Google claims to have built the fastest supercomputer for AI

April 05, 2023

Google made public new details about the supercomputers it uses to train its AI models, sending the price of its parent company Alphabet up by 1.3%.

Google claims that its latest generation of Tensor chips, or Tensor Processing Units, is the fastest, most energy-efficient and most optimized chips.

Google revealed how it has strung more than 4,000 of the chips together into a supercomputer using its own custom-developed optical switches to help connect individual machines.

AI models like ChatGPT and Bard have exploded in size and have become far too large to store on a single chip.

Currently, all major software studios are using NVIDIA’s A100 processors.

But now Google claims that its latest Tensor chips outperform NVIDIA’s offering in every conceivable parameter.

The AI generated text models have become very popular in recent months and have been advancing at exponential speed.