TPUs are Google’s specialized ASICs built exclusively for accelerating tensor-heavy matrix multiplication used in deep learning models. TPUs use vast parallelism and matrix multiply units (MXUs) to ...

Google has spent more than a decade developing silicon, a bet that's paying off in a big way from the AI boom. The company says increased demand for its Tensor Processing Units, or TPUs, is one reason ...

Scientists in China have developed a tensor processing unit (TPU) that uses carbon-based transistors instead of silicon – and they say it's extremely energy efficient. When you purchase through links ...

Google says its new Ironwood chip, the seventh generation of the company’s Tensor Processing Unit, is more than four times faster than its prior version. The disclosure signals a fresh push to speed ...