Optimizing the Weather Research and Forecasting Model with OpenMP Offload and Codee
Oden Institute for Computational Engineering & Sciences, The University of Texas at Austin, Austin, TX 78712
arXiv:2409.07232 [cs.DC], (11 Sep 2024)
@misc{chayanon2024optimizingweatherresearchforecasting,
title={Optimizing the Weather Research and Forecasting Model with OpenMP Offload and Codee},
author={Chayanon and Wichitrnithed and Woo-Sun-Yang and Yun and He and Brad Richardson and Koichi Sakaguchi and Manuel Arenaz and William I. Gustafson Jr. au2 and Jacob Shpund and Ulises Costi Blanco and Alvaro Goldar Dieste},
year={2024},
eprint={2409.07232},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2409.07232}
}
Currently, the Weather Research and Forecasting model (WRF) utilizes shared memory (OpenMP) and distributed memory (MPI) parallelisms. To take advantage of GPU resources on the Perlmutter supercomputer at NERSC, we port parts of the computationally expensive routines of the Fast Spectral Bin Microphysics (FSBM) microphysical scheme to NVIDIA GPUs using OpenMP device offloading directives. To facilitate this process, we explore a workflow for optimization which uses both runtime profilers and a static code inspection tool Codee to refactor the subroutine. We observe a 2.08x overall speedup for the CONUS-12km thunderstorm test case.
September 15, 2024 by hgpu
