Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Field
-
astroplasma simulations to GPU (in CUDA). The specific goals to be pursued within the 2-year time period (until the end of 2026) are rather well-defined by the milestones of the SPACE project, but the candidate
-
with a previous background on GPU computing are especially encouraged to apply. However, other research profiles, within the realm of computation physics, especially with a background in strongly
-
optimizing PIC algorithms for modern heterogeneous architectures, including CPUs, GPUs, and other accelerators, the project seeks to achieve unprecedented efficiency and resolution in plasma simulations
-
optimizing PIC algorithms for modern heterogeneous architectures, including CPUs, GPUs, and other accelerators, the project seeks to achieve unprecedented efficiency and resolution in plasma simulations
-
for modern heterogeneous architectures, including CPUs, GPUs, and other accelerators, the project seeks to achieve unprecedented efficiency and resolution in plasma simulations. This advancement will enable
-
, Probabilistic Inference, Algebraic Topology and Wavelet analysis theory. Familiar with Matlab/Python/C++ programming. Experience with Pytorch and multi-GPU model deployment. Experience in analyzing complex
-
, Probabilistic Inference, Algebraic Topology and Wavelet analysis theory. Familiar with Matlab/Python/C++ programming. Experience with Pytorch and multi-GPU model deployment. Experience in analyzing complex
-
Post-doctorate position (M/F) : Exascale Port of a 3D Sparse PIC Simulation Code for Plasma Modeling
further GPU porting. The exploration of C++ programming models for performance portability, such as Kokkos or StarPU, will form a second part. A comparative study will evaluate the different implementations
-
simulations, we utilize the high-performance LBM framework waLBerla, predominantly written in C++, but increasingly adapted for GPU computations through automatic code generation using Python scripts. In
-
heterogeneous architectures, including CPUs, GPUs, and other accelerators, the project seeks to achieve unprecedented efficiency and resolution in plasma simulations. This advancement will enable high-fidelity