Evaluation of algorithms for the solution of the drift flux equations on advanced computers

Current efforts are underway to develop and evaluate numerical algorithms for the parallel solution of the large sparse matrix equations associated with the finite difference representation of the macroscopic Navier-Stokes equations. Our work has concentrated on the one-dimensional drift flux form of the Navier-Stokes equations. Direct and iterative algorithms that may be suitable for implementation on parallel computer architectures are evaluated in terms of accuracy and overall execution speed. This work has application to engineering and training simulators, on-line process control systems, and engineering work stations where increased computational speeds are required. Results from a drift flux code run on a large supercomputer indicate that faster than real time simulations are possible with several of the algorithms being considered, however, the direct algorithms have provided the fastest and most accurate results