Sparse neural networks can greatly facilitate the deployment of neural networks on resource-constrained platforms as they offer compact model sizes while retaining inference accuracy. Because of the sparsity in parameter matrices, sparse neural netwo
rks can, in principle, be exploited in accelerator architectures for improved energy-efficiency and latency. However, to realize these improvements in practice, there is a need to explore sparsity-aware hardware-software co-design. In this paper, we propose a novel silicon photonics-based sparse neural network inference accelerator called SONIC. Our experimental analysis shows that SONIC can achieve up to 5.8x better performance-per-watt and 8.4x lower energy-per-bit than state-of-the-art sparse electronic neural network accelerators; and up to 13.8x better performance-per-watt and 27.6x lower energy-per-bit than the best known photonic neural network accelerators.
We propose an optimization method to improve power efficiency and robustness in silicon-photonic-based coherent integrated photonic neural networks. Our method reduces the network power consumption by 15.3% and the accuracy loss under uncertainties by 16.1%.
Silicon-photonic neural networks (SPNNs) offer substantial improvements in computing speed and energy efficiency compared to their digital electronic counterparts. However, the energy efficiency and accuracy of SPNNs are highly impacted by uncertaint
ies that arise from fabrication-process and thermal variations. In this paper, we present the first comprehensive and hierarchical study on the impact of random uncertainties on the classification accuracy of a Mach-Zehnder Interferometer (MZI)-based SPNN. We show that such impact can vary based on both the location and characteristics (e.g., tuned phase angles) of a non-ideal silicon-photonic device. Simulation results show that in an SPNN with two hidden layers and 1374 tunable-thermal-phase shifters, random uncertainties even in mature fabrication processes can lead to a catastrophic 70% accuracy loss.
