Multigrid on Unstructured Grids Using an Auxiliary Set of Structured Grids

Craig C. Douglas
Sachit Malhotra
Martin H. Schultz

Yale University
Department of Computer Science
P.O. Box 208285
New Haven, CT 06520-8285
USA


Unstructured grids do not have a convenient and natural multigrid framework
for actually computing and maintaining a high floating point rate on standard
computers.  In fact, just the coarsening process is expensive for many
applications.  Since unstrucutured grids play a vital role in many scientific
computing applications, many modifications have been proposed to solve this
problem.  One suggested solution is to map the original unstructured grid onto
a structured grid.  This can be used as a fine grid in a standard multigrid
algorithm to precondition the original problem on the unstructured grid.  We
show that unless extreme care is taken, this mapping can lead to a system with
a high condition number which eliminates the usefulness of the multigrid
method.

Theorems with lower and upper bounds are provided.  Simple examples show that
the upper bounds are sharp.