[petsc-users] Execution time of superlu_dist increase in multiprocessing

Hong Zhang hzhang at mcs.anl.gov
Tue May 20 08:13:40 CDT 2014

国熙 :
You have to experiment to find out which package and options to give
better performance. Run your code with '-help' to see available
runtime options for mumps and superlu_dist. Then try different
options. I would try different matrix ordering first.

Different packages and solvers give different performance for an
application. One cannot expect same performance.

> I'm working on standard eigensolving with spectrum transform. I tried mumps
> and superlu_dist for ST. But I found that when I run my program  with more
> process, execution time of mumps decrease, but time of superlu_dist
> increase. Both of them are called by options like
> char  common_options[]      = "-st_ksp_type preonly -st_pc_type lu
> -st_pc_factor_mat_solver_package mumps";
> ierr = PetscOptionsInsertString(common_options);CHKERRQ(ierr);
> Shall I set more parameters to get benefit of parallel computing when using
> superlu_dist? My mattype is mpiaij.
> Your sincerely
> Guoxi

More information about the petsc-users mailing list