Optimizing the Weather Research and Forecasting Model with OpenMP Offload and Codee

Conference · Mon Dec 30 04:00:00 EST 2024

DOI:https://doi.org/10.1109/SCW63240.2024.00243· OSTI ID:2519665

Wichitrnithed, Chayanon (Namo) ^[1]; Yang, Woo- Sung ^[2]; He, Yun (Helen) ^[3]; Richardson, Brad ^[2]; Sakaguchi, Koichi ^[4]; Arenaz, Manuel ^[5]; Gustafson, William I. ^[4]; Shpund, Jacob ^[4]; Costi Blanco, Ulises ^[6]; Goldar Dieste, Alvaro ^[6]

---

1. Odin Institute
2. Lawrence Berkeley National Laboratory
3. Lawrence Livermore National Laboratory
4. BATTELLE (PACIFIC NW LAB)
5. Appentra Solutions S.L
6. Appentra Solutions

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 routine Fast Spectral Bin Microphysics (FSBM) 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 an 2.24x overall speedup for the CONUS-12km storm test case.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 2519665
• Report Number(s): PNNL-SA-202641
• Country of Publication: United States
• Language: English