Title :
Taking Advantage of Collective Operation Semantics for Loosely Coupled Simulations
Author :
Wu, Joe Shang-Chieh ; Sussman, Alan
Author_Institution :
Dept. of Comput. Sci., Maryland Univ., College Park, MD
Abstract :
Although a loosely coupled component-based framework offers flexibility and versatility for building and deploying large-scale multi-physics simulation systems, the performance of such a system can suffer from excessive buffering of data objects which may or may not be transferred between components. By taking advantages of the collective properties of parallel simulation components, which is common for data-parallel scientific applications, an optimization method, which we call buddy-help, can greatly enhance overall performance. Buddy-help can reduce the time taken for buffering operations in an exporting component, when there are timing differences across processes in the exporting component. The optimization enables skipping unnecessary buffering operations, once another process, which has already performed the collective export operation, has determined that the buffered data would never be needed. Because an analytical study would be very difficult due to the complexity of the overall coupled simulation system, the performance improvement enabled by buddy-help is investigated via a micro-benchmark specifically designed to illustrate the behavior of coupled simulation scenarios under which buddy-help can provide performance gains.
Keywords :
digital simulation; object-oriented programming; optimisation; parallel programming; physics computing; buddy-help optimization method; collective export operation semantics; data-parallel scientific applications; large-scale multiphysics simulation systems; loosely coupled component-based framework; Analytical models; Computational modeling; Computer science; Computer simulation; Educational institutions; Large-scale systems; Magnetohydrodynamics; Optimization methods; Spatial resolution; USA Councils;
Conference_Titel :
Parallel and Distributed Processing Symposium, 2007. IPDPS 2007. IEEE International
Conference_Location :
Long Beach, CA
Print_ISBN :
1-4244-0910-1
Electronic_ISBN :
1-4244-0910-1
DOI :
10.1109/IPDPS.2007.370318