Litcius/Paper detail

A domain-specific supercomputer for training deep neural networks

Norman P. Jouppi, Doe Hyun Yoon, George Thomas Kurian, Sheng Li, Nishant Patil, James Laudon, Cliff Young, David A. Patterson

2020Communications of the ACM253 citationsDOIOpen Access PDF

Abstract

Google's TPU supercomputers train deep neural networks 50x faster than general-purpose supercomputers running a high-performance computing benchmark.

Topics & Concepts

SupercomputerComputer scienceTraining (meteorology)Domain (mathematical analysis)Artificial neural networkParallel computingArtificial intelligenceComputational scienceMathematicsMeteorologyPhysicsMathematical analysisStochastic Gradient Optimization TechniquesAdvanced Neural Network ApplicationsParallel Computing and Optimization Techniques