Advancing Science at Exascale – Discover the Latest Research from NumPEx
NumPEx is leading exascale computing research, advancing high-performance computing (HPC) to tackle the biggest scientific and industrial challenges. Our team is working on the latest algorithms, architectures and software optimisations for the next generation of computational science.
Here you will find our scientific publications, hosted on HAL, with the latest results and breakthroughs from the NumPEx community. Whether you are a researcher, an industry professional or simply a curious person interested in exascale computing, these publications will give you a glimpse of the future of HPC.
We are always looking for new talents – students, researchers, engineers – who want to shape the future of computational science. Interested in contributing to this field? Have a look at our work and join us to push the limits of performance and innovation.
131 publications
Efficient Fine-Scale Simulation of Nonlinear Hyperelastic Lattice Structures
Clément Guillet, Thibaut Hirschler, Pierre Jolivet, Pablo Antolin, Robin Bouclier
Computer Methods in Applied Mechanics and Engineering · vol. 461 · pp. 119202
A Methodology for System-Scale I/O Pattern Taxonomy for HPC Workloads
Théo Jolivel, François Tessier, Jakob Luettgau, Gabriel Antoniu, Philippe Deniel
SBAC-PAD 2026 - 38th IEEE/SBC International Symposium on Computer Architecture and High Performance Computing · Madrid, ES
Mixed-Precision Computing for Scientific Discovery: Formats, Co-Design, and Responsible Approximation
Emmanuel Agullo, Hartwig Anzt, Daniel Bauer, David Bindel, Alfredo Buttari, Alexandru Calotoiu + 34 more
Preprint · arxiv
Numerical stability of tree tensor network operations, and a stable rounding algorithm
Marc Baboulin, Oguz Kaya, Theo Mary, Matthieu Robeyns
SIAM Journal on Matrix Analysis and Applications
Certified Bayesian optimal experimental design: from Expected Information Gain to Signal-to-Noise Ratio
Mohamed Doumbouya, Arthur Vidard, Olivier Zahm
Preprint · arxiv
NewMadeleine: An Optimizing Communication Library for High-Performance Networks
Olivier Aumage, Elisabeth Brunet, Alexandre Denis, Nathalie Furmento, Brice Goglin, Raymond Namyst + 2 more
Software deposit
Mixed precision accumulation for neural network inference guided by componentwise forward error analysis
El-Mehdi El Arar, Silviu-Ioan Filip, Theo Mary, Elisa Riccietti
IMA Journal of Numerical Analysis
Mixed-precision algebraic multigrid with Jacobi and FSPAI smoothing on GPUs
Emmanuel Agullo, Ani Anciaux-Sedrakian, Alfredo Buttari, Petr Vacek
Preprint
MojitO/S: system, energy and network monitoring tools at the O/S level
Diane Orhan, Georges da Costa
Preprint
Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks
Laurynas Varnas, Julien Herrmann, Alexander Heinlein, Serge Gratton, Alena Kopaničáková
Preprint
Réduction dynamique des traces par l’analyse de performance a la volée
Tom Gavé
Ecole Nationale Supérieure d'Electronique, Informatique et Radiocommunications de Bordeaux
Sharp Probabilistic Normwise Backward Error Bounds for LU Factorization
Liam Burke, El-Mehdi El Arar, Stef Graillat, Theo Mary
Preprint
