Physics – High Energy Physics – High Energy Physics - Lattice
Scientific paper
2010-10-29
Physics
High Energy Physics
High Energy Physics - Lattice
11 pages, 7 figures, to appear in the Proceedings of Supercomputing 2010 (submitted April 12, 2010)
Scientific paper
10.1109/SC.2010.40
Graphics Processing Units (GPUs) are having a transformational effect on numerical lattice quantum chromodynamics (LQCD) calculations of importance in nuclear and particle physics. The QUDA library provides a package of mixed precision sparse matrix linear solvers for LQCD applications, supporting single GPUs based on NVIDIA's Compute Unified Device Architecture (CUDA). This library, interfaced to the QDP++/Chroma framework for LQCD calculations, is currently in production use on the "9g" cluster at the Jefferson Laboratory, enabling unprecedented price/performance for a range of problems in LQCD. Nevertheless, memory constraints on current GPU devices limit the problem sizes that can be tackled. In this contribution we describe the parallelization of the QUDA library onto multiple GPUs using MPI, including strategies for the overlapping of communication and computation. We report on both weak and strong scaling for up to 32 GPUs interconnected by InfiniBand, on which we sustain in excess of 4 Tflops.
Babich Ronald
Clark Michael A.
Joó Bálint
No associations
LandOfFree
Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-404867