Skip to Content

A New Optical Chip Makes Light Work of Optimization Problems

Hewlett Packard Labs has developed a complex processor that uses light to outperform regular chips on tasks like the traveling salesman problem.
January 3, 2017

As Moore’s Law stutters, computing companies are looking to develop ways to calculate using light rather than electrons. Now researchers at Hewlett Packard Labs have built one of the most complex optical chips yet, and claim that it could be used to perform optimization tasks more efficiently than regular hardware.

 IEEE Spectrum reports that the team has traded electrons for light beams to build a device that features 1,052 optical components that all work together to crunch numbers.The researchers claim that the approach can be used to identify solutions to complex optimization problems more efficiently than normal chips. As an example, the team says that it will be able to crunch through the traveling salesman problem—a classic mathematical challenge that demands the calculation of the most efficient route between a number of points—far faster than its rivals.

Other optical computing techniques promise similar advantages. As we recently reported, laser-based computing approaches are being used to analyze genetic data and intelligently compress information faster than normal computers. Along with their speed gains, light-based chips could also use less energy.

Such advantages explain why chip giants like Intel are also working out how to build optical computing hardware. The Hewlett Packard Labs creation is another milepost on the road to making lighter work of the problem.

(Read more: IEEE Spectrum, “Intel Tries to Rearchitect the Computer—and Itself,” “Light Chips Could Mean More Energy-Efficient Data Centers,” “Computing with Lasers Could Power Up Genomics and AI”)

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.