Will Networks on Chip Close the Productivity Gap?

We introduce two properties of the design process called the arbitrary composability and the linear effort properties. We argue that a design paradigm, which has these two properties is scalable and has the potential to keep up with the pace of technology advances. Then we discuss some of the trends that will enforce significant changes on current design methodologies and techniques. Finally, we argue that the emerging Network-on-Chip (NoC) paradigm promises to address these trends and challenges and has all prerequisites to provide the arbitrary composability and the linear effort properties. Consequently we conclude that NoC is a likely basis for future System-on-Chip platforms and methodologies.