Proceedings of The 33rd International Symposium on Lattice Field Theory — PoS(LATTICE 2015) · 2016 · 31 citations · 6 references
ComputingComputer ScienceHigh-performance ComputingHeterogeneous ComputingParallel AlgorithmsParallel ComputingData ParallelismParallel ArchitecturesParallel Computer ArchitectureParallel Computing SystemsParallel Numerical Linear AlgebraParallel Numerical MethodsDomain DecompositionHigh-performance Computing OptimizationMultigrid ConvergenceParallel SolversSimd ArchitecturesSimd ExecutionSimd ParallelismVectorization
We present details of our implementation of the Wuppertal adaptive algebraic multigrid code DD-AMG on SIMD architectures, with particular emphasis on the Intel Xeon Phi processor (KNC) used in QPACE 2. As a smoother, the algorithm uses a domain-decomposition-based solver code previously developed for the KNC in Regensburg. We optimized the remaining parts of the multigrid code and conclude that it is a very good target for SIMD architectures. Some of the remaining bottlenecks can be eliminated by vectorizing over multiple test vectors in the setup, which is discussed in the contribution of Daniel Richtmann.
6