AutoWM: a novel domain-specific tool for universal multi-/many-core accelerations of the WRF cloud microphysics

摘要

In large-scale atmospheric simulations, microphysics parameterization often takes a large portion of simulation time and usually consists of dozens of parameterization schemes. Performance optimizing these schemes one by one on different hardware platforms is tedious and error-prone even for skilled programmers. In this work, we propose AutoWM, a novel domain-specific tool for universal performance accelerations of the famous weather research and forecasting model (WRF) microphysics on multi-/many-core systems. The main idea of AutoWM is to reconstruct various schemes into compositions of common building blocks and optimize these building blocks instead of the schemes on target platforms for reusing. To achieve this goal, a light-weight domain-specific language, WML, is provided to describe different microphysics schemes so that the workflow information can be parsed and extracted easily. Experiments on the popular WRF single/double moments microphysics schemes show that AutoWM can automatically generate well optimized microphysics kernels on three multi- and many-core platforms including Intel Ivy Bridge, Intel Xeon Phi and Chinese homegrown SW26010, with the average floating-point efficiency reaching 47%, 20% and 10% of the theoretical peak performance, respectively.