The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Authors: Tim Powell (Hartree Centre, STFC), Nuno Nobre (Hartree Centre, STFC), Chris Skylaris (University of Southampton, Faraday Institution), Hariswaran Sitaraman (National Renewable Energy Laboratory (NREL)), Ramakrishnan Kannan (Oak Ridge National Laboratory (ORNL))
Abstract: With the increasing prevalence of electric vehicles and Net Zero targets, battery simulation is crucial. HPC facilitates accurate simulations of battery electrochemistry and thermal behavior, allowing improved predictions of cell performance, cyclic life, and safety to inform R&D. This BoF will address the challenges of bringing a mature software ecosystem into the exascale and AI era. The BoF will consist of a combined talk from an international group who are engaged in developing battery simulations for exascale applications, followed by an audience discussion and panel session sharing insights, obstacles, and solutions to accelerate the collaborative development of batteries.
Long Description: This BoF will explore the challenges of transitioning mature scientific codebases to Exascale computing platforms, using battery modelling as a concrete case study. Significant progress has been made in modelling the complex multi-physics processes involved in lithium-ion battery operation and degradation, leading to multiple mature research codes and extensive software ecosystems across the global battery research community. However, many of these codes were developed for previous generations of HPC systems and face major challenges when targeting Exascale architectures, particularly as heterogeneous platforms (CPU/GPU/AI accelerators) become the norm.
Batteries are an ideal focus for this discussion because they embody many of the most demanding challenges in computational science today. Accurately predicting battery behaviour requires coupling physical phenomena across a vast range of length and timescales, from sub-micron particle fractures and electrochemical reactions at millisecond scales, to thermal propagation, mechanical stresses, and aging processes unfolding over months or years at pack level. Yet even with current HPC capabilities, most detailed simulations remain limited to short operational windows, often seconds or minutes, far short of the long-term behaviours industry urgently needs. As global demand for batteries accelerates, driven by electric vehicles, grid storage, and the Net Zero transition, improved modelling capabilities at scale are critical for innovation, safety, and lifetime optimization. The extreme computational demands of this domain make it both uniquely challenging and highly representative of the broader HPC challenges faced by many scientific domains approaching Exascale.
The primary goal of this BoF is to foster a focused community discussion on the practical, technical, and organizational barriers involved in evolving these software environments to fully exploit Exascale HPC.
Session topics:
- Porting and optimizing existing codes for heterogeneous Exascale systems.
- Coupling multi-scale, multi-physics models efficiently at scale.
- Interoperability challenges between independent research codes.
- Leveraging AI and ML surrogate models to accelerate high-fidelity simulation.
- Ensuring long-term software sustainability and workforce development.
While batteries provide a compelling and timely example, the underlying challenges addressed in this BoF are relevant to the entire HPC community, particularly for domains that have grown rich software ecosystems over decades of research. The discussion will bring together computational scientists, domain experts, software developers, and industrial partners to share experience, best practices, and collaborative opportunities.
This BoF builds directly on SC24’s successful “Next-Gen Battery Simulation at Exascale” BoF, which focused on the computational challenges of battery modelling. Based on strong interest from that discussion, this year’s session shifts the focus to the software and ecosystem transition challenges associated with moving mature, real-world scientific codes into the Exascale era. This reflects a natural evolution of the conversation as many domains now face the practical realities of adapting their established software stacks for next-generation computing architectures.
Expected outcomes include:
- Share practical experiences in code porting, optimization, and multi-code coupling on heterogeneous HPC systems.
- Foster cross-disciplinary collaboration between battery scientists, HPC experts, and industry partners.
- Explore the use of AI surrogate models, advanced numerical methods, and workflow orchestration to accelerate large-scale, long-timescale simulations.
- Identify community priorities and actionable steps for advancing Exascale-capable battery modelling.