From cTuning.org
(Difference between revisions)
(New page: {{CMenu:CTools|MilepostGCC}} * 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://nikhilka...) |
Current revision (18:55, 17 March 2010) (view source) |
||
(One intermediate revision not shown.) | |||
Line 1: | Line 1: | ||
{{CMenu:CTools|MilepostGCC}} | {{CMenu:CTools|MilepostGCC}} | ||
- | * | + | == MILEPOST 1.5 GCC 4.4.0: == |
+ | |||
+ | * MILEPOST GCC / cTuning web-services test: | ||
+ | |||
+ | milepost-gcc --ct-test *.c | ||
+ | |||
+ | You can also use test script ./__test_milepost_gcc | ||
+ | |||
+ | * Using optimization cases directly from the Collective Optimization Database (referenced by unique ID) - it is useful for multi-objective optimization, to share optimization cases within the community or when publishing papers and results on program optimization: | ||
+ | |||
+ | milepost-gcc --ct-opt=11475790782770590 *.c | ||
+ | |||
+ | You can also use demo script ./__compile_using_milepost_gcc_with_fixed_optimization to understand how to configure your own system. | ||
+ | |||
+ | * Predict good optimizations (execution time, code size, compilation time) based on correlation of program features and optimizations using collective optimization knowledge (empirical iterative feedback-directed compilation performed by multiple users and shared in the Collective Optimization Database): | ||
+ | |||
+ | milepost-gcc -Oml *.c | ||
+ | |||
+ | You can also use demo script ./__compile_using_milepost_gcc_with_prediction_optimization to understand how to configure your own system. | ||
+ | |||
+ | == Real usage cases: == | ||
+ | |||
+ | * Nikhil Kapur 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]. | ||
* 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 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. | ||
+ | |||
+ | * Grigori Fursin used MILEPOST GCC to optimize several audio/video libraries for ARC for execution time and code size constraints. |
Current revision
Navigation: cTuning.org > CTools > MilepostGCC
MILEPOST 1.5 GCC 4.4.0:
- MILEPOST GCC / cTuning web-services test:
milepost-gcc --ct-test *.c
You can also use test script ./__test_milepost_gcc
- Using optimization cases directly from the Collective Optimization Database (referenced by unique ID) - it is useful for multi-objective optimization, to share optimization cases within the community or when publishing papers and results on program optimization:
milepost-gcc --ct-opt=11475790782770590 *.c
You can also use demo script ./__compile_using_milepost_gcc_with_fixed_optimization to understand how to configure your own system.
- Predict good optimizations (execution time, code size, compilation time) based on correlation of program features and optimizations using collective optimization knowledge (empirical iterative feedback-directed compilation performed by multiple users and shared in the Collective Optimization Database):
milepost-gcc -Oml *.c
You can also use demo script ./__compile_using_milepost_gcc_with_prediction_optimization to understand how to configure your own system.
Real usage cases:
- Nikhil Kapur is trying to use MILEPOST GCC to optimize Mozilla code. More info is available at 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.
- Grigori Fursin used MILEPOST GCC to optimize several audio/video libraries for ARC for execution time and code size constraints.