A Second-Order Distributed Trotter-Suzuki Solver with a Hybrid Kernel
Swedish School of Library and Information Science, University of Boras, Allegatan 1, Boras, S-501 90, Sweden
arXiv:1208.2407v1 [physics.comp-ph] (12 Aug 2012)
@article{2012arXiv1208.2407W,
author={Wittek, Peter and Cucchietti, Fernando M.},
title={"{A Second-Order Distributed Trotter-Suzuki Solver with a Hybrid Kernel}"},
journal={ArXiv e-prints},
archivePrefix={"arXiv"},
eprint={1208.2407},
primaryClass={"physics.comp-ph"},
keywords={Computational Physics; Distributed, Parallel, and Cluster Computing; Quantum Physics},
year={2012},
month={aug}
}
The Trotter-Suzuki approximation leads to an efficient algorithm for solving the time-dependent Schroedinger equation. Using existing highly optimized CPU and GPU kernels, we developed a distributed version of the algorithm that runs efficiently on a cluster. Our implementation also improves single node performance, and is able to use multiple GPUs within a node. The scaling is close to linear using the CPU kernels, whereas the efficiency of GPU kernels improve with larger matrices. We also introduce a hybrid kernel that simultaneously uses multicore CPUs and GPUs in a distributed system. This kernel is shown to be efficient when the matrix size would not fit in the GPU memory. Larger quantum systems scale especially well with a high number nodes. The code is available under an open source license.
August 14, 2012 by hgpu
