AI Benchmark: Running Deep Neural Networks on Android Smartphones

TL;DR

This paper evaluates the current capabilities and limitations of running deep neural networks on Android smartphones by analyzing hardware resources, frameworks, and real-world performance across major mobile chipsets.

Contribution

It provides a comprehensive overview of AI frameworks, hardware acceleration, and performance benchmarking on Android devices, highlighting current limitations and capabilities.

Findings

Performance varies significantly across different mobile chipsets.

Hardware acceleration resources are crucial for efficient AI processing.

Real-world benchmarks reveal the current state of AI performance on smartphones.

Abstract

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.