From cTuning.org
Line 14: | Line 14: | ||
<div align="left" style="background-color:#FF7F7F"> | <div align="left" style="background-color:#FF7F7F"> | ||
* After long thinking and discussions with cTuning community, we may expect to get a new version of cTuning in Fall, 2011. Please, stay tuned through Grigori Fursin's [http://twitter.com/grigori_fursin twitter] or [[Community|cTuning mailing lists]]. | * After long thinking and discussions with cTuning community, we may expect to get a new version of cTuning in Fall, 2011. Please, stay tuned through Grigori Fursin's [http://twitter.com/grigori_fursin twitter] or [[Community|cTuning mailing lists]]. | ||
- | * 2 new reference journal publications with more scientific aspects/details on cTuning.org are now available online: [http://fursin.net/wiki/index.php5?title=Research:Dissemination#FT2010 collective optimization (ACM TACO'10)] and [http://fursin.net/wiki/index.php5?title=Research:Dissemination#FKMP2011 machine learning enabled self-tuning compiler for multi-objective optimizations (IJPP'11)] | + | * '''2 new reference journal publications''' with more scientific aspects/details on cTuning.org are now available online: [http://fursin.net/wiki/index.php5?title=Research:Dissemination#FT2010 collective optimization (ACM TACO'10)] and [http://fursin.net/wiki/index.php5?title=Research:Dissemination#FKMP2011 machine learning enabled self-tuning compiler for multi-objective optimizations (IJPP'11)] |
* 2 open calls for papers related to cTuning.org: [http://cTuning.org/workshop-smart2011 SMART 2011 (@ CGO 2011)] and ADAPT 2011 (@ PLDI 2011) | * 2 open calls for papers related to cTuning.org: [http://cTuning.org/workshop-smart2011 SMART 2011 (@ CGO 2011)] and ADAPT 2011 (@ PLDI 2011) | ||
</div> | </div> |
Revision as of 22:34, 26 January 2011
![]() |
MILEPOST GCC |
machine-learning enabled self-tuning compiler |
Web shortcut: http://cTuning.org/milepost-gcc Navigation: cTuning.org > CTools
MILEPOST GCC is now a part of the cTuning Compiler Collection (cTuning CC).
MILEPOST GCC is the first practical attept to build machine learning enabled open-source self-tuning production (and research) compiler that can adapt to any architecture using iterative feedback-directed compilation, machine learning and collective optimization. It is based on production quality GCC that supports more than 30 families of architectures and can compile real, large applications including Linux, and on Interactive Compilation Interface that provides plugin system to access internals of compilers. MILEPOST GCC attempts to correlate program features and program optimizations during empirical iterative compilation to predict good optimizations for unseen programs based on prior learning. MILEPOST and cTuning infrastructure automates code and architecture optimization to improve execution time, code size, compilation time and other characteristics at the same time. This technology is not GCC-dependent and can be used in any compiler using common Interactive Compilation Interface and compiler independent plugins. The first version of the MILEPOST GCC and MILEPOST framework has been created during the MILEPOST project. All public MILEPOST developments have been coordinated by Grigori Fursin. More information can be found in the following paper about MILEPOST GCC. ![]()
|
|