按层优化权重选择，显著降低神经网络加速器能耗
Layer-wise Weight Selection for Power-Efficient Neural Network Acceleration
- 构建分层能量模型，结合激活统计与高位汉明距离分组
- 实现58.6%能耗降低，仅损失2-3%精度
- 适合硬件能效优化需求的模型压缩场景
流式阵列加速器执行卷积神经网络时，能耗主要来自乘累加（MAC）单元的翻转活动。尽管已有工作利用权重相关的MAC功耗进行压缩，但现有方法常依赖全局激活模型、粗略能耗代理或不区分层级的策略，限制了其在真实硬件上的效果。本文提出一种面向能耗的分层压缩框架，显式利用MAC与层级级能耗特性。首先构建分层感知的MAC能耗模型，融合每层激活统计与22位部分和跳变的MSB-Hamming距离分组，并集成到片上阵列映射中以估算卷积层能耗。在此模型基础上，引入量化感知训练中的能耗-精度协同优化权重选择算法，以及基于能耗优先的分层调度策略，在全局精度约束下更激进地压缩高能耗层。不同CNN模型的实验表明，可实现最高58.6%的能耗降低，精度仅下降2-3%，优于当前最先进功耗感知基线。
原文摘要 · Abstract (English)
Systolic array accelerators execute CNNs with energy dominated by the switching activity of multiply accumulate (MAC) units. Although prior work exploits weight dependent MAC power for compression, existing methods often use global activation models, coarse energy proxies, or layer-agnostic policies, which limits their effectiveness on real hardware. We propose an energy aware, layer-wise compression framework that explicitly leverages MAC and layer level energy characteristics. First, we build a layer-aware MAC energy model that combines per-layer activation statistics with an MSB-Hamming distance grouping of 22-bit partial sum transitions, and integrate it with a tile-level systolic mapping to estimate convolution-layer energy. On top of this model, we introduce an energy accuracy co-optimized weight selection algorithm within quantization aware training and an energy-prioritized layer-wise schedule that compresses high energy layers more aggressively under a global accuracy constraint. Experiments on different CNN models demonstrate up to 58.6\% energy reduction with 2-3\% accuracy drop, outperforming a state-of-the-art power-aware baseline.
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。