Recorded Presentation
High-Definition Poster
Jessica Imlau Dagostini 1, 2, Sowmya Yellapragada3, 2, Kevin Gott2, Rebecca Hartman-Baker2
1University of California Santa Cruz, 2NERSC/LBL, 3University of Utah
Presented at the 2025 ACM/IEEE Supercomputing Conference (SC25)
In this work, we present a new toolbox designed to streamline the collection and analysis of load balancing data from WarpX/AMReX simulations. Our tools enable running simulations and efficiently collect and parse load balancing data from WarpX runs, and a mechanism to re-run collected data with different load balancing strategies for posterior analysis and comparison. We demonstrate the applicability of our tool by performing the full-step process of collection and data analysis with a laser-ion simulation.
Access the full codebase, data, and documentation for this project. The repository includes all the necessary files to reproduce the research and explore the code.
