Survey of Machine Learning Accelerators

TL;DR

This survey updates the landscape of AI accelerators, analyzing recent trends in architectures, performance, and power consumption across a variety of innovative technologies and designs.

Contribution

It provides a comprehensive summary of recently announced AI accelerators, including performance, power metrics, and technological diversity, with trend analysis.

Findings

Increasing diversity in accelerator architectures

Notable trends in power consumption and numerical precision

Growth in accelerators for training and inference

Abstract

New machine learning accelerators are being announced and released each month for a variety of applications from speech recognition, video object detection, assisted driving, and many data center applications. This paper updates the survey of of AI accelerators and processors from last year's IEEE-HPEC paper. This paper collects and summarizes the current accelerators that have been publicly announced with performance and power consumption numbers. The performance and power values are plotted on a scatter graph and a number of dimensions and observations from the trends on this plot are discussed and analyzed. For instance, there are interesting trends in the plot regarding power consumption, numerical precision, and inference versus training. This year, there are many more announced accelerators that are implemented with many more architectures and technologies from vector engines, dataflow engines, neuromorphic designs, flash-based analog memory processing, and photonic-based processing.