Performance of embedded boundary methods for CFD with complex geometry

In this paper, we discuss some of the issues in obtaining high performance for block-structured adaptive mesh refinement software for partial differential equations in complex geometry using embedded boundary/volume-of-fluid methods. We present the design of an adaptive embedded boundary multigrid algorithm for elliptic problems. We show examples in which this new elliptic solver scales to 1000 processors. We also apply this technology to more complex mathematical and physical algorithms for incompressible fluid dynamics and demonstrate similar scaling.