Google claims that it has developed artificial intelligence software that can design computer chips faster than humans can.
Google researchers published a new paper in Nature on Wednesday describing “an edge-based graph convolutional neural network architecture” that learned how to design the physical layout of a semiconductor in a way that allows “chip design to be performed by artificial agents with more experience than any human designer.”
The researchers 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.
Here’s how the researchers described their achievement in the abstract of the paper:
Despite five decades of research, chip floorplanning has defied automation, requiring months of intense effort by physical design engineers to produce manufacturable layouts. Here we present a deep reinforcement learning approach to chip floorplanning. In under six hours, our method automatically generates chip floorplans that are superior or comparable to those produced by humans in all key metrics, including power consumption, performance and chip area.
In terms of design, Google is referring to 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.
Google has already used this AI system to produce the floorplan of a next-generation TPU – its Tensor Processing Unit, which the web giant uses to accelerate the neural networks in its search engine, public cloud, AlphaGo and AlphaZero, and other projects and products, notes the report.
In effect, Google is using machine-learning software to optimize future chips that speed up machine-learning software. The virtuous cycle of AI designing chips for AI looks like it’s only just getting started.