Programming on parallel architectures

HPC Project offers theoretical and practical training sessions to help customers mastering programing on parallel architectures. Training sessions can be organized in Paris or Montpellier (normal package) or onsite. Please contact us regarding specific demands in training.

Programming on parallel architectures (3 days)

The “programming on parallel architectures” course provides you with the concrete bases to tackle HPC programming on your applications with:

• architectural background of parallel computers (SIMD, MIMD, vector, multicores, GPU, Cell), shared or distributed memory, networks, power consumption, storage and I/O;
• parallel concepts with concurrent programming, parallel algorithmics, design patterns, parallelization, memory organization;
• parallel programming with parallel libraries, multithread programming (OpenMP, TBB), GPU Computing with CUDA and Open CL, message passing programming (MPI), splitted-address space languages;