High Throughput Multi-Channel Parallelized Diffraction Convolutional Neural Network Accelerator

TL;DR

This paper introduces a high-throughput optical convolutional neural network accelerator that leverages diffraction optics for parallel processing, achieving speeds comparable to modern electronic systems and significantly surpassing previous optical methods.

Contribution

It demonstrates the first operation-parallelized Fourier optical CNN accelerator capable of processing multiple kernels simultaneously, greatly enhancing speed and efficiency.

Findings

Achieved about 100x speedup over existing optical diffraction processors.

Processed large-scale matrices approximately 10 times faster than current electronic systems.

Enabled simultaneous multi-kernel processing in Fourier domain using optical diffraction.

Abstract

Convolutional neural networks are paramount in image and signal processing including the relevant classification and training tasks alike and constitute for the majority of machine learning compute demand today. With convolution operations being computationally intensive, next generation hardware accelerators need to offer parallelization and algorithmic-hardware homomorphism. Fortunately, diffractive display optics is capable of million-channel parallel data processing at low latency, however, thus far only showed tens of Hertz slow single image and kernel capability, thereby significantly underdelivering from its performance potential. Here, we demonstrate an operation-parallelized high-throughput Fourier optic convolutional neural network accelerator. For the first time simultaneously processing of multiple kernels in Fourier domain enabled by optical diffraction has been achieved alongside with already conventional in the field input parallelism. Additionally, we show an about one hundred times system speed up over existing optical diffraction-based processors and this demonstration rivals performance of modern electronic solutions. Therefore, this system is capable of processing large-scale matrices about ten times faster than state of art electronic systems.