Teaching Hardware Design of Fixed-Point Digital Signal Processing Systems

Signal processing theory and practice are enabling and driving forces behind multimedia de-vices, communications systems, and even such diverse fields as automotive and medical sys-tems. Over 90 % of the signal processing systems on the market used fixed-point arithmetic because of the cost, power, and area savings that fixed-point systems provide. However, most colleges and universities do not teach or teach only a very little fixed-point signal process-ing. This issue is being addressed slowly around the country but now a new challenge or opportunity presents itself. As reconfigurable logic technology matures, field-programmable gate arrays (FPGAs) are increasingly used for signal processing systems. They have the ad-vantage of tremendous throughput, great flexibility, and system integration. The challenge is that signal processing in FPGAs is a much less constrained problem than signal processing in special purpose microprocessors. The opportunity arises in that it is now possible to explore more options and, more especially, to take a more systems-level approach to signal processing systems. In short, designing a signal processing system using FPGAs provides opportunities to look at many system design issues and trade-offs in a classroom setting. We have developed a course to teach signal processing in FPGAs at Georgia Institute of Technology and in this paper we consider the challenges and methods of teaching fixed-point system design in this course. We discuss the topics chosen and how they differ from traditional microprocessor-based courses. We also discuss how systems engineering concepts are woven into the course.