• Current projects/events
    • I am member of the NumPEX project on ExaScale. I am member of the integrated project ExaDOST on data mangement and I am responsible of the internaitonal collaborations.
    • The main objective of the ADMIRE project is to establish this control by creating an active I/O stack that dynamically adjusts computation and storage requirements through intelligent global coordination, malleability of computation and I/O, and the scheduling of storage resources along all levels of the storage hierarchy. To achieve this, we will develop a software-defined framework based on the principles of scalable monitoring and control, separated control and data paths, and the orchestration of key system components and applications through embedded control points. I am responsible of the WP6 (Intelligent Controller)
    • With Pete Beckman and Swan Peranau from ANL we are organizing the the RADR workshop (in conjunction with IPDPS).
    • I am the program chair of the COLOC workshop (in conjuntion with Euro-Par).
    • The goal of the TADaaM Inria project (joint with Univ. Bordeaux and Bordeaux INP) is to design and build a stateful system-wide service layer for HPC systems. This layer will be twofold. First, it will abstract low level features of thesystem (e.g. topology, network, resource usage) and the software stack (e.g. threads, data). Second, applications will be able to register their needs and behavior thanks to a carefully designed API. With these two sets of information, the layer will optimize the execution of all the running applications in a coordinate fashion and at system-scale.
    • The GRID'5000 project aims at building a highly reconfigurable, controlable and monitorable experimental Grid platform gathering 9 sites geographically distributed in France featuring a total of 5000 CPUs. I was responsible of the Nancy site which hosts 3 clusters (96, 240 and 184 CPUs). I am now responsible of the Bordeaux site which hosts 2 clusters.
    • I am member of the Joint Laboratory for Extrem-Scale Computing between INRIA and the University of Ilinois at Urbana Champaign, Argonne National Lab, BSC, Univ of Tennessee, Riken, Julich and Inria. The joint lab focuses on software challenges found in complex high-performance computers.
    • I am member of the steering committee of the ICPP Conference since 2022.
  • Past projects
    • I was member of the Inria project Lab on the converegnce of HPC and Big Data (2018-2021).
    • I was member of the steering committee of the Euro-Par conference from 2011 to 2021.
    • I was member of the steering committee of the Cluster conference from 2010 to 2020.
    • I was the vice chair of the Network for Sustainable Ultrascale Computing (NESUS) european COST Action IC 1305. The goal of the NESUS Action was to establish an open European research network targeting sustainable solutions for ultrascale computing aiming at cross fertilization among HPC, large scale distributed systems, and big data management (2013-2018).
    • I was member and chair of the Inria partner of the ELCI project. The main goal of the ELCI project (Environnement Logiciel pour le Calcul Intensif / Software Environment for High-Performance Computing) was to improve numerical-simulation and computer science techniques, using real-world simulation codes, so that they fully exploit future generations of high-end hardware.
    • I was member of the COLOC ITEA project that aimed at providing new models, mechanisms and tools for improving applications performance and supercomputer resources usage taking into account data locality and concurrency. I was responsible of the WP2: data transfer and locality modeling
    • I was member of the MOEBUS ANR project. This project focused on the efficient execution of parallel applications submitted by various users and sharing resources in large-scale high-performance computing environments. I was the head of task 3: Multi-objectives Scheduling. Duration: 4 years (2013-2017).
    • I was member of the MORSE associated team between INRIA, UTK and UCD. The goal of Matrices Over Runtime Systems at Exascale (MORSE) project was to design dense and sparse linear algebra methods that achieve the fastest possible time to an accurate solution on large-scale multicore systems with GPU accelerators, using all the processing power that future high end systems can make available.
    • I was member of the Inria Runtime Inria team until 2015.
    • I have been leading the European COST Action ComplexHPC: Open European Network for High-Performance Computing in Complex Environments from 2009 to 2013. This Action gathered more than 20 countries and 30 partners in Europe. The goal of the Action was to establish a European research network focused on high performance heterogeneous computing in order to address the whole range of challenges posed by these new platforms including models, algorithms, programming tools and applications.
    • I was the leader of the ALEAE INRIA ARC (2009-2011). The goal aleae is to provide models and algorithmic solutions in the field of resource management that cope with uncertainties in large-scale distributed systems.
    • The goal of wrekavoc is to define and control the heterogeneity of a given platform by degrading CPU, network or memory capabilities of each node composing this platform.
    • Network of excelence CoreGRID. It is a european research network on foundations, software infrastructures and applications for large scale distributed, grid and peer-to-peer technologies. Member of the work-package 6 "resources managenent" (2005-2008).
    • ACI data masses AGIR. New imaging processing algorithm on the GRID. Progressive transmission of medical images.
    • NSF-INRIA project. Collaboration with ICL of the Univ. of Tennessee and the GRAAL project of INRIA. I Collaborate with the Netsolve team on adaptive online compression.
    • ARC INRIA OTaPHe. Scheduling parallel tasks on heterogeneous platforms.
    • ACI data masses GRID-Explorer. Design and of a GRID emulator. Responsible of the heterogenity emulation task.
    • ARC INRIA RedGRID. Data redistribution for code-coupling applications  and computational steering.
    • I  collaborated to the DIET environment that is a PSE with a hierarchical set of agents.
    • ACI GRID ASP. Collaboration with Gerald Monard from ECBT. I designed an application for computing the potential energy surface of a system of molecules.
    • During my postdoc I worked within the INRIA ARC OURAGAN on Scilab parallel  which aims to provide a transparent way for accessing distributed resources. For instance I worked on interfacing Scilab with Netsolve .
    • Euro-tops projects with Matra-Caps systems. Automatic parallelization of high-performance applications.
  • Past events