OpenSBLI: A framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures

Abstract

Exascale computing will feature novel and potentially disruptive hardware architectures. Exploiting these to their full potential is non-trivial. Numerical modelling frameworks involving finite difference methods are currently limited by the 'static' nature of the hand-coded discretisation schemes and repeatedly may have to be re-written to run efficiently on new hardware. In contrast, OpenSBLI uses code generation to derive the model's code from a high-level specification. Users focus on the equations to solve, whilst not concerning themselves with the detailed implementation. Source-to-source translation is used to tailor the code and enable its execution on a variety of hardware.

Author accepted version, with a small amendment: the link in the "Code Availability" section has been updated, and now refers to the OpenSBLI source code repository on GitHub. Accepted for publication in the Journal of Computational Science on 8 November 2016

References in corpus (4)

• DOLFIN: Automated Finite Element Computing
• Firedrake: automating the finite element method by composing abstractions
• OPESCI-FD: Automatic Code Generation Package for Finite Difference Models
• Devito: Towards a generic Finite Difference DSL using Symbolic Python

Cited by in corpus (13)

• Devito (v3.1.0): an embedded domain-specific language for finite differences and geophysical exploration
• Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies
• OpenSBLI: Automated code-generation for heterogeneous computing architectures applied to compressible fluid dynamics on structured grids
• Loop Tiling in Large-Scale Stencil Codes at Run-time with OPS
• A shared compilation stack for distributed-memory parallelism in stencil DSLs
• Multirate Time-Integration based on Dynamic ODE Partitioning through Adaptively Refined Meshes for Compressible Fluid Dynamics
• A mesh-free framework for high-order direct numerical simulations of combustion in complex geometries
• Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
• STREAmS: a high-fidelity accelerated solver for direct numerical simulation of compressible turbulent flow
• fmmgen: Automatic Code Generation of Operators for Cartesian Fast Multipole and Barnes-Hut Methods
• Evaluating the Arm Ecosystem for High Performance Computing
• Energy efficiency of finite difference algorithms on multicore CPUs, GPUs, and Intel Xeon Phi processors
• Beyond 16GB: Out-of-Core Stencil Computations