IBM uses light for ultra-fast computing in AI systems

Photonic integrated circuits use light instead of electricity for computing

IBM uses light for ultra-fast computing in AI systems

Photo for representation. — iStock

New Delhi, January 10

IBM researchers have developed a way to dramatically reduce latency in Artificial Intelligence (AI) systems by using light, instead of electricity, to create ultra-fast computing.

The IBM team, along with scientists from the universities of Oxford, Muenster and Exeter, achieved this by using photonic integrated circuits that use light instead of electricity for computing.

The light-based tensor core could be used, among other applications, for autonomous vehicles.

In a Nature paper, they have detailed combination of photonic — demonstrating a photonic tensor core that can perform computations with unprecedented, ultra-low latency and compute density.

“Our tensor core runs computations at a processing speed higher than ever before. It performs key computational primitives associated with AI models such as deep neural networks for computer vision in less than a microsecond, with remarkable areal and energy efficiency,” IBM said in a blog post.

In 2015, researchers from Oxford University, the University of Muenster and the University of Exeter developed a photonic phase change memory device that could be written to and read from optically.

The new photonic tensor core can perform a so-called convolution operation in a single time step.

Convolution is a mathematical operation on two functions that outputs a third function expressing how the shape of one is changed by the other.

“We use a measure called TOPS to assess the number of Operations Per Second, in Trillions, that a chip is able to process” said Abu Sebastian from IBM Research.

This is just the beginning.

“We expect that with reasonable scaling assumptions, we can achieve an unprecedented PetaMAC (thousand trillion MAC operations) per second per mm2,” IBM said.

In comparison, the compute density associated with state-of-the-art AI processors is less than 1 TOPS/mm2, meaning less than a trillion operations per second per mm2,” IBM said. IANS

Top Stories

60 km, 5 routes, nod for Republic Day rally: Farmers

60 km, 5 routes, nod for Republic Day rally: Farmers

But Delhi Police say talks in final stages I No decision tak...

U-turn by nabbed man, claims was forced to lie

U-turn by nabbed man, claims was forced to lie

Farm leaders refute statement to police

Post slogans, Didi refuses to address event

Post slogans, Didi refuses to address event

PM on stage, ‘Jai Shri Ram’ chants I CM says it’s unacceptab...

Covaxin shots in Punjab, six more states from next week

Covaxin shots in Punjab, six more states from next week

Exhilarating, says IAS officer Panda after jab

BJP, Cong neck and neck in Himachal ZP elections

BJP, Cong neck and neck in Himachal ZP elections

CM, LoP suffer setback on their home turfs

Cities

View All