Why design must change: Rethinking digital design

Summary form only given. The IC industry is facing a huge paradox. On one hand, with the slowing of the performance and power gains provided by scaling, designers need to find new ways of delivering value to their customers. Historically this has meant creating more application specialized chips and systems. On the other hand the rising NRE costs for chip design (now over $10M/chip) has caused the number of chip design starts to fall. Everyone today seems to be talking about building programmable platforms to ensure the total available market is large enough to justify the chip design costs. To get out of this paradox, we need to change the way we think about chip design. Reducing digital NRE costs requires moving the end user designers up a level in abstraction. For many reasons I don't believe that either the current SoC, or high-level language effort will succeed. Instead, we should acknowledge that working out the interactions in a complex design is complex, and will cost a lot of money, even when we do it well. The key is to leverage this work over a broader class of chips. This approach leads to the idea of building chip-generators and not chips. That is instead of building a programmable chip to meet a broad class of application needs, you create a virtual programmable chip, that is MUCH more flexible than any real chip. The application designer (the new chip designer) will then configure this substrate to optimize for their application. The generator will take this information and then create the desired chip. While there are many very hard problems that need to be addressed to make this work, but none of them seem insurmountable. In fact I will provide some examples which indicate the promise of this approach like having the generator choose the core that is the most energy efficient for your application mix.