Google’s TPU’s being primed for the Quantum Jump

As the world is gearing in direction of extra automation and AI, the necessity for quantum computing has additionally grown exponentially. Quantum computing lies on the intersection of quantum physics and high-end pc expertise, and in a couple of means, maintain the important thing to our AI-driven future.

Quantum computing requires state-of-the-art instruments to carry out high-end computing. This is the place TPUs turn out to be useful. TPUs or Tensor Processing Units are custom-built ASICs (Application Specific Integrated Circuits) to execute machine studying duties effectively. TPUs are particular {hardware} developed by Google for neural community machine studying, specifically customised to Google’s Machine Learning software program, Tensorflow.

The liquid-cooled Tensor Processing units, constructed to fit into server racks, can ship as much as 100 petaflops of compute. It powers Google merchandise like Google Search, Gmail, Google Photos and Google Cloud AI APIs. 

What’s Floq?

With the necessity for quantum computing growing and the assets to construct heavy machines getting scarcer, the need to create a program for sooner computation has turn into paramount. To that finish, Google has provide you with an API known as, Floq.

Sandbox at Alphabet, Google’s secretive software program improvement staff, is the mind belief behind Floq. Floq permits builders to harness TPUs to simulate quantum computing workloads. Google offered Floq to 50 groups as a part of the QHack Open Hackathon.

The Sandbox at Alphabet staff repurposed TPUs to speed up simulations within the cloud to permit builders to make use of frontends like TensorCirculation Quantum and PennyLane to construct quantum fashions and run them remotely on Floq.

Floq simulators run 10 to 100x sooner than the most recent simulations accelerated by GPUs when it comes to runtime, in accordance with Sandbox at Alphabet scientist Guillaume Verdon.

“The team has been experimenting with how to use Floq for physics, machine learning. And we have developed our own open-source library for tensor networks that run on TPUs. It’s [surprising] how good the chips are for quantum simulation. It’s almost like they were designed for this task,” Vernon mentioned.

See Also


Floq, as soon as launched extensively, will work hand-in-hand with Cirq, Google’s service that provides builders entry to its quantum computing {hardware}. It will rival IBM’s Quantum Experience suite and simulators from Intel, Amazon, and Microsoft.

Like Russian President Vladimir Putin mentioned, within the AI arms race, the nation with one of the best tech will rule the world. The quantum computer systems are the key drivers of this AI race. Interestingly, again within the early 2000s, Wired’s Kevin Kelly requested Google founders concerning the enterprise mannequin and the way Google Search would convey income, they responded by merely saying: “Oh, we’re actually building an artificial intelligence company.”

Google has certainly stayed the course. Though the Floq was introduced in February in a dwell streaming occasion, it didn’t entice a number of media consideration. But it’s clear that Floq has the potential to vary the quantum computing sport and provides Alphabet an edge over the rivals. Though many of the particulars about Floq is saved beneath the wraps, the world is certainly wanting ahead to its future iterations and the large reveal.

Table of Contents

Subscribe to our Newsletter

Get the most recent updates and related presents by sharing your electronic mail.

Join Our Telegram Group. Be a part of an interesting on-line group. Join Here.

Peter Mathew

Passionate about all issues media and communications. I really like being a journalist, although you may see me learn a guide or watch a traditional movie in my free time.


Please enter your comment!
Please enter your name here