Google’s New Custom Chip May Not Live Up to the Hype

Google last week announced the Tensor Processing Unit, a custom application-specific integrated circuit, at Google I/O. Built for machine learning applications, TPU has been running in Google’s data centers for more than a year. Google’s AlphaGo software, which thrashed an 18-time international Go champion in a match earlier this year, ran on servers using TPUs. These server racks house the TPUs used in the AlphaGo matches with Lee Sedol. TPU is tailored for TensorFlow, Google’s software library for machine intelligence, which it turned over to the open source community last year. Moore Still Rules For machine learning, TPUs provide an order-of-magnitude better-optimized performance per watt, Google said. It’s comparable to fast-forwarding technology about seven years — three generations of Moore’s Law. That claim is misleading, according to Kevin Krewell, a…


Link to Full Article: Google’s New Custom Chip May Not Live Up to the Hype