Course/Event Essentials
Event/Course Start
Event/Course End
Event/Course Format
In person
Primary Event/Course URL
Training Content and Scope
Scientific Domain
Technical Domain
Level of Instruction
Intermediate
Advanced
Other
Sector of the Target Audience
Research and Academia
Industry
Public Sector
Other (general public...)
HPC Profile of Target Audience
Application Users
Application Developers
Data Scientists
System Administrators
Language of Instruction
Other Information
Organiser
Supporting Project(s)
EuroCC2/CASTIEL2
Event/Course Description
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
Participation in the course Introduction to Supercomputing Part I (Unix shell and remote access to supercomputers), and optionally Part II too.
The language of instruction is English.