Editing a Springer Nature Reference: Handbook of Hardware/Software Codesign

Hardware/software (HW/SW) Codesign was first introduced as a new design methodology for SoC (system-on-chip) to design hardware and software concurrently in order to reduce design time and cost. Today, the term subsumes any methodology to design complex electronic systems, up to distributed embedded systems, encompassing the full spectrum of system design issues from initial behavior specification to final implementation. In spite of its significance and usefulness, we discovered that it is quite difficult for new researchers and students to understand and learn about its benefits and full impact on real system design, particularly because there did not exist any book or reference that covers the depth and breadth of HW/SW Codesign until the time of editing this handbook. Thus, we decided to edit this handbook to quench the thirst for reference. To make a major and authoritative reference book on HW/SW Codesign, we invited as chapter authors well-known distinguished researchers from around the world. This handbook presents the core issues of hardware/software codesign and key techniques in the design flow. In addition, selected co-design tools and design environments are described as well as case studies that demonstrate the usefulness of HW/SW Codesign.

This handbook consists of nine parts, of which Part I presents the introduction of HW/SW Codesign with the overall flow of the HW/SW Codesign methodology and the subsequent parts deal with individual design steps of the methodology. Anyone who newly enters this field is recommended to read Part I first to understand the methodology and its breadth. Since a researcher usually focuses on one or a few specific design steps, he/she can go directly to the corresponding part that consists of chapters that are specialized in the main research subjects in the individual design step. Since each chapter presents as well basic knowledge as the state-of-the-art techniques on the subject, this handbook will serve as a golden reference book to find a research topic to explore.

However, ten years ago, when we developed the idea for our textbook, there were no resources available for data analysts who did not have extensive graduate-level training in statistics or a closely-related field. Existing textbooks assumed a high level of background knowledge and focused on technical details rather than the key ideas needed to apply statistical machine learning methods in practice. We set out to fill this gap by writing a textbook that is accessible to a broad audience. Our textbook assumes just a previous course or two in statistics or probability, and in particular, does not require knowledge of matrix algebra. We use simple language to distill complicated ideas down to their essence. Instead of just starting off with the fanciest and shiniest statistical learning methods, we build up from the basics so that readers can understand the building blocks of the more advanced methods. We also include, in each chapter, a computing lab written in the very popular open-source statistical software environment R, so that readers can learn how to apply these methods in practice.  

Our textbook has been very successful: it has been cited more than 10,000 times according to Google Scholar and has been an Amazon bestseller since it was published in 2013, with over 1,000 reviews averaging 4.7/5.0 stars.

In the early stage of development, HW/SW co-simulation served as an enabling technique of HW/SW codesign of an SoC and several commercial tools have been successfully deployed in semiconductor industries to improve design productivity. Nowadays, its application domains are being widened as demonstrated in Part IX of this handbook. Since the methodology starts from the initial specification method of the system that affects the subsequent design steps, model-based design is widely adopted. Even though there is no consensus on ultimate models, extensive researches have been performed on the modeling and the associated analysis/synthesis techniques, which we consider most exciting in academia.

As the system complexity grows, the bottleneck of system design lies in the verification of the design. To make verification easier, we think it is necessary to use formal models for the high-level specification of the system. We are currently developing a generic design framework based on formal models of computation, particularly focusing on how to synthesize and verify the embedded software running on various hardware platforms. Also, hybrid design techniques that exploit the strength of design-time analysis of cost, timing, reliability, and security with run-time decision-making on the mapping of tasks to processors or other components will become more and more important with the increasing complexity and dynamism in workload