Jinlei Shen <[email protected]> writes: > Hi, > > Thanks a lot for the replies. They are really helpful. > > I just used the ksp ex2.c as an example to test the parallelization on my > cluster, since the example have flexible number of unknowns. > I do observe that for larger size of the problem, the speed-up shows better > with more processors.
That example is intended to be readable by people new to PETSc, but it is not a good choice for benchmarking because it uses a naive distribution and solves an extremely easy problem. Perhaps a large deformation elasticity example (SNES ex16) would be more representative of your target application?
signature.asc
Description: PGP signature
