High Performance Computing: Programming GPU using CUDA (Basic)

PrerequisitesNew

The course aims to give a very introductory overview of GPU Programming and CUDA language.

• All current Cambridge University members (departments and colleges)
• Especially University alumni (PhD) and researchers
• Further details regarding eligibility criteria are available

• Basic C knowledge is required
• Basic knowledge of Unix environment
• No required knowledge of GPU computer is needed

Number of sessions: 2

• 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)

• Presentations and short practicals at the end of the day

• CUDA and PuTTY on MCS Windows

• 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

• One full day

• Unix: Introduction to the Command Line Interface (Self-paced)
• High Performance Computing: An Introduction
• High Performance Computing: Programming GPU using Open ACC

• High Performance Computing
• Programming and Scripting
• Scientific Computing
• UIS Systems