Exa-MA: Methods and Algorithms for Exascale

Building the future of exascale computing through advanced numerical methods, AI-enhanced algorithms, and production-ready open-source software.

Our Mission

The Exa-MA project is part of France’s PEPR NumPEx initiative, dedicated to pushing the frontiers of exascale computing. We develop and deploy:

Advanced Methods

Novel discretizations, solvers, and algorithms optimized for exascale architectures

AI Integration

Scientific machine learning for simulation, model reduction, and optimization

Open Software

Production-ready libraries that abstract hardware complexity and enable seamless portability

Validated Impact

Demonstrators, benchmarks, and real-world applications across scientific domains

Exa-MA brings together leading French institutions (CEA, École Polytechnique, Inria, Sorbonne Université, Université de Strasbourg) with a budget of 6.255 M€ over the project duration.

Recent Achievements

2025 Highlights

Up to 50× Speedup
GenEO preconditioning on large-scale problems (45M DoFs, 2916 cores)

8000 GPU Scale
Bayesian optimization on LUMI supercomputer with fractal decomposition

80-200% CPU Savings
Neural operators accelerating Newton iterations, domain-decomposed PINNs

Urban Meshing
Feature-preserving alpha wrapping (CGAL 6.0) and urban-scale mesh generation (Ktirio-Geom)

HPC Benchmarking
Automated CI/CD pipeline: code → EuroHPC runs in < 24h

Impact at a Glance

36 Publications

16 Software Packages

18 Frameworks

55 Person-Years

Work Packages Overview

Exa-MA is organized into seven scientific work packages plus project management:

Numerical Methods

WP1

Discretization – Mesh generation/adaptation (AMR), finite element framework, nonconforming methods, parallel-in-time, multiphysics coupling

WP2

Model Reduction & Scientific ML – Physics-driven deep learning, neural operators, data-driven ROM, reduced basis, multi-fidelity, super-resolution

WP3

Solvers – Mixed precision Krylov, data compression, variable accuracy, saddle point systems, partitioned multiphysics

Data & Decision

WP4

Inverse Problems & Data Assimilation – Deterministic/stochastic methods, observation strategies, multi-fidelity schedules, model updates

WP5

Optimization – Combinatorial/continuous, surrogate-based, shape optimization, AutoML at exascale

WP6

Uncertainty Quantification – Kernel-based sensitivity, UQ in PDE framework, surrogate modeling, acceleration on exascale

Integration & Coordination

WP7

Showroom & Benchmarking – Testing/benchmarking environment, CI/CD, verification/validation, co-design coordination, training materials

WP0

Project Management – Coordination, scientific/technical oversight, computing resources, communication, reporting

Latest News & Updates

Upcoming Events

January 2026
General Assembly 2026 – Progress review in Aix-en-Provence

February 2026
Trans-Numériques 2026 – France’s digital continuum conference

Stay informed about project milestones, publications, and community events:

Getting Started

Whether you’re a researcher, developer, or end user, find your entry point:

For Researchers

Start with Results and Impact to see our latest publications and scientific contributions

For Developers

Visit the Software Stack to explore packages, APIs, and CI/CD status

For Students

Check Training & Events for workshops and educational resources

For Partners

Learn about Consortium Partners and collaboration opportunities

Main Navigation

About Exa-MA

Resources and Updates