François Trahay

Full professor

Inria Benagil team

Research interests

• Performance analysis
• High Performance Systems
• Runtime systems for HPC
• Multithreading over hierarchical, multicore machines

Selected publications

The complete list of my publications is available here.

• PYTHIA: an oracle to guide runtime system decisions. Alexis Colin, François Trahay, Denis Conan. In IEEE Cluster 2022. [bib] [pdf]
• Using differential execution analysis to identify thread interference. Mohamed Saïd Mosli Bouksi, François Trahay, et al. In IEEE TPDS. [bib] [pdf]
• NumaMMA: Numa MeMory Analyzer. François Trahay, Manuel Selva, Lionel Morel, Kevin Marquet. In ICPP 2018. [bib] [pdf]
• EZTrace: a generic framework for performance analysis. François Trahay, François Rue, Mathieu Faverge, Yutaka Ishikawa, Raymond Namyst and Jack Dongarra. In CCGrid 2011. [bib] [pdf]
• A scalable and generic task scheduling system for communication libraries. François Trahay and Alexandre Denis. In Cluster 2009. [bib] [pdf]

Current PhD students

• Catherine Guelque, co-advised with Valentin Honoré (2023-2026). Topic: performance analysis at exascale
• Lucas Van Lanker, co-advised with Elisabeth Brunet, and Hugo Taboada (2024-2027). Topic: performance projection of GPU applications
• Jules Risse, co-advised with Amina Guermouche (2024-2027). Topic: fine-grain energy consumption measurement
• Martin Horth, co-advised with Olivier Levillain, Théo Combe, and Matthieu Touloucanon (2024-2027). Topic: fine-grain energy consumption measurement

Former PhD students

• Alexis Colin, co-advised with Denis Conan (2019-2022). Topic: performance analysis-directed feedback to runtime systems [pdf], now game engine developer at Spiders Games.
• Mohamed Said Mosli Bouksiaa, co-advised with Gaël Thomas (2014-2018). Topic: Semi-automatic performance analysis. [pdf], now software engineer at Claap.

Teaching

• Head of the Master of Computer Science at Institut Polytechnique de Paris