Accelerating high-resolution weather models with deep-learning hardware
The next generation of weather and climate models will have an unprecedented level of resolution and model complexity, and running these models efficiently will require taking advantage of future supercomputers and heterogeneous hardware. In this paper, we investigate the use of mixed-precision har...
Main Authors: | Hatfield, S, Chantry, M, Duben, P, Palmer, T |
---|---|
Format: | Conference item |
Published: |
Association for Computing Machinery
2019
|
Similar Items
-
Scale-selective precision for weather and climate forecasting
by: Chantry, M, et al.
Published: (2019) -
Machine learning emulation of gravity wave drag in numerical weather forecasting
by: Chantry, M, et al.
Published: (2021) -
Improving weather forecast skill through reduced precision data assimilation
by: Hatfield, S, et al.
Published: (2017) -
Modelling, exploration and optimization of hardware accelerators for deep learning applications
by: Dutt, Arko
Published: (2023) -
Posits as an alternative to floats for weather and climate models
by: Klöwer, M, et al.
Published: (2019)