Time-space-wavelength multiplexed photonic tensor core using WDM SiGe EAM array chiplets
A. Prapas, Miltiadis Moralis‐Pegios, Apostolos Tsakyridis, Stefanos Kovaios, Odysseas Asimopoulos, Christos Pappas, Theodoros Moschos, Manos Kirtas, Nikolaos Passalis, Konstantinos Vyrsokinos, Anastasios Tefas, Nikos Pleros · Optics Express · 2025
Photonic neural networks (PNNs) are projected to be the next-generation AI platform, driving significant advances in compute energy and area efficiency by leveraging light's parallelism across space, wavelength, and time. Here we present a photonic integrated tensor core (PITC) architecture that combines an arrayed waveguide grating router (AWGR)-enabled PNN with a SiGe electro-absorption modulator (EAM) array following a chiplet-based silicon photonic (SiPho) accelerator setup for multi-wavelength data and weight encoding. The 8 × 8 PITC architectural layout was experimentally validated in two AI benchmark workloads at 20 Gbaud, successfully classifying the IRIS and MNIST datasets yielding Cohen's kappa-scores of 0.8438 and 0.7421, respectively.