Massively Parallel Computation of Accurate Densities for N-body Dark Matter Simulations using the Phase-Space-Element Method
arXiv:1612.09491 · doi:10.1016/j.ascom.2017.05.005
Abstract
This paper presents an accurate density computation approach for large dark matter simulations, based on a recently introduced phase-space tessellation technique and designed for massively parallel, heterogeneous cluster architectures. We discuss a memory efficient construction of an oct-tree structure to sample the mass densities with locally adaptive resolution, according to the features of the underlying tetrahedral tessellation. We propose an efficient GPU implementation for the computationally intensive operation of intersecting the tetrahedra with the cubical cells of the deposit grid, that achieves a speedup of almost an order of magnitude compared to an optimized CPU version. We discuss two dynamic load balancing schemes - the first exchanges particle data between cluster nodes and deposits all tetrahedra for each block of the grid structure on single nodes, whereas the second approach uses global reduction operations to obtain the total masses. We demonstrate the scalability of our algorithms for up to 256 GPUs and TB-sized simulation snapshots, resulting in tessellations with over 400 billion tetrahedra.
arXiv commentaccepted manuscript; code implementation available at https://github.com/kaehlerr/ADECO
References in corpus (18)
- Cosmological Hydrodynamics with Adaptive Mesh Refinement: a new high resolution code called RAMSES
- Enzo: An Adaptive Mesh Refinement Code for Astrophysics
- Adaptive Refinement Tree - a new high-resolution N-body code for cosmological simulations
- ZOBOV: a parameter-free void-finding algorithm
- Nyx: A Massively Parallel AMR Code for Computational Cosmology
- Tracing the Dark Matter Sheet in Phase Space
- The Cosmic Web, Multi-Stream Flows, and Tessellations
- GreeM : Massively Parallel TreePM Code for Large Cosmological N-body Simulations
- The Properties of Cosmic Velocity Fields
- A new approach to simulating collisionless dark matter fluids
- GOTPM: A Parallel Hybrid Particle-Mesh Treecode
- An adaptively refined phase-space element method for cosmological simulations and collisionless dynamics
- Dark Sky Simulations: Early Data Release
- VINE -- A numerical code for simulating astrophysical systems using particles I: Description of the physics and the numerical methods
- An exact general remeshing scheme applied to physically conservative voxelization
- 2HOT: An Improved Parallel Hashed Oct-Tree N-Body Algorithm for Cosmological Simulation
- A Novel Approach to Visualizing Dark Matter Simulations
- Noiseless Gravitational Lensing Simulations
Cited by in corpus (4)
- Large-scale dark matter simulations
- Symphony: Cosmological Zoom-in Simulation Suites over Four Decades of Host Halo Mass
- Milky Way-est: Cosmological Zoom-in Simulations with Large Magellanic Cloud and Gaia-Sausage-Enceladus Analogs
- The SAGA Survey. V. Modeling Satellite Systems around Milky Way-mass Galaxies with Updated UniverseMachine