Lyncs-API: a Python API for Lattice QCD applications

Bacchio, Simone; Finkenrath, Jacob; Stylianou, Christodoulos

doi:10.48550/arxiv.2201.03873

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These improvements could be achieved by moving to Grid or perhaps by using Kokkos [34] as a performance-portability layer. In addition, the interfacing layer provided by Lyncs [35] could allow combining different libraries (Grid and QUDA, for example) and enable both task parallelism and higher programmer productivity. All of these challenges, however, require a significant personnel investment into software development for lattice field theory, ideally as a community effort.…”

Section: Discussionmentioning

confidence: 99%

Twisted mass ensemble generation on GPU machines

Kostrzewa¹,

Bacchio²,

Finkenrath³

et al. 2023

Proceedings of the 39th International Symposium on Lattice Field Theory — PoS(LATTICE2022)

View full text Add to dashboard Cite

We present how we ported the Hybrid Monte Carlo implementation in the tmLQCD software suite to GPUs through offloading its most expensive parts to the QUDA library. We discuss our motivations and some of the technical challenges that we encountered as we added the required functionality to both tmLQCD and QUDA. We further present some performance details, focussing in particular on the usage of QUDA's multigrid solver for poorly conditioned light quark monomials as well as the multi-shift solver for the non-degenerate strange and charm sector in 𝑁 𝑓 = 2 + 1 + 1 simulations using twisted mass clover fermions, comparing the efficiency of state-of-the-art simulations on CPU and GPU machines. We also take a look at the performanceportability question through preliminary tests of our HMC on a machine based on AMD's MI250 GPU, finding good performance after a very minor additional porting effort. Finally, we conclude that we should be able to achieve GPU utilisation factors acceptable for the current generation of (pre-)exascale supercomputers with subtantial efficiency improvements and real time speedups compared to just running on CPUs. At the same time, we find that future challenges will require different approaches and, most importantly, a very significant investment of personnel for software development.

show abstract

Section: Discussionmentioning

confidence: 99%