Compute Distance Matrices with GPU
Bioinformatics and Biostatistics Department, University of Louisville, Louisville, Kentucky 40292, USA
Third Annual International Conference on Advances in Distributed and Parallel Computing (ADPC 2012), 2012
@article{kim2012compute,
title={Compute Distance Matrices with GPU},
author={Kim, Seongho and Ouyang, Ming},
year={2012}
}
Given a data matrix where the rows are objects and the columns are variables, researchers often want to compute all the pairwise distances among the objects. Due to the design of Nvidia GPU architecture, CUDA code can work with ease data matrices where the numbers of rows and columns are multiples of sixteen. The present work proposes a padding strategy that add additional rows and columns of zeros to the matrix so that a matrix of any size may be processed by a simple and fast CUDA kernel function. For Pearson correlation coefficient, the GPU computation 15.9 to 33.5 times faster than the CPU.
October 1, 2012 by hgpu
