Large Scale GPU Accelerated PPMLR-MHD Simulations for Space Weather Forecast

TL;DR

This paper presents a GPU-accelerated, parallel implementation of the PPMLR-MHD model for simulating space weather, achieving real-time, high-accuracy results by optimizing data transfer and workload distribution across CPUs and GPUs.

Contribution

The work introduces a hybrid CPU-GPU implementation of PPMLR-MHD that significantly improves simulation speed and scalability for space weather modeling.

Findings

Achieved real-time, high-accuracy space weather simulations.

Scaled up to 151 processes on Titan at Oak Ridge National Laboratory.

Reduced data transfer overhead using GPU Direct technology.

Abstract

PPMLR-MHD is a new magnetohydrodynamics (MHD) model used to simulate the interactions of the solar wind with the magnetosphere, which has been proved to be the key element of the space weather cause-and-effect chain process from the Sun to Earth. Compared to existing MHD methods, PPMLR-MHD achieves the advantage of high order spatial accuracy and low numerical dissipation. However, the accuracy comes at a cost. On one hand, this method requires more intensive computation. On the other hand, more boundary data is subject to be transferred during the process of simulation.s In this work, we present a parallel hybrid solution of the PPMLR-MHD model implemented using the computing capabilities of both CPUs and GPUs. We demonstrate that our optimized implementation alleviates the data transfer overhead by using GPU Direct technology and can scale up to 151 processes and achieve significant performance gains by distributing the workload among the CPUs and GPUs on Titan at Oak Ridge National Laboratory. The performance results show that our implementation is fast enough to carry out highly accurate MHD simulations in real time.