Research activities: projects

Participants: Luc Hogie, Nicolas Chleq [service de développement et d’expérimentation Inria Sophia Antipolis-Méditerranée], Michel Syska.

Duration: october 2014 - .

The objective of Big Graphs is to provide a distributed platform for very large graphs processing. A typical data set for testing purpose is a sample of the Twitter graph~: 240GB on disk, 398M vertices, 23G edges, average degree of 58 and max degree of 24635412.

We started the project in 2014 with the evaluation of existing middlewares (GraphX / Spark and Giraph / Hadoop). After having tested some useful algorithms (written according to the BSP model) we decided to develop our own platform. This platform is based on the existing biggrph library and we are now in the phasis where we focus on the quality and the improvement of the code. In particular we have designed strong test suites and some non trivial bugs have been fixed. We also have solved problems of scalability, in particular concerning the communication layer with billions of messages exchanged between BSP steps. We also have implemented specific data structures for BSP and support for distributed debugging. This comes along with the implementation of algorithms such as BFS or strongly connected components that are run on the NEF cluster.

This project is a joint work of the three EPI Coati, Diana and Scale and has been supported by an ADT grant.

Download biggrph

The following software are useful tools that bring basic services to the platform (they are not dedicated to biggrph).

• jacaboo is a framework aiming at facilitating the deployment and the bootstrapping of distributed Java applications over Share-Nothing Clusters (SNCs). The primary motivation for developing jacaboo is to have an efficient and comprehensive deployment infrastructure for the biggrph distributed graph library.
• ldjo (Live Distributed Java Objects) is a framework for the development and the deployment of Java distributed data structures. Alongside with data aspect of distributed data structures, ldjo comes with mechanisms for processing them in a distributed/parallel way. In particular it provides implementations of Map/Reduce and Bulk Synchronous Parallel (BSP).
• octojus provides an object-oriented RPC (Remote Procedure Call) implementation in Java. At a higher abstraction level, octojus provides a framework for the development of systolic algorithms, a batch scheduler, as well as an implementation of Map/Reduce. The latter is used in the biggrph graph computing platform.

See also the centralized cousin : Grph

---

Participants: Marco Biazzini, David Coudert, Stéphane Pérennes, Michel Syska.

Duration: May 2014 - April 2015.

This collaboration with Amadeus (a major European IT Provider for the global travel and tourism industry) aims at assessing the benefits that digital technologies can bring in complex travel distribution applications. Indeed, these applications require both high performance algorithms and distributed programming methods to search for the best solutions among billions of combinations, in a very short time thanks to the simultaneous use of several hundreds (if not thousands) of computers. These benefits will be demonstrated in an application to build ’off the shelf’ optimized packages, fully customized to best meet the complex demands of the traveler.

This project is a joint work of the two EPI Coati, and Scale and has been supported by a contract with Amadeus (see announce)

---

Participants: Mohamed Amine Bergach, Robert de Simone, Michel Syska.

Duration: November 2011 - April 2015.

Bilateral grant (contract CIFRE) with Kontron (worldwide company which designs and manufactures embedded systems) on the topic Graphic Processing Units for Signal Processing. The result of this collaboration is the PhD defense of the thesis: M. A. BERGACH. Adaptation of the Fast Fourier Transform processing on hybrid integrated CPU/GPU architecture, Université Nice Sophia Antipolis, October 2015, https://hal.inria.fr/tel-01245958.

This project is a joint work of the two EPI Coati, and Aoste and has been supported by a contract with Kontron

---

• ANR Blanc STINT, 2014-2017
• ANR Blanc AGAPE, 10/2009-09/2013

---