2009 | OriginalPaper | Chapter
Accelerated Discovery of Discrete M-Clusters/Outliers on the Raster Plane Using Graphical Processing Units
Authors : Christian Trefftz, Joseph Szakas, Igor Majdandzic, Gregory Wolffe
Published in: Computational Science – ICCS 2009
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
This paper presents two discrete computational geometry algorithms designed for execution on Graphics Processing Units (GPUs). The algorithms are parallelized versions of sequential algorithms intended for application in geographical data mining. The first algorithm finds clusters of
m
points, called m-clusters, in the rasterized plane. The second algorithm complements the first by identifying outliers, those points which are not members of any m-clusters. The use of a raster representation of coordinates provides an ideal data stream environment for efficient GPU utilization. The parallel algorithms have low memory demands, and require only a limited amount of inter-process communication. Initial performance analysis indicates the algorithms are scalable, both in problem size and in the number of seeds, and significantly outperform commercial implementations.