Agradecimentos: The authors would like to acknowledge the HPI Future SOC Lab for providing the computing resources. The first author would also like to acknowledge the Federal Institute of São Paulo at Piracicaba for supporting his research

Este artigo foi apresentado no evento International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2018

Abstract: Ensembles of Online Sequential Extreme Learning Machine algorithm are suitable for forecasting Data Streams with Concept Drifts. Nevertheless, data streams forecasting require high-performance implementations due to the high incoming samples rate. In this work, we proposed to tune-up three...

Abstract: Ensembles of Online Sequential Extreme Learning Machine algorithm are suitable for forecasting Data Streams with Concept Drifts. Nevertheless, data streams forecasting require high-performance implementations due to the high incoming samples rate. In this work, we proposed to tune-up three ensembles, which operates with the Online Sequential Extreme Learning Machine, using high-performance techniques. We reim-plemented them in the C programming language with Intel MKL and MPI libraries. The Intel MKL provides functions that explore the multithread features in multicore CPUs, which expands the parallelism to multiprocessors architectures. The MPI allows us to parallelize tasks with distributed memory on several processes, which can be allocated within a single computational node, or spread over several nodes. In summary, our proposal consists of a two-level parallelization, where we allocated each ensemble model into an MPI process, and we parallelized the internal functions of each model in a set of threads through Intel MKL. Thus, the objective of this work is to verify if our proposals provide a significant improvement in execution time when compared to the respective conventional serial approaches. For the experiments, we used a synthetic and a real dataset. Experimental results showed that, in general, the high-performance ensembles improve the execution time, when compared with its serial version, performing up to 10-fold faster

Fechado