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