Hybrid Programming and Performance for Beam Propagation Modeling
|Title||Hybrid Programming and Performance for Beam Propagation Modeling|
|Publication Type||Conference Paper|
|Year of Publication||2012|
|Authors||Min, MS, Fu, J, Mametjanov, A|
|Conference Name||11th International Computatioal Accelerator Physics Conference (ICAP 2012)|
|Conference Location||Rostock-Warnemunde, Germany|
We examined hybrid parallel infrastructures in order to ensure performance and scalability for beam propagation modeling as we move toward extreme-scale systems. Using an MPI programming interface for parallel algorithms, we expanded the capability of our existing electromagnetic solver to a hybrid (MPI/shared-memory) model that can potentially use the computer resources on future-generation computing architecture more efficiently. As a preliminary step, we discuss a hybrid MPI/OpenMP model and demonstrate performance and analysis on the leadership class computing systems such as the IBM BG/P, BG/Q, and Cray XK6. Our hybrid MPI/OpenMP model achieves speedup when the computation amounts are large enough to compensate the OMP threading overhead.