CUDA-Accelerated HD-ODETLAP: Lossy High Dimensional Gridded Data Compression
Rensselaer Polytechnic Institute, 110 8th Street, Troy, NY, USA 12180
2012 International Workshop on Modern Accelerator Technologies for GIScience (MAT4GIScience 2012), 2012
@article{franklin2012cuda,
title={CUDA-Accelerated HD-ODETLAP: Lossy High Dimensional Gridded Data Compression?},
author={Franklin, W.R. and Li, Y. and Lau, T.Y. and Fox, P.},
year={2012}
}
We present High-dimensional Overdetermined Laplacian Partial Differential Equations (HD-ODETLAP), a high dimensional lossy compression algorithm and CUDA implementation that exploits data correlations across multiple dimensions of gridded GIS data. Exploiting the GPU gives a considerable speedup. In addition, HD-ODETLAP compresses much better than JPEG2000 and 3D-SPIHT, when fixing either the average or the maximum error.
August 8, 2012 by hgpu
