dolfin team mailing list archive

["Garth N. Wells" <gnw20@xxxxxxxxx>]

You cannot

  (a) rely on machines that manage dynamically the CPU clock speed and
spin down the hard disk, especially laptops, to generate reliable
(short) timings.

  (b) get a tuned installation with Dorsal

My times (not using Dorsal) are:

    Init MPI                     |      0.018783    0.018783     1
    Init PETSc                 |    0.00043392  0.00043392     1
    Init dof vector             |    0.00064111  0.00064111     1

Garth

On Sun, Oct 14, 2012 at 7:33 AM, Johannes Ring <johannr@xxxxxxxxx> wrote:
> On Sun, Oct 14, 2012 at 6:45 AM, Anders Logg <logg@xxxxxxxxx> wrote:
>> PetscInitialize is taking a really long time for me. Is it just my
>> PETSc build (petsc-3.2-p6 via Dorsal) or does anyone else see the same
>> thing?
>>
>> Try the latest trunk and add a call to list_timings() just before the
>> plot command in the Poisson demo. I see this:
>>
>> Init MPI                    |      0.025922    0.025922     1
>> Init PETSc                  |       0.45424     0.45424     1
>> Init dof vector             |       0.45455     0.45455     1
>
> I get this on my laptop (Debian sid with libpetsc3.2-dev package):
>
> Init MPI                    |      0.036537    0.036537     1
> Init PETSc                  |    0.00026798  0.00026798     1
> Init dof vector             |    0.00041413  0.00041413     1
>
> This is what I get on bigblue (cluster on Simula) with PETSc 3.3-p3
> built via Dorsal:
>
> Init MPI                    |      0.029151    0.029151     1
> Init PETSc                  |    0.00062299  0.00062299     1
> Init dof vector             |    0.00091791  0.00091791     1
>
> Johannes
>
> _______________________________________________
> Mailing list: https://launchpad.net/~dolfin
> Post to     : dolfin@xxxxxxxxxxxxxxxxxxx
> Unsubscribe : https://launchpad.net/~dolfin
> More help   : https://help.launchpad.net/ListHelp