BriefGPT.xyz
Oct, 2023
PolyThrottle: 边缘设备上的能效高的神经网络推断
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices
HTML
PDF
Minghao Yan, Hongyi Wang, Shivaram Venkataraman
TL;DR
通过使用约束性贝叶斯优化，该研究论文研究在推理阶段配置与能耗之间的关系，提出了PolyThrottle解决方案，能够在满足应用约束条件的同时，对个别硬件组件进行优化配置，从而将能耗降低了36%。
Abstract
As
neural networks
(NN) are deployed across diverse sectors, their energy demand correspondingly grows. While several prior works have focused on reducing
energy consumption
during training, the continuous operat
→