Clustering is an important task in data mining that has become more challenging due to the ever-increasing size of available datasets. To cope with these big data scenarios, a high-performance clustering approach is required. Sparse grid clustering is a density-based clustering method that uses a sparse grid density estimation as its central building block. The underlying density estimation approach enables the detection of clusters with non-convex shapes and without a predetermined number of clusters. In this work, we introduce a new distributed and performance-portable variant of the sparse grid clustering algorithm that is suited for big data settings. Our compute kernels were implemented in OpenCL to enable portability across a wide range of architectures. For distributed environments, we added a manager-worker scheme that was implemented using MPI. In experiments on two supercomputers, Piz Daint and Hazel Hen, with up to 100 million data points in a 10-dimensional dataset, we show the performance and scalability of our approach. The dataset with 100 million data points was clustered in 1198s using 128 nodes of Piz Daint. This translates to an overall performance of 352TFLOPS. On the node-level, we provide results for two GPUs, Nvidia's Tesla P100 and the AMD FirePro W8100, and one processor-based platform that uses Intel Xeon E5-2680v3 processors. In these experiments, we achieved between 43% and 66% of the peak performance across all compute kernels and devices, demonstrating the performance portability of our approach.

This paper presents a multi-swarm PSO algorithm for the Quadratic Assignment Problem (QAP) implemented on the OpenCL platform. Our work was motivated by results of time efficiency tests performed for single-swarm algorithm implementation that showed clearly that the benefits of a parallel execution platform can be fully exploited provided the processed population is large. The described algorithm can be executed in two modes: with independent swarms or with migration. We discuss the algorithm construction as well as we report results of tests performed on several problem instances from the QAPLIB library. During the experiments the algorithm was configured to process large populations. This allowed us to collect statistical data related to values of goal function reached by individual particles. We use them to demonstrate on two test cases that although single particles seem to behave chaotically during the optimization process, when the whole population is analyzed, the probability that a particle will select a near-optimal solution grows.