A New Golden Age in Computer Architecture: Empowering the Machine-Learning Revolution
Authors:
- 16 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 38 (2) , 21-29
Abstract
The end of Moores law and Dennard scaling has led to the end of rapid improvement in general-purpose program performance. Machine learning (ML), and in particular deep learning, is an attractive alternative for architects to explore. It has recently revolutionized vision, speech, language understanding, and many other fields, and it promises to help with the grand challenges facing our society. The computation at its core is low-precision linear algebra. Thus, ML is both broad enough to apply to many domains and narrow enough to benefit from domain-specific architectures, such as Googles Tensor Processing Unit (TPU). Moreover, the growth in demand for ML computing exceeds Moores law at its peak, just as it is fading. Hence, ML experts and computer architects must work together to design the computing systems required to deliver on the potential of ML. This article offers motivation, suggestions, and warnings to computer architects on how to best contribute to the ML revolution.Keywords
This publication has 9 references indexed in Scilit:
- Artificial intelligence for analyzing orthopedic trauma radiographsActa Orthopaedica, 2017
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus PhotographsJAMA, 2016
- Hybrid computing using a neural network with dynamic external memoryNature, 2016
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Caffe2014
- On rectified linear units for speech processing2013
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012