Assign optimization for algorithmic differentiation reuse index management strategies

TL;DR

This paper introduces a novel index reuse strategy for algorithmic differentiation that combines memory efficiency with copy optimization, improving scalability in complex computations.

Contribution

It proposes a new index reuse approach that integrates copy optimization, enhancing the scalability and efficiency of algorithmic differentiation methods.

Findings

The new method reduces memory usage compared to traditional schemes.

It improves scalability in real-world CFD applications.

Performance gains are demonstrated on SU2 solver tests.

Abstract

The identification of primal variables and adjoint variables is usually done via indices in operator overloading algorithmic differentiation tools. One approach is a linear management scheme, which is easy to implement and supports memory optimization for copy statements. An alternative approach performs a reuse of indices, which requires more implementation effort but results in much smaller adjoint vectors. Therefore, the vector mode of algorithmic differentiation scales better with the reuse management scheme. In this paper, we present a novel approach that reuses the indices and allows the copy optimization, thus combining the advantages of the two aforementioned schemes. The new approach is compared to the known approaches on a simple synthetic test case and a real-world example using the computational fluid dynamics solver SU2.