From cTuning.org
(Difference between revisions)
Current revision (22:05, 21 May 2010) (view source) |
|||
| Line 19: | Line 19: | ||
== Misc: == | == Misc: == | ||
| - | * Nik is trying to use MILEPOST GCC to optimize [https://bugzilla.mozilla.org/show_bug.cgi?id=502352 Mozilla] code. More info is available at [http://nikhilkapur.blogspot.com/search/label/Mozilla his blog]. | + | * Nik is trying to use cTuning CC/MILEPOST GCC to optimize [https://bugzilla.mozilla.org/show_bug.cgi?id=502352 Mozilla] code. More info is available at [http://nikhilkapur.blogspot.com/search/label/Mozilla his blog]. |
| - | * Yuriy Kashikov has been using MILEPOST GCC to optimize BerkeleyDB and reported speedups of 1.4 times in comparison with native GCC 4.4.0 (-O3) on several Intel Xeon machines without loosing much compilation time or code size. | + | * Yuriy Kashikov has been using cTuning CC/MILEPOST GCC to optimize BerkeleyDB and reported speedups of 1.4 times in comparison with native GCC 4.4.0 (-O3) on several Intel Xeon machines without loosing much compilation time or code size. |
Current revision
Navigation: cTuning.org > CTools > MilepostGCC
Contents |
References:
Publications:
- MILEPOST GCC: machine learning based research compiler (link).
- Collective Tuning Initiative: automating and accelerating development and optimization of computing systems (link).
- Collective optimization (link).
Press:
- IBM press-release about MILEPOST GCC (2009.06.30, 2008.06.30).
- InfoWorld: Rethinking code optimization for mobile and multicore
- Slashdot.org: IBM Releases Open Source Machine Learning Compiler
- Dr Dobb: Milepost GCC Now Available
- HPCWire: IBM Research Announces Intelligent Compiler
- ICT Results: Machine-learning revolutionises software development
Misc:
- Nik is trying to use cTuning CC/MILEPOST GCC to optimize Mozilla code. More info is available at his blog.
- Yuriy Kashikov has been using cTuning CC/MILEPOST GCC to optimize BerkeleyDB and reported speedups of 1.4 times in comparison with native GCC 4.4.0 (-O3) on several Intel Xeon machines without loosing much compilation time or code size.