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 networks 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.

中文翻译：

---

SONIC：用于节能深度学习的硅光子稀疏神经网络推理加速器

稀疏神经网络可以极大地促进神经网络在资源受限平台上的部署，因为它们提供紧凑的模型尺寸，同时保持推理精度。由于参数矩阵的稀疏性，原则上可以在加速器架构中利用稀疏神经网络来提高能效和延迟。然而，要在实践中实现这些改进，需要探索稀疏感知的软硬件协同设计。在本文中，我们提出了一种新型的基于硅光子学的稀疏神经网络推理加速器，称为 SONIC。我们的实验分析表明，与最先进的稀疏电子神经网络加速器相比，SONIC 可以实现高达 5.8 倍的每瓦性能和 8.4 倍的低每比特能量；每瓦性能提升高达 13.8 倍和 27。