SC13 Denver, CO

The International Conference for High Performance Computing, Networking, Storage and Analysis

Massive Parallelization of a Linear Scaling DFT Code OpenMX.

Authors: Truong Vinh Truong Duy (Japan Advanced Institute of Science and Technology and University of Tokyo), Taisuke Ozaki (Japan Advanced Institute of Science and Technology)

Abstract: OpenMX is an open-source first-principles calculation code based on density functional theory for explaining and predicting materials' properties. We massively parallelize OpenMX by developing a domain decomposition method for atoms and grids. In the atom decomposition, we develop a modified recursive bisection method based on the moment of inertia tensor for reordering the atoms from 3D to 1D along a principal axis so that the atoms that are close in real space are also close on the axis to ensure data locality. The atoms are then divided into sub-domains depending on their projections onto the principal axis in a balanced way among the processes. In the grid decomposition, we define four data structures to make data locality consistent with that of the clustered atoms. Benchmark results show that the parallel efficiency at 131,072 cores is 67.7% compared to the baseline of 16,384 cores on the K computer.

Poster: pdf
Two-page extended abstract: pdf

Poster Index