Distributed Newest Vertex Bisection
Provides theoretical guarantees for distributed mesh refinement, benefiting users of parallel adaptive finite element methods.
The paper addresses the problem of distributed adaptive conforming refinement, showing bounds on the maximum number of iterations needed. The algorithm is implemented in DUNE-ALUGrid.
Distributed adaptive conforming refinement requires multiple iterations of the serial refinement algorithm and global communication as the refinement can be propagated over several processor boundaries. We show bounds on the maximum number of iterations. The algorithm is implemented within the software package DUNE-ALUGrid.