iTLS is an EPSRC sponsored project between the Universities of Manchester and Edinburgh.

The computer industry is undergoing the "multi-core" revolution. When you buy a PC off the shelf these days, it is inevitably "dual-core" or "quad-core". This idea of more and more CPU "cores" executing in parallel is expected to continue to the hundreds and thousands. The problem of coordinating these cores is challenging and unsolved. The iTLS project applies Machine Learning technologies to address this problem.


Principal Investigators: Gavin Brown, Mikel Lujan, Ian Watson,

Research Staff: Narayanan Edakunni (previously Jeremy Singer)
PhDs: Adam Pocock, Paris Yiapanis

News: Jeremy Singer has left the project to take up a lectureship at Glasgow. Nara Edakunni will be joining the project in May.


Publications:

Garbage Collection Auto-Tuning for Java MapReduce on Multicores
Jeremy Singer, Mikel Lujan, George Kovoor, Gavin Brown
Intl Symposium on Memory Management 2011, San Jose, California.

The Economics of Garbage Collection
J. Singer, R. Jones, G. Brown and M. Lujan
Intl Symposium on Memory Management. June 2010

Toward a More Accurate Understanding of the Limits of the TLS Execution Paradigm
N.Ioannou, J.Singer, S.Khan, P.Xekalakis, P.Yiapanis, A.Pocock, G.Brown, M.Lujan, I.Watson, and M.Cintra
Intl Symposium on Workload Characterization (IISWC). Dec 2010

Online Nonstationary Boosting
Adam Pocock, Paraskevas Yiapanis, Jeremy Singer, Mikel Lujan, and Gavin Brown
Intl Workshop on Multiple Classifier Systems. Cairo, April 2010

Static Java Program Features for Intelligent Squash Prediction
Jeremy Singer, Paraskevas Yiapanis, Adam Pocock, Mikel Luja°n, Gavin Brown, Nikolas Ioannou and Marcelo Cintra
Proceedings of the 4th Workshop on Statistical and Machine Learning Approaches to Architecture and Compilation (SMART). Jan 2010

Fundamental Nano-Patterns to Characterize and Classify Java Methods
Jeremy Singer, Gavin Brown, Mikel Luj√an, Adam Pocock and Paraskevas Yiapani
Intl Workshop Language Descriptions, Tools and Applications (LDTA). March 2009

An Information Theoretic Evaluation of Software Metrics for Object Lifetime Prediction
Sebastien Marion, Gavin Brown, Richard Jones, Mikel Luja°n, Chris Ryder and Ian Watson
Workshop on Statistical and Machine learning approaches applied to ARchitectures and compilaTion. Jan 2008