for Astrophysics

Over the past five years, graphics processing units (GPUs) have had a transformational effect on numerical lattice quan-tum chromodynamics (LQCD) calculations in nuclear and particle physics. While GPUs have been applied with great success to the post-Monte Carlo “analysis ” phase which ac-counts for a substantial fraction of the workload in a typi-cal LQCD calculation, the initial Monte Carlo “gauge field generation ” phase requires capability-level supercomputing, corresponding to O(100) GPUs or more. Such strong scaling has not been previously achieved. In this contribution, we demonstrate that using a multi-dimensional parallelization strategy and a domain-decomposed preconditioner allows us to scale into this regime. We present results for two popular discretizations of the Dirac operator, Wilson-clover and im-proved staggered, employing up to 256 GPUs on the Edg