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 ...

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 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 ...