Training#
Objectives:
Getting familiar with High Performance Computing cluster environment architectures: e.g. Shaheen , Ibex , Neser
Getting familiar with the HPC software ecosystems
Introduction on job scheduling on different HPC environments
Provide suggestions and advise on how to execute your application (e.g. SLURM constrains, workflows, job-dependencies etc.)
How to run different types of jobs (e.g OpenMP , MPI and CUDA jobs )
Tips and tricks and Dos and Don’ts targeted to achieve the best performance for your workloads on the underlying architecture