High Performance Computing: Programming GPU using CUDA (Basic) PrerequisitesNew
Description
The course aims to give a very introductory overview of GPU Programming and CUDA language.
Target audience
- All current Cambridge University members (departments and colleges)
- Especially University alumni (PhD) and researchers
- Further details regarding eligibility criteria are available
Prerequisites
- Basic C knowledge is required
- Basic knowledge of Unix environment
- No required knowledge of GPU computer is needed
Topics covered
- GPU Programming in general
- Introduction and principles
- Basic GPU architecture design
- Basic CUDA
- Memory model
- Execution model
- Basic kernel: syntax and reserved words
- Data management allocation and deallocation
- Data movement: host-to-device/device-to host, sync and ascync transfers
- Runtime execution flow
- Basic overview of the tools (compiler options)
Format
- Presentations and short practicals at the end of the day
Taught using
- CUDA and PuTTY on MCS Windows
Notes
- The course is very introductory and propedeutical to those who want to continue learning GPU Computing
- It is a course for new learners, it is not recommended for people who had already previous experiences with CUDA
- HPCS users will have the opportunity to perform experiments directly to Wilkes
Duration
- One full day
Related courses
- Unix: Introduction to the Command Line Interface (Self-paced)
- High Performance Computing: An Introduction
- High Performance Computing: Programming GPU using Open ACC
Themes
Events available