Grid5000:Home: Difference between revisions

Revision as of 22:48, 22 January 2015

Grid'5000

Grid'5000 is a large-scale and versatile testbed for experiment-driven research in all areas of computer science, with a focus on parallel and distributed computing including Cloud, HPC and Big Data.

Key features:

provides access to a large amount of resources: 1000 nodes, 8000 cores, grouped in homogeneous clusters, and featuring various technologies: 10G Ethernet, Infiniband, GPUs, Xeon PHI
highly reconfigurable and controllable: researchers can experiment with a fully customized software stack thanks to bare-metal deployment features, and can isolate their experiment at the networking layer
advanced monitoring and measurement features for traces collection of networking and power consumption, providing a deep understanding of experiments
designed to support Open Science and reproducible research, with full traceability of infrastructure and software changes on the testbed
a vibrant community of 500+ users supported by a strong technical team

Read more about our teams, our publications, and acceptable usage on the testbed. Then get an account, and learn to use the testbed with our Getting Started tutorial and the rest of our Users portal.

Grid'5000 is supported by a scientific interest group (GIS) hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations. Inria has been supporting Grid'5000 through ADT ALADDIN-G5K (2007-2013), ADT LAPLACE (2014-2016), and IPL HEMERA (2010-2014).

Latest publications from Grid'5000 users

Five random publications that benefited from Grid'5000 (at least 2925 overall):

François Lemaire, Louis Roussel. Parameter Estimation using Integral Equations. Maple Transactions, 2024, Proceedings of the Maple Conference 2023, 4 (1), 10.5206/mt.v4i1.17126. hal-04560846v2 view on HAL pdf
Léo Valque. 3D Snap rounding. Computer Science cs. Université de Lorraine, 2024. English. NNT : 2024LORR0337. tel-05016163 view on HAL pdf
Alexandre Sabbadin, Abdel Kader Chabi Sika Boni, Hassan Hassan, Khalil Drira. Optimizing network slice placement using Deep Reinforcement Learning (DRL) on a real platform operated by Open Source MANO (OSM). Tunisian-Algerian Conference on Applied Computing (TACC 2023), Nov 2023, Sousse, Tunisia. hal-04265140 view on HAL pdf
Georges da Costa, Atom Deutsch-Filippi, Igor Fontana de Nardin, Jean-Marc Nicod, Veronika Rehn-Sonigo, et al.. Cooperative vs. non-cooperative marketplace for computing jobs to be run on geo-distributed data centers only supplied by renewable energies. Cluster Computing, 2025, 28 (10), pp.637. 10.1007/s10586-025-05300-5. hal-05239473 view on HAL pdf
Cherif Latreche, Nikos Parlavantzas, Hector A Duran-Limon. FoRLess: A Deep Reinforcement Learning-based approach for FaaS Placement in Fog. UCC 2024 - 17th IEEE/ACM International Conference on Utility and Cloud Computing, Dec 2024, Sharjah, United Arab Emirates. pp.1-9. hal-04791252 view on HAL pdf

Current status (at 2025-11-05 07:34): 3 current events, 6 planned (details)

Latest news

Grid'5000 tutorial days in Lille

We are happy to let you known that tutorials around Grid'5000 will be organized in Lille on November 20th, 2014, with a few seats available for people outside Lille. All information on the dedicated web page.

Grid'5000 spring school now finished

The Grid'5000 spring school took place between June 16th, 2014 and June 19th, 2014 in Lyon. Three awards were given for presentation or challenge entries (the challenge entries ended as a tie):

Best presentation award to Miguel Liroz Gistau, Reza Akbarinia and Patrick Valduriez

Best challenge entry to Tomasz Buchert, Emmanuel Jeanvoine and Lucas Nussbaum

Best challenge entry to Jonathan Pastor and Laurent Pouilloux

Grid'5000 sites

Current funding

As from June 2008, INRIA is the main contributor to Grid'5000 funding.

INRIA

CNRS

Universities

University Joseph Fourier, Grenoble
University of Rennes 1, Rennes
Institut National Polytechnique de Toulouse / INSA / FERIA / Université Paul Sabatier, Toulouse
University Bordeaux 1, Bordeaux
University Lille 1, Lille
Ecole Normale Supérieure, Lyon
Université de Reims Champagne-Ardenne, Reims

Regional councils

Aquitaine
Bretagne
Champagne-Ardenne
Provence Alpes Côte d'Azur
Nord Pas de Calais
Lorraine

@@ Line 10: / Line 10: @@
 * provides '''access to a large amount of resources''': 1000 nodes, 8000 cores, grouped in homogeneous clusters, and featuring various technologies: 10G Ethernet, Infiniband, GPUs, Xeon PHI
 * '''highly reconfigurable and controllable''': researchers can experiment with a fully customized software stack thanks to bare-metal deployment features, and can isolate their experiment at the networking layer
-* '''advanced monitoring and measurement features for networking and power consumption''', to provide a deep understanding of experiments
+* '''advanced monitoring and measurement features for traces collection of networking and power consumption''', providing a deep understanding of experiments
 * '''designed to support Open Science and reproducible research''', with full traceability of infrastructure and software changes on the testbed
 * '''a vibrant community''' of 500+ users supported by a strong technical team