Daniel S. Katz, E. Robert Tisdale, Charles D. Norton
Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, Pasadena, CA, 91109, USA
E-mail: {Daniel.S.Katz, E.Robert.Tisdale, Charles.D.Norton}@jpl.nasa.gov
The development of large-scale multi-disciplinary scientific applications for high-performance computers today involves managing the interaction between portions of the application developed by different groups. The CCA (Common Component Architecture) Forum is developing a component architecture specification to address high-performance scientific computing, emphasizing scalable (possibly-distributed) parallel computations. This paper presents an examination of the CCA software in sequential and parallel electromagnetics applications using unstructured adaptive mesh refinement (AMR). The CCA learning curve and the process for modifying Fortran 90 code (a driver routine and an AMR library) into two components are described. The performance of the original applications and the componentized versions are measured and shown to be comparable.