From cTuning.org

Jump to: navigation, search
cTuning.org > CDatabase 

If you are interested in the current projects, would like to add new project or would like to help with the implementations, you are welcome to participate in the discussions below. You are also encouraged to send a summary email to the cTuning Discussions Mailing List (mail, web view/register) to keep cTuning community informed about your feedback. You can also contact cTuning steering committee if you have general questions. Finally, you can also select a Wiki option to watch the modifications of this page.

(simply self-register at this website to join our community and edit open Wiki pages)

Contents

Add confidence for optimization cases

Description: Provide statistical analysis plugin to calculate confidence for optimization cases. Besides helping end-users, it can be useful for academic purposes to be able to compare optimization results (speedups) from different papers ...

Who is interested?: Sid Touati, Grigori Fursin

Who may have time to help?:, <please, add yourself>

How to proceed?:

Automate compiler/architecture testing

Description: Develop plugins for CCC and cDatabase to test-stress compiler using iterative compilation and find bugs automatically (illegal combinations of compiler optimizations, dependency between optimizations, etc).

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?:, <please, add yourself>

How to proceed?:

Add whole system (Linux) optimization support

Description: .

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?:, <please, add yourself>

How to proceed?:

Combine database with architectural/system simulators

Description: Develop common representation for architectural configurations to enable hardware/software co-optimization (partially on-going in the MILEPOST project)

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?:, <please, add yourself>

How to proceed?:

Representation of program fine-grain optimizations

Description: Develop (an XML) representation of the fine-grain optimizations using CTools:ICI - match optimization info with the program structure and keep track of program changes/optimizations.

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?:, <please, add yourself>

How to proceed?:

Connection with CCC Framework to collect optimization cases transparently

Description: We want to extend our prototype described in FT2010,FT2009 within GCC CTools:ICI and CCC Framework to automate compiler and architecture design and optimization based on statistical analysis.

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?:, <please, add yourself>

How to proceed?:

Plugins to predict program optimizations based on statistical and machine learning

Description: On-going, based on MILEPOST technology FMTP2008.

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: Grigori Fursin, <please, add yourself>

How to proceed?:

Plugins to predict program parallelization based on statistical and machine learning

Description: Extend MILEPOST technology to suggest program parallelization - currently in the brainstorming stage ...

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?:

Add academic plugins

Description: Add plugins to draw graphs, build tables, prepare reports, etc ...

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?:


Extend predictive scheduling for heterogeneous multi-core systems

Description: Extend predictive scheduling for heterogeneous multi-core systems based on statistical analysis described in JGVP2009

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?:


Add plugin to list good optimization cases for a given compiler on a given architecture across all programs

Description:

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?: on-going but help will be appreciated


Add plugin to suggest best default optimization heuristic for performance/code size/compilation time instead of -O3,-O2,-Os, etc

Description:

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?: on-going but help will be appreciated


Add plugin to compare different compilers and their optimizations

Description:

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?: on-going but help will be appreciated



Add heterogeneous multi-core info to the database (CPU/GPU or CELL-like architectures)

Description:

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?:



Add dataset features

Description: Extend LCWP2009

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?: brainstorming stage



Pruning large amount of information

Description: Pruning data to leave only important information

Who is interested?: Grigori Fursin, <please, add yourself>

Who may have time to help?: <please, add yourself>

How to proceed?: brainstorming stage

Locations of visitors to this page

Tweet