Floating-Point Transformer 4
Ce projet a pour objectif d’utiliser les grands modèles de langage pour aider à l’analyse et la transformation automatique de code flottant.
Project Leader : fabienne jezequel
10/01/2024
Algorithmes en précision mixte pour le calcul haute performance
Project Leader : Theo Mary
10/01/2023
Architectures Novatrices pour Capteur Fibre Optique Acoustique Distribué
Project Leader : Fabienne Jezequel
10/01/2023
Methods and Algorithms for Exascale
Project Leader : Pierre Jolivet
01/01/2023
https://numpex.org/exama-methods-and-algorithms-for-exascale/
HPDDM - high-performance unified framework for domain decomposition methods
HPDDM is a collection of preconditioners based on domain decomposition, either overlapping or non-overlapping. They can be used to solve large linear systems, as typically encountered when discretizing partial differential equations. These preconditioners can be used in conjunction with various Krylov methods. The library is usable in C, C++, Python, or Fortran codes.
Project Leader : Pierre JOLIVET
12/01/2022
Un jumeau numérique mécanique assisté par les splines et basé sur les images pour l'analyse de structures lattices réelles
Project Leader : Pierre Jolivet
10/01/2022
Plateforme d'analyse pour l'arithmétique flotante
Réf. DR&I / INFOLAB : C21/0289
Project Leader : Fabienne Jezequel
10/01/2020
Sûreté numérique pour les preuves assistées par ordinateur
C20/1155
Project Leader : Marc Mezzaroba
10/01/2020
FiXiF - Reliable fixed-point implementation of linear signal processing (and control) algorithms
FiXiF is a suite of tools used to implement filters on embedded devices (usually DSP, micro-controllers, FPGA or ASIC) with finite-precision impact in minds (fixed- or floating-point arithmetic).
Project Leader : Thibault HILAIRE
08/01/2017
PROMISE - PRecision OptiMISE
PROMISE is a tool to auto-tune the precision of floating-point variables in numerical codes.
Project Leader : Fabienne JEZEQUEL
01/01/2016
ExBLAS - Exact Basic Linear Algebra Subprograms
ExBLAS aims at providing algorithms and implementations for fundamental linear algebra operations (like those included in the BLAS library) that deliver reproducible and accurate results with small or without losses to their performance on modern parallel architectures.
Project Leader : Stef GRAILLAT
01/01/2014
SAM - Stochastic Arithmetic in Multiprecision
The SAM library enables rounding error estimation in arbitrary precision programs.
Project Leader : Fabienne JEZEQUEL
01/01/2010
CADNA - Control of Accuracy and Debugging for Numerical Application
CADNA is a library which allows to perform scientific computations with the estimation and the control of the round-off error propagation.
Project Leader : Fabienne JEZEQUEL
01/10/1992