|
Abstract : |
A molecular-dynamics program typically takes several man-years to write and therefore is representative for a large class of scientific programs whose rewriting should not be taken lightly. This paper discusses two Intel hypercube adaptations, UHGROMOS and EulerGROMOS (in progress), of a "dusty-deck " moleculardynamics code, GROMOS. UHGROMOS uses a low-impact parallelization strategy to minimize modifications to GROMOS. In UHGROMOS, the nonbonded force computation, which usually accounts for at least 90 % of the computation time in GROMOS, is the focus for parallelization. This simple approach results already in acceptable performance for typical applications and parallelcomputer resources. However, the lack of spatial locality in data distribution limits overall processor utilization. To overcome this limitation, EulerGROMOS uses a spatial decomposition which enhances locality and permits the design of scalable data-structures and algorithms for all parts of GROMOS. The two implementations use very different strategies for distributing the molecular data and the computation, but both reuse at least 90 % of the original, sequential GROMOS code. The paper discusses intended applications and target hardware, emphasizing their influence on the parallelization strategies. We present simulation results and analysis for UHGROMOS and discuss tradeoffs between the two versions. 1, |
