A Comparative study of parallel CPU/GPU implementations of the K-Means Algorithm

The K-Means algorithm is one of the most sophisticated and known algorithms for data-clustering. In this study, we will show the K-Means algorithm as it relates to OpenCL, which is a widespread parallel ecosystem that is reliable for processing and mining datasets that are large in scale. Additionally, we propose a comparative study of the three most efficient K-means algorithm implementations: The Lloyd-Forgy’s sequential Method Implementation, a parallel implementation targeting the CPU using OpenMP and finally one of the most complex implementations that uses an OpenCL language. Typically, the measure of performance is done using different data sizes. For large datasets under OpenCL, when comparing the GPU-based parallel algorithm to the CPU-based serial algorithm, the results have shown a good acceleration effect. On the other hand, for small data sets, the OpenMP implementation has turned out to be the best choice.