Difference between revisions of "GPGPU"
From OpenFOAMWiki
LP FluiDyna (Talk | contribs) m (→Closed Source) |
(Removed the TurboCFD thing for Amazon and added ROCm's port of PARALUTION) |
||
(6 intermediate revisions by 4 users not shown) | |||
Line 16: | Line 16: | ||
* [http://www.paralution.com PARALUTION] | * [http://www.paralution.com PARALUTION] | ||
− | ** {{versionInfo}} | + | ** {{versionInfo}}{{version2.3}} |
** Precision: unknown | ** Precision: unknown | ||
** Features: [http://www.paralution.com/documentation/ Documentation] | ** Features: [http://www.paralution.com/documentation/ Documentation] | ||
− | ** | + | ** Forum: [http://www.paralution.com/forums/ Public Forums at Paralution] |
+ | ** It's designed to work with CUDA. | ||
+ | |||
+ | * [https://github.com/ROCmSoftwarePlatform/rocALUTION rocALUTION] and [https://github.com/ROCmSoftwarePlatform/rocSPARSE rocSPARSE] | ||
+ | ** These two are essentially ports of PARALUTION for AMD's ROCm solutions. More details are [https://github.com/Atizar/RapidCFD-dev/issues/46#issuecomment-425268846 provided here]. | ||
+ | ** There is no clear indication of how to use it with OpenFOAM, but it should be possible to use PARALUTION's plugin mechanism. | ||
* [http://code.google.com/p/cufflink-library/ cufflink-library] | * [http://code.google.com/p/cufflink-library/ cufflink-library] | ||
− | ** {{versionInfo}}{{version1.6-ext}}{{version3.0-ext}} | + | ** {{versionInfo}}{{version1.6-ext}}{{version3.0-ext}}{{version3.1-ext}}{{version3.2-ext}} |
− | ** | + | ** Was fully integrated into {{version3.0-ext}} and is supported since then. |
− | + | ** [https://github.com/chegdan/cufflink-library Repository at Github] | |
− | * [ | + | |
− | + | ||
− | + | ||
− | + | ||
+ | * [https://sim-flow.com/rapid-cfd-gpu/ RapidCFD] | ||
+ | ** {{versionInfo}}{{version2.3.1}} | ||
+ | ** Precision: Double-precision | ||
<br> | <br> | ||
+ | |||
== Closed Source == | == Closed Source == | ||
The ones on this list are mostly composed of source code that is not available to their client. Usually this means that the binaries that work with the GPU act as a server (data transacted over files or similar) and are therefore not directly linked to OpenFOAM. | The ones on this list are mostly composed of source code that is not available to their client. Usually this means that the binaries that work with the GPU act as a server (data transacted over files or similar) and are therefore not directly linked to OpenFOAM. | ||
− | * [http:// | + | * [http://vratis.com/what-is-speedit/ SpeedIT Extreme] by [http://vratis.com Vratis] |
** {{versionInfo}}{{version1.7}}{{version2.0}}{{version2.1}}{{version2.2}} | ** {{versionInfo}}{{version1.7}}{{version2.0}}{{version2.1}}{{version2.2}} | ||
** Precision: Single-Precision and Double-Precision | ** Precision: Single-Precision and Double-Precision | ||
* [http://www.fluidyna.com/content/culises Culises] by [http://www.fluidyna.com FluiDyna] | * [http://www.fluidyna.com/content/culises Culises] by [http://www.fluidyna.com FluiDyna] | ||
− | ** {{versionInfo | + | ** {{versionInfo}}{{version2.2}}{{version2.3}} |
** Precision: Single-Precision and Double-Precision | ** Precision: Single-Precision and Double-Precision | ||
** Announcements: [http://www.cfd-online.com/Forums/openfoam-news-announcements-other/129740-fluidyna-releases-culises-1-1-gpu-based-acceleration-openfoam.html FluiDyna releases Culises 1.1 for GPU-based acceleration of OpenFOAM] | ** Announcements: [http://www.cfd-online.com/Forums/openfoam-news-announcements-other/129740-fluidyna-releases-culises-1-1-gpu-based-acceleration-openfoam.html FluiDyna releases Culises 1.1 for GPU-based acceleration of OpenFOAM] | ||
+ | ** '''Note''': There is no entry page (18:26, 17 June 2018 (CEST)) to the public, therefore it's possible that this has been discontinued. | ||
[[Category:OpenFOAM on GPGPU]] | [[Category:OpenFOAM on GPGPU]] |
Latest revision as of 17:33, 3 August 2019
This page aims to compile a list of solutions on using General Purpose Graphical Processing Units for OpenFOAM (GPGPU at Wikipedia).
1 Open Source
This list includes those that have commercial support, but all have the source code licensed under an OSI approved license.
- Symscape's GPU Linear Solver Library for OpenFOAM
- Valid versions:
- Precision: Single-Precision only
- Performance reports: CFD Performance Comparison Between GPU and CPU
- Versions:
- PARALUTION
- Valid versions:
- Precision: unknown
- Features: Documentation
- Forum: Public Forums at Paralution
- It's designed to work with CUDA.
- rocALUTION and rocSPARSE
- These two are essentially ports of PARALUTION for AMD's ROCm solutions. More details are provided here.
- There is no clear indication of how to use it with OpenFOAM, but it should be possible to use PARALUTION's plugin mechanism.
- cufflink-library
- Valid versions:
- Was fully integrated into and is supported since then.
- Repository at Github
2 Closed Source
The ones on this list are mostly composed of source code that is not available to their client. Usually this means that the binaries that work with the GPU act as a server (data transacted over files or similar) and are therefore not directly linked to OpenFOAM.
- Culises by FluiDyna
- Valid versions:
- Precision: Single-Precision and Double-Precision
- Announcements: FluiDyna releases Culises 1.1 for GPU-based acceleration of OpenFOAM
- Note: There is no entry page (18:26, 17 June 2018 (CEST)) to the public, therefore it's possible that this has been discontinued.