The ever-increasing volume of data has necessitated a new computing paradigm, embodied through Artificial Intelligence (AI) and Large Language Models (LLMs). Digital electronic AI computing systems, however, are gradually reaching their physical plateaus, stimulating extensive research towards next-generation AI accelerators. Photonic Neural Networks (PNNs), with their unique ability to capitalize on the interplay of multiple physical dimensions including time, wavelength, and space, have been brought forward with a credible promise for boosting computational power and energy efficiency in AI processors. In this article, we experimentally demonstrate a novel multidimensional arrayed waveguide grating router (AWGR)-based photonic AI accelerator that can execute tensor multiplications at a record-high total computational power of 262 TOPS, offering a ~24x improvement over the existing waveguide-based optical accelerators. It consists of a 16x16 AWGR that exploits the time-, wavelength- and space- division multiplexing (T-WSDM) for weight and input encoding together with an integrated Si3N4-based frequency comb for multi-wavelength generation. The photonic AI accelerator has been experimentally validated in both Fully-Connected (FC) and Convolutional NN (NNs) models, with the FC and CNN being trained for DDoS attack identification and MNIST classification, respectively. The experimental inference at 32 Gbaud achieved a Cohen's kappa score of 0.867 for DDoS detection and an accuracy of 92.14% for MNIST classification, respectively, closely matching the software performance.
View on arXiv@article{pappas2025_2503.03263,
title={ A 262 TOPS Hyperdimensional Photonic AI Accelerator powered by a Si3N4 microcomb laser },
author={ Christos Pappas and Antonios Prapas and Theodoros Moschos and Manos Kirtas and Odysseas Asimopoulos and Apostolos Tsakyridis and Miltiadis Moralis-Pegios and Chris Vagionas and Nikolaos Passalis and Cagri Ozdilek and Timofey Shpakovsky and Alain Yuji Takabayashi and John D. Jost and Maxim Karpov and Anastasios Tefas and Nikos Pleros },
journal={arXiv preprint arXiv:2503.03263},
year={ 2025 }
}