Computational Benefit of GPU Optimization for the Atmospheric Chemistry Modeling

Abstract

Global chemistry-climate models are computationally burdened as the chemical mechanisms become more complex and realistic. Optimization for graphics processing units (GPU) may make longer global simulation with regional detail possible, but limited study has been done to explore the potential benefit for the atmospheric chemistry modeling. Hence, in this study, the second-order Rosenbrock solver of the chemistry module of CAM4-Chem is ported to the GPU to gauge potential speed-up. We find that on the CPU, the fastest performance is achieved using the Intel compiler with a block interleaved memory layout. Different combinations of compiler and memory layout lead to~11.02× difference in the computational time. In contrast, the GPU version performs the best when using a combination of fully interleaved memory layout with block size equal to the warp size, CUDA streams for independent kernels, and constant memory. Moreover, the most efficient data transfer between CPU and GPU is gained by allocating the memory contiguously during the data initialization on the GPU. Compared to one CPU core, the speed-up of using one GPU alone reaches a factor of~11.7× for the computation alone and~3.82× when the data transfer between CPU and GPU is considered. Using one GPU alone is also generally faster than the multithreaded implementation for 16 CPU cores in a compute node and the single-source solution (OpenACC). The best performance is achieved by the implementation of the hybrid CPU/GPU version, but rescheduling the workload among the CPU cores is required before the practical CAM4-Chem simulation.

Importance of Ice Nucleation and Precipitation on Climate with the Parameterization of Unified Microphysics Across Scales version 1 (PUMASv1)

“…Therefore, it is possible to achieve massive parallelism for a parameterization by carefully restructuring the code and increasing the number of columns (for a global model, this means increasing the horizontal resolution), which then becomes a natural fit for GPU computing (Sun et al, 2018).…”

Importance of ice nucleation and precipitation on climate with the Parameterization of Unified Microphysics Across Scales version 1 (PUMASv1)

“…For example, the Community Earth System Model version 2 (CESM2; Danabasoglu et al, 2020) has been shown to have a higher supercooled liquid fraction than observed (Gettelman et al, 2020), which has been linked to a higher climate sensitivity than previous versions (Gettelman et al, 2019b). In addition, cloud microphysics controls the formation of precipitation, which is often too light and too frequent in large-scale weather and climate models (Stephens et al, 2010). This frequency bias has been shown to be directly attributable to cloud microphysics (Gettelman et al, 2021).…”

Climate model-informed deep learning of global soil moisture distribution

“…Progress has been made to accelerate weather, climate and atmospheric-chemistry models with general purpose graphics processing units (GPUs) (Yashiro et al, 2016;Alvanos and Christoudias, 2017;Sun et al, 2018;Fuhrer et al, 2018;Müller et al, 2019), but a wider utilisation is pending. Other high performance computing applications such as lattice quantum chromodynamics with typically smaller codebase and less legacy code swiftly exploited the computational resources of GPUs (Egri et al, 2007;Clark et al, 2010).…”