Title | ||
---|---|---|
Software Engineering in Parallel and Distributed Scientific Computing: A Case Study from Industrial Practice |
Abstract | ||
---|---|---|
We report on results from an interdisciplinary research project of computer scientists, mechanical engineers and numerical analysts from industry and academia. We have designed and implemented a portable distributed memory parallel version of CFX-TfC, a state of the art computa- tional fluid dynamics simulation software package that fea- tures finite volume discretization on unstructured hybrid grids in combination with an algebraic multigrid solver. Performance results on a number of parallel hardware plat- forms indicate high efficiency and scalability. Systematic application of software engineering methods has been a key contribution to success and helped to avoid bottlenecks found in many other parallel CFD codes. A key module of TfC, the algebraic multigrid solver (AMG), has been re-designed according to the object ori- ented paradigm. The object oriented (OO) AMG solver has been implemented in C++. OO technology has increased the solver's maintainability and readability. Run-time effi- ciency is acceptable (compared to the Fortran 77 version); it could still be improved by applying further optimizations. Since networks of workstations (NOWs) are of particular interest for small and medium enterprises (SMEs), we have implemented a resource manager that allows PVM applica- tions such as Par-CFX-TfC to be executed in batch mode without interfering with interactive users. The resource manager features transparent checkpointing and process migration. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/PDSE.1998.668179 | Kyoto |
Keywords | Field | DocType |
industrial practice,case study,scientific computing,software engineering,fluid dynamics,scalability,object oriented software engineering,simulation software,resource management,hardware,algebraic multigrid,parallel programming,object oriented programming,c,computational modeling,application software,distributed memory,small and medium enterprises,process migration,object oriented,resource manager,batch mode,finite volume,computational fluid dynamics,small and medium enterprise,mechanical engineering | Software Engineering Process Group,Software engineering,Object-oriented programming,Computer science,Process migration,Distributed design patterns,Object-oriented software engineering,Computational science,Component-based software engineering,Application software,Social software engineering | Conference |
ISBN | Citations | PageRank |
0-8186-8467-4 | 0 | 0.34 |
References | Authors | |
3 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peter Luksch | 1 | 35 | 13.92 |
ursula maier | 2 | 0 | 0.34 |
matthias weidmann | 3 | 0 | 0.68 |
matthias weidmann | 4 | 0 | 0.68 |
peter bastian | 5 | 0 | 0.34 |
alexander haas | 6 | 0 | 0.34 |