English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deploying deep learning (DL) on mobile devices has been a notable trend inrecent years. To support fast inference of on-device DL, DL libraries play acritical role as algorithms and hardware do. Unfortunately, no prior work everdives deep into the ecosystem of modern DL libs and provides quantitativeresults on their performance. In this paper, we first build a comprehensivebenchmark that includes 6 representative DL libs and 15 diversified DL models.We then perform extensive experiments on 10 mobile devices, which help reveal acomplete landscape of the current mobile DL libs ecosystem. For example, wefind that the best-performing DL lib is severely fragmented across differentmodels and hardware, and the gap between those DL libs can be rather huge. Infact, the impacts of DL libs can overwhelm the optimizations from algorithms orhardware, e.g., model quantization and GPU/DSP-based heterogeneous computing.Finally, atop the observations, we summarize practical implications todifferent roles in the DL lib ecosystem.

Benchmarking of DL Libraries and Models on Mobile Devices