Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Video course · 12 chapters · 715 min · certificate

CUDA Programming Course – High-Performance Computing with GPUs

A freeCodeCamp CUDA course: the deep learning ecosystem, CUDA setup, a C/C++ refresher, how GPUs work, writing kernels, the CUDA API, fast matrix multiplication, Triton, PyTorch extensions and a final MNIST MLP project.

Become a memberAlready a member? Sign in

What you'll learn

  • Set up a CUDA environment
  • Explain GPU architecture
  • Write CUDA kernels
  • Use the CUDA API and libraries
  • Optimise matrix multiplication
  • Use Triton and PyTorch extensions

Chapters

12 chapters · 715:11
  1. 16:52 01Intro Members Intro GPUs for HPC.
  2. 20:51 02Ecosystem Members Deep learning ecosystem Where CUDA fits.
  3. 9:20 03Setup Members CUDA setup Environment.
  4. 48:44 04C/C++ Members C/C++ review Prerequisites.
  5. 15:53 05GPUs Members Intro to GPUs How they work.
  6. 123:46 06Kernels Members Writing your first kernels Threads and blocks.
  7. 99:56 07API Members The CUDA API Libraries and calls.
  8. 167:14 08Matmul Members Faster matrix multiplication Optimisation.
  9. 42:07 09Triton Members Triton Higher-level kernels.
  10. 13:27 10Extensions Members PyTorch extensions Custom ops.
  11. 143:03 11Project Members MNIST MLP project Final project.
  12. 13:58 12Wrap-up Members Next steps and outro Keep going.