An Auto-tuning Solution to Data Streams Clustering in OpenCL
Parallel and Distributed Systems Group, Delft University of Technology, Delft, the Netherlands
The Second International Workshop on Frontier of GPU Computing(FGC’11), Dalian, China
@inproceedings{fang2011auto,
title={An Auto-tuning Solution to Data Streams Clustering in OpenCL$}$},
author={Fang, J. and Varbanescu, A.L. and Sips, H. and Fang, J. and Varbanescu, A.L. and Sips, H.},
booktitle={The Second International Workshop on Frontier of GPU Computing (FGC’11), Dalian, China$}$},
year={2011}
}
Due to its applicability to numerous types of data, including telephone records, web documents, and click streams, the data stream model has recently attracted attention. For analysis of such data, it is crucial to process the data in a single pass, or a small number of passes, using little memory. This paper provides an OpenCL implementation for data streams clustering, and then presents several optimizations for it, which make it more efficient in terms of memory usage. In order to maximize performance for different problem sizes and architectures, we also propose an auto-tuning solution. Experimental results show that our fully optimized implementation can perform 2.1x and 1.4x faster than the native OpenCL implementation on NVIDIA GTX480 and AMDHD5870, respectively; it can also achieve 1.4x to 3.3x speedup relative to the original CUDA implementation solution on GTX480.
October 3, 2011 by hgpu
