2021 BRN Discussion, page-12602

This may be relevant for future versions of Akida. Google used machine learning to speed up the tape-out process of their latest TPU. What usually took months was reduced down to 6 hours and with as good or better results as the experts would achieve. If ML can be used to help design future versions of Akida the design process has potential to be reduced significantly.

https://www.theregister.com/2021/06/09/google_ai_chip_floorplans/

Google claims not only has it made an AI that's faster and as good as if not better than humans at designing chips, the web giant is using it to design chips for faster and better AI.

By designing, we mean the drawing up of a chip's floorplan, which is the arrangement of its subsystems – such as its CPU and GPU cores, cache memory, RAM controllers, and so on – on its silicon die. The placement of the minute electronic circuits that make up these modules can affect the microchip's power consumption and processing speed: the wiring and signal routing needed to connect it all up matters a lot.

In a paper to be published this week in Nature, and seen by The Register ahead of publication, Googlers Azalia Mirhoseini and Anna Goldie, and their colleagues, describe a deep reinforcement-learning system that can create floorplans in under six hours whereas it can take human engineers and their automated tools months to come up with an optimal layout.