Julien Jaeger

Julien Jaeger is a research engineer at CEA and in the LIHPC. After defending its Ph.D. at the University of Versailles Saint-Quentin-En-Yvelines, he joined the MPC team at CEA in 2012, to work on its MPI implementation. From 2019 to 2022, he lead the MPC team working in parallel programming languages such as MPI and OpenMP, their scheduling and interactions on supercomputers. He is an active member of the MPI Forum, participating in designing the new versions of the MPI Standard.

Julien Jaeger est un ingénieur-chercheur du CEA et du LIHPC. Il a rejoint l’équipe MPC au CEA en 2012, après avoir soutenu sa thèse en Informatique à l’Université de Versailles Saint-Quentin-En-Yvelines la même année. Depuis 2019, il est à la tête de l’équipe MPC travaillant sur les modèles de programmation parallèle comme MPI et OpenMP, leur ordonnancement et leurs interactions sur les supercalculateurs HPC. Il est un membre actif du MPI Forum, participant aux nouvelles versions du standard MPI.


In the last decade, Julien Jaeger has taught multiple topics in the field of Programming Languages and HPC. Currently, he is the head of the following courses

  • TOP (UVSQ) – Techniques d’Optimisation de la Parallélisation (Methods for parallel program optimization) : this course gives tips on how to improve parallel programs (MPI, threads, hybrid MPI+X), how to measure a parallel programs, what you should care about in a parallel program, and some insights about implementations and interactions between multiple runtime.
  • APM (UVSQ) – Architecture et Programmation d’accélérateurs Matériels (Hardware accelerators Architecture and Programming) : this course introduces hardware accelerators such as GPUs, their characteristics and differences with CPUs. Programming languages for accelerators are also taught, with a focus on CUDA, OpenMP and OpenACC, and introductions to OpenCL, SYCL and Kokkos.
  • PPD (ENSIIE) – Programmation Parallèle Distribuée (Distributed Parallelism Programming) : this course presents parallel programming for distributed memory. It mainly focuses on MPI covering both basic and advanced topics (point-to-point, collective and one-sided communications; blocking, nonblocking, persistent and partitioned communications; dataypes; IOs). This course also provides an introduction to high speed networks and the network topologies found in nowadays supercomputers, to RDMA, to PGAS models, and to the MPI Forum.


His research topics focus on parallel programming, scheduling, interactions between runtime, and tools for parallel programming.



Joachim Protze, Marc-André Hermanns, Matthias S. Müller, Van-man Nguyen, Julien Jaeger, Emmanuelle Saillard, Patrick Carribault and Denis Barthou, MPI detach – Towards automatic asynchronous local completion, In Journal on Parallel Computing vol.109. (pdf|bib|doi)

Stéphane Bouhrour Thibaut Pépin and Julien Jaeger, Towards leveraging collective performance with the support of MPI 4.0 features in MPC, In Journal on Parallel Computing vol.109. (pdf|bib|doi)


Thomas Dionisi, Stéphane Bouhrour, Julien Jaeger, Patrick Carribault and Marc Pérache, Enhancing Load-balancing of MPI Applications with Workshare, In Euro-Par 2021 . (pdf|bib|doi)

Daniel J. Holmes, Anthony Skjellum, Julien Jaeger, Ryan E. Grant, Purushotham V. Bangalore, Matthew G. F. Dosanjh, Amanda Bienz and Derek Schafer, Partitioned Collective Communication, In International Workshop on Exascale MPI (ExaMPI) 2021 . (pdf|bib|doi)

Jean-Baptiste Besnard, Julien Adam, Allen D. Malony, Sameer Shende, Julien Jaeger, Patrick Carribault and Marc Pérache, Exploring Space-Time Trade-Off in Backtraces, In  Proceedings of the 12th and 13th Workshop on Parallel Tools for High performance Computing. (pdf|bib|doi)


Edgar A. León, Balazs Gerofi, Julien Jaeger, Guillaume Mercier, Rolf Riesen, Masamichi Takagi, Brice Goglin, Application-Driven Requirements for Node Resource Management in Next-Generation Systems, in Proceedings of the 2020 International Workshop on Runtime and Operating Systems for Supercomputers – ROSS 2020. (pdf|bib|doi)

Van Man Nguyen, Emmanuelle Saillard, Julien Jaeger, Denis Barthou, Patrick Carribault, PARCOACH Extension for Static MPI Nonblocking and Persistent Communication Validation, In Fourth International Workshop on Software Correctness for HPC Applications – CORRECTNESS 2020. (pdf|bib|doi)

Bouhrour S. and Jaeger J., Implementation and performance evaluation of MPI persistent collectives in MPC: a case study, in Proceedings of the 27th European MPI Users’ Group Meeting – EuroMPI/USA 2020. (pdf|bib|doi|final version)

Roussel A., Carribault P., and Jaeger J., Preliminary Experience with OpenMP Memory Management Implementation, In International Workshop on OpenMP – IWOMP’20. (pdf|bib|doi|final version)

Nguyen V.-M., Saillard E., Jaeger J., Barthou D., and Carribault P., Automatic Code Motion to Extend MPI Nonblocking Overlap Window, in 1st Workshop on Compiler-assisted Correctness Checking and Performance Optimization for HPC – C3PO’20. (pdf|bib|doi|final version)


A. Denis, J. Jaeger, E. Jeannot, M. Pérache and H. Taboada, Study on progress threads placement and dedicated cores for overlapping MPI nonblocking collectives on manycore processor, in International Journal on High Performance Computing and Applications. (pdf|bib)

Besnard, J. B., Jaeger, J., Malony, A. D., Shende, S., Taboada, H., Pérache, M., & Carribault, P. (2019, September). Mixing ranks, tasks, progress and nonblocking collectives. In Proceedings of the 26th European MPI Users’ Group Meeting. (pdf|bib)

Purushotham V. Bangalore P., Rabenseifner R., Holmes D., Jaeger J., Mercier G., Blaas{-}Schenner C., and Skjellum A. Exposition, clarification, and expansion of {MPI} semantic terms and conventions: is a nonblocking {MPI} function permitted to block?. In Proceedings of the 26th European MPI Users’ Group Meeting (pp. 1-10). (pdf|bib)

Vieira, R. B., Capra, A., Carribault, P., Jaeger, J., Pérache, M., & Roussel, A.,  Detecting Non-Sibling Dependencies in OpenMP Task-Based Applications. In International Workshop on OpenMP (pp. 231-245). Springer, Cham. (pdf|bib)

Julien Adam, Maxime Kermarquer, Jean-Baptiste Besnard, Leonardo Bautista-Gomez, Marc Pérache, Patrick Carribault, Julien Jaeger, Allen D. Malony, Sameer Shende, Checkpoint/Restart Approaches for a Thread-Based MPI Runtime, in Parallel Computing (2019), doi: https://doi.org/10.1016/j.parco.2019.02.006. (pdf|bib)


A. Denis, J. Jaeger, E. Jeannot, M. Pérache and H. Taboada, Progress Thread Placement for Overlapping MPI Non-Blocking Collectives using Simultaneous Multi-Threading, in EuroPar 2018 Workshops : COLOC (pdf|bib)

H. Brunie, J. Jaeger, P. Carribault and D. Barthou, Profile-Guided Scope-Based Dynamic Data Allocation Method, in MEMSYS 2018. (pdf|bib)

M. Sergent, M. Dagrada, P. Carribault, J. Jaeger, M. Pérache and G. Papauré, Efficient Communication/Computation Overlap with MPI+OpenMP Runtimes Collaboration, in EuroPar 2018 (pdf|bib)

A. Denis, J. Jaeger, E. Jeannot, M. Pérache and H. Taboada, Dynamic Placement of Progress Thread for Overlapping MPI Non-Blocking Collectives on Manycore Processor, in EuroPar 2018 (pdf|bib)

J. Adam, J.-B. Besnard, A.. Malony, S. Shende, M. Pérache, P. Carribault and J. Jaeger, Transparent High-Speed Network Checkpoint/Restart in MPI, in EuroMPI 2018 (pdf|bib)


A. Loussert, B. Welterlen, P. Carribault, J. Jaeger, M. Pérache and R. Namyst, Resource-Management Study in HPC Runtime-Stacking Context, in 29th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2017), IEEE, Pages 177-184. (pdf|bib)

A. Capra, P. Carribault, J.-B. Besnard, A. Mallony, M. Pérache, and J. Jaeger, User Co-scheduling for MPI+OpenMP Applications Using OpenMP Semantics, in International Workshop on OpenMP 2017 (IWOMP 2017), Springer, Pages 203-216. (pdf|bib)
The final authenticated version is available on https://doi.org/10.1007/978-3-319-65578-9_14

J.-B. Besnard, A. Mallony, S. Shende, M. Pérache, P. Carribault and J. Jaeger, Towards a Better Expressiveness of the Speedup Metric in MPI Context, in 46th International Conference on Parallel Processing Workshops (ICPPW) 2017, PSTI 2017, IEEE (pdf|bib)


J.-B. Besnard, J. Adam, S. Shende, M. Pérache, P. Carribault, J. Jaeger and A. Mallony, Introducing Task-Containers as an Alternative to Runtime-Stacking, in EuroMPI 2016, ACM (pdf|bib)


J.-B. Besnard, A. Mallony, S. Shende, M. Pérache, P. Carribault and J. Jaeger, An MPI Halo-Cell Implementation for Zero-Copy Abstraction,  in EuroMPI 2015, ACM. (pdf|bib)

J. Jaeger, E. Saillard, P. Carribault and D. Barthou, Correctness Analysis of MPI-3 Non-Blocking Communications in PARCOACH, in EuroMPI 2015, ACM (short paper). (pdf|bib|poster)

J. Jaeger, A. Mahéo, P. Carribault, M. Pérache and W. Jalby, Optimisation des opérations collectives dans les applications MPI+OpenMP, in Chocs Avancees 2014, pages 44-45 (2015) (in french). (bib)

J. Jaeger, P. Carribault, and M. Pérache, Fine‐grain data management directory for OpenMP 4.0 and OpenACC, in Concurrency and Computation: Practice and Experience (2014), Pages 1528-1539 (2015), ACM. (pdf|bib)


J. Jaeger, P. Carribault, and M. Pérache, Data-Management Directory for OpenMP 4.0 and OpenACC, in Euro-Par 2013: Parallel Processing Workshops. Springer Berlin Heidelberg, 2014. (pdf|bib)


J. Jaeger and D. Barthou, Automatic efficient data layout for multithreaded stencil codes on CPUs and GPUs, in 19th International Conference on High Performance Computing (2012), Pages 1-10, Pune, India, 2012, doi: 10.1109/HiPC.2012.6507504.


J. Jaeger and D. Barthou, Combining experimental search and performance model for adaptive optimization, in Hipeac Workshop on Statistical and Machine Learning Approaches to Architectures and compilation, Paphos, Cyprus. 2009.

L. Plagne, F. Hülsemann, D. Barthou, and J. Jaeger, Parallel expression template for large vectors, In Proceedings of the 8th workshop on Parallel/High-Performance Object-Oriented Scientific Computing (POOSC ’09). ACM, New York, NY, USA, Article 8, 1–8. https://doi.org/10.1145/1595655.1595663

K. Ibrahim, J. Jaeger, Z. Liu, et al, in 14th Workshop on Compiler for Parallel Computing (CPCP 2009), Zurich, Switzerland, 2009.