# A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization

arXiv: https://arxiv.org/abs/2205.11244 · HTML: https://mlsanity.com/paper/2205.11244/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 17 May 2022.

## Builds on (most cited first, 8 of 8)

- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.00090/) (2018)
- [CrossLight: A Cross-Layer Optimized Silicon Photonic Neural Network Accelerator](https://mlsanity.com/paper/2102.06960/) (2021)
- [A Survey on Silicon Photonics for Deep Learning](https://mlsanity.com/paper/2101.01751/) (2021)
- [ROBIN: A Robust Optical Binary Neural Network Accelerator](https://mlsanity.com/paper/2107.05530/) (2021)
- [BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization](https://mlsanity.com/paper/2002.03090/) (2020)
- [ARXON: A Framework for Approximate Communication over Photonic Networks-on-Chip](https://mlsanity.com/paper/2103.08828/) (2021)
- [LORAX: Loss-Aware Approximations for Energy-Efficient Silicon Photonic Networks-on-Chip](https://mlsanity.com/paper/2002.11289/) (2020)

## Built on by (most cited first, 9 of 9)

- [RecLight: A Recurrent Neural Network Accelerator with Integrated Silicon Photonics](https://mlsanity.com/paper/2209.00084/) (2022)
- [Machine Learning Accelerators in 2.5D Chiplet Platforms with Silicon Photonics](https://mlsanity.com/paper/2301.12252/) (2023)
- [SafeLight: Enhancing Security in Optical Convolutional Neural Network Accelerators](https://mlsanity.com/paper/2411.16712/) (2024)
- [Cross-Layer Design for AI Acceleration with Non-Coherent Optical Computing](https://mlsanity.com/paper/2303.12910/) (2023)
- [Accelerating Neural Networks for Large Language Models and Graph Processing with Silicon Photonics](https://mlsanity.com/paper/2401.06885/) (2024)
- [OPIMA: Optical Processing-In-Memory for Convolutional Neural Network Acceleration](https://mlsanity.com/paper/2407.08205/) (2024)
- [A Comparative Analysis of Microrings Based Incoherent Photonic GEMM Accelerators](https://mlsanity.com/paper/2402.03149/) (2024)
- [Optical Computing for Deep Neural Network Acceleration: Foundations, Recent Developments, and Emerging Directions](https://mlsanity.com/paper/2407.21184/) (2024)
- [Accelerating Diffusion Models for Generative AI Applications with Silicon Photonics](https://mlsanity.com/paper/2603.07626/) (2026)

## Abstract (arXiv)

Parameter quantization in convolutional neural networks (CNNs) can help generate efficient models with lower memory footprint and computational complexity. But, homogeneous quantization can result in significant degradation of CNN model accuracy. In contrast, heterogeneous quantization represents a promising approach to realize compact, quantized models with higher inference accuracies. In this paper, we propose HQNNA, a CNN accelerator based on non-coherent silicon photonics that can accelerate both homogeneously quantized and heterogeneously quantized CNN models. Our analyses show that HQNNA achieves up to 73.8x better energy-per-bit and 159.5x better throughput-energy efficiency than state-of-the-art photonic CNN accelerators.