Complex-valued matrix-vector multiplication system for a large-scale optical FFT

Recent advancements in optical convolutional neural net-works (CNNs) and radar signal processing systems have brought an increasing need for the adoption of optical fast Fourier transform (OFFT). Presently, the fast Fourier transform (FFT) is executed using electronic means within prevailing architectures. However, this electronic approach faces limitations in terms of both speed and power con-sumption. Concurrently, existing OFFT systems struggle to balance the demands of large-scale processing and high pre-cision simultaneously. In response, we introduce a novel, to the best of our knowledge, solution: a complex-valued matrix-vector system harnessed through wavelength selec-tive switches (WSSs) for the realization of a 24-input optical FFT, achieving a high-accuracy level of 5.4 bits. This study capitalizes on the abundant wavelength resources available to present a feasible solution for an optical FFT system with a large N. (c) 2023 Optica Publishing Group

Automated summary

Recent advancements in optical convolutional neural networks and radar signal processing systems have led to an increasing need for the adoption of optical fast Fourier transform (OFFT). Traditional electronic methods for fast Fourier transform (FFT) face limitations in terms of speed and power consumption, while existing OFFT systems struggle to meet the demands of large-scale processing and high precision. This study presents a novel solution using a complex-valued matrix-vector system and wavelength selective switches (WSSs) to achieve a 24-input optical FFT with a high accuracy level of 5.4 bits.