4 free CUDA resources to learn GPU programming from scratch, from NVIDIA to Oxford
techNmak · x · 2026-10-19
Four free resources for learning GPU programming from zero: (1) NVIDIA's official Modern CUDA C++ course with lectures, slides and notebooks on parallel algorithms, CUDA streams and kernel writing; (2) freeCodeCamp's 12-hour CUDA course by Elliot Arledge, from setup through kernels, memory management, matrix multiplication and custom PyTorch ops; (3) University of Illinois' Applied Parallel Programming covering execution/memory models, tiling, reductions, scans and convolution; (4) Oxford's CUDA Programming on NVIDIA GPUs with free slides and exercises by Mike Giles and Wes Armour.
More from Infra
- AI Toolkit adds LoRA training for Qwen 3.8 27B: 70-80 tok/s captioning under 20GB VRAM on RTX 5090 — ostrisai · 2026-10-19
- Local LLM on a gaming laptop: Qwen 27B hits 441 tok/s prefill but only 9.1 tok/s decode on RTX 5080 — draginol · 2026-10-19
- vLLM is now ~2x faster thanks to agentic-generated fused model definitions — mohbibi_ · 2026-10-19
- Microsoft reportedly returns ~10% of GPUs contracted from Nscale in hyperscaler power play — abhiadesai · 2026-10-19
- Photonic chip critique: heterogeneous coupling remains the bottleneck — one chip per 4-inch wafer — jwt0625 · 2026-10-19
- Bindu Reddy: NeoClouds Like CoreWeave May Be Better Off Declaring Bankruptcy — bindureddy · 2026-10-19