I think does the trick: https://bitbucket.org/petsc/petsc/pull-requests/1106/change-fortran-null-pointer-to-match-c/diff
Barry > On Sep 5, 2018, at 5:55 PM, Jed Brown <[email protected]> wrote: > > It is safe in Fortran to write > > call DMDestroy(da, ierr) > call DMDestroy(da, ierr) > > but not > > da = PETSC_NULL_DM > call DMDestroy(da, ierr) > > That's pretty lame and inconsistent with the analogous C concept. > Should we either change the value of PETSC_NULL_DM or change the > generated Destroy code?
