Algorithmic Transforms in the Implementation of K-Means Clustering onReconfigurable Hardware

摘要

In mapping the k-means algorithm to FPGA hardware, we examined algorithm leveltransforms that dramatically increased the achievable parallelism. We apply the k-means algorithm to multi-spectral and hyper-spectral images, which have tens to hundreds of channels per pixel of data. K-means is an iterative algorithm that assigns each pixel to one of k clusters. K-means is a common solution to the segmentation of multi-dimensional data. The standard soft-ware implementation of k-means uses floating-point arithmetic and Euclidean distances. Floating point arithmetic and the multiplication-heavy Euclidean distance calculation are fine on a general purpose processor, but they have large area and speed penalties when implemented on an FPGA. In order to get the best performance of k-means on an FPGA, the algorithm needs to be transformed to eliminate these operations. We examined the effects of using two other distance measures, Manhattan and Max, that do not require multipliers. We also examined the effects of using fixed precision and truncated bit widths in the algorithm. It is important to explore algorithmic level transforms and tradeoffs when mapping an algorithm to reconfigurable hardware. A direct translation of the standard software implementation of k-means would result in a very inefficient use of FPGA hardware resources. Analysis of the algorithm and data is necessary for a more efficient implementation. Our resulting implementation exhibits approximately a 200 times speed up over a software implementation.