Evaluation of the Tensor Processing Unit: A Deep Neural Network Accelerator for the Datacenter

David Patterson
EECS Professor Emeritus and Professor in the Graduate School
UC Berkeley

Friday, February 8, 2:40 PM
E2-180

Abstract:  With the ending of Moore’s Law, many computer architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. The Tensor Processing Unit (TPU), deployed in Google datacenters since 2015, is a custom chip that accelerates deep neural networks (DNNs).  We compare the TPU to contemporary server-class CPUs and GPUs deployed in the same datacenters.