SANTANA Project: Advanced parallel linear solvers for the CFD simulation 
software CODA

This research project will investigate iterative solvers for use in the software 
suite CODA developed by Onera, Airbus and DLR under the SANTANA project. CODA is 
a CFD solver for aircraft design and it features innovative algorithms as well 
as advanced software technology concepts dedicated to HPC. The Spliss library, 
used in CODA to handle linear algebra problems, provides an excellent framework 
for parallel computing. However, the high number of iterations currently 
observed for the block-Jacobi preconditioned Newton-Krylov solver clearly 
indicates that further improvements are necessary. In this project, we will 
carefully analyze and identify bottlenecks using the mathematical structure of 
the system and its HPC implementation.

There is a wide range of algorithmic choices in the literature that can enable 
algorithmic improvements and hence faster and more robust convergence. These 
include advanced domain decomposition techniques as well as modern multi-level 
and multi-grid methods, possibly combined with modern low-density direct 
methods.
While these algorithms can serve as efficient preconditioners, we will also 
explore advanced Krylov subspace techniques, including subspace recycling 
techniques over time steps and deflation techniques to overcome  convergence 
blocking. Recently randomized linear algebra has shown promise in efficiently 
solving implicit RANS equations using Newton-Krylov methods and will be 
investigated in this project for its feasibility in CODA. The selected improved 
solvers will be integrated into the CODA tool, possibly based on interfacing 
with existing libraries. The post-doc researcher in this position is expected to 
collaborate closely with another researcher working on the same project.


Skills required:
•You have defended your thesis less than 3 years from the date of this job 
offer.
• PhD in applied mathematics, fluid dynamics, computer science, iterative 
solvers, numerical linear algebra,
high performance computing.
• Knowledge of preconditioners applied to large-scale problem
• Proficiency in programming languages C++ and Python.
• Familiarity with HPC environments and performance optimization.

To apply, please send your CV and covering letter to carola.kruse@cerfacs.fr, 
applications are open until 03/03/2025.

https://cerfacs.fr/en/offer/santana-project-advanced-parallel-linear-solvers-
for-the-cfd-simulationsoftware-coda/