April 19, 2024
High-performance implementations of k-Nearest Neighbor Search (kNN) 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 kNN 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 kNN 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 kNN search time speedups range between 1.5x-200x over various state-of-the-art GPU baselines and datasets. In evaluation, we provide several insights on RT architectures’ ability to efficiently build and traverse the tree by analyzing the kNN search time trends.
About Durga Mandarapu
Durga is a CS PhD student advised by Prof. Milind Kulkarni. Her research interests are in High-Performance Computing and Databases. Her work focuses on using GPUs to accelerate irregular tree-based applications.