Empowering Cloud-Resolving Models Through GPU and Asynchronous I/O

Scientists Involved: Wei-Kuo Tao (PI), Xiaowen Li (Co-I), Xiping Zeng (Co-I), Toshihisa Matsui (Co-I)

Objective. The effects of aerosols on weather and climate are the largest uncertainty in predicting anthropogenic impact on the current weather and climate models. In this project, technology on GPU (graphics processing units) and Asynchronous I/O is used to empower cloud-resolving models (CRMs) and consequently significantly improve the modeling capability of the aerosol effects on weather prediction and climate change studies.

Approach. 

• Computationally intensive components of CRMs (i.e., the microphysics and radiation) is ported to accelerate their performance. 

• An asynchronous I/O tool is developed to improve model efficiency.

• A data compression mechanism is developed to further empower the asynchronous I/O tool.