Benchmarking Google's new TPUv2 – RiseML Blog

We are currently collecting all feedback and already started working on a more complete report -- stay tuned! For most of us, deep learning still happens on Nvidia GPUs. There is currently no alternative with practical relevance. Google's Tensor Processing Unit (TPU), a custom-developed chip for deep learning, promises to change that. Nine months after the initial announcement, Google last week finally released TPUv2 to early beta users on the Google Cloud Platform.