Parallel Computation of Turbulent Flows Using Equation Decomposition Scheme

Abstract

ABSTRACTA problem independent, equation decomposition scheme of parallel computation is adopted and tested using a two-dimensional turbulent channel flow. The incompressible Navier-Stokes equations, incorporated with the SIMPLEC algorithm and a two-layer turbulence model, were distributed to four nodes of IBM SP2 parallel machine using the PVM software and solved simultaneously. The computation domain and the interior iteration loop for the solution of every transport equation is the same, load balancing among different machines is automatically satisfied. Since all the transport equations and the flow field was solved and updated simultaneously, the solutions obtained from the equation decomposition scheme at each time step were more accurate than those obtained from a unit process code, which in turn sharply reduced the required convergence time steps. Without modifying any of the solution algorithm, or tuning the computer code, the rate of convergence speeds up more than four times by invoking four nodes of parallel machines using the equation decomposition scheme.