From cTuning.org

(Difference between revisions)
Jump to: navigation, search
Current revision (12:39, 30 November 2010) (view source)
 
Line 1: Line 1:
-
<div style="font-style: italic; background-color: #FF7F7F">
 
-
:::::::::'''ANNOUNCEMENT:''' After the release of the [[CTools:CTuningCC|cTuning CC (MILEPOST GCC)]] and a relatively quiet summer and autumn 2010 spent mostly on thinking ;), we plan to resume our open collaborative activities in 2011 and will work on a new collaborative platform and a repository cTuning<sub>2</sub>. Currently, we are looking for additional funding to keep it running and to access various new hardware (embedded or HPC systems, GPUs, etc) to perform empirical collective learning and optimization to suggest better program optimizations or hardware designs based on multi-objective criteria (execution time/power/architecture size/code size/compilation time/etc) ([http://fursin.net/wiki/index.php5?title=Research:Dissemination#Fur2009 ref<sub>1</sub>], [http://fursin.net/wiki/index.php5?title=Research:Dissemination#FT2009 ref<sub>2</sub>], [[CDatabase|ref<sub>3</sub>]]), so if you are interested to support cTuning initiative in 2011, please don't hesitate to contact [http://fursin.net/research Dr. Grigori Fursin] (cTuning founder and R&D coordinator). More information will be available at the beginning of 2011.</div>
 
-
 
<div align="center">
<div align="center">
<font size = 5>[[Dissemination:Workshops:SMART10|SMART'10]] Workshop Program</font>
<font size = 5>[[Dissemination:Workshops:SMART10|SMART'10]] Workshop Program</font>

Current revision

SMART'10 Workshop Program

Sunday, January 24, 2010
Pisa, Italy
(co-located with HiPEAC 2010 Conference)


(Proceedings in one pdf)


[ SMART'10 Foreword ]

14:00-14:05 SMART'10 Program Chair introduction

David Whalley, Florida State University, USA
14:05-15:00 Keynote talk: Moving adaptation into individual optimizations

Prof. Keith Cooper
Rice University, USA

Over the past fifteen years, many researchers have tried to address the fundamental problem that a compiler should adapt its behavior to properties of the code presented for compilation. As a result, we have seen approaches that include derivation of scheduling heuristics, discovery of good sets of command-line flags to control compilation, genetic programming, schemes to select and order passes, and approaches that run multiple competing techniques and retain the best result.

This talk will focus on issues that arise in building compiler-based optimizations that have internal mechanisms for adaptation. Some optimizations, such as inline substitution, appear to be natural candidates for internal adaptation. Others, such as lazy code motion, do not. The talk will examine some of the issues that make internal adaptation desirable and profitable. It will discuss prior work, current work, and future opportunities.

15:00-15:30 Automatic Selection of Machine Learning Models for WCET-aware Compiler Heuristic Generation

Paul Lokuciejewski, Marco Stolpe, Katharina Morik, Peter Marwedel
TU Dortmund University, Germany


(paper pdf) (slides pdf)

15:30-15:45 Coffee Break
15:45-16:15 Application Heartbeats: A Generic Interface for Expressing Performance Goals and Progress in Self-Tuning Systems

Henry Hoffmann, Jonathan Eastep, Marco Santambrogio, Jason Miller, Anant Agarwal
MIT, USA


(paper pdf) (slides pdf)

16:15-16:45 Automated Timer Generation for Empirical Tuning

Josh Magee, Qing Yi, R. Clint Whaley
University of Texas at San Antonio, USA


(paper pdf) (slides pdf)

16:45-17:15 Static Java Program Features for Intelligent Squash Prediction

Jeremy Singer 1, Paraskevas Yiapanis 1, Adam Pocock 1, Mikel Lujan 1, Gavin Brown 1, Nikolas Ioannou 2, Marcelo Cintra 2

1 University of Manchester, UK
2 University of Edinburgh, UK
(paper pdf) (slides pdf)

17:15-17:45 Smartlocks: Self-Aware Synchronization through Lock Acquisition Scheduling

Jonathan Eastep, David Wingate, Marco Santambrogio, Anant Agarwal
MIT, USA


(paper pdf) (slides pdf)

Locations of visitors to this page