Nested OpenMP Parallelization of a Hierarchical Data Clustering Algorithm
Abstract
This paper presents a high performance parallel implementation of a hierarchical data clustering algorithm. The OpenMP programming model, either enhanced with our lightweight runtime support or through its tasking model, deals with the high irregularity of the algorithm and allows for efficient exploitation of the inherent loop-level nested parallelism. Thorough experimental evaluation demonstrates the performance scalability of our parallelization and the effective utilization of computational resources, which results in a clustering approach able to provide high quality clustering of very large datasets.