hypre/boomeramg may be the way to go, especially for the Poisson problem. -pc_type hypre -pc_hypre_type boomeramg (-help for lots of tuning options.).
Barry On Sun, 11 Feb 2007, Ben Tay wrote: > Well, > > I am simulating unsteady flow past a moving airfoil at Re~10^4. I'm using > fractional step FVM, which means that I need to solve a momentum and poisson > equation. > > To reach a periodic state takes quite a few hours and so I'm trying to find > ways to speed up the process. I thought parallelizing the code would help > but it seems like it's not the case. > > I'm now trying out different types of solver/preconditioner available on > PETSc to assess their performance. Is there other external solvers, which > PETSc interfaces, which are recommended? I'm thinking of using multigrid to > solve the poisson eqn... wonder if hypre/BoomerAMG etc would help... > > > On 2/11/07, Lisandro Dalcin <dalcinl at gmail.com> wrote: > > > > On 2/10/07, Ben Tay <zonexo at gmail.com> wrote: > > > In other words, for my CFD code, it is not possible to parallelize it > > > effectively because the problem is too small? > > > > > > Is these true for all parallel solver, or just PETSc? I was hoping to > > reduce > > > the runtime since mine is an unsteady problem which requires many steps > > to > > > reach a periodic state and it takes many hours to reach it. > > > > Can you describe your specific application and how are you solving it? > > As Barry said, your need-for-speed is not likely to be solved by > > running in parallel. > > > > > > -- > > Lisandro Dalc??n > > --------------- > > Centro Internacional de M??todos Computacionales en Ingenier??a (CIMEC) > > Instituto de Desarrollo Tecnol??gico para la Industria Qu??mica (INTEC) > > Consejo Nacional de Investigaciones Cient??ficas y T??cnicas (CONICET) > > PTLC - G??emes 3450, (3000) Santa Fe, Argentina > > Tel/Fax: +54-(0)342-451.1594 > > > > >
