26 July 2026 to 1 August 2026
University of Maryland, College Park
US/Eastern timezone

Machine-Learning-Accelerated Multigrid Setup for Lattice QCD Dirac Solves

27 Jul 2026, 14:40
20m
Benjamin Banneker B (Adele H. Stamp Student Union)

Benjamin Banneker B

Adele H. Stamp Student Union

3972 Campus Dr, College Park, MD 20742
Contributed talk Algorithms and artificial intelligence Algorithms and artificial intelligence

Speaker

Simon Pfahler (University of Regensburg)

Description

Gauge-field generation in lattice QCD is dominated by repeated solves of the Dirac equation. While multigrid preconditioners reduce solve costs significantly, their expensive setup phase limits overall efficiency. We introduce a gauge-equivariant neural network that accelerates this setup by using approximate low modes from previous configurations, exploiting the autocorrelation along the Markov chain. We tested the method on quenched ensembles at beta=6 with two lattice sizes (8^3 x 16 and 16^3 x 32). Comparing our setup method to a standard multigrid setup with similar computational cost, we find that our setup method leads to a substantially faster multigrid solve. Remarkably, networks trained on the smaller volume generalize to the larger lattice without the need for retraining. These results demonstrate a promising path toward more efficient large-scale lattice QCD simulations.

Authors

Simon Pfahler (University of Regensburg) Daniel Knüttel (University of Regensburg) Riccardo Costantini (University of Regensburg) Christoph Lehner (Universität Regensburg) Tilo Wettig (University of Regensburg)

Presentation materials