Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290943602> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4290943602 abstract "Deep Neural Network (DNN) based recommendation systems are widely used in the modern internet industry for a variety of services. However, the rapid expansion of application scenarios and the explosive global internet traffic growth have caused the industry to face increasing challenges to serve the complicated recommendation workflow regarding online recommendation efficiency and compute resource overhead. In this paper, we present a GPU-accelerated online serving system, namely Lion, which consists of the staged event-driven heterogeneous pipeline, unified memory manager, and automatic execution optimizer to handle web-scale traffic in a real-time and cost-effective way. Moreover, Lion provides a heterogeneous template library to enable fast development and migration for diverse in-house web-scale recommendation systems without requiring knowledge of heterogeneous programming. The system is currently deployed at Baidu, supporting over twenty recommendation services, including news feed, short video clips, and the search engine. Extensive experimental studies on five real-world deployed online recommendation services demonstrate the superiority of the proposed GPU-accelerated online serving system. Since launched in early 2020, Lion has answered billions of recommendation requests per day, and has helped Baidu successfully save millions of U.S. dollars in hardware and utility costs per year." @default.
- W4290943602 created "2022-08-13" @default.
- W4290943602 creator A5006200768 @default.
- W4290943602 creator A5019272364 @default.
- W4290943602 creator A5021552476 @default.
- W4290943602 creator A5036990432 @default.
- W4290943602 creator A5039683708 @default.
- W4290943602 creator A5044128348 @default.
- W4290943602 creator A5056837500 @default.
- W4290943602 creator A5088664989 @default.
- W4290943602 date "2022-08-14" @default.
- W4290943602 modified "2023-10-16" @default.
- W4290943602 title "Lion: A GPU-Accelerated Online Serving System for Web-Scale Recommendation at Baidu" @default.
- W4290943602 cites W165252454 @default.
- W4290943602 cites W2057819258 @default.
- W4290943602 cites W2060393849 @default.
- W4290943602 cites W2135682468 @default.
- W4290943602 cites W2475334473 @default.
- W4290943602 cites W2605350416 @default.
- W4290943602 cites W2611998574 @default.
- W4290943602 cites W2723293840 @default.
- W4290943602 cites W2883929540 @default.
- W4290943602 cites W2884001105 @default.
- W4290943602 cites W2913334236 @default.
- W4290943602 cites W2943267175 @default.
- W4290943602 cites W2950960796 @default.
- W4290943602 cites W2963842088 @default.
- W4290943602 cites W2976670629 @default.
- W4290943602 cites W2984020950 @default.
- W4290943602 cites W3014810041 @default.
- W4290943602 cites W3015302520 @default.
- W4290943602 cites W3016842236 @default.
- W4290943602 cites W3034539665 @default.
- W4290943602 cites W3043023836 @default.
- W4290943602 cites W3169109617 @default.
- W4290943602 cites W3205539956 @default.
- W4290943602 cites W3206393216 @default.
- W4290943602 cites W4213455337 @default.
- W4290943602 doi "https://doi.org/10.1145/3534678.3539058" @default.
- W4290943602 hasPublicationYear "2022" @default.
- W4290943602 type Work @default.
- W4290943602 citedByCount "0" @default.
- W4290943602 crossrefType "proceedings-article" @default.
- W4290943602 hasAuthorship W4290943602A5006200768 @default.
- W4290943602 hasAuthorship W4290943602A5019272364 @default.
- W4290943602 hasAuthorship W4290943602A5021552476 @default.
- W4290943602 hasAuthorship W4290943602A5036990432 @default.
- W4290943602 hasAuthorship W4290943602A5039683708 @default.
- W4290943602 hasAuthorship W4290943602A5044128348 @default.
- W4290943602 hasAuthorship W4290943602A5056837500 @default.
- W4290943602 hasAuthorship W4290943602A5088664989 @default.
- W4290943602 hasConcept C110875604 @default.
- W4290943602 hasConcept C111919701 @default.
- W4290943602 hasConcept C136197465 @default.
- W4290943602 hasConcept C136764020 @default.
- W4290943602 hasConcept C154945302 @default.
- W4290943602 hasConcept C177212765 @default.
- W4290943602 hasConcept C2779960059 @default.
- W4290943602 hasConcept C41008148 @default.
- W4290943602 hasConcept C43521106 @default.
- W4290943602 hasConcept C49774154 @default.
- W4290943602 hasConcept C557471498 @default.
- W4290943602 hasConcept C77088390 @default.
- W4290943602 hasConceptScore W4290943602C110875604 @default.
- W4290943602 hasConceptScore W4290943602C111919701 @default.
- W4290943602 hasConceptScore W4290943602C136197465 @default.
- W4290943602 hasConceptScore W4290943602C136764020 @default.
- W4290943602 hasConceptScore W4290943602C154945302 @default.
- W4290943602 hasConceptScore W4290943602C177212765 @default.
- W4290943602 hasConceptScore W4290943602C2779960059 @default.
- W4290943602 hasConceptScore W4290943602C41008148 @default.
- W4290943602 hasConceptScore W4290943602C43521106 @default.
- W4290943602 hasConceptScore W4290943602C49774154 @default.
- W4290943602 hasConceptScore W4290943602C557471498 @default.
- W4290943602 hasConceptScore W4290943602C77088390 @default.
- W4290943602 hasFunder F4320321001 @default.
- W4290943602 hasLocation W42909436021 @default.
- W4290943602 hasOpenAccess W4290943602 @default.
- W4290943602 hasPrimaryLocation W42909436021 @default.
- W4290943602 hasRelatedWork W1508315017 @default.
- W4290943602 hasRelatedWork W1998527728 @default.
- W4290943602 hasRelatedWork W2048639071 @default.
- W4290943602 hasRelatedWork W2748952813 @default.
- W4290943602 hasRelatedWork W2883909875 @default.
- W4290943602 hasRelatedWork W2946077020 @default.
- W4290943602 hasRelatedWork W2968745142 @default.
- W4290943602 hasRelatedWork W2992088541 @default.
- W4290943602 hasRelatedWork W4241563956 @default.
- W4290943602 hasRelatedWork W4246292613 @default.
- W4290943602 isParatext "false" @default.
- W4290943602 isRetracted "false" @default.
- W4290943602 workType "article" @default.