2011/09/20 by Andrea Nobile, Nobile, Andrea
Physics and Astronomy · #FOS: Physical sciences #High Energy Physics - Lattice (hep-lat) #hep-lat
paper · pdf · doi:10.48550/arxiv.1109.4279
7 pages, Lattice 2010 Proceedings
arxiv created 2011/09/20 · arxiv updated 2011/09/21
We discuss the implementation and optimization challenges for a Wilson-Dirac solver with Clover term on QPACE, a parallel machine based on Cell processors and a torus network. We choose the mixed-precision Schwarz preconditioned FGCR algorithm in order to circumvent network bandwidth and latency constraints, to make efficient use of the multicore parallelism and on-chip memory, and to achieve flexibility in the choice of lattice sizes. We present benchmarks on up to 256 QPACE nodes showing an aggregate sustained performance of about 10 TFlops for the complete solver and very good scaling.