If you are comfortable submitting jobs on HPC systems and managing input and output data on the file systems, this course will help you utilize the system’s computing capacity by running parallel jobs effectively.
What will you learn in this training?
In this training, you will:
- learn the fundamentals of performance analysis
- understand the key Slurm parameters for parallel job scheduling, including threads, cores, sockets, nodes, and processes
- perform practical exercises on the national supercomputer Snellius to execute tightly coupled parallel tasks
- learn about the characteristics of embarrassingly parallel jobs and techniques to efficiently handle concurrency engage in practical exercises using QCG Pilotjob.
For whom?
This course is suitable for anyone with a basic understanding of cluster computing who wants to improve their ability to run parallel jobs efficiently on supercomputers.
Prerequisites
You should have:
Your own laptop with an up-to-date browser and a terminal emulator. The use of the operating systems Linux and macOS is preferred, but not mandatory. For Windows users we recommend to download MobaXterm (portable version) as terminal emulator.