HAWX框架加速神经网络近似设计，比传统方法快23倍以上。
HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs
- 通过多级敏感度评分，智能筛选近似计算单元。
- 在LeNet-5上实现超300万倍的滤波器级搜索加速。
- 适合芯片设计者快速优化大模型硬件部署效率。
本文提出HAWX，一种面向硬件的可扩展近似搜索框架，采用多层级敏感度评分（操作、滤波器、层、模型）指导异构AxC模块的有选择性集成。基于准确率、功耗和面积的预测模型，HAWX显著加速候选配置评估，在层级搜索中实现超过23倍加速（含两个近似块），在LeNet-5的滤波器级搜索中更达3×10⁶倍以上加速，同时保持与穷举搜索相当的精度。在VGG-11、ResNet-18和EfficientNetLite等主流DNN基准上验证，其效率优势随网络规模呈指数级增长。HAWX支持空间与时间型加速器架构，可集成现成或定制的近似单元。
原文摘要 · Abstract (English)
This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer, and model) to guide selective integration of heterogeneous AxC blocks. Supported by predictive models for accuracy, power, and area, HAWX accelerates the evaluation of candidate configurations, achieving over 23* speedup in a layer-level search with two candidate approximate blocks and more than (3*106)* speedup at the filter-level search only for LeNet-5, while maintaining accuracy comparable to exhaustive search. Experiments across state-of-the-art DNN benchmarks such as VGG-11, ResNet-18, and EfficientNetLite demonstrate that the efficiency benefits of HAWX scale exponentially with network size. The HAWX hardware-aware search algorithm supports both spatial and temporal accelerator architectures, leveraging either off-the-shelf approximate components or customized designs.
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。