Performance Characterization of TSMP2 on Heterogeneous High-Performance Computing Architectures
Extreme-scale heterogeneous computing systems are becoming central to coupled Earth system simulations, where strongly interacting component models impose performance and scalability requirements. TSMP2, the second-generation Terrestrial Systems Modelling Platform, uses a Multiple Program Multiple Data (MPMD) coupling strategy to target modern heterogeneous nodes composed of multi-core CPUs and accelerators. In this contribution, we present a systematic performance characterization of TSMP2 across heterogeneous hardware hierarchies, including intra-chip, intra-node, and inter-node configurations. Experiments are conducted on current leadership-class platforms, including JURECA-DC and the exascale JUPITER system. To isolate architectural and coupling effects, we use a controlled idealized benchmark configuration with uniform soil properties. We analyze resource allocation strategies across heterogeneous deployments, and identify architectural configurations that optimize efficiency. The results show trade-offs in the performance of coupled MPMD workflows on emerging HPC architectures and highlight challenges in executing multi-physics models at extreme scale. Our findings provide practical guidance for optimizing coupled simulation frameworks and offer insights that are applicable to other heterogeneous HPC applications.
Authors
- Jörg Benke (ORCID: https://orcid.org/0000-0003-2707-1629)
- Ana González‐Nicolás (ORCID: https://orcid.org/0000-0003-2869-8255)
- Daniel Caviedes‐Voullième (ORCID: https://orcid.org/0000-0001-7871-7544)
- Stefan Poll (ORCID: https://orcid.org/0000-0003-2527-0747)
- Paul Rigor (ORCID: https://orcid.org/0009-0003-5256-9215)
Institutions
- Forschungszentrum Jülich (DE)
- Jülich Supercomputing Centre (DE)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-16
- DOI
- https://doi.org/10.5281/zenodo.24274582
- Primary Topic
- Parallel Computing and Optimization Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00