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

Approximate nearest neighbor (ANN) search is a widely applied technique inmodern intelligent applications, such as recommendation systems and vectordatabases. Therefore, efficient and high-throughput execution of ANN search hasbecome increasingly important. In this paper, we first characterize thestate-of-the-art product quantization-based method of ANN search and identify asignificant source of inefficiency in the form of unnecessary pairwise distancecalculations and accumulations. To improve efficiency, we propose JUNO, anend-to-end ANN search system that adopts a carefully designed sparsity- andlocality-aware search algorithm. We also present an efficient hardware mappingthat utilizes ray tracing cores in modern GPUs with pipelined execution ontensor cores to execute our sparsity-aware ANN search algorithm. Ourevaluations on four datasets ranging in size from 1 to 100 million searchpoints demonstrate 2.2x-8.5x improvements in search throughput. Moreover, ouralgorithmic enhancements alone achieve a maximal 2.6x improvement on thehardware without the acceleration of the RT core.

JUNO: Optimizing High-Dimensional Approximate Nearest Neighbour Search with Sparsity-Aware Algorithm and Ray-Tracing Core Mapping