Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Field
-
scientists and engineers are accustomed to. Moreover, the vast majority of the performance associated with these reduced precision formats resides on special hardware units such as tensor cores on NVIDIA GPUs
-
to support computations on GPU hardware with various types of Finite Element methods. This work is embedded in a research project considering structure preserving Finite Element methods for multiphase flows
-
algorithms. The post-doc will carry out theoretical work on causal abstraction and causal alignment, implement algorithms and experimental pipelines in Python/PyTorch, and run experiments on GPU clusters
-
time steps, will be explored. For these two projects, the GPU-based version of SCHISM under development will also be tested. Type of recruitment 12-month postdoctoral contract based in La Rochelle (17
-
-atmosphere dynamics. We will build an AI-enabled modeling system that couples a GPU-optimized ocean model with a biogeochemical module and AI-based, kilometer-scale atmospheric forecasts. This system will
-
frameworks, e.g., Caffe, TensorFlow, PyTorch, and GPU-acceleration frameworks, e.g., CUDA will be a plus. Outstanding SW development and programming skills in C++, Python, ROS tools and libraries. Excellent
-
programming in C++ and Python. - Mandatory mastery of GPU programming (CUDA) for optimization. - Experience with Deep Learning frameworks (PyTorch). - Knowledge of the AliceVision architecture is a major asset
-
-atmosphere dynamics. We will build an AI-enabled modeling system that couples a GPU-optimized ocean model with a biogeochemical module and AI-based, kilometer-scale atmospheric forecasts. This system will
-
their publications Experience programming GPUs with CUDA, SYCL, HIP or OpenMP Experience using and developing code with AMReX Experience in performance engineering to improve code scalability and reduce time-to
-
will benefit from the Jean Zay supercomputer to perform intensive GPU calculations but also MARBEC/LIRMM GPU shared resources (https://umr-marbec.fr/recherche/dispositifs-de-recherche/den/ ). His/her