Explore projects
-
-
Updated
-
TALENT / TALENT / LASER - NoteMyProgress Plug-in
GNU General Public License v3.0 onlyUpdated -
Updated
-
Published in Euro-Par 2022:
Maël Madon, Georges da Costa, Jean-Marc Pierson. Characterization of Different User Behaviors for Demand Response in Data Centers. 28th International Conference on Parallel and Distributed Computing : Parallel Processing (Euro-Par 2022), Aug 2022, Glasgow, United Kingdom. pp.53-68, ⟨10.1007/978-3-031-12597-3_4⟩. ⟨hal-03768237⟩
Artefact : https://gitlab.irit.fr/sepia-pub/open-science/demand-response-user/-/tree/europar2022
Updated -
Exemple d'expérience reproductible
Dans cette version, on fournit en plus un Dockerfile qui permet d'automatiquement reconstruire l'environnement de départ d'exécuter dans celui-ci l'expérimentation
Updated -
Exemple de projet reproductible
Dans cette version, on ajoute une gestion de l'aléatoire et du paramétrage et le workflow est formalisé de cette façon le futur expérimentateur est assuré de pouvoir reproduire avec + d'exactitude.
Updated -
sepia-pub / Open Science / Expe replay feedback
GNU General Public License v3.0 or laterPublished in FGCS in 2024:
Maël Madon, Georges da Costa, Jean-Marc Pierson. Replay with Feedback: How does the performance of HPC system impact user submission behavior?. Future Generation Computer Systems, inPress, ⟨10.1016/j.future.2024.01.024⟩. ⟨hal-04432711⟩
Artefact: https://gitlab.irit.fr/sepia-pub/open-science/expe-replay-feedback/-/tree/fgcs-2024
Updated -
sepia-pub / Expetator
GNU General Public License v3.0 or laterA tool for running HPC benchmarks using several type of leverages (DVFS) and low-level monitoring (hardware performance counters, RAPL) mostly on Grid5000.
Documentation is available here: https://expetator.readthedocs.io/
Updated -
Published in SUSCOM 2025
Georges Da Costa, Hardware and application aware performance, power and energy models for modern HPC servers with DVFS Sustainable Computing : Informatics and Systems, 2025, 46, pp.101106. ⟨10.1016/j.suscom.2025.101106⟩
Updated -
sepia-pub / LightOM2M
OtherLightOM2M WILL BE AVAILABLE ON NOVEMBER 2022.
This projet is an opensource to deploy oneM2M architecture on very constrained devices. It implements a common service entity (CSE) at the gateway level. Typical usage could be on microcontroller like ESP8266.
This project has been partially founded by Toulouse Tech Transfert in a valorisation process and developed inside laboratories of CNRS. It is now managed mainly at IRIT.
Contact: thierry.monteil@irit.fr
Updated -
Published in Europar 2024
Danilo Carastan-Santos, Georges da Costa, Millian Poquet, Patricia Stolf, Denis Trystram. Light-weight prediction for improving energy consumption in HPC platforms. 2024. ⟨hal-04566184⟩
Updated -
Source code of arXiv:2206.05146 "Deriving the Internet public peering interconnection capacity using complex network analysis"
Updated -
This repository hosts the code for the paper "Zero-shot learning for multilingual discourse relation classification" by Eleni Metheniti, Philippe Muller, Chloé Braud, and Margarita Hernández-Casas.
Updated -
Experimental rendering extensions for Radium. Obsolete since 2021-06. Will be removed in 2022-06
Updated -
Updated
-
Updated
-