Arkade: k-Nearest Neighbor Search With Non-Euclidean Distances using GPU Ray Tracing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mandarapu, Durga, Nagarajan, Vani, Pelenitsyn, Artem, Kulkarni, Milind
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909177072320512
author Mandarapu, Durga
Nagarajan, Vani
Pelenitsyn, Artem
Kulkarni, Milind
author_facet Mandarapu, Durga
Nagarajan, Vani
Pelenitsyn, Artem
Kulkarni, Milind
contents High-performance implementations of $k$-Nearest Neighbor Search ($k$NN) in low dimensions use tree-based data structures. Tree algorithms are hard to parallelize on GPUs due to their irregularity. However, newer Nvidia GPUs offer hardware support for tree operations through ray-tracing cores. Recent works have proposed using RT cores to implement $k$NN search, but they all have a hardware-imposed constraint on the distance metric used in the search -- the Euclidean distance. We propose and implement two reductions to support $k$NN for a broad range of distances other than the Euclidean distance: Arkade Filter-Refine and Arkade Monotone Transformation, each of which allows non-Euclidean distance-based nearest neighbor queries to be performed in terms of the Euclidean distance. With our reductions, we observe that $k$NN search time speedups range between $1.6$x-$200$x and $1.3$x-$33.1$x over various state-of-the-art GPU shader core and RT core baselines, respectively. In evaluation, we provide several insights on RT architectures' ability to efficiently build and traverse the tree by analyzing the $k$NN search time trends.
format Preprint
id arxiv_https___arxiv_org_abs_2311_09168
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Arkade: k-Nearest Neighbor Search With Non-Euclidean Distances using GPU Ray Tracing
Mandarapu, Durga
Nagarajan, Vani
Pelenitsyn, Artem
Kulkarni, Milind
Graphics
Distributed, Parallel, and Cluster Computing
Performance
High-performance implementations of $k$-Nearest Neighbor Search ($k$NN) in low dimensions use tree-based data structures. Tree algorithms are hard to parallelize on GPUs due to their irregularity. However, newer Nvidia GPUs offer hardware support for tree operations through ray-tracing cores. Recent works have proposed using RT cores to implement $k$NN search, but they all have a hardware-imposed constraint on the distance metric used in the search -- the Euclidean distance. We propose and implement two reductions to support $k$NN for a broad range of distances other than the Euclidean distance: Arkade Filter-Refine and Arkade Monotone Transformation, each of which allows non-Euclidean distance-based nearest neighbor queries to be performed in terms of the Euclidean distance. With our reductions, we observe that $k$NN search time speedups range between $1.6$x-$200$x and $1.3$x-$33.1$x over various state-of-the-art GPU shader core and RT core baselines, respectively. In evaluation, we provide several insights on RT architectures' ability to efficiently build and traverse the tree by analyzing the $k$NN search time trends.
title Arkade: k-Nearest Neighbor Search With Non-Euclidean Distances using GPU Ray Tracing
topic Graphics
Distributed, Parallel, and Cluster Computing
Performance
url https://arxiv.org/abs/2311.09168