Optimization and Scaling of OpenFOAM-based Urban Modeling Simulations

Urban modeling and simulation are critical for addressing urbanization challenges. Optimizing and scaling these simulations can significantly reduce simulation time and resource usage, enabling faster decision making and policy formulation. This paper investigates the performance optimization and scalability of the twin-building case. The study covers various optimization techniques, including compiler-level switches, MPI-specific binding flags, optimal decomposition strategies, and the utilization of vendor-specific compilers. Through extensive experimentation, a significant performance boost was achieved, increasing the performance by approximately 47 times and reducing the simulation time to 46 seconds. This was accomplished by scaling the prototype Twin Building 26.17M case across more than 1,000 CPU-only cores. These findings underscore the importance of performance optimization strategies in effectively harnessing computational resources for large-scale urban modeling simulations. The study improves performance and serves as a basis for future research on heterogeneous computing platforms to enhance simulation time.