I was not aware that SolverCG is using multiple threads. I even briefly
scanned the source code, but could not spot anything that looked like
it.

It's not SolverCG itself but things like SparseMatrix::vmult that are parallelized. If you have a simple preconditioner you spend much time in vmult, so you get decent speedup.

Best
 W.

------------------------------------------------------------------------
Wolfgang Bangerth               email:            [email protected]
                                www: http://www.math.tamu.edu/~bangerth/

_______________________________________________
dealii mailing list http://poisson.dealii.org/mailman/listinfo/dealii

Reply via email to