Parallelization of Compute Intensive Applications into Workflows based on Services in BeesyCluster

Abstract

The paper presents an approach for modeling, optimization and execution of workflow applications based on services that incorporates both service selection and partitioning of input data for parallel processing by parallel workflow paths. A compute-intensive workflow application for parallel integration is presented. An impact of the input data partitioning on the scalability is presented. The paper shows a comparison of the theoretical model of workflow execution and real execution times. The execution of this distributed workflow is compared to a highly parallel approach using MPI. Finally, results for an integrated workflow/MPI approach are shown.