用向量量化压缩神经元权重，让类脑芯片省下超一半内存
VQ4SNN: Vector Quantization for Memory-Efficient FPGA Spiking Neural Networks
- 用两级内存结构替代传统存储，通过向量量化共享权重
- 在不增加逻辑资源的前提下，BRAM占用减少52%-61%
- 专为FPGA设计，适合边缘计算中的低功耗类脑芯片部署
脉冲神经网络（SNN）为边缘AI提供了节能范式，但其在FPGA上的部署受限于片上内存对突触权重的存储能力。为解决这一瓶颈，本文提出VQ4SNN，一种面向硬件的架构，通过向量量化（VQ）实现权重共享以降低内存需求。据我们所知，这是首个将VQ应用于流水线空间数据流SNN加速器的FPGA实现。VQ4SNN采用两级内存组织：紧凑指针与共享量化权重向量码本，取代传统权重存储。设计融合了面向FPGA的内存映射与分析式量化参数选择，在保持推理精度的同时实现高效部署。实验表明，相比当前最先进的无压缩FPGA SNN，总BRAM用量减少52%-61%，且未增加整体逻辑资源利用率。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for edge AI, making them attractive for hardware acceleration. However, deploying dense SNNs on FPGAs is constrained by limited on-chip memory for synaptic weight storage. To address this bottleneck, we propose VQ4SNN, a hardware-aware architecture that reduces memory requirements through Vector Quantization (VQ)-based weight sharing. To the best of our knowledge, this is the first application of VQ to pipelined spatial-dataflow SNN accelerators on FPGAs. VQ4SNN replaces conventional weight storage with a two-level memory organization consisting of compact pointers and a shared codebook of quantized weight vectors. The proposed design integrates FPGA-aware memory mapping with analytical VQ parameter selection, enabling efficient deployment on such accelerators while preserving inference accuracy. The experimental results show a reduction of 52-61% in the total number of BRAMs compared to the state-of-the-art uncompressed FPGA SNNs without increasing overall logic utilization.
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。