English

A Hybrid MPI+Threads Approach to Particle Group Finding Using Union-Find

Distributed, Parallel, and Cluster Computing 2020-03-26 v1 Data Structures and Algorithms

Abstract

The Friends-of-Friends (FoF) algorithm is a standard technique used in cosmological NN-body simulations to identify structures. Its goal is to find clusters of particles (called groups) that are separated by at most a cut-off radius. NN-body simulations typically use most of the memory present on a node, leaving very little free for a FoF algorithm to run on-the-fly. We propose a new method that utilises the common Union-Find data structure and a hybrid MPI+threads approach. The algorithm can also be expressed elegantly in a task-based formalism if such a framework is used in the rest of the application. We have implemented our algorithm in the open-source cosmological code, SWIFT. Our implementation displays excellent strong- and weak-scaling behaviour on realistic problems and compares favourably (speed-up of 18x) over other methods commonly used in the NN-body community.

Keywords

Cite

@article{arxiv.2003.11468,
  title  = {A Hybrid MPI+Threads Approach to Particle Group Finding Using Union-Find},
  author = {James S. Willis and Matthieu Schaller and Pedro Gonnet and John C. Helly},
  journal= {arXiv preprint arXiv:2003.11468},
  year   = {2020}
}

Comments

12 pages, 4 figures. Proceedings of the ParCo 2019 conference, Prague, Czech Republic, September 10-13th, 2019

R2 v1 2026-06-23T14:27:00.411Z