From cTuning.org
Line 1: | Line 1: | ||
{{CTitle|http://ctuning.org/wiki/images/logo_cbench.gif|Collective Benchmark|Enabling realistic benchmarking and optimization}} | {{CTitle|http://ctuning.org/wiki/images/logo_cbench.gif|Collective Benchmark|Enabling realistic benchmarking and optimization}} | ||
{{News| | {{News| | ||
+ | |||
+ | * '''2009.June.01''' - After nearly 1 year of developments we released/updated all our open-source collaborative [[CTools|R&D tools]]: | ||
+ | ** fully redesigned and documented [[CTools:ICI|Interactive Compilation Interface]] v2.0 for GCC 4.4.0 synchronized with the official plugin GCC branch - transforming compilers into plugin-enabled research toolsets | ||
+ | ** [[cTools:MilepostGCC|MILEPOST GCC 4.4.0]] pre-release version at SVN - automating program optimization and compiler optimization heuristic tuning using machine learning | ||
+ | ** [[CTools:CCC|Continuous Collective Compilation Framework v2.0]] - enabling automatic collaborative program optimization based on statistical and machine learning techniques | ||
+ | ** [[CTools:CBench|Collective Benchmark/MiDataSets v1.0]] - enabling realistic program optimization research and benchmarking using multiple open-source programs/datasets.<BR><BR>We also updated [[CDatabase|Collective Optimization Database]] with various optimization cases for Intel and AMD processors and comparison of different compilers including GCC, LLVM, Open64, Intel, etc - enabling sharing and reuse of optimization knowledge.<BR><BR>We would like to thank [[Community:People|cTuning community]] for feedback, help and support! You are welcome to join this [[Community|community effort]] to automate program optimization and compiler/architecture design. | ||
* '''2009.April.27''' - We gave a talk at the University of Illinois at Urbana-Champaign about [http://ctuning.org Collective Tuning Initiative and tools] and [http://www.milepost.eu MILEPOST project] ("Collective Optimization, run-time adaptation and machine learning"). Presentation is available [http://unidapt.org/presentations/presentation_fursin_uiuc2009.pdf here]. We would like to thank all the UIUC colleagues for a very interesting and useful feedback.<br> | * '''2009.April.27''' - We gave a talk at the University of Illinois at Urbana-Champaign about [http://ctuning.org Collective Tuning Initiative and tools] and [http://www.milepost.eu MILEPOST project] ("Collective Optimization, run-time adaptation and machine learning"). Presentation is available [http://unidapt.org/presentations/presentation_fursin_uiuc2009.pdf here]. We would like to thank all the UIUC colleagues for a very interesting and useful feedback.<br> |
Revision as of 22:51, 1 June 2009
![]() |
Collective Benchmark |
Enabling realistic benchmarking and optimization |
News |
|
Navigation: cTuning.org > CTools
Collective Benchmark (cBench) is a collection of open-source sequential and parallel programs with multiple datasets assembled by the community to enable realistic benchmarking and research on program and architecture optimization. The source code of individual programs is simplified to ease portability. All the benchmarks now include scripts to be used with Continuous Collective Compilation Framework to perform automatic optimizations (iterative compilation) using GCC, LLVM, GCC4CIL, Open64, PathScale, Intel and other compilers and a wide range of architectures. This collection of programs can later be used to create specialized benchmarks.
cBench is an evolving project driven by the community demands - you are welcome to join the project, extend or add benchmarks and datasets and provide performance analysis, leave feedback and add your optimization data to the Collective Optimization Database to help the community optimize their programs. You can also communicate with cTuning community through our mailing lists.
- Projects to extend cBench (development plan and suggestions) - > 5 projects
- Current development:

cBench is an open collaborative community-driven project. You are welcome to join us and participate in discussions, developments or provide feedback and suggestions to extend cBench or add new benchmarks/datasets.