CUDA Graphs - Intro & Basics
Topics covered in this part:
- how normal CPU ↔ GPU execution works
- what a kernel launch is and where CPU launch overhead comes from
- why launching many small kernels individually can become a bottleneck
- what CUDA Graphs are and how they reduce CPU launch overhead
- common benefits of using CUDA Graphs
- the two ways to create CUDA Graphs:
- Explicit Graph Construction
- Stream Capture
- where these graph creation methods are used
- the CUDA Graph lifecycle:
- capture → instantiate/prepare → replay