Task-decomposed Overlapped Preconditioner for Sustained Strong Scalability on Accelerated Exascale Systems
Jansson N, Karp M, Páll S, Markidis S, Schlatter P (2026)
Publication Type: Conference contribution
Publication year: 2026
Publisher: Association for Computing Machinery, Inc
Pages Range: 186-193
Conference Proceedings Title: Proceedings of Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region, SCA/HPCAsia 2026
Event location: Osaka, JPN
ISBN: 9798400720673
Abstract
We detail our work on improving the performance and scalability of key numerical methods in the high-fidelity spectral element code Neko on accelerated exascale machines. Eifficient preconditioners are essential in incompressible fluid dynamics; however, the most eifficient method (with respect to convergence) might be challenging to implement with good performance on an accelerator. We present our development of a GPU-optimised preconditioner with task overlapping for the pressure-Poisson equation, improving the preconditioner's throughput (in TDoF/s) by close to 60%. The new preconditioner is explained in detail, together with detailed performance studies on accelerated Cray EX platforms, including strong scalability studies on LUMI and Frontier.
Authors with CRIS profile
Involved external institutions
Sweden (SE)How to cite
APA:
Jansson, N., Karp, M., Páll, S., Markidis, S., & Schlatter, P. (2026). Task-decomposed Overlapped Preconditioner for Sustained Strong Scalability on Accelerated Exascale Systems. In Proceedings of Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region, SCA/HPCAsia 2026 (pp. 186-193). Osaka, JPN: Association for Computing Machinery, Inc.
MLA:
Jansson, Niclas, et al. "Task-decomposed Overlapped Preconditioner for Sustained Strong Scalability on Accelerated Exascale Systems." Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region, SCA/HPCAsia 2026, Osaka, JPN Association for Computing Machinery, Inc, 2026. 186-193.
BibTeX: Download