用光门控与分层映射提升光神经网络的鲁棒性与能效。
ROSA: Robust and Energy-Efficient Microring-Based Optical Neural Networks via Optical Shift-and-Add and Layer-Wise Hybrid Mapping
- 引入光移位相加模块和分层混合映射策略。
- 能效延迟积降低64%，准确率提升8.3%。
- 适合低功耗光学计算芯片设计者参考。
本文提出ROSA，一种基于微环谐振器的光神经网络架构，通过光学移位相加（OSA）模块和分层混合映射策略，提升鲁棒性与能效。该工作构建了考虑数模转换器与热漂移的噪声感知电压-权重模型，并设计了工作负载感知框架，协同优化微环阵列尺寸与分层数据流。优化后的阵列相较DEAP-CNNs与通用紧凑阵列，聚合相对能效延迟积（EDP）分别降低64%和26%。OSA模块进一步实现29%的EDP下降。所提混合映射策略在CIFAR-10上较权重固定映射准确率提升8.3%，平均能效延迟积低于DEAP-CNNs达54.7%。
原文摘要 · Abstract (English)
This work presents ROSA, a microring-based optical neural network architecture that improves robustness and energy efficiency using an optical shift-and-add (OSA) module and a layer-wise hybrid mapping strategy. It introduces a noise-aware voltage-to-weight model considering DAC and thermal variations, and a workload-aware framework to co-optimize MRR array size and layer-wise dataflow. Optimized arrays reduce the aggregated relative energy-delay product (EDP) by 64% and 26% compared with DEAP-CNNs and a general compact array, respectively. OSA further contributes 29% EDP reduction. The proposed hybrid mapping strategy improves CIFAR-10 accuracy by 8.3% over weight-stationary mapping while achieving an average 54.7% lower EDP than DEAP-CNNs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。