Skip to content
Snippets Groups Projects
user avatar
Mark OLESEN authored
Updated I1, I2, I6, GC2 and associated microbenchmarks

See merge request committees/hpc!11
19a7f20e

OpenFOAM HPC Benchmark Suite

The repository is intended to be a shared repository with relevant data-sets and information created in order to:

  • Provide user guides and initial scripts to set-up and run different data-sets on different HPC architectures.
  • Provide the community a homogeneous term of reference to compare different hardware architectures, software environments, configurations, etc.
  • Define a common set of metrics/KPI (Key Performance Indicators) to measure performances.
Structure of the Suite / Adding new benchmarks
  • The file structure of the repository is aligned to the file structure of OpenFOAM tutorials (specifying type of the flow, particular solver, turbulence model etc.).
  • The table structure within this overview is mainly organised according to the outline defined within the exaFOAM project (see the corresponding description).
  • New benchmarks may be put in any of the provided (or newly defined) categories suitable for the case.
  • Each benchmark case should provide a README.md file with a description and a thumbnail image to be included within this overview. These files should be located in the root directory of the case.
  • The thumbnail image has to be 50 pixels high, the width is not constrained.
exaFOAM Project

Motivation

Computational Fluid Dynamics performance on HPC is notably worse than idealised algorithms, due to inherent bandwidth needs, three-dimensional and time-date handling with non-sparse matrix dependencies, spatial domain decomposition requirements, I/O challenges. Independent software vendors (ISVs) have rightly concentrated their efforts on different customer demands such as complex physics modelling (turbulence, multi-phase, combustion/reactions, particulates, heat transfer). However, we see increasingly now that there is a commercial need to improve performance of industrial software and codes. There is an increasingly stated need to redress the balance between performance and functionality, perhaps even to re-learn the lessons of parallelism and vectorisation explored during the 1980s, due to the approaching of the hybrid pre-exascale era in HPC.

The ambitious exaFOAM project (2021-2024) aimed to overcome these limitations through the development and validation of a range of algorithmic improvements. Improvements across the entire CFD process chain (pre-processing, simulation, I/O, post- processing) were developed.

Benchmarks

The developments of the exaFOAM project are showcased by

  • Grand Challenges (GC) that are designed to push available HPC systems to their limits and showcase the performance gains achieved over the duration of the project,
  • Industrial Applications (B) that are primarily driven by the expectations of the project's industrial observer partners,
  • Microbenchmarks (MB) that are derived from the Grand Challenges and Industrial and can be used for the continuous assessment of the software components during development.

The cases related to each other are identified via a separate column in the tables below. For some of the benchmarks, grid and restart files are available in the DaRUS data repository of the University of Stuttgart.

Key Performance Indicators

The KPIs defined during the project always represent the ratio of the KPI before and after (KPI_before / KPI_after) and are thus dimensionless. Common metrics are:

  • TTS = time-to-solution
  • CTS = cost-to-solution
  • PTS = power-to-solution
  • PMC = peak memory consumption
  • SDU = scratch disc-space used

Non-quantifiable KPIs:

  • ET = enabling technology: something that was impossible
  • CBF = critical bug fix: a fix that is required to run the case
  • EA = extending applicability: something that worked but was not usable for e.g. larger cases, HPC or depending on specific setups

Grand Challenges

                     Case Study Related Cases Description Links
tn GC1 – High-lift Common Research Model MB9 rhoPimpleFoam – 3D compressible flow, WMLES turbulence modeling Case
tn GC2 – DLR-CJH Combustor MB11 XiFoam – turbulent combustion, LES turbulence modeling Case RestartFiles

Industrial Applications

                     Case Study Related Cases Description Links
tn B1 – FLOX® Gas Turbine (DLR-CJH) MB3 MB4 reactingFoam – turbulent combustion with detailed chemistry and LES turbulence modeling Case
tn B2 – TME Car MB6 adjointOptimisationFoam – unsteady adjoint optimization, external flow, DDES turbulence modeling Case RestartFiles
tn B4 – Complex Profile Extrusion MB7 MB19 viscoelasticFluidFoam (customized) – 3D laminar, viscoelastic flow Case RestartFiles
tn B5 – DrivAer-rot MB8 pimpleFoam – incompressible, external flow with rotating wheels using ACMI, DDES turbulence modeling Case
tn B6 – Offshore Wind Park MB12 pimpleFoam – incompressible flow, wind turbines using actuator line model, LES turbulence modeling with synthetic turbulence inlet condition turbulentDigitalFilterInlet Case RestartFiles
tn B7 – Aeroacoustics DrivAer derivative MB16 MB17 rhoPimpleFoam – compressible external flow, acoustic impact on the driver’s side-class, SA-IDDES Case RestartFiles
tn B8 – Modified “Steckler” fire fireFoam – turbulent combustion with RANS or LES turbulence modeling Case
tn B9 – DrivAer ExtAero Derivative pimpleFoam – incompressible external flow, MRF for wheel rotation, SA-DDES Case RestartFiles

Microbenchmarks

                     Case Study Related Cases Description Links
tn MB1 – Cavity 3D icoFoam – incompressible laminar flow Case
none MB2 – Compressible starting square jet rhoPimpleFoam – compressible flow, LES turbulence modeling Case
tn MB3 – Laminar Diffusion Counter-Flow Flame B1 reactingFoam – laminar combustion with detailed chemistry Case
tn MB4 – DLR-JHC burner B1 reactingFoam – turbulent combustion with detailed chemistry and LES turbulence modeling Case
tn MB5 – ERCOFTAC Conical diffuser simpleFoam – incompressible flow, RANS turbulence modeling Case
tn MB6 – Two cylinders in line B2 adjointOptimisationFoam – unsteady adjoint optimization, 2D laminar flow Case
tn MB7 – Viscoelastic Lid-driven Cavity B4 viscoelasticFluidFoam – 2D laminar, viscoelastic flow Case RestartFiles
tn MB8 – Rotating Wheel B5 pimpleFoam – incompressible, external flow with rotating wheels using ACMI, DDES turbulence modeling Case
tn MB9 – High-lift airfoil GC1 rhoPimpleFoam – 2D compressible flow, DDES turbulence modeling Case
tn MB10 – ERCOFTAC Conical diffuser LES pimpleFoam – incompressible flow, LES turbulence modeling Case RestartFiles
tn MB11 – Pitz&Daily Combustor GC2 XiFoam – turbulent combustion, LES turbulence modeling Case RestartFiles
tn MB12 – Model Wind Farm B6 pimpleFoam – incompressible flow, wind turbines using actuator disc model, LES turbulence modeling Case
tn MB13 – Marine Propeller rhoPimpleFoam – compressible flow, LES turbulence modelling Case
tn MB14 – Hydroacoustic Shedding Cylinder rhoPimpleFoam – 2D compressible flow, LES turbulence modelling Case
tn MB15 – 1D Hydroacoustic Wave Train rhoPimpleFoam – 1D compressible laminar flow Case
tn MB16 – Simplified HMC Aeroacoustic Vehicle B7 rhoPimpleFoam – compressible flow, LES turbulence modelling Case RestartFiles
tn MB17 – 1D Aeroacoustic Wave Train B7 rhoPimpleFoam – 1D compressible laminar flow Case
tn MB18 – Gas / Spray Penetration sprayFoam – compressible multiphase flow with Lagrangian spray Case
tn MB19 – Profile Extrusion B4 viscoelasticFluidFoam (customized) – 3D laminar, viscoelastic flow Case RestartFiles

Other Benchmarks

                     Case Study Description Links
tn Cavity 3D (PRACE White paper) icoFoam – incompressible laminar flow Case
tn Motorbike simpleFoam – incompressible flow, RANS turbulence modeling Case