Sort by
Refine Your Search
-
Listed
-
Category
-
Program
-
Employer
-
Field
-
available hardware accelerator platforms. The most cost-efficient and energy-efficient way to build this correlator system is with FPGAs near the receivers, tensor-core-enabled GPUs for correlations, and an
-
processor topology. On modern servers, Non-Uniform Memory Access (NUMA) architectures and GPU accelerators introduce asymmetric memory access costs that remain largely invisible to application-level code yet
-
différents types de parallélisme, que ce soit au niveau d'un nœud de calcul (CPU et GPU) qu'au niveau d'une grappe de PC. Cet environnement inclura les outils nécessaires à la description et à la construction
-
-field code, written in the Cuda C language and parallelized on a single GPU (Graphical Processor Unit). A parallelization on multiple GPUs would be a welcome development during the thesis. Where to apply
-
, Z. Ye, P. Sun, X. Wang, Y. Luo, T. Zhang, and Y. Wen, “Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision,” arXiv preprint arXiv:2205.11913, 2022. [5] J. Lin, W.-M
-
bioimaging and bioinformatics team at IBENS, under the supervision of Auguste Genovesio. The postdoctoral researcher will have access to a workstation as well as computing servers equipped with GPUs. Where
-
highly-motivated candidate, skilled in numerical model development (programming in FORTRAN, numerical methods, HPC environment). Experience in numerical methods on unstructured grids and/or GPU would be
-
fonctionnant sur CPU et GPU, cette thèse de doctorat vise à caractériser la dynamique de ces ondes de choc, leur évolution à long terme et leur signature observationnelle. Cette thèse est financée par une bourse
-
platforms and our local CPU and GPU clusters; implementing Python tools for automating CSP/DFT calculations; - Participation in the scientific activities of the Applied Quantum Chemistry group (IC2MP) and the
-
variety of computational devices (e.g. CPUs and GPUs) while ensuring overall consistency and performance. - contribute to identify new CSE applications domains, such as condensed matter systems, quantum