[petsc-users] Is PetscSFBcast deterministic (just checking, I assume it is)

[Barry Smith]

   We might consider having a universal reproduce flag that fixes everything to be reproducible (for debugging purposes) instead of operation specific ones like -matstash_reproduce.



> On Jul 29, 2021, at 11:45 AM, Jed Brown <jed at jedbrown.org> wrote:
> 
> Provided it's the same SF, yes. (We use MPI_Waitall instead of MPI_Waitsome or this, though we may be able to shave some time using MPI_Waitsome.)
> 
> Matrix assembly from the stash is a common place; try -matstash_reproduce.
> 
> Mark Adams <mfadams at lbl.gov> writes:
> 
>> GAMG is not deterministic and I'm trying to figure out why.
>> Thanks,
>> Mark