The Accelerators and Communications for HPC team leads cutting-edge research and development around accelerators/coprocessors in HPC. We are involved in low-level networking and MPI research, collaborating directly with leading vendors such as NVIDIA, Intel, or Huawei.
We collaborate closely with the two major accelerator/coprocessor vendors for HPC: NVIDIA and Intel. We organize locally international events such as the PUMPS Summer School, Courses on CUDA/OpenACC, and the Annual MNHACK, and collaborate in the organization of related international conferences and workshops such as SC, IEEE Cluster, or AsHES.
Key Duties
- To assist on research-oriented software developments and evaluations within our HPC networking / OpenMP offloading / MPI lines of research. This involves coding at system level (runtime systems, etc.) but also at application level so as to evaluate the developments
- To help on developing research papers targeting well-recognized venues
Data de tancament: Dijous, 31 Octubre, 2024
Més posts de Recerca
Cap comentari:
Publica un comentari a l'entrada