[petsc-dev] SeqSBAIJ v. MPISBAIJ

[Smith, Barry F.]

  Pierre,

    Your code did expose another error, I have pushed a fix in the same branch*.

  Stefano,

    I think you are partially right about the sizes of a SBAIJ matrix. I think it is ok for the number of columns to be greater than the number of rows (no information is lost or missing) but one cannot have more rows than columns (because there is no place to store the information for those final rows). I have added error checks and documents for this.

  Thanks

   Barry

* As mentioned above your example doesn't make sense because has more rows than columns. 


> On Aug 3, 2019, at 9:11 AM, Stefano Zampini <stefano.zampini at gmail.com> wrote:
> 
> Pierre,
> 
> The SBAIJ format is for square matrices, it doesn’t make sense for rectangular matrices
> Anyway, I have found few bugs with SBAIJ, please have a look at https://bitbucket.org/petsc/petsc/branch/stefano_zampini/sbaij-example
> 
> Stefano
> 
>> On Aug 2, 2019, at 6:00 PM, Pierre Jolivet via petsc-dev <petsc-dev at mcs.anl.gov> wrote:
>> 
>> <ex232.c>
>