$O(a)$-improved QCD+QED Wilson Dirac operator on GPUs

TL;DR

This paper demonstrates how offloading Dirac operator inversions to GPUs using the QUDA library significantly accelerates lattice QCD+QED simulations, enabling more precise physics predictions with improved computational efficiency.

Contribution

The authors adapt the QUDA library for their specific physics applications, achieving substantial speed-ups and enhancing performance portability on GPU clusters for lattice QCD+QED simulations.

Findings

Significant potential speed-up in Dirac operator inversions on GPUs.

Minimal library modifications needed for physics-specific applications.

Enhanced performance portability and readiness for pre-exascale computing.

Abstract

Markov Chain Monte Carlo simulations of lattice Quantum Chromodynamics (QCD) are the only known tool to investigate non-perturbatively the theory of the strong interaction and are required to perform precision tests of the Standard Model of Particle Physics. As the Markov Chain is a serial process, the sole option for improving the sampling rate is accelerating each individual update step. Heterogeneous clusters of GPU-accelerated nodes offer large total memory bandwidth which can be used to speed-up our application, openQxD-1.1, which is dominated by inversions of the Dirac operator, a large sparse matrix. In this work we investigate offloading the inversion to GPU using the lattice-QCD library QUDA, and our early results demonstrate a significant potential speed-up in the time-to-solution for state-of-the-art problem sizes. Minimal extensions to the existing QUDA library are required for our specific physics programme while greatly enhancing the performance portability of our code and retaining the reliability and robustness of existing applications in openQxD-1.1. Our new interface will enable us to utilize pre-exascale infrastructure and reduce the systematic uncertainty in our physics predictions by incorporating the effects of quantum electromagnetism (QED) in our simulations.