Refactoring the MPS/University of Chicago Radiative MHD(MURaM) Model for GPU/CPU Performance Portability Using OpenACC Directives

TL;DR

This paper refactors the MURaM radiative MHD model to achieve GPU/CPU performance portability using OpenACC directives, enabling faster simulations of solar phenomena across different hardware.

Contribution

It introduces a directive-based approach to refactor MURaM for performance portability, maintaining a single source code for CPUs and GPUs, and demonstrates significant speedups and scalability.

Findings

1.73x speedup of RTS routine on a single GPU over CPU.

GPU performance equivalent to 69 CPU cores.

Effective scaling up to 96 GPUs.

Abstract

The MURaM (Max Planck University of Chicago Radiative MHD) code is a solar atmosphere radiative MHD model that has been broadly applied to solar phenomena ranging from quiet to active sun, including eruptive events such as flares and coronal mass ejections. The treatment of physics is sufficiently realistic to allow for the synthesis of emission from visible light to extreme UV and X-rays, which is critical for a detailed comparison with available and future multi-wavelength observations. This component relies critically on the radiation transport solver (RTS) of MURaM; the most computationally intensive component of the code. The benefits of accelerating RTS are multiple fold: A faster RTS allows for the regular use of the more expensive multi-band radiation transport needed for comparison with observations, and this will pave the way for the acceleration of ongoing improvements in RTS that are critical for simulations of the solar chromosphere. We present challenges and strategies to accelerate a multi-physics, multi-band MURaM using a directive-based programming model, OpenACC in order to maintain a single source code across CPUs and GPUs. Results for a $288^3$ test problem show that MURaM with the optimized RTS routine achieves 1.73x speedup using a single NVIDIA V100 GPU over a fully subscribed 40-core Intel Skylake CPU node and with respect to the number of simulation points (in millions) per second, a single NVIDIA V100 GPU is equivalent to 69 Skylake cores. We also measure parallel performance on up to 96 GPUs and present weak and strong scaling results.