Performance Optimisation of Smoothed Particle Hydrodynamics Algorithms for Multi/Many-Core Architectures
arXiv:1612.06090 · doi:10.1109/HPCS.2017.64
Abstract
We describe a strategy for code modernisation of Gadget, a widely used community code for computational astrophysics. The focus of this work is on node-level performance optimisation, targeting current multi/many-core IntelR architectures. We identify and isolate a sample code kernel, which is representative of a typical Smoothed Particle Hydrodynamics (SPH) algorithm. The code modifications include threading parallelism optimisation, change of the data layout into Structure of Arrays (SoA), auto-vectorisation and algorithmic improvements in the particle sorting. We obtain shorter execution time and improved threading scalability both on Intel XeonR ( on Ivy Bridge) and Xeon PhiTM ( on Knights Corner) systems. First few tests of the optimised code result in faster execution on second generation Xeon Phi (Knights Landing), thus demonstrating the portability of the devised optimisation solutions to upcoming architectures.
arXiv comment8 pages, 2 columns, 4 figures, accepted as paper at HPCS Proceedings 2017, IEEE XPLORE
References in corpus (8)
- The cosmological simulation code GADGET-2
- Populating a cluster of galaxies - I. Results at z=0
- Substructures in hydrodynamical cluster simulations
- Improving convergence in smoothed particle hydrodynamics simulations without pairing instability
- Galaxies in N-body simulations: overcoming the overmerging problem
- nIFTy galaxy cluster simulations I: dark matter & non-radiative models
- Major Mergers Going Notts: Challenges for Modern Halo Finders
- Exploiting the Space Filling Curve Ordering of Particles in the Neighbour Search of Gadget3