A DETAILED STUDY ON PERFORMANCE OPTIMIZATION OF CLUSTERING ON GPU

Clustering can be considered the most important unsupervised learning technique. Clustering is “the process of organizing objects into groups whose members are similar in some way”. It is used for simplification, pattern detection and data concept construction. As clustering is prime component for many scientific and engineering applications using Data mining, This paper focus on optimizing performance of clustering using parallelization. Many Clustering algorithms give best performance on small dataset. But when large dataset will apply then performance will main issue so that will optimize using GPU. Because GPU giving much Higher Performance. parallelization of clustering will be implemented on GPU based various programming modal like CUDA, Open MP, and Open Acc. Comparison of result will be used to suggest best platform for clustering.