"Adaptive Application Composition in Quantum Chemistry"
L. Li, J. P. Kenny, M.-S. Wu, K. Huck, A. Gaenko, M. S. Gordon, C. L. Janssen, L. C. McInnes, H. M. Netzloff, B. Norris, T. L. Windus
Proceedings of the 5th International Conference on the Quality of Software Architectures: Architectures for Adaptive Software Systems, East Stroudsburg, PA, USA, Springer-Verlag, , pp. 194-211. Also Preprint ANL/MCS-P1575-0209
Preprint Version: [pdf]
Component interfaces, as advanced by the Common Component Architecture (CCA), enable easy access to complex software packages for high-performance scientific computing. A recent focus has been incorporating support for computational quality of service (CQoS) the automatic composition, substitution, and dynamic reconfiguration of component applications. Several leading quantum chemistry packages have achieved interoperability by adopting CCA components. Running these computations on diverse computing platforms requires selection among many algorithmic and hardware configuration parameters; typical educated guesses or trial and error can result in unexpectedly low
performance. Motivated by the need for faster runtimes and increased productivity for chemists, we present a flexible CQoS approach for quantum chemistry that uses a generic CQoS database component to create a training database with timing results and metadata for a range of calculations. The database then interacts with a chemistry CQoS component and other infrastructure to facilitate adaptive application composition for new calculations.