This is an Inside Science story. Artificial intelligence can design computer microchips that perform at least as well as those designed by human experts, devising such blueprints thousands of times faster. This new research from Google is already helping with the design of microchips for the company's next generation of AI computer systems. The process of designing the physical layout of a chip's parts, known as floor planning, is key to a device's ultimate performance. This complex task often requires months of intense efforts from experts, and despite five decades of research, no automated floorplanning technique has reached human-level performance until now.

This is an Inside Science story. Artificial intelligence can design computer microchips that perform at least as well as those designed by human experts, devising such blueprints thousands of times faster. This new research from Google is already helping with the design of microchips for the company's next generation of AI computer systems. The process of designing the physical layout of a chip's parts, known as floor planning, is key to a device's ultimate performance. This complex task often requires months of intense efforts from experts, and despite five decades of research, no automated floorplanning technique has reached human-level performance until now.

One emerging trend in chip design is a move away from bigger, grander designs that double the number of transistors every 18 months, as Moore's Law stipulates. Instead, there is growing interest in specialized chips for specific tasks such as AI and machine learning, which are advancing rapidly on scales measured in weeks and months. But chips take much longer than this to design, and that means new microprocessors cannot be designed quickly enough to reflect current thinking. "Today's chips take years to design, leaving us with the speculative task of optimizing them for the machine learning models of two to five years from now," lament Azalia Mirhoseini, Anna Goldie and colleagues at Google, who have come up with a novel way to speed up this process. Their new approach is to use AI itself to speed up the process of chip design.

Azalia Mirhoseini, a research scientist at Google Brain, is using artificial intelligence itself to make better chips for artificial intelligence. Many microchips that are used for AI weren't specifically built for it. Most are repurposed from hardware used in video and gaming. As a result, these older, human-engineered designs leave much to be desired in terms of energy efficiency, cost, and functionality. Mirhoseini's system--which trained itself using trial and error, based on the AI concept of reinforcement learning--can produce chip designs in just a few hours.