Lab 7 & 8 - Parallel/GPU computing

Introduction¶

Welcome to the lab for the last two lectures - Parallel & GPU computing. It entails some independent work on the software you intend to use the cluster for. This task accounts for the last two labs, making it the last task you have to submit.

Task¶

You have to choose a software to analyze and also run using some method of parallelisation on the Rocket cluster. If you don't know which software to choose, a solid option would be PyTorch. For example, PyTorch could be executed with just parallel processing, with GPUs, or with both. There are good tutorials for these including steps for execution. For PyTorch you can also find an example in the cluster documentation. If you're having doubts about choosing something, ask the course team.

Since the software packages you select can be very different, there is no fixed agenda for this lab. Take your time and if you happen to have trouble, ask in Slack. For more general discussions, the labs can help you best.

The task is to answer the questions found in the lab document. You can download it as either a markdown file — which you can edit and fill in directly — or a PDF. Most of the questions require you to read the documentation of the software you are interested in. In the end there is also a practical section. You set up and execute your code. The markdown file has an extension of .txt so you can download it, but the correct extension here is actually .md, change this. There are many options for rendering markdown files and converting them to PDF, search Google and find a suitable one.

Submission¶

There is no automatic testing and the last day for submission is December 21, 2026 23:59. This way, there is enough time to review everything and fix any problems. The reports are graded as they come in, so submit earlier to get approved earlier. You can either answer the questions at the corresponding sections by editing the downloaded markdown (or PDF) file or in free form, but specify which point you're answering to. The submission should be done on the courses page.