Seeking Portability and Productivity for Numerical Weather Prediction Model Code

Achieving hardware-specific implementation and optimization while maintaining productivity in an increasingly diverse environment of supercomputing architectures is challenging and requires rethinking traditional numerical weather prediction model programming designs. We provide insights into the ongoing porting and development of ECMWF’s non-hydrostatic FVM atmospheric dynamical core option in Python with the domain-specific library GT4Py. The presentation highlights the GT4Py approach for implementing weather and climate models, shows preliminary high-performance computing results on CPUs and GPUs for FVM and other ECMWF relevant codes, and outlines the roadmap for the overall model porting project with partners at CSCS and ETH Zurich.