[petsc-dev] SeqSBAIJ v. MPISBAIJ

[Smith, Barry F.]

   Pierre,

    I have fixed this bug in https://bitbucket.org/petsc/petsc/pull-requests/1941/fix-bug-in-matmpisbaijsetpreallocationcsr/diff

    Thanks for reporting and especially providing the test case

   Barry

> On Aug 1, 2019, at 6:49 PM, Smith, Barry F. via petsc-dev <petsc-dev at mcs.anl.gov> wrote:
> 
> 
>  Yes it is a bug, working on it now. 
> 
> 
>> On Aug 1, 2019, at 9:13 AM, Pierre Jolivet via petsc-dev <petsc-dev at mcs.anl.gov> wrote:
>> 
>> Hello,
>> The attached example is a little confusing for me.
>> How come I don’t get the same matrix out-of-the-box?
>> For me, the “correct” matrix is the SeqSBAIJ, how can I get MatMPISBAIJSetPreallocationCSR to assemble the same matrix?
>> Do I have to resort to first assembling SeqSBAIJ matrices and then calling MatCreateMPIMatConcatenateSeqMat if I don’t want to play around with my input arrays?
>> 
>> Thanks,
>> Pierre
>> 
>> <foo.c>
>