Future-proof massively-parallel execution of multi-block applications
Lead Research Organisation:
University of Southampton
Department Name: Faculty of Engineering & the Environment
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Organisations
People |
ORCID iD |
Neil David Sandham (Principal Investigator) |
Publications
Jacobs C
(2017)
OpenSBLI: A framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures
in Journal of Computational Science
Jammy S
(2016)
Block-structured compressible Navier-Stokes solution using the OPS high-level abstraction
in International Journal of Computational Fluid Dynamics
Jammy S
(2019)
Performance evaluation of explicit finite difference algorithms with varying amounts of computational and memory intensity
in Journal of Computational Science
Lusher D
(2018)
Shock-wave/boundary-layer interactions in the automatic source-code generation framework OpenSBLI
in Computers & Fluids
Mudalige G
(2019)
Large-scale performance of a DSL-based multi-block structured-mesh application for Direct Numerical Simulation
in Journal of Parallel and Distributed Computing
Reguly I
(2016)
High Performance Computing
Reguly I
(2017)
Beyond 16GB
Reguly I
(2017)
Loop Tiling in Large-Scale Stencil Codes at Run-time with OPS
Reguly I
(2017)
Beyond 16GB: Out-of-Core Stencil Computations
Description | A new Open source code has been developed and released. OpenSBLI is a Python-based modelling framework that is capable of expanding a set of differential equations written in Einstein notation, and automatically generating C code that performs the finite difference approximation to obtain a solution. This C code is then targeted with the OPS library towards specific hardware backends, such as MPI/OpenMP for execution on CPUs, and CUDA/OpenCL for execution on GPUs. The main focus of OpenSBLI is on the solution of the compressible Navier-Stokes equations with application to shock-boundary layer interactions (SBLI). However, in principle, any set of equations that can be written in Einstein notation may be solved. |
Exploitation Route | Open source code can be applied to other application areas where finite difference solutions of ordinary and partial differential equations are desired. The OpenSBLI code is now suitable for applications in high speed aerodynamics, see for example https://eprints.soton.ac.uk/445538/ |
Sectors | Aerospace Defence and Marine |
URL | http://www.southampton.ac.uk/engineering/about/staff/nds9.page |
Description | Software developed has enabled us to assess the energy-efficiency of numerical algorithms. The open source software OpenSBLI has been released. version 2 has now been released (2019) We have also used the software for advanced undergraduate teaching (modules SESA6061 and SESA6082), enabling 100 student to date to have exposure to a research computer code. A benchmark version of the OpenSBLI code has been used during procurement of the Archer 2 national supercomputer. |
Sector | Aerospace, Defence and Marine,Energy |
Impact Types | Societal |
Description | Extending the buffet envelope: step change in data quantity and quality of analysis |
Amount | £311,065 (GBP) |
Funding ID | EP/R037167/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 09/2018 |
End | 03/2022 |
Description | Horizon 2020 ExaFLOW project |
Amount | € 326,000 (EUR) |
Funding ID | 671571 |
Organisation | European Union |
Sector | Public |
Country | European Union (EU) |
Start |
Title | OpenSBLI |
Description | Open source code released in 2021 |
Type Of Material | Improvements to research infrastructure |
Year Produced | 2021 |
Provided To Others? | Yes |
Impact | Benchmark code for ARCHER2 procurement |
URL | https://github.com/opensbli |
Title | OpenSBLI |
Description | OpenSBLI is a Python-based modelling framework that is capable of expanding a set of differential equations written in Einstein notation, and automatically generating C code that performs the finite difference approximation to obtain a solution. This C code is then targetted with the OPS library towards specific hardware backends, such as MPI/OpenMP for execution on CPUs, and CUDA/OpenCL for execution on GPUs. |
Type Of Material | Improvements to research infrastructure |
Provided To Others? | No |
Impact | Open source software released in Nov 2016 |
URL | https://opensbli.github.io |