American Physical Society Sites|APS|Journals|PhysicsCentral|Physics

Session M12: Invited Session: The Impact of Heterogeneous High Performance Computing Platforms on Computational Physics

11:15 AM–2:15 PM, Wednesday, March 5, 2014
Room: 205

Sponsoring Unit: DCOMP
Chair: Barry Schneider, National Science Foundation

Abstract ID: BAPS.2014.MAR.M12.3

Abstract: M12.00003 : Using GPUs in Lattice Chromodynamics*

12:27 PM–1:03 PM

Preview Abstract      Abstract  

Author:

Andrei Alexandru
(The George Washington University)

Lattice quantum chromodynamics (QCD) calculations were one of the first applications to demonstrate the potential of GPUs in the area of high-performance computing, because the nature of lattice QCD calculations matches well the GPUs' computational model. In this talk, we will discuss ways to effectively use GPUs for lattice calculations using the overlap operator, a discretization that preserves chiral symmetry even at nonzero lattice spacing and makes possible lattice QCD simulations in the parameter region relevant to Nuclear Physics. We will show that the large memory footprint of these codes requires the use of multiple GPUs in parallel and we will discuss methods used to implement this operator efficiently: mixed-precision for inverters, hybrid CPU/GPU memory use for eigensolvers, and MPI/OpenMP/CUDA parallelization strategies required to take full advantage of both GPU and CPU available resources. We compare the performance of our codes on a GPU cluster and a CPU cluster with similar interconnects. We discuss the strong scaling for problem sizes relevant to current lattice QCD simulations.

*Research supported by NSF and DOE.

To cite this abstract, use the following reference: http://meetings.aps.org/link/BAPS.2014.MAR.M12.3