In plain words: A running survey collects peak speed and power numbers for every publicly announced commercial AI chip and plots them together to show how the field is moving. The latest update adds charts sorted by release date and covers newer neuromorphic, photonic, and memory-based inference chips, revealing how speed and power have shifted over time.

Abstract · AI and ML Accelerator Survey and Trends

This paper updates the survey of AI accelerators and processors from past three years. This paper collects and summarizes the current commercial accelerators that have been publicly announced with peak 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 again discussed and analyzed. Two new trends plots based on accelerator release dates are included in this year's paper, along with the additional trends of some neuromorphic, photonic, and memristor-based inference accelerators.

Albert Reuther, Peter Michaleas, Michael Jones, Vijay Gadepally, Siddharth Samsi, Jeremy Kepner
arXiv:2210.04055 · cs.AR · submitted Oct 8, 2022
abstract · pdf · html · 10 pages, 4 figures, 2022 IEEE High Performance Extreme Computing (HPEC) Conference. arXiv admin note: substantial text overlap with arXiv:2009.00993, arXiv:2109.08957