• Corpus ID: 148571877

SPH-EXA: Enhancing the Scalability of SPH codes Via an Exascale-Ready SPH Mini-App

  title={SPH-EXA: Enhancing the Scalability of SPH codes Via an Exascale-Ready SPH Mini-App},
  author={Danilo Guerrera and Aur{\'e}lien Cavelan and Rub{\'e}n M. Cabez{\'o}n and David Imbert and Jean-Guillaume Piccinali and Ali Mohammed and Lucio Mayer and Darren S. Reed and Florina M. Ciorba},
Numerical simulations of fluids in astrophysics and computational fluid dynamics (CFD) are among the most computationally-demanding calculations, in terms of sustained floating-point operations per second, or FLOP/s. It is expected that these numerical simulations will significantly benefit from the future Exascale computing infrastructures, that will perform 10^18 FLOP/s. The performance of the SPH codes is, in general, adversely impacted by several factors, such as multiple time-stepping… 

Figures and Tables from this paper



Towards a Mini-App for Smoothed Particle Hydrodynamics at Exascale

This work extrapolates the common basic SPH features in the three codes for the purpose of consolidating them into a pure-SPH, Exascale-ready, optimized, mini-app, serving as direct feedback to the parent codes, to improve their performance and overall scalability.

SPHYNX: an accurate density-based SPH method for astrophysical applications

Hydrodynamical instabilities and shocks are ubiquitous in astrophysical scenarios. Therefore, an accurate numerical simulation of these phenomena is mandatory to correctly model and understand many

Equalizing resolution in smoothed-particle hydrodynamics calculations using self-adaptive sinc kernels

Context. The smoothed-particle hydrodynamics (SPH) technique is a numerical method for solving gas-dynamical problems. It has been applied to simulate the evolution of a wide variety of astrophysical

Fundamental differences between SPH and grid methods

We have carried out a comparison study of hydrodynamical codes by investigating their performance in modelling interacting multiphase fluids. The two commonly used techniques of grid and smoothed

A test suite for quantitative comparison of hydrodynamic codes in astrophysics

We test four commonly used astrophysical simulation codes, enzo, flash, gadget and hydra, using a suite of numerical problems with analytic initial and final states. Situations similar to the

Adaptive techniques for clustered N-body cosmological simulations

This paper presents the parallel design of ChaNGa and address many challenges arising due to the high dynamic ranges of clustered datasets, and proposes optimizations based on adaptive techniques.

Core-collapse supernovae in the hall of mirrors

Context. Modeling core-collapse supernovae (SNe) with neutrino transport in three dimensions (3D) requires tremendous computing resources and some level of approximation. We present a first

Shock simulation by the particle method SPH

MiniGhost: A Miniapp for Exploring Boundary Exchange Strategies Using Stencil Computations in Scientific Parallel Computing

This report describes miniGhost, a miniapp designed for exploration of the capabilities of current as well as emerging and future architectures within the context of current and future architecture applications, and joins the suite of miniapps developed as part of the Mantevo project.