Grid5000:Home: Difference between revisions
No edit summary |
No edit summary |
||
| Line 9: | Line 9: | ||
Key features: | 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 | * 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 | * '''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 networking and power consumption''', to provide a deep understanding of experiments | ||
* '''designed to support Open Science and reproducible research''', with full traceability of infrastructure and software changes on the testbed | * '''designed to support Open Science and reproducible research''', with full traceability of infrastructure and software changes on the testbed | ||
Revision as of 22:46, 22 January 2015
|
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:
|
Latest publications from Grid'5000 users
Five random publications that benefited from Grid'5000 (at least 2928 overall):
- 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
- Théophile Dubuc. Détection d'anomalies de latence dans les systèmes distribués avec eBPF. Système d'exploitation cs.OS. Ecole normale supérieure de lyon - ENS LYON, 2024. Français. NNT : 2024ENSL0109. tel-05064342 view on HAL pdf
- Rosa Pagano, Sophie Cerf, Bogdan Robu, Quentin Guilloteau, Raphaël Bleuse, et al.. Making Control in High Performance Computing for Overload Avoidance Adaptive in Time and Job Size. CCTA 2024 - 8th IEEE Conference on Control Technology and Applications, Aug 2024, Newcastle Upon Tyne, United Kingdom. pp.1-8. hal-04669743 view on HAL pdf
- Emile Cadorel, Dimitri Saingre. A Protocol to Assess the Accuracy of Process-Level Power Models. Cluster 2024, IEEE, Sep 2024, Kobe, Japan. hal-04720926 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
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
|
UniversitiesUniversity Joseph Fourier, Grenoble |
Regional councilsAquitaine |
