We present an algorithm for neighbor search in molecular simulations on graphics processing units (GPUs) based on bounding volume hierarchies (BVHs). The BVH is compressed into a low-precision, quantized representation to increase the BVH traversal speed compared to a previous implementation. We find that neighbor search using the quantized BVH is roughly two to four times faster than current state-of-the-art methods using uniform grids (cell lists) for a suite of benchmarks for common molecular simulation models. Based on the benchmark results, we recommend using the BVH instead of a single cell list for neighbor list generation in molecular simulations on GPUs.
@article{arxiv.1901.08088,
title = {Quantized bounding volume hierarchies for neighbor search in molecular simulations on graphics processing units},
author = {Michael P. Howard and Antonia Statt and Felix Madutsa and Thomas M. Truskett and Athanassios Z. Panagiotopoulos},
journal= {arXiv preprint arXiv:1901.08088},
year = {2019}
}