The most popular and comprehensive Open Source ECM platform
Let us know more
Artificial Intelligence: Advancing from Optimizing Win Positions in Chess to Semiconductor Chip Floorplanning Placement
Chip designers are turning to artificial intelligence to help both speed up the chip design process but also make chip designs more efficient.
AI has been very successful in solving and winning board game challenges, like Chess and Go. The next logical step is to try to use AI to assist with the design and development of very complex components, like semiconductors. Computer chips are some of the most complex thing that humans create. Compared to board games, the complexity of design of semiconductor chips is significantly more difficult, but it can be approached in a similar way. Instead of identifying and optimizing for “win conditions” of a board game, chip design can be optimized for things like computational efficiency.
Google, Nvidia, Synopsys, and Samsung are just a few of the companies that are experimenting with the use of AI as part of the chip design process. The early reports are that results have been very good.
Song Han, MIT professor, said that “AI-powered co-design of software and hardware is a rapidly growing direction. We have seen promising results.”
Azalia Mirhoseini and Anna Goldie, Google engineers, said that as AI “is exposed to a greater volume and variety of chips, it becomes both faster and better at generating optimized placements for new chip blocks, bringing us closer to a future in which chip designers are assisted by artificial agents with vast chip placement experience. A fast, high-quality, automatic chip placement method could greatly accelerate chip design and enable co-optimization with earlier stages of the chip design process. After all that hardware has done for machine learning, we believe that it is time for machine learning to return the favor.”
