AI RESEARCH
SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference
arXiv CS.LG
•
ArXi:2603.21908v1 Announce Type: new Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often too coarse to capture intra-inference variations, whereas fine-grained operator-level scaling suffers from prohibitive performance degradation due to significant hardware switching latency. This paper presents SparseDVFS, a fine-grained, sparse-aware DVFS framework designed for energy-efficient edge inference.