Multi-dimensional characterization of temporal data mining on graphics processors
Department of Computer Science, Virginia Tech
Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International Symposium on In IEEE International Symposium on Parallel & Distributed Processing (IPDPS’09) (2009), pp. 1-12.
@conference{archuleta2009multi,
title={Multi-dimensional characterization of temporal data mining on graphics processors},
author={Archuleta, J. and Cao, Y. and Scogland, T. and Feng, W.},
booktitle={Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International Symposium on},
pages={1–12},
issn={1530-2075},
year={2009},
organization={IEEE}
}
Through the algorithmic design patterns of data parallelism and task parallelism, the graphics processing unit (GPU) offers the potential to vastly accelerate discovery and innovation across a multitude of disciplines. For example, the exponential growth in data volume now presents an obstacle for high-throughput data mining in fields such as neuroscience and bioinformatics. As such, we present a characterization of a MapReduced-based data-mining application on a general-purpose GPU (GPGPU). Using neuroscience as the application vehicle, the results of our multi-dimensional performance evaluation show that a ldquoone-size-fits-allrdquo approach maps poorly across different GPGPU cards. Rather, a high-performance implementation on the GPGPU should factor in the 1) problem size, 2) type of GPU, 3) type of algorithm, and 4) data-access method when determining the type and level of parallelism. To guide the GPGPU programmer towards optimal performance within such a broad design space, we provide eight general performance characterizations of our data-mining application.
November 19, 2010 by hgpu
