Tal Ben-Nun, Linus Groner, Florian Deconinck, Tobias Wicky, Eddie Davis, Johann Dahm, Oliver Elbert, Rhea George, Jeremy McGibbon, Lukas Trümper, Elynn Wu, Oliver Fuhrer, Thomas Schulthess, Torsten Hoefler:
Productive Performance Engineering for Weather and Climate Modeling with Python
(In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'22), ISBN: 9784665454445, Nov. 2022)
Abstract
Earth system models are developed with a tight coupling to target hardware, often containing specialized code predicated on processor characteristics. This coupling stems from using imperative languages that hard-code computation schedules and layout. We present a detailed account of optimizing the Finite Volume Cubed-Sphere Dynamical Core (FV3), improving productivity and performance. By using a declarative Python-embedded stencil domain-specific language and data-centric optimization, we abstract hardware-specific details and define a semi-automated workflow for analyzing and optimizing weather and climate applications. The workflow utilizes both local and full-program optimization, as well as user-guided fine-tuning. To prune the infeasible global optimization space, we automatically utilize repeating code motifs via a novel transfer tuning approach. On the Piz Daint supercomputer, we scale to 2,400 GPUs, achieving speedups of up to 3.92x over the tuned production implementation at a fraction of the original code.
Documents
download article: download slides:
Recorded talk (best effort)
BibTeX
@inproceedings{, author={Tal Ben-Nun and Linus Groner and Florian Deconinck and Tobias Wicky and Eddie Davis and Johann Dahm and Oliver Elbert and Rhea George and Jeremy McGibbon and Lukas Trümper and Elynn Wu and Oliver Fuhrer and Thomas Schulthess and Torsten Hoefler}, title={{Productive Performance Engineering for Weather and Climate Modeling with Python}}, year={2022}, month={Nov.}, booktitle={Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'22)}, isbn={9784665454445}, source={http://www.unixer.de/~htor/publications/}, }
