From cTuning.org

(Difference between revisions)
Jump to: navigation, search
Current revision (15:51, 12 September 2015) (view source)
 
(97 intermediate revisions not shown.)
Line 1: Line 1:
 +
'''''NEWS: Since 2015, we moved all related developments to our new [http://github.com/ctuning/ck/wiki Collective Knowledge Framework]! Demo of a new live repository is available [http://cknowledge.org/repo here].'''''
 +
 +
 +
 +
 +
 +
 +
 +
 +
{{CTitle|http://ctuning.org/wiki/images/milepost_image.jpg|MILEPOST GCC|machine-learning enabled self-tuning compiler}}
 +
 +
{{CShortCut|milepost-gcc}}
 +
{{CMenu:CTools|}}
{{CMenu:CTools|}}
-
<div align="center" style="margin: 8px; float: right;">
+
{{NEWS}}
-
http://ctuning.org/wiki/images/gcc-ici-structure.gif
+
-
</div>
+
-
* '''[[CTools:ICI:Downloads|Download MILEPOST GCC 4.4.0]]'''
+
<div style="color:red; font-weight:bold; "><H2>
-
* '''[[CTools:ICI|Further developments]]
+
* MILEPOST GCC is now a part of the [[CTools:CTuningCC|cTuning Compiler Collection (cTuning CC)]].
 +
* Reference publication about MILEPOST GCC in IJPP'11 is now available [http://fursin.net/wiki/index.php5?title=Research:Dissemination#FKMP2011 here].
 +
</H2></div>
-
MILEPOST GCC is the first machine learning enabled open-source self-tuning research compiler that can adapt to any architecture using iterative feedback-directed compilation, machine learning and collective optimization. It combines the strength of the production quality [http://gcc.gnu.org GCC] that supports more than 30 families of architectures and can compile real, large applications including Linux, and the flexibility of the [[CTools:ICI|Interactive Compilation Interface]] that transforms GCC into the research compiler. It is currently based on predictive modeling using program and machine-specific features, execution time, hardware counters and offline training. MILEPOST GCC includes IBM [[CTools:MilepostGCC:StaticFeatures|static program feature extractor]].
 
-
Original development of the MILEPOST GCC and MILEPOST Framework has been coordinated by [http://fursin.net/research Grigori Fursin] (2006-2009) and the [http://unidapt.org UNIDAPT group] with the help of Cupertino Miranda and Zbigniew Chamski (extending Interactive Compilation Interface), Edwin Bonilla (extending machine learning techniques), Mircea Namolaru (integrating static program feature extractor) and John Thomson (performance evaluation). In June, 2009, MILEPOST GCC [[CTools:ICI:Downloads|has been released]] and all further developments have been integrated with the [http://ctuning.org/ctools cTuning tools]: [http://ctuning.org/cdatabase Collective Optimization Database], [http://ctuning.org/cpredict cTuning optimization prediction web-services], [http://ctuning.org/ici Interactive Compilation Interface for GCC], [http://ctuning.org/ccc Continuous Collective Compilation Framework] to enable collaborative community-driven developments after the end of the [http://www.milepost.eu MILEPOST project] (August 2009).  
+
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 [http://gcc.gnu.org GCC] that supports more than 30 families of architectures and can compile real, large applications including Linux, and on [[CTools:ICI|Interactive Compilation Interface]] that provides plugin system to access internals of compilers. MILEPOST GCC attempts to correlate [[CTools:MilepostGCC:StaticFeatures|program features]] and [[CDatabase|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 [[CTools:ICI|Interactive Compilation Interface]] and compiler independent plugins. The first version of the MILEPOST GCC and [[CTools:MilepostFramework|MILEPOST framework]] has been created during the [http://cTuning.org/project-milepost MILEPOST project]. All public MILEPOST developments have been coordinated by [http://fursin.net/research Grigori Fursin]. More information can be found in the following paper about [http://unidapt.org/index.php/Dissemination#FMTP2008 MILEPOST GCC].
-
You are warmly welcome to join [http://ctuning.org/wiki/index.php/Community cTuning community] and follow/participate in developments and discussions using cTuning Wiki-based portal and 2 mailing lists: [http://groups.google.com/group/ctuning-discussions high volume development list] and [http://groups.google.com/group/ctuning-announce low volume announcement list].
+
<div align="center">http://ctuning.org/wiki/images/img-milepost-gcc-structure.gif</div>
-
More details about our current and future developments can be found in the following publications:
+
* '''Background:'''
-
* [http://unidapt.org/index.php/Dissemination#FT2009 "Collective Optimization" ]
+
**[[CTools:MilepostGCC:Motivation|Motivation and history]]  
-
* [http://unidapt.org/index.php/Dissemination#FMTP2008 "MILEPOST GCC: machine learning based research compiler"]
+
**[[CTools:MilepostGCC:Usage|Usage scenarios / stories]]
-
* [http://unidapt.org/index.php/Dissemination#Fur2009 "Collective Tuning Initiative: automating and accelerating development and optimization of computing systems"]
+
**[[CTools:MilepostGCC:Resources|Resources (links, publications, etc)]]
-
Tuning hardwired compiler optimizations for rapidly evolving hardware makes porting an optimizing compiler for each new platform extremely challenging. Our radical approach is to develop a modular, extensible, self-tuning intelligent compiler that automatically learns the best optimization heuristics based on combining feedback-directed iterative compilation and machine learning. MILEPOST GCC is a machine learning based compiler that automatically adjusts its optimization heuristics to improve execution time, code size, or compilation time of specific programs on different architectures. Currently, we use several iterative search strategies within CCC framework to find combinations of good optimization flags to substitute GCC default optimization levels for a particular architecture (such as -O0,-O1,-O2,-O3,-Os which we will not need in the future adaptive compilers) or tune optimization passes on a function-level for a particular program. Our preliminary experimental results show that it is possible to considerably reduce execution time of various benchmarks (MiBench, MediaBench, EEMBC, SPEC) on a range of platforms (x86, x8664, IA64, ARC, Longson/Godson, etc) entirely automatically. MILEPOST GCC can be used interactively in research on adaptive computing through the Interactive Compilation Interface (we currently support optimization pass selection and reordering, plugins and event mechanism to invoke any passes on demand (such as program feature extraction pass) or tune cost-models of specific transformations within passes).
+
* [[CTools:MilepostGCC:Downloads|'''Downloads''']]
 +
 
 +
* [[CTools:MilepostGCC:Documentation|'''Documentation''']]
 +
 
 +
* [[CTools:MilepostGCC:Feedback|'''User suggestions and feedback''']]
 +
 
 +
* [[CTools:MilepostGCC:Dev:Bugs|'''Bug reports''']]
 +
 
 +
* [[CTools:MilepostGCC:FAQs|'''FAQs''']] - Does MILEPOST GCC solve all optimization problems? How similar is it ACOVEA tool? etc...
 +
 
 +
* '''Related:'''
 +
** [http://ctuning.org/wiki/index.php/Special:CPredict Online predictor of optimizations based on program features].
 +
** [[CDatabase|Collective optimization repository]] to continuously collect profitable optimization cases from the community that improve program execution time, code size, compilation time, etc...
 +
** [[CTools:CCC|CCC framework]] - Continuous Collective Compilation Framework to automate search of profitable optimization cases to improve program execution time, code size, compilation time, etc. It is used to train MILEPOST GCC and has some similarities with the useful [http://www.coyotegulch.com/products/acovea ACOVEA tool] but also allows automatic sharing of optimization knowledge with the community in the [[CDatabase|Collective Optimization Database]] and uses plugins to implement various search techniques besides genetic algorithms.
 +
** [http://cTuning.org/project-milepost Official info for the MILEPOST project (2006-2009)].
 +
 
 +
----
 +
 
 +
<div align="center">
 +
{| cellspacing="0" cellpadding="3" border="0" width="100%" style="color: black;"
 +
|-
 +
| align="center" style="background: rgb(0, 100, 159) none repeat scroll 0% 0%; -moz-background-clip: -moz-initial; -moz-background-origin: -moz-initial; -moz-background-inline-policy: -moz-initial; color: white;" | '''MILEPOST GCC friends:'''
 +
|-
 +
| align="center" valign="top" | {{CTools:MilepostGCC:Logo_Friends}}
 +
|}
 +
</div>

Current revision

NEWS: Since 2015, we moved all related developments to our new Collective Knowledge Framework! Demo of a new live repository is available here.





milepost_image.jpg

MILEPOST GCC

machine-learning enabled self-tuning compiler 
Web shortcut: http://cTuning.org/milepost-gcc

Navigation: cTuning.org > CTools

NOTES:

cTuning Google discussions list


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.

img-milepost-gcc-structure.gif
  • FAQs - Does MILEPOST GCC solve all optimization problems? How similar is it ACOVEA tool? etc...
MILEPOST GCC friends:
logo_unidapt1.gif logo_inria.gif logo_uvsq1.jpg logo_embecosm.gif logo_ue.gif logo_ibm.jpg logo_arc.gif logo_milepost.jpglogo_ict.gif logo_hipeac.jpg
Retrieved from "https://ctuning.org/wiki/index.php/CTools:MilepostGCC"
Locations of visitors to this page