A parallel processing system for simulations of vortex blob interactions

The vortex method in the simulation of 2D incompressible flows with complex interacting circulations is very attractive if compared with other nowadays widespread methods. However, the vortex method is computationally very expensive and suggests the adoption of suitably powerful computing units. Our group analysed some parallelisation techniques of the algorithm, in order to obtain the best performances on a dedicated parallel architecture. A promising architecture was simulated in a PVM (Parallel Virtual Machine) environment to identify correctness and efficiency of the selected choices. The implementation of the most promising one on a Special Purpose Computer (SPC) based on i860 Risc Intel units is in progress. The porting of the parallelised algorithm into the SPC will result into a low-cost system, completely available to the user, with expected performances comparable to those of modern supercomputers.