Date(s) - 2018-05-07
09:30 CEST - 14:30 CEST
EMBL Heidelberg, Room 202
This course provides a hands-on introduction to cluster/high performance computing using the resources available at EMBL. After introducing the important concepts, the course will focus on hands-on exercises and examples, giving participants an opportunity to become familiar with working in a cluster enviornment. Participants will also learn about recommended practices when using the compute cluster, and receive advice on how best to use this powerful resource in their work.
- Introduction: core concepts AKA What is a cluster? What is a job scheduler?
- Scheduling jobs
- Job management
- Requesting resources
- Accessing specialist software
- Notifications and reporting
- Debugging: why isn’t my job running? Why did my job fail?
- Best practices
This course is intended for scientists using command line tools/software in their research, who would like to learn to use the HPC cluster to increase the scale and/or decrease the duration of their computational analyses/tasks. Course participants are expected to have some prior experience of working on the Linux/Mac command line and writing scripts (e.g. in R, Python, Bash, etc). If you are already familiar with the fundamentals of cluster computing, you may not gain a lot from this training and might prefer to attend one of the planned intermediate and/or advanced courses in this area.
Course participants are expected to bring their own laptop along to the course. The laptop must be capable of connecting to the EMBL cluster via
ssh in the shell. Participants are expected to have some prior experience of working on the Linux/Mac command line and writing scripts (e.g. in R, Python, Bash, etc). For those wanting to gain more experience of these before the course, relevant Bio-IT/EMBL Centres course materials are available.
If you have any questions about the course, please don’t hesitate to contact Toby Hodges, Mike Smith, and/or Jure Pečar.
This event is fully booked.