Grid5000:Home

From Grid5000
Revision as of 14:30, 12 February 2021 by Bjonglez (talk | contribs) (Fix news link)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
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 and 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.

Grid'5000 is merging with FIT to build the SILECS Infrastructure for Large-scale Experimental Computer Science. Read an Introduction to SILECS (April 2018)


Recently published documents and presentations:

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 2022-05-17 20:30): 2 current events, 1 planned (details)


Random pick of publications

Five random publications that benefited from Grid'5000 (at least 2382 overall):

  • Ajinkya Kulkarni, Vincent Colotte, Denis Jouvet. Improving transfer of expressivity for end-to-end multispeaker text-to-speech synthesis. EUSIPCO 2021 - 29th European Signal Processing Conference, European Association for Signal Processing (EURASIP), Aug 2021, Dublin / Virtual, Ireland. 10.23919/EUSIPCO54536.2021.9616249. hal-02978485v3 view on HAL pdf
  • Brij Mohan Lal Srivastava. Speaker Anonymization: Representation, Evaluation and Formal Guarantees. Artificial Intelligence cs.AI. Inria Lille Nord Europe - Laboratoire CRIStAL - Université de Lille, 2021. English. tel-03539738 view on HAL pdf
  • Pavlos Kranas, Boyan Kolev, Oleksandra Levchenko, Esther Pacitti, Patrick Valduriez, et al.. Parallel Query Processing in a Polystore. Distributed and Parallel Databases, Springer, In press, pp.39. 10.1007/s10619-021-07322-5. lirmm-03148271 view on HAL pdf
  • Vincenzo Innocente, Paul Zimmermann. Accuracy of Mathematical Functions in Single, Double, Extended Double and Quadruple Precision. 2022. hal-03141101v2 view on HAL pdf
  • Amina Guermouche, Anne-Cécile Orgerie. Thermal design power and vectorized instructions behavior. Concurrency and Computation: Practice and Experience, Wiley, 2022, 34 (2), pp.e6261. 10.1002/cpe.6261. hal-03185821 view on HAL pdf


Latest news

Rss.svgCluster "sirius" from Nvidia is available in the default queue

We have the pleasure to announce that a new cluster named "sirius" is available at Lyon.

This cluster consists in only one Nvidia DGX A100 node with 2 AMD EPYC 7742 CPUs (64 cores per CPU) and 8 Nvidia A100 (40 GiB) GPUs, 1TB of DDR4 RAM, 2x1.92 TB SSD + 4x3.84 TB SSD disks and a coming-soon infiniband network.

Energy monitoring is available for this cluster, provided by the same wattmeter devices as used for the other clusters in Lyon.

This cluster is tagged as "exotic", so the `-t exotic` option must be provided to oarsub to select sirius.

This machine has been funded by LIP laboratory with the support of INRIA Grenoble Rhone-Alpes and ENS Lyon.

-- Grid'5000 Team 11:30, Wed, May 11th 2022 (CEST)

Rss.svgUbuntu 22.04 LTS environment available

A kadeploy environment (image) for Ubuntu Jammy Jellyfish 22.04 LTS (ubuntu2204-min) is now available and registered in all Grid'5000 sites with Kadeploy.

Only x86_64 architecture is available for now. For ARM (arm64/aarch64) and POWER 8 (ppc64/ppc64le), you can use the previous Ubuntu 20.04 LTS images (ubuntu2004-min).

Please refer to our getting started document to learn how to deploy such an image on the platform [1].

This image is built with Kameleon (just like other Grid'5000 environments). The recipe is available in the environments-recipes git repository.

If you need other system images for your work, please let us know.

-- Grid'5000 Team 13:40, Fri, May 6th 2022 (CEST)

Rss.svgEnd of support for Debian 9 "Stretch" environments

We are going to drop support for the stretch/debian9 environments on April 30st 2022.

The last version of strech environments i.e 2021100608 will remain available on /grid5000. You can still access older versions of debian 9 environments under the archive directory (see /grid5000/README.unmaintained-envs for more information).

-- Grid'5000 Team 14:40, Tue, 19 Apr 2022 (CEST)

Rss.svgSyntax simplification of the OAR job submissions and removal of allow_classic_ssh job type

Three behavior changes about OAR on Grid'5000 have been made, to simplify the job submission commands.


1. Syntax simplification mechanism to ease OAR job submissions. As announced previously, a syntax simplification mechanism has been deployed on Grid'5000. It is now enabled by default (until today, its usage was available only by using the `syntax-simplifier` job type).

Here are some examples of its possibilities:

  • `oarsub -p dahu-19` will reserve the dahu-19 node
  • `oarsub -p dahu` will reserve one node on the dahu cluster
  • `oarsub -p "ssd&256GB" -l nodes=2` will reserve two nodes with SSD storage and at least 256GB of memory
  • `oarsub -l "{host+disk&grimoire}` will reserve one node on grimoire cluster with all its disks
  • `oarsub -p "host IN (yeti-1,yeti-2,yeti-3)` will reserve one of the listed nodes (here FQDN and simple quotes are omitted)

Syntax simplification implements the following features:

  • automatic addition of simple quotes for character strings in expressions
  • automatic expansion of nodes' short names to long names (FQDN)
  • usage of "&" as an alternative to "and"; "|" as an alternative to "or"
  • aliases to translate short and simple keywords to OAR resource filter expressions, for the most common resources (GPUs, clusters, nodes, disks,…)

The available aliases and a more complete overview are available on the [OAR Syntax simplification] page. Please note that the standard OAR syntax is still supported. The simplifications described here are not replacements but additions. If you encountered any issues, the syntax simplification can be disabled by adding the `no-syntax-simplifier` job type at job submission (typically, by adding `-t no-syntax-simplifier` to your oarsub command line).


2. OAR's job type `allow_classic_ssh` is removed.

It is now possible to connect using `ssh` to nodes reser...


Read more news

Grid'5000 sites

Current funding

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

INRIA

Logo INRIA.gif

CNRS

CNRS-filaire-Quadri.png

Universities

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