arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02738physics.optics
收藏

光子脉冲哈希检索的硬件实现

Hardware Implementation of Photonic Spiking Hash Retrieval

State Key Laboratory of Integrated Service Networks, Xidian University(西安电子科技大学综合业务网理论及关键技术国家重点实验室);State Key Discipline Laboratory of Wide Band gap Semiconductor Technology, School of Microelectronics, Xidian University(西安电子科技大学微电子学院宽禁带半导体技术国家重点学科实验室)

Shangxuan Shi, Shuiying Xiang, Xintao Zeng, Yonghang Chen, Wanting Yu, Yahui Zhang, Xingxing Guo, Yue Hao

AI总结:

本文提出了一种基于光子脉冲神经网络的硬件实现方案,实现了高效、低能耗的二进制代码生成与高精度检索。

摘要:

哈希检索是大规模相似性搜索的关键技术,广泛应用于检索增强生成(RAG)大型语言模型(LLMs)、大规模图像库和生物信息学序列匹配。然而,传统电子哈希实现处理高维数据时面临严重的能耗和延迟瓶颈,而现有的光子神经网络往往缺乏在模拟噪声下直接生成二进制代码的鲁棒机制。为了解决这些挑战,我们提出了一种硬件软件协同设计的光子脉冲哈希框架。我们利用分布式反馈激光器(DFB-SA)的非线性阈值动态特性,实现单步脉冲神经网络(SNN)的最终二值化。关键的是,引入了硬件感知的量化边距损失,以最大化决策边距,有效缓解由光学强度波动引起的位翻转。在MNIST(图像)和20 Newsgroups(文本)数据集上验证,我们的系统展示了稳健的二进制代码生成和与数字基线相当的高检索精度。最显著的是,所提出的光子架构具有更高的效率,编码延迟为2.294 ns/查询,能耗为73.70 pJ/查询。这项工作为高吞吐量信息检索任务中的超快、低能耗光电子神经形态计算提供了稳健且可行的路径。

英文摘要:

Hashing retrieval is a pivotal technology for large-scale similarity search, widely applied in retrieval-augmented generation (RAG) for large language models (LLMs), massive image repositories, and bioinformatics sequence matching. However, traditional electronic hashing implementations face severe bottlenecks in power consumption and latency when processing high-dimensional data, while existing photonic neural networks often lack robust mechanisms for direct binary code generation under analog noise. To address these challenges, we propose a hardware-software co-designed photonic spiking hashing framework. We utilize the nonlinear thresholding dynamics of a distributed feedback laser with saturable absorber (DFB-SA) to realize the final binarization of a single-step spiking neural network (SNN). Crucially, a hardware-aware quantization margin loss is introduced to maximize the decision margin, effectively mitigating bit flips caused by optical intensity fluctuations. Validated on MNIST (image) and 20 Newsgroups (text) datasets, our system demonstrates robust binary code generation and high retrieval accuracy comparable to digital baselines. Most significantly, the proposed photonic architecture exhibits superior efficiency with an encoding latency of 2.294 ns/query and an energy consumption of 73.70 pJ/query. This work offers a robust and viable path for ultra-fast, energy-efficient optoelectronic neuromorphic computing in high-throughput information retrieval tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑