2022/02/14 by Qiyang Zhang, Xiang Li, Zhang, Qiyang +15 · 1 citation
Computer Science · Engineering · #Age of Information Optimization #FOS: Computer and information sciences #Green IT and Sustainability #IoT and Edge/Fog Computing #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI)
paper · pdf · doi:10.48550/arxiv.2202.06512
openalex publication_date 2022/02/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deploying deep learning (DL) on mobile devices has been a notable trend in recent years. To support fast inference of on-device DL, DL libraries play a critical role as algorithms and hardware do. Unfortunately, no prior work ever dives deep into the ecosystem of modern DL libs and provides quantitative results on their performance. In this paper, we first build a comprehensive benchmark that includes 6 representative DL libs and 15 diversified DL models. We then perform extensive experiments on 10 mobile devices, which help reveal a complete landscape of the current mobile DL libs ecosystem. For example, we find that the best-performing DL lib is severely fragmented across different models and hardware, and the gap between those DL libs can be rather huge. In fact, the impacts of DL libs can overwhelm the optimizations from algorithms or hardware, e.g., model quantization and GPU/DSP-based heterogeneous computing. Finally, atop the observations, we summarize practical implications to different roles in the DL lib ecosystem.