in the world, and fect reduction receives a significant focus in our are practitioners of the art. The information modem manufacturing world, and high-quality captured here is world class. I know you will diagnostics is the key step in that process. find the material to be an excellent reference in of product failures enables step func Analysis your application. tion improvements in yield and reliability. which works to reduce cost and open up new Dr. Paul R. Low applications and technologies. IBM Vice President and This book describes the process ofdefect re of Technology Products General Manager duction in the microelectronics world."

It is a great pleasure that we are now publishing the fourth volume of the series on PUILS, through which we have been introducing the progress in ultrafast intense laser science, the frontiers of which are rapidly expanding, thanks to the progress in ultrashort and high-power laser technologies. The interdisciplinary nature of this research ?eld is attracting researchers with di?erent expertise and backgrounds. As in the previousvolumeson PUILS, each chapter in the presentvolume, which is in the range of 15-25 pages, begins with an introduction in which a clear and concise account of the signi?cance of the topic is given, followed by a description of the authors' most recent research results. All the chapters are peer-reviewed. The articles of this fourth volume cover a diverse range of the interdisciplinary research ?eld, and the topics may be grouped into four categories: strong ?eld ionization of atoms (Chaps. 1-2), excitation, ioni- tion and fragmentation of molecules (Chaps. 3-5), nonlinear intense optical phenomena and attosecond pulses (Chaps. 6-8), and laser solid interactions and photoemissions (Chaps. 9-11).

Switched-Current Design and Implementation of Oversampling A/D Converters discusses the switched-current (SI) technique and its application in oversampling A/D converters design. The SI technique is an analog sampled-data technique that fully exploits the digital CMOS process. Compared with the traditional switched-capacitor (SC) technique, the SI technique has both pros and cons that are highlighted in the book. With the consideration of similarity and difference of SI and SC techniques, oversampling A/D converter architectures are tailored and optimized for SI design and implementation in the book. Switched-Current Design and Implementation of Oversampling A/D Converters emphasizes the practical aspects of SI circuits without tedious mathematical derivations, and is full of circuit design and implementation examples. There are more than 10 different chips included in the book, demonstrating the high-speed (over 100 MHz) and ultra-low-voltage (1.2 V) operation of SI circuits and systems in standard digital CMOS processes. Therefore, the book is of special value as a practical guide for designing SI circuits and SI oversampling A/D converters. Switched-Current Design and Implementation of Oversampling A/D Converters serves as an excellent reference for analog designers, especially A/D converter designers, and is of interest to digital designers for real-time signal processing who need A/D interfaces. The book may also be used as a text for advanced courses on the subject.

This book has been conceived to extend the generally published work on one- and two-dimensional digital filters in order to include some of the more recently developed ideas. It is intended to supplement and build on the classical books which cover the fundamental concepts of the topic. As a consequence of this, the basic theory is stated in a compact manner and is not developed thoroughly, as this would result in considerable duplication of existing books. The main theme of the book has been to provide a comprehensive background to the methods available for the realization of both recursive and nonrecursive digital filters, and to give an insight into some of the more recent implementation procedures. The book is planned to cover one- and two-dimensional systems in parallel, showing the techniques which are applicable in both areas, and also the limitations and constraints necessary when a one-dimensional technique is extended to systems of higher dimensionality. The theme of the book commences with several chapters on the design of filter transfer functions to meet given specifications. This is followed by a discussion of methods of implementing these in a practical system and the limitations imposed as a result of noise and finite word length. Finally, a discussion of some applications is included.

The Digitization of Cinematic Visual Effects: Hollywood s Coming of Age, by Rama Venkatasawmy, analyzes how the Hollywood cinema industry s visual effects applications have not only motivated the expansion of filmmaking praxis, they have also influenced the evolution of viewing pleasures and spectatorship experiences. Following the digitization of their associated technologies, VFX have been responsible for multiplying the strategies of representation and storytelling, as well as extending the range of stories that can potentially be told onscreen. By the same token, the visual standards of the Hollywood film s production and exhibition have been growing in sophistication. On the basis of displaying groundbreaking VFX immaculately realized through the application of cutting-edge technologies and craftsmanship and of projecting such a significant degree of visual innovation and originality, certain Hollywood movies have established techno-visual trends and industrial standards for subsequent filmmaking practice. Hollywood cinema s entry into the digital realm is intertwined with the intensification of conglomeratic practices within the movie business, the domain of techno-scientific R&D in filmmaking, and the unification of corporate media, information technology, and entertainment. Hence, the standardization of, and convergence toward, the digital medium is emblematic of Hollywood cinema s techno-industrial evolution in the late twentieth century. Accordingly, this volume identifies various synergies and partnerships between VFX providers, movie studios, graphic designers, and more that have emerged from a progressive growth of awareness in Hollywood of the digital medium s potential."

Nonlinear and Hybrid Systems in Automotive Control will enable researchers, control engineers and automotive engineers to understand the engine and whole-vehicle models necessary for control. A new generation of control strategies has become necessary because of the increasingly rigorous requirements of vehicle and engine control systems for accuracy, ride comfort, safety, complexity, functionality and emission levels. In contrast with earlier systems, these new control systems are based on dynamic physical models and the principles of advanced nonlinear control. The contributors to this work come from both academic and industrial backgrounds and the subjects they cover include: suspension control; modelling of driver position and behaviour; anti-lock braking systems and optimal braking control; stability analysis of hybrid systems; Hamiltonian formulation of bond graphs; approximation of maximal controlled safe sets for hybrid systems. This book should be of use to academic researchers and graduate students as well as to engineers in the automotive industry.

In this groundbreaking new volume, computer researchers discuss the development of technologies and specific systems that can interpret data with respect to domain knowledge. Although the chapters each illuminate different aspects of image interpretation, all utilize a common approach - one that asserts such interpretation must involve perceptual learning in terms of automated knowledge acquisition and application, as well as feedback and consistency checks between encoding, feature extraction, and the known knowledge structures in a given application domain. The text is profusely illustrated with numerous figures and tables to reinforce the concepts discussed.