Survey of Machine Learning Accelerators

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.

arXiv comment12 pages, 2 figures, IEEE-HPEC conference, Waltham, MA, September 21-25, 2020. arXiv admin note: text overlap with arXiv:1908.11348

References in corpus (9)

• Deep Learning with Coherent Nanophotonic Circuits
• Deep Learning with Limited Numerical Precision
• Mixed Precision Training
• An Analysis of Deep Neural Network Models for Practical Applications
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• A Survey of Neuromorphic Computing and Neural Networks in Hardware
• Survey and Benchmarking of Machine Learning Accelerators
• EIE: Efficient Inference Engine on Compressed Deep Neural Network
• Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Going

Cited by in corpus (16)

• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• An optical neural network using less than 1 photon per multiplication
• AI and ML Accelerator Survey and Trends
• AI Accelerator Survey and Trends
• Integrated Photonic Tensor Processing Unit for a Matrix Multiply: a Review
• TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers
• Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial
• A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model
• Towards Energy Consumption and Carbon Footprint Testing for AI-driven IoT Services
• Deep Photonic Reservoir Computer for Speech Recognition
• Asymmetrical estimator for training encapsulated deep photonic neural networks
• Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
• From Domain-Specific Languages to Memory-Optimized Accelerators for Fluid Dynamics
• Passive All-Optical Nonlinear Neuron Activation via PPLN Nanophotonic Waveguides
• Lincoln AI Computing Survey (LAICS) and Trends
• Metrics for spin-based computing