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