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

AI applications pose increasing demands on performance, so it is notsurprising that the era of client-side distributed software is becomingimportant. On top of many AI applications already using mobile hardware, andeven browsers for computationally demanding AI applications, we are alreadywitnessing the emergence of client-side (federated) machine learningalgorithms, driven by the interests of large corporations and startups alike.Apart from mathematical and algorithmic concerns, this trend especially demandsnew levels of computational efficiency from client environments. Consequently,this paper deals with the question of state-of-the-art performance bypresenting a comparison study between native code and different browser-basedimplementations: JavaScript, ASM.js as well as WebAssembly on a representativemix of algorithms. Our results show that current efforts in runtimeoptimization push the boundaries well towards (and even beyond) native binaryperformance. We analyze the results obtained and speculate on the reasonsbehind some surprises, rounding the paper off by outlining future possibilitiesas well as some of our own research efforts.

The Need for Speed of AI Applications: Performance Comparison of Native vs. Browser-based Algorithm Implementations