{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ai-benchmark-running-deep-neural-networks-on","title":"AI Benchmark: Running Deep Neural Networks on Android Smartphones","arxiv_id":"1810.01109","date":"2018-10-02","proceeding":null,"authors":["Andrey Ignatov","Radu Timofte","William Chou","Ke Wang","Max Wu","Tim Hartley","Luc van Gool"],"abstract":"Over the last years, the computational power of mobile devices such as\nsmartphones and tablets has grown dramatically, reaching the level of desktop\ncomputers available not long ago. While standard smartphone apps are no longer\na problem for them, there is still a group of tasks that can easily challenge\neven high-end devices, namely running artificial intelligence algorithms. In\nthis paper, we present a study of the current state of deep learning in the\nAndroid ecosystem and describe available frameworks, programming models and the\nlimitations of running AI on smartphones. We give an overview of the hardware\nacceleration resources available on four main mobile chipset platforms:\nQualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the\nreal-world performance results of different mobile SoCs collected with AI\nBenchmark that are covering all main existing hardware configurations.","url_abs":"http://arxiv.org/abs/1810.01109v2","url_pdf":"http://arxiv.org/pdf/1810.01109v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ai-benchmark-running-deep-neural-networks-on","repo_url":"https://github.com/Video-Streaming-Pipeline/Video-Streaming-Pipeline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.01109","atlas_url":"https://app.syntology.ai/?focus=1810.01109","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}