On 2/8/07, Ben Tay <zonexo at gmail.com> wrote:
> i'm trying to solve my cfd code using PETSc in parallel. Besides the linear
> eqns for PETSc, other parts of the code has also been parallelized using
> MPI.

Finite elements or finite differences, or what?

> however i find that the parallel version of the code running on 4 processors
> is even slower than the sequential version.

Can you monitor the convergence and iteration count of momentum and
poisson steps?


> in order to find out why, i've used the -info option to print out the
> details. there are 2 linear equations being solved - momentum and poisson.
> the momentum one is twice the size of the poisson. it is shown below:

Can you use -log_summary command line option and send the output attached?

> i saw some statements stating "seq". am i running in sequential or parallel
> mode? have i preallocated too much space?

It seems you are running in parallel. The "Seq" are related to local,
internal objects. In PETSc, parallel matrices have inner sequential
matrices.

> lastly, if Ax=b, A_sta and A_end from  MatGetOwnershipRange and b_sta and
> b_end from VecGetOwnershipRange should always be the same value, right?

I should. If not, you are likely going to get an runtime error.

Regards,

-- 
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


Reply via email to