[petsc-users] 1D parallel split of dense matrix

[Yann Jobic]

Hi Stefano,
You're right, i just switched the rows and colomns, and it's working 
fine. However, i've done this in order to have better performance when i 
access the rows, with MatGetRow. With this order, i need 
MatGetColumnVector, which is believe  is kind of slow, as stated in the 
comments of the implementation (but i couldn't find it again, maybe i 
was looking at an old implementation?).
I still don't understand why i can not use the transpose of this matrix, 
as i give the right parallel decomposition. It should be a bijective 
operation no ?
I think i'll be using the KSPMatSolve of Pierre, so i don't have to 
redevelop this part.
Thanks a lot,
Yann


Le 9/17/2020 à 6:29 PM, Stefano Zampini a écrit :
> Yann
> 
>   you want to have the number of columns equal to the number of rhs. Not 
> the number of rows.
> This is also consistent in terms of logical layouts. Simply create and 
> dump the matrix this way and you can read in parallel splitting yhe rows 
> ( ie the logical size per process of the vectors)
> 
> Il Gio 17 Set 2020, 18:09 Pierre Jolivet <pierre.jolivet at enseeiht.fr 
> <mailto:pierre.jolivet at enseeiht.fr>> ha scritto:
> 
>     Hello Yann,
>     This is probably not fully answering your question, but the proper
>     way to solve a system with N RHS is _not_ to use KSPSolve(), but
>     instead KSPMatSolve(), cf.
>     https://www.mcs.anl.gov/petsc/petsc-dev/docs/manualpages/KSP/KSPMatSolve.html.
>     If you are tracking master (from the GitLab repository), it’s
>     available out of the box. If you are using the release tarballs, it
>     will be available in 3.14.0 scheduled to be released in a couple of
>     days.
>     If you want to know more about the current status of block solvers
>     in PETSc, please feel free to have a look at this preprint:
>     http://jolivet.perso.enseeiht.fr/article.pdf
>     If you are using a specific PC which is not “multi-RHS ready”, see
>     the list at the top of page 5, please let me know and I’ll tell you
>     how easy to support it.
>     Thanks,
>     Pierre
>