Accelerating lattice QCD simulations with 2 flavours of staggered fermions on multiple GPUs using OpenACC - a first attempt

TL;DR

This paper demonstrates a significant speed-up in lattice QCD simulations with 2 flavors of staggered fermions by using multiple GPUs and OpenACC, highlighting the potential of directive-based programming for scientific computing.

Contribution

First attempt to accelerate lattice QCD simulations on multiple GPUs using OpenACC, achieving over three times speed-up without CUDA.

Findings

Over three times speed-up compared to CPU MPI implementation

Bandwidth bound nature limits parallelization gains

OpenACC enables effective GPU acceleration for lattice QCD

Abstract

We present the results of an effort to accelerate a Rational Hybrid Monte Carlo (RHMC) program for lattice quantum chromodynamics (QCD) simulation for 2 flavours of staggered fermions on multiple Kepler K20X GPUs distributed on different nodes of a Cray XC30. We do not use CUDA but adopt a higher level directive based programming approach using the OpenACC platform. The lattice QCD algorithm is known to be bandwidth bound; our timing results illustrate this clearly, and we discuss how this limits the parallelization gains. We achieve more than a factor three speed-up compared to the CPU only MPI program.