Object-oriented implementation of algebraic multi-grid solver for lattice QCD on SIMD architectures and GPU clusters
arXiv:2111.05012 · doi:10.1007/978-3-030-86976-2_15
Abstract
A portable implementation of elaborated algorithm is important to use variety of architectures in HPC applications. In this work we implement and benchmark an algebraic multi-grid solver for Lattice QCD on three different architectures, Intel Xeon Phi, Fujitsu A64FX, and NVIDIA Tesla V100, in keeping high performance and portability of the code based on the object-oriented paradigm. Some parts of code are specific to an architecture employing appropriate data layout and tuned matrix-vector multiplication kernels, while the implementation of abstract solver algorithm is common to all architectures. Although the performance of the solver depends on tuning of the architecture-dependent part, we observe reasonable scaling behavior and better performance than the mixed precision BiCGSstab solvers.
arXiv comment17 pages, 7 figures. The 21st International Conference on Computational Science and Its Applications, ICCSA 2021
References in corpus (9)
- Solving Lattice QCD systems of equations using mixed precision solvers on GPUs
- 2+1 Flavor Lattice QCD toward the Physical Point
- Adaptive multigrid algorithm for the lattice Wilson-Dirac operator
- Helium nuclei, deuteron and dineutron in 2+1 flavor lattice QCD
- Solution of the Dirac equation in lattice QCD using a domain decomposition method
- Adaptive Multigrid Algorithm for Lattice QCD
- Lattice QCD and the Schwarz alternating procedure
- DD-AMG on QPACE 3
- Practical Implementation of Lattice QCD Simulation on SIMD Machines with Intel AVX-512