M6: Understanding Tensor Core Architecture

In this sixth module, we will focus on tensor cores in CUDA and how various classes of applications can benefit from their acceleration capabilities, especially in the domains of AI/Machine learning to HPC.

Pre-recorded Lectures

Note: The pre-recorded videos for M6 will be posted after Tuesday’s lecture.

There will be no additional recordings for this last module.

All slide and code materials will be accessible via the course repository.

Synchronous Session (In-Person Lecture)

As a reminder here are the dates and times for the synchronous session for this module:

Week 9

  • Dates/Times

    • Tuesday May 20th @ 5:30pm-7:20pm

  • Session Outline

    • Dynamic Parallelism

    • Introduction to Tensor Core Architecture

    • Course Recap

Assignment