Workflow Performance Profiles: Development and Analysis
AUTHORS: D. Król, R. Ferreira da Silva, E. Deelman, V. Lynch
ABSTRACT
This paper presents a method for performance pro les de- velopment of scienti c work ow. It addresses issues related to: work ows execution in a parameter sweep manner, collecting performance informa- tion about each work ow task, and analysis of the collected data with statistical learning methods. The main goal of this work is to increase the understanding about the performance of studied work ows in a sys- tematic and predictable way. The evaluation of the presented approach is based on a real scienti c work ow developed by the Spallation Neutron Source - a DOE research facility at the Oak Ridge National Laboratory. The work ow executes an ensemble of molecular dynamics and neutron scattering intensity calculations to optimize a model parameter value
