On Fri, 31 May 2013 19:46:11 -0500 Jed Brown <[email protected]> wrote: > Jan Blechta <[email protected]> writes: > > > I guess that PETSc never updates ghost dofs unless user explicitly > > calls `VecGhostUpdateBegin/End`. Is it correct? > > PETSc never conflates global and local spaces. Global vectors don't > have ghost dofs and do not even know they exist. Special global > vectors have a function VecGhostGetLocalForm that gets a sequential > representation that includes ghost points. Those ghost points are > updated by VecGhostUpdateBegin/End.
Is it that local representation returned by VecGhostGetLocalForm contains: 1. ghost values 2. view to non-ghosted values in global vector so that when on changes global vector (say by KSP) then values 2. changes appropriately while 1. remains unchanged? Jan > _______________________________________________ > fenics mailing list > [email protected] > http://fenicsproject.org/mailman/listinfo/fenics _______________________________________________ fenics mailing list [email protected] http://fenicsproject.org/mailman/listinfo/fenics
