Introduction to GPUs on Argus (Win10): Glossary

Key Points

Intro to GPU computing

  • GPU vs CPU

  • Suitable problems for GPU

  • CUDA, and high level GPU environments

  • Where to get one
Confirming your GPU environment and setup

  • Check GPU card is installed and working

  • Check CUDA is installed

  • Confirm CUDA and your GPU device driver are compatible

  • Check Visual Studio is installed
Visual Studio basics

  • Basics of VS including build, run and debug

  • Finding out the specs for your GPU by running deviceQuery

  • Compiled vs Interpreted programming languages

  • GPU advantages and disadvantages
A simple GPU example, vector addition

  • Input data must be copied from CPU (host) to GPU (device).

  • Kernels are run in parallel while errors are caught.

  • Output data must be copied from GPU (device) back to CPU (host).
Advanced CUDA examples

  • There are a lot of CUDA examples but sometimes your GPU will not support all the functionality

  • Not all GPUs are compliant with all software
Logging out of Argus

  • What happens if you disconnect or logout INCORRECTLY

  • What happnes if you signout CORRECTLY

Glossary

FIXME