Grid5000:Home

Grid'5000 is a precursor infrastructure of SLICES-RI, Scientific Large Scale Infrastructure for Computing/Communication Experimental Studies.
Content on this website is partly outdated. Technical information remains relevant.

Grid'5000

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

Key features:

provides access to a large amount of resources: 15000 cores, 800 compute-nodes grouped in homogeneous clusters, and featuring various technologies: PMEM, GPU, SSD, NVMe, 10G and 25G Ethernet, Infiniband, Omni-Path
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 solid technical team

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

Published documents and presentations:

Presentation of Grid'5000 (April 2019)
Report from the Grid'5000 Science Advisory Board (2018)

Older documents:

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).

Current status (at 2025-10-13 20:45): 3 current events, 2 planned (details)

Random pick of publications

Five random publications that benefited from Grid'5000 (at least 2924 overall):

Guillaume Helbecque, Ezhilmathi Krishnasamy, Nouredine Melab, Pascal Bouvry. GPU-Accelerated Tree-Search in Chapel versus CUDA and HIP. 14th IEEE Workshop Parallel / Distributed Combinatorics and Optimization (PDCO 2024), May 2024, San Francisco, United States. 10.1109/IPDPSW63119.2024.00156. hal-04551856 view on HAL pdf
Adrien Berthelot, Eddy Caron, Mathilde Jay, Laurent Lefèvre. Estimating the environmental impact of Generative-AI services using an LCA-based methodology. CIRP LCE 2024 - 31st Conference on Life Cycle Engineering, Jun 2024, Turin, Italy. pp.1-10. hal-04346102v2 view on HAL pdf
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. hal-04983485 view on HAL pdf
Mai Huong Do, Millian Poquet, Georges da Costa. FedE-ator : A framework for energy consumption analysis of federated learning in distributed systems. Compas’2025 : Parallélisme / Architecture/ Système, Jul 2025, Bordeaux, France. hal-05181877 view on HAL pdf
Albert d'Aviau de Piolant, Hayfa Tayeb, Bérenger Bramas, Mathieu Faverge, Abdou Guermouche, et al.. Improving energy efficiency of HPC applications using unbalanced GPU power capping. 2024. hal-04883872v2 view on HAL pdf

Latest news

Tutorials of the SLICES-FR school 2025

The tutorial of the first SLICES-FR School, which was held from July 7th to 11th in Lyon are available on the following pages:

All tutorials

Grid'5000 tutorials

-- Grid'5000 Team 15:19, 1 October 2025 (CEST)

End of support for Debian10 environments

Support for the debian10/buster kadeploy environments is stopped due to the end of upstream support and compatibility issues with recent hardware.

The last version of the debian10 environments (version 2025082716) will remain available on /grid5000. Older versions can still be accessed in the archive directory (see /grid5000/README.unmaintained-envs for more information).

-- Grid'5000 Team 09:21, 1 October 2025 (CEST)

Cluster "chuc" is now in the default queue in Lille

We are pleased to announce that the Chuc[1] cluster of Lille is now available in the default queue.

Chuc is a cluster composed of 8 nodes Apollo 6500 Gen10 Plus.

Each node features:

1x CPU AMD EPYC 7513 (Zen 3), x86_64, 32 cores/CPU

4x GPU Nvidia A100-SXM4-40GB (40 GiB)

512 GiB RAM

4x 1.92 TB SSD SAS HPE

Due to a wattmeter hardware error, the cluster's energy consumption cannot be monitored via wattmeters yet.

You will be informed when the physical energy monitoring is available on this cluster.

This cluster was funded by the CornelIA CPER project.

[1] https://www.grid5000.fr/w/Lille:Hardware#chuc

Best regards,

Grid'5000 Technical Team

-- Grid'5000 Team 09:51, 15 September 2025 (CEST)

Cluster "larochette" is now in the default queue in Luxembourg

We are pleased to announce that the larochette[1] cluster of Luxembourg is now available in the default queue.

Larochette is a cluster composed of 7 nodes, each with 4 MI210 AMD GPUs.

Each node features:

2x CPU Intel Xeon Platinum 8568Y+ (48 cores/CPU, 2 threads/cores)

4x AMD Instinct MI210 (64 GiB each)

512 GiB RAM

1x 3.2TB NVME disk

This cluster was funded by the University of Luxembourg.

[1] https://www.grid5000.fr/w/Luxembourg:Hardware#larochette

-- Grid'5000 Team 17:46, 26 August 2025 (CEST)

Grid'5000 sites

Current funding

INRIA

CNRS

Universities

IMT Atlantique
Université Grenoble Alpes, Grenoble INP
Université Rennes 1, Rennes
Institut National Polytechnique de Toulouse / INSA / FERIA / Université Paul Sabatier, Toulouse
Université Bordeaux 1, Bordeaux
Université Lille 1, Lille
École Normale Supérieure, Lyon

Regional councils

Aquitaine
Auvergne-Rhône-Alpes
Bretagne
Champagne-Ardenne
Provence Alpes Côte d'Azur
Hauts de France
Lorraine