Inverse problem Low-rank compression Modeling Block low-rank compression BEM Multicore architecture Topology Hybrid parallelization Level-set Turbulence Locality Lossy compression Accelerators Pipeline Analyse numérique Multicore architectures HPC Numerical detection Predictive Models Cutting and Packing Conjugate Gradient method OpenMP Task-based programming LU factorization FMM Task-based ALE Arbitrtary Lagrangian Eulerian Fault tolerance Adaptation de maillage High order scheme Aetiological lithiasis Integer programming DAG based runtime Runtime system Scheduling Absorbing Boundary Conditions Optical mapping Column Generation Programming model Mesh adaptation Data locality Asymptotic analysis Cholesky Factorization Sparse direct solvers Discontinuous Galerkin method Sparse linear solver Fluid mechanics Cholesky factorization Algorithms Runtime StarPU Distributed computing Accelerator Automatic recognition Penalization method Memory Contention Algorithmic Simulation Penalization Robustesse Fast multipole methods Sparse direct solver Domain decomposition Load balancing Fish-like swimming Heterogeneous architectures NUMA Branch-cut-and-price Soft-erreur Détection numérique Heterogeneous architecture Uncertainty Quantification Robustness Sensibilité Gradient Conjugué MPI Fast multipole method Robust optimization Multicore Processing High performance computing Pénalisation Deep learning Exascale Optimal transportation BGK model Discrete velocity model Sensitivity Routing Bandwidth Parallelism Placement Memory footprint Multicore AVX-512 Starpu-simgrid Bit-flip Collision model GPU Dense linear algebra Heterogeneous computing