Re: [Libmesh-devel] Global parameters

[Benjamin K. <ben...@na...>]

> The trouble would be the dense rows and columns that each new scalar
> would add to the sparsity pattern.

It adds a column to every row, but that is not a problem for all the other
rows, right?  It is just one more entry that gets stored in that sparse row?

The major issue is that the last row is fully dense, as you point out.  It
seems like an inefficiency, and unfair to the poor processor that ends up
with that dof.  I wonder if there is a specific hack for this somewhere deep
in the bowels of petsc or trilinos...

-Ben