With the rapid development of artificial intelligence and the emergence of various new sensors, autonomous driving has grown in popularity in recent years. The implementation of autonomous driving requires new sources of sensory data, such as cameras, radars, and lidars, and the algorithm processing requires a high degree of parallel computing. In this regard, traditional CPUs have insufficient computing power, while DSPs are good at image processing but lack sufficient performance for deep learning. Although GPUs are good at training, they are too “power-hungry,” which can affect vehicle performance. Therefore, this book looks to the future, arguing that custom ASICs are bound to become mainstream. With the goal of ICs design for autonomous driving, this book discusses the theory and engineering practice of designing future-oriented autonomous driving SoC chips. The content is divided into thirteen chapters, the first chapter mainly introduces readers to the current challenges and research directions in autonomous driving. Chapters 2–6 focus on algorithm design for perception and planning control. Chapters 7–10 address the optimization of deep learning models and the design of deep learning chips, while Chapters 11-12 cover automatic driving software architecture design. Chapter 13 discusses the 5G application on autonomous drving. This book is suitable for all undergraduates, graduate students, and engineering technicians who are interested in autonomous driving.

How to design for optimum maintenance capabilities and minimize the repair time Design for Maintainability offers engineers a wide range of tools and techniques for incorporating maintainability into the design process for complex systems. With contributions from noted experts on the topic, the book explains how to design for optimum maintenance capabilities while simultaneously minimizing the time to repair equipment. The book contains a wealth of examples and the most up-to-date maintainability design practices that have proven to result in better system readiness, shorter downtimes, and substantial cost savings over the entire system life cycle, thereby, decreasing the Total Cost of Ownership. Design for Maintainability offers a wealth of design practices not covered in typical engineering books, thus allowing readers to think outside the box when developing maintainability design requirements. The books principles and practices can help engineers to dramatically improve their ability to compete in global markets and gain widespread customer satisfaction. This important book: Offers a complete overview of maintainability engineering as a system engineering discipline Includes contributions from authors who are recognized leaders in the field Contains real-life design examples, both good and bad, from various industries Presents realistic illustrations of good maintainability design principles Provides discussion of the interrelationships between maintainability with other related disciplines Explores trending topics in technologies Written for design and logistics engineers and managers, Design for Maintainability is a comprehensive resource containing the most reliable and innovative techniques for improving maintainability when designing a system or product.

Swarm intelligence is one of the fastest growing subfields of artificial intelligence and soft computing. This field includes multiple optimization algorithms to solve NP-hard problems for which conventional methods are not effective. It inspires researchers in engineering sciences to learn theories from nature and incorporate them. Swarm Intelligence: Foundation, Principles, and Engineering Applications provides a comprehensive review of new swarm intelligence techniques and offers practical implementation of Particle Swarm Optimization (PSO) with MATLAB code. The book discusses the statistical analysis of swarm optimization techniques so that researchers can analyse their experiment design. It also includes algorithms in social sectors, oil and gas industries, and recent research findings of new optimization algorithms in the field of engineering describing the implementation in machine learning. This book is written for students of engineering, research scientists, and academicians involved in the engineering sciences.

The physical design flow of any project depends upon the size of the design, the technology, the number of designers, the clock frequency, and the time to do the design. As technology advances and design-styles change, physical design flows are constantly reinvented as traditional phases are removed and new ones are added to accommodate changes in

Unlike most available sources that focus on deep neural network (DNN) inference, this book provides readers with a single-source reference on the needs, requirements, and challenges involved with on-device, DNN training semiconductor and SoC design. The authors include coverage of the trends and history surrounding the development of on-device DNN training, as well as on-device training semiconductors and SoC design examples to facilitate understanding.

As the complexity of electronic systems continues to increase, the micro-electronic industry depends upon automation and simulations to adapt quickly to market changes and new technologies. Compiled from chapters contributed to CRC's best-selling VLSI Handbook, this volume of the Principles and Applications in Engineering series covers a broad rang

This book addresses the automatic sizing and layout of analog integrated circuits (ICs) using deep learning (DL) and artificial neural networks (ANN). It explores an innovative approach to automatic circuit sizing where ANNs learn patterns from previously optimized design solutions. In opposition to classical optimization-based sizing strategies, where computational intelligence techniques are used to iterate over the map from devices’ sizes to circuits’ performances provided by design equations or circuit simulations, ANNs are shown to be capable of solving analog IC sizing as a direct map from specifications to the devices’ sizes. Two separate ANN architectures are proposed: a Regression-only model and a Classification and Regression model. The goal of the Regression-only model is to learn design patterns from the studied circuits, using circuit’s performances as input features and devices’ sizes as target outputs. This model can size a circuit given its specifications for a single topology. The Classification and Regression model has the same capabilities of the previous model, but it can also select the most appropriate circuit topology and its respective sizing given the target specification. The proposed methodology was implemented and tested on two analog circuit topologies.

The second of two volumes in the Electronic Design Automation for Integrated Circuits Handbook, Second Edition, Electronic Design Automation for IC Implementation, Circuit Design, and Process Technology thoroughly examines real-time logic (RTL) to GDSII (a file format used to transfer data of semiconductor physical layout) design flow, analog/mixed signal design, physical verification, and technology computer-aided design (TCAD). Chapters contributed by leading experts authoritatively discuss design for manufacturability (DFM) at the nanoscale, power supply network design and analysis, design modeling, and much more. New to This Edition: Major updates appearing in the initial phases of the design flow, where the level of abstraction keeps rising to support more functionality with lower non-recurring engineering (NRE) costs Significant revisions reflected in the final phases of the design flow, where the complexity due to smaller and smaller geometries is compounded by the slow progress of shorter wavelength lithography New coverage of cutting-edge applications and approaches realized in the decade since publication of the previous edition—these are illustrated by new chapters on 3D circuit integration and clock design Offering improved depth and modernity, Electronic Design Automation for IC Implementation, Circuit Design, and Process Technology provides a valuable, state-of-the-art reference for electronic design automation (EDA) students, researchers, and professionals.

Algorithms for VLSI Physical Design Automation, Second Edition is a core reference text for graduate students and CAD professionals. Based on the very successful First Edition, it provides a comprehensive treatment of the principles and algorithms of VLSI physical design, presenting the concepts and algorithms in an intuitive manner. Each chapter contains 3-4 algorithms that are discussed in detail. Additional algorithms are presented in a somewhat shorter format. References to advanced algorithms are presented at the end of each chapter. Algorithms for VLSI Physical Design Automation covers all aspects of physical design. In 1992, when the First Edition was published, the largest available microprocessor had one million transistors and was fabricated using three metal layers. Now we process with six metal layers, fabricating 15 million transistors on a chip. Designs are moving to the 500-700 MHz frequency goal. These stunning developments have significantly altered the VLSI field: over-the-cell routing and early floorplanning have come to occupy a central place in the physical design flow. This Second Edition introduces a realistic picture to the reader, exposing the concerns facing the VLSI industry, while maintaining the theoretical flavor of the First Edition. New material has been added to all chapters, new sections have been added to most chapters, and a few chapters have been completely rewritten. The textual material is supplemented and clarified by many helpful figures. Audience: An invaluable reference for professionals in layout, design automation and physical design.

The first of two volumes in the Electronic Design Automation for Integrated Circuits Handbook, Second Edition, Electronic Design Automation for IC System Design, Verification, and Testing thoroughly examines system-level design, microarchitectural design, logic verification, and testing. Chapters contributed by leading experts authoritatively discuss processor modeling and design tools, using performance metrics to select microprocessor cores for integrated circuit (IC) designs, design and verification languages, digital simulation, hardware acceleration and emulation, and much more. New to This Edition: Major updates appearing in the initial phases of the design flow, where the level of abstraction keeps rising to support more functionality with lower non-recurring engineering (NRE) costs Significant revisions reflected in the final phases of the design flow, where the complexity due to smaller and smaller geometries is compounded by the slow progress of shorter wavelength lithography New coverage of cutting-edge applications and approaches realized in the decade since publication of the previous edition—these are illustrated by new chapters on high-level synthesis, system-on-chip (SoC) block-based design, and back-annotating system-level models Offering improved depth and modernity, Electronic Design Automation for IC System Design, Verification, and Testing provides a valuable, state-of-the-art reference for electronic design automation (EDA) students, researchers, and professionals.