Parallel VQ compression using PNN algorithm for PC Grid system

Abstract

PC Grid is a promising platform to achieve a high performance computing with less construction cost. A kind of parameter sweep applications (PSA) can be efficiently carried out on the PC Grid, but there exist parallel applications are not suitable for it. We focus on PNN (Pairwise Nearest Neighbor) codebook generation algorithm for the VQ compression algorithm and propose a parallel version of the PNN algorithm suitable for the PC Grid, called "One-step Grid PNN", as well as "multi-step Grid PNN", which reduces the computation complexity on a master computer. The Grid PNN is a modified version of the PNN algorithm that creates a different codebook than the original PNN does, thus the quality of a codebook created by using the Grid PNN may be worse than that of a codebook by the original PNN. However, our experimental results show that the quality of the codebook is almost same as that of the original one. We also confirm the effectiveness of the one-step and multi-step Grid PNN by the evaluation of the computational complexity of the algorithm and experiments executed on a PC cluster system.