cambridge-iccs / cudalabmorning

Morning session for CUDA lab

Introduction to CUDA Lab

Accelerators such as GPUs are prevalent both within personal computing as well as within high performance computing systems. Compared with traditional CPU architectures, performance is leveraged through a design which favours a high number of parallel compute cores at the expense of imposing significant software challenges.

This introductory lab is designed to follow lectures which provide some insight into GPU architectures and insight into developing GPU code using CUDA.

To get started you will need a Python environment with the jupyterlab package installed. The preferred method is to install this inside a virtual environment.

You can then launch the notebook using

jupyter-lab LabExercise.ipynb

cudalabmorning's Issues

Level and pace

Is the level and pace of this course appropriate to the audience? I am used to much more handholding (including links and step by step commands for setup etc) in courses, assuming that the audience might have no prior experience with the topic and might, potentially, not be very technical.

I suppose we can assume a technical audience with programming experience here? I am still wondering whether providing a quick start guide (with commands to copy and paste for the venv, installing jupyterlab, and what else is required - nvcc) might make thinks go more smoothly on the day.