kANN on the GPU with Shifted Sorting

Shengren Li, Lance Simons, Jagadeesh Bhaskar Pakaravoor, Fatemeh Abbasinejad, John D. Owens, Nina Amenta
University of California at Davis
High Performance Graphics, 2012


   title={kANN on the GPU with Shifted Sorting},

   author={Bhaskar, S.L.L.S.J. and Owens, P.F.A.J.D. and Amenta, N.},



Download Download (PDF)   View View   Source Source   



We describe the implementation of a simple method for finding k approximate nearest neighbors (ANNs) on the GPU. While the performance of most ANN algorithms depends heavily on the distributions of the data and query points, our approach has a very regular data access pattern. It performs as well as state of the art methods on easy distributions with small values of k, and much more quickly on more difficult problem instances. Irrespective of the distribution and also roughly of the size of the set of input data points, we can find 50 ANNs for 1M queries at a rate of about 1200 queries/ms.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: