AI Benchmark: Running Deep Neural Networks on Android Smartphones
This study addresses the challenge of running AI algorithms on mobile devices for developers and researchers, providing a comprehensive benchmark but is incremental as it builds on existing hardware and framework analyses.
The paper benchmarks the performance of deep neural networks on Android smartphones, evaluating hardware acceleration across four major chipset platforms and presenting real-world performance results for various mobile SoCs.
Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones. We give an overview of the hardware acceleration resources available on four main mobile chipset platforms: Qualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the real-world performance results of different mobile SoCs collected with AI Benchmark that are covering all main existing hardware configurations.