Proven Distributed Memory Parallelization of Particle Methods (2401.02180v1)
Abstract: We provide a mathematically proven parallelization scheme for particle methods on distributed-memory computer systems. Particle methods are a versatile and widely used class of algorithms for computer simulations and numerical predictions in various applications, ranging from continuum fluid dynamics and granular flows, using methods such as Smoothed Particle Hydrodynamics (SPH) and Discrete Element Methods (DEM) to Molecular Dynamics (MD) simulations in molecular modeling. Particle methods naturally lend themselves to implementation on parallel-computing hardware. So far, however, a mathematical proof of correctness and equivalence to sequential implementations was only available for shared-memory parallelism. Here, we leverage a formal definition of the algorithmic class of particle methods to provide a proven parallelization scheme for distributed-memory computers. We prove that these parallelized particle methods on distributed memory computers are formally equivalent to their sequential counterpart for a well-defined class of particle methods. Notably, the here analyzed parallelization scheme is well-known and commonly used. Our analysis is, therefore, of immediate practical relevance to existing and new parallel software implementations of particle methods and places them on solid theoretical grounds.
- Yaser Afshar and Ivo F. Sbalzarini. 2016. A Parallel Distributed-Memory Particle Method Enables Acquisition-Rate Segmentation of Large Fluorescence Microscopy Images. PLoS One 11, 4 (2016), e0152528. https://doi.org/10.1371/journal.pone.0152528
- B J Alder and T E Wainwright. 1957. Molecular dynamics simulation of hard sphere system. J. Chem. Phys. 27 (1957), 1208–1218.
- Gene M Amdahl. 1967. Validity of the single processor approach to achieving large scale computing capabilities. In Proceedings of the April 18-20, 1967, spring joint computer conference. 483–485.
- Johannes Bamme and Ivo F. Sbalzarini. 2021. A Mathematical Definition of Particle Methods. CoRR abs/2105.05637 (2021). https://doi.org/10.48550/ARXIV.2105.05637 arXiv:2105.05637
- Using DC PSE operator discretization in Eulerian meshless collocation methods improves their robustness in complex geometries. Computers & Fluids 136 (2016), 285–300.
- Discrete region competition for unknown numbers of connected regions. IEEE Trans. Image Process. 21, 8 (2012), 3531–3545.
- G. H. Cottet and S. Mas-Gallic. 1990. A Particle Method to Solve the Navier-Stokes System. Numer. Math. 57 (1990), 805–827.
- P. Degond and S. Mas-Gallic. 1989. The Weighted Particle Method for Convection-Diffusion Equations. Part 1: The Case of an Isotropic Viscosity. Math. Comput. 53, 188 (1989), 485–507.
- A General Deterministic Treatment of Derivatives in Particle Methods. J. Comput. Phys. 180 (2002), 686–709.
- R. A. Gingold and J. J. Monaghan. 1977. Smoothed particle hydrodynamics - Theory and application to non-spherical stars. Royal Astronomical Society, Montly Notices 181 (1977), 375–378.
- John Gustafson. 1988. Reevaluating Amdahl’s Law. Commun. ACM 31 (05 1988), 532–533. https://doi.org/10.1145/42411.42415
- R. W. Hockney and J. W. Eastwood. 1988. Computer Simulation using Particles. Institute of Physics Publishing.
- OpenFPM: A scalable open framework for particle and particle-mesh codes on parallel computers. Comput. Phys. Commun. 241 (2019), 155–177.
- Implementation and performance of FDPS: a framework for developing parallel particle simulation codes. Publications of the Astronomical Society of Japan 68, 4 (2016), 54.
- A Domain-Specific Language and Editor for Parallel Particle Methods. ACM Trans. Math. Softw. 44, 3 (2018), 34.
- A Whole-Cell Computational Model Predicts Phenotype from Genotype. Cell 150 (2012), 389–401.
- Reproducing Kernel Particle Methods. Int. J. Numer. Meth. Fluids 20 (1995), 1081–1106.
- J. J. Monaghan. 2005. Smoothed particle hydrodynamics. Rep. Prog. Phys. 68 (2005), 1703–1759.
- NAMD: a Parallel, Object-Oriented Molecular Dynamics Program. The International Journal of Supercomputer Applications and High Performance Computing 10, 4 (1996), 251–268. https://doi.org/10.1177/109434209601000401 arXiv:https://doi.org/10.1177/109434209601000401
- POOMA: a framework for scientific simulation on parallel architectures. In Proceedings. First International Workshop on High-Level Programming Models and Supportive Environments, A. Bode, M. Gerndt, R.G. Hackenberg, and H. Hellwagner (Eds.). Tech. Univ. Munchen; Res. Centre Julich; Central Inst. Appl. Math.; 10th IEEE Int. Parallel Process. Symposium; IEEE Comput. Soc. Tech. Committee on Parallel Process.; ACM SIGARCH, IEEE Comput. Soc. Press, Los Alamitos, CA, USA, 41–49.
- PPM – A Highly Efficient Parallel Particle-Mesh Library for the Simulation of Continuum Systems. J. Comput. Phys. 215, 2 (2006), 566–588.
- Discretization Correction of General Integral PSE Operators in Particle Methods. J. Comput. Phys. 229 (2010), 4159–4182.
- Efficient collective swimming by harnessing vortices through deep reinforcement learning. Proceedings of the National Academy of Sciences 115, 23 (2018), 5849–5854. https://doi.org/10.1073/pnas.1800923115 arXiv:https://www.pnas.org/doi/pdf/10.1073/pnas.1800923115
- Jens H. Walther and Ivo F. Sbalzarini. 2009. Large-scale parallel discrete element simulations of granular flow. Engineering Computations 26, 6 (2009), 688–697.
- Johannes Pahlke (2 papers)
- Ivo F. Sbalzarini (45 papers)