Parallel IQMR Method for Unsymmetric Large and Sparse Linear Systems in Computational Fluid Dynamics

| We mainly examine the application of the improved version of the quasi-minimal residual (IQMR) method 20], 21] for the solutions of linear systems of equations with unsymmetric coeecient matrices arising from the discretization of uid dynamic problems on massively parallel distributed memory computers. We will deal with implicit nite diierence schemes for solving the Euler equations. These schemes may arise from the implicit treatment of the time dependent equations or from the use of New-ton's method for the solution of the steady state equations. In both situations it is very necessary to solve a large and sparse unsymmetric linear systems at each iteration. We will examine the eeectiveness of IQMR in the solution of these systems. We compared the resulting method to some existed approaches by numerical experimental results carried out on massively parallel distributed memory computer Parsytec GC/PowerPlus. Our goal is to show that the IQMR method is a more eecient alternative for solving implicit computational uid dynamics problems.