Technology 2 min read

New Algorithm Enables Computer Chips to Design Themselves

CROCOTHERY / Shutterstock.com

CROCOTHERY / Shutterstock.com

Researchers at Google have just developed an algorithm to help computer chips attain optimum circuitry placement.

One significant challenge of computer design is figuring out how to pack the chips — a process known as chip floor planning.

It involves ergonomically packing thousands of components while ensuring that they maintain power and communicate flawlessly. What’s more, the arrangement must occur within a space that’s the size of a fingernail.

It’s similar to what interior decorators do when laying out plans to dress up a room.

The difference — aside from the absence of furniture — is digital circuitry involves more than a one-floor plan. Instead, designers must consider integrated layouts on multiple floors.

Not only is the process tedious, but it’s also time-consuming. Since chip components are continually improving, a floor plan often becomes outdated fast.

That’s about to change.

In an announcement, senior Google research engineers Anna Goldie and Azalia Mirhoseini said they developed an algorithm that addresses this issue. Here’s how it works.

Training Computer Chips to Design Themselves

According to the researchers, the algorithm can learn how to achieve optimum circuitry placement in computer chips.

The new system analyzes millions of potential possibilities, instead of thousands, which is the current norm. That way, it can provide chips that are smaller, faster, cheaper, and that’ll take advantage of the latest innovation.

What’s more, the algorithm can do all these in the fraction of the time that chip design currently requires.

In a statement published on arxiv.org, a repository of scientific research managed by Cornell University, the designers explained:

“We believe that it is AI itself that will provide the means to shorten the chip design cycle, creating a symbiotic relationship between hardware and AI, with each fueling advances in the other.”

The new algorithm uses the concept of reinforcement learning. In other words, the system generates rewards and punishment for each proposed design until it identifies the best approach.

The resulting assembly-line production is superior to designs created by human engineers. And this would ultimately help create computer chips that are smaller but more powerful.

Read More: Artificial Neurons on Silicon Chips Could Cure Chronic Diseases

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.