Emmanuel Jeanvoine

Contact Address: Université de Lausanne Centre Informatique - Amphimax Emmanuel Jeanvoine CH-1015 Lausanne Switzerland Email: emmanuel#dot#jeanvoine#at#unil#dot#ch GPG key

Current activities

HPC specialist at University of Lausanne

From February 2020, I’ve joined the Scientific Computing and Research Support Unit of the University of Lausanne. Our team offers computing and storage infrastructures, as well as research support.

I mainly provide researchers of the University with the following support:

• access to the clusters
• build the scientific software stack
• parallel computing (CPU and GPU): OpenMP, MPI, Cuda
• scientific programming: Python, C++, Julia, R
• code optimization
• courses: Linux, parallel computing with Python and Julia, Python/R/Singularity on the clusters
• documentation for our HPC users

I’m also in charge of some DevOps tasks dedicated to our research infrastructures like:

• automated provisioning of the virtual infratructure
• automated provisioning of HPC resources: scheduler accounts and storage systems

Past activities

DevOps team leader at Quarkslab

From 2016 to 2020, I’ve been working at Quarkslab, a high-end cyber-security company based in Paris.

I was in charge of:

• Automated deployment and scalability of the products
• System hardening
• Continuous integration
• Infrastructure

Research engineer at Inria

From 2008 to 2016, I’ve been working as a research engineer in computer science at Inria (Saclay and Nancy research centers).

My interests were:

• Distributed systems
• High performance computing
• Software defined networks
• Parallel computing
• Cloud and Grid infrastructures

Some projects I worked on:

• Distributed systems emulator (see the Distem project)
• Cluster deployment (see the Kadeploy3 project)
• Bringing the SOFA framework for advanced medical simulation to the operating room (see the SOFA-OR project)

Community tasks

• Operational lead of the national Continuous Integration service
• Tutor for some young software engineers
• Spread best practices for software development

Ph.D. thesis

• Title: Middleware for the efficient and reliable execution of distributed applications in dynamic and very large scale grids
• Advisor: Christine Morin
• Summary:

  The emergence of the grid computing allows the scientific community to consider the access to an unequaled computing power. However, some characteristics of a grid like the large scale, the dynamic behavior of the resources that compose the grid and their heterogeneity make its use very complex. This thesis study the design of system services for the execution of distributed applications in large scale grids. Thanks to a fully distributed and a generic approach, our system can harness the resources of any grid model, even those composed of dynamic and heterogeneous resources. In order to simplify the use of a grid, we suggest to provide users with a single system image that allows to hide the distribution of the resources. We also suggest services designed to execute a wide range of distributed applications in an efficient and reliable way.

• Manuscript (in french): pdf.gz, ps.gz, TEL
• Defense (2007/11/27): pdf.gz

Master thesis

• Title: Quality of service in active networks
• Advisors: Hervé Guyennet, Éric Garcia, David Fuin
• Summary:

  The aim was to implement quality of service mechanisms in active networks. In this purpose, we have presented the concepts of quality of service and active networks, then we have drawn up an overview of existing works. Next, we have proposed an original mechanism of quality of service in active networks based on streams classification and scheduling. We have implemented this in ANTS and Tamanoir active nodes. Finally, we have realised experimentations in order to validate and to test the efficacity of our implementations.

• Manuscript (in french): pdf.gz

Publications

• Distem: Evaluation of Fault Tolerance and Load Balancing Strategies in Real HPC Runtimes through Emulation Cristian Ruiz, Joseph Emeras, Emmanuel Jeanvoine, Lucas Nussbaum In proceedings on the 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), May 2016, Cartagena, Colombia. 2016 pdf
• Performance evaluation of containers for HPC Cristian Ruiz, Emmanuel Jeanvoine, Lucas Nussbaum In Proceedings of Workshop on Virtualization in High-Performance Cloud Computing, held in conjuction with Euro-Par 2015, Vienna, Austria, August 2015 pdf
• Framework for Augmented Reality in Minimally Invasive Laparoscopic Surgery Bruno Marques, Rosalie Plantefève, Frederick Roy, Nazim Haouchine, Emmanuel Jeanvoine, Igor Peterlik, Stéphane Cotin In Proceedings of iOR15: 1st International Workshop on Intelligent Operating Rooms, 17th International Conference on E-health Networking, Application & Services (IEEE Healthcom 2015), Boston, USA, October 2015
• Emulation at Very Large Scale with Distem Tomasz Buchert, Emmanuel Jeanvoine, Lucas Nussbaum In SCALE Challenge 2014, held in conjunction with CCGrid 2014, Chicago, USA, May 2014 pdf
• Scalable and Reliable Data Broadcast with Kascade Stéphane Martin, Tomasz Buchert, Pierric Willemet, Olivier Richard, Emmanuel Jeanvoine, Lucas Nussbaum In Proceedings of International Workshop on High Performance Data Intensive Computing, in conjunction with IEEE IPDPS 2014, Phoenix, USA, May 2014 pdf
• Adding Virtualization Capabilities to the Grid’5000 Testbed Daniel Balouek, Alexandra Carpen Amarie, Ghislain Charrier, Frédéric Desprez, Emmanuel Jeannot, Emmanuel Jeanvoine, Adrien Lèbre, David Margery, Nicolas Niclausse, Lucas Nussbaum, Olivier Richard, Christian Perez, Flavien Quesnel, Cyril Rohr, Luc Sarzyniec In Cloud Computing and Services Science, Vol 367:3–20, 2013 link
• Design and Evaluation of a Virtual Experimental Environment for Distributed Systems Luc Sarzyniec, Tomasz Buchert, Emmanuel Jeanvoine, Lucas Nussbaum In Proceedings of the 21st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP 2013), Belfast, Ireland, February 2013 pdf
• Kadeploy3: Efficient and Scalable Operating System Provisioning for Clusters Emmanuel Jeanvoine, Luc Sarzyniec, Lucas Nussbaum In USENIX ;login:, Vol 38(1):38–44, february 2013 pdf
• Scalability Testing of the Kadeploy Cluster Deployment System using Virtual Machines on Grid’5000 Luc Sarzyniec, Sébastien Badia, Emmanuel Jeanvoine, Lucas Nussbaum In SCALE Challenge 2012, held in conjunction with CCGrid’2012, Ottawa, Canada, May 2012 pdf
• Déploiement et partitionnement dynamique de clusters avec Kadeploy et Kavlan Emmanuel Jeanvoine, Nicolas Niclausse, Lucas Nussbaum, David Margery Poster presented at Journées Réseaux (JRES 2011), Toulouse, France, November 2011 pdf
• Relaxed Synchronization with Ordered Read-Write Locks Jens Gustedt and Emmanuel Jeanvoine In Proceedings of the Euro-par 2011 Workshops (HPSS 2011), Part 1, LNCS 7155, Pages 387–397, Bordeaux, France, August 2011 pdf
• RW-OGS : an optimized random walk protocol for resource discovery in large scale dynamic grids Emmanuel Jeanvoine and Christine Morin In Proceedings of the 9th IEEE/ACM International Conference on Grid Computing (GRID 2008), Pages 168–175, Tsukuba, Japan, October 2008 pdf
• Vigne: Executing Easily and Efficiently a Wide Range of Distributed Applications in Grids Emmanuel Jeanvoine, Christine Morin and Daniel Leprince In Proceedings of Euro-Par 2007, Pages 394–403, Rennes, France, 2007 pdf
• Using Overlay Networks to Build Operating System Services for Large Scale Grids Emmanuel Jeanvoine, Louis Rilling, Christine Morin and Daniel Leprince In Scalable Computing: Practice and Experience, Vol. 8(3):229–239, 2007 pdf
• GAMoSe: An Accurate Monitoring Service for Grid Applications Thomas Ropars, Emmanuel Jeanvoine and Christine Morin In 6th International Symposium on Parallel and Distributed Computing (ISPDC 2007), Pages 295–302, Hagenberg, Austria, July 2007 pdf
• Architecture distribuée pour la gestion des ressources dans des grilles à grande échelle Emmanuel Jeanvoine, Louis Rilling, Christine Morin and Daniel Leprince In Actes de NOTERE 2006, Pages 231–242, Toulouse, France, June 2006 pdf
• Using Overlay Networks to Build Operating System Services for Large Scale Grids Emmanuel Jeanvoine, Louis Rilling, Christine Morin and Daniel Leprince In Proceedings of the 5th International Symposium on Parallel and Distributed Computing (ISPDC 2006), Pages 191–198, Timisoara, Romania, July 2006 pdf
• Un protocole de découverte de ressources optimisé pour l’allocation de ressources dans les grilles Emmanuel Jeanvoine, Christine Morin and Daniel Leprince In Actes de CFSE-5 2006, Pages 49–59, Perpignan, France, October 2006 pdf
• Distributed Operating System for Resource Discovery and Allocation in Federated Clusters Emmanuel Jeanvoine Poster presented at the 20th ACM Symposium on Operating Systems Principles (SOSP 2005), Brighton, UK, October 2005 pdf
• Quality of Service Vertical and Horizontal Integration in Active Nodes David Fuin, Éric Garcia, Hervé Guyennet and Emmanuel Jeanvoine In Proceedings of the IEEE joint International Conference on Autonomic and Autonomous Systems (ICAS’05) and International Conference on Networking and Services (ICNS’05), Pages 30, Tahiti, French Polynesia, October 2005 pdf