Learning CUDA From Scratch: A 100-Problem Curriculum for GPU Programming and HPC Engineering
Summary
A structured GitHub repository offering 100 progressive problems to learn CUDA GPU programming, from basic "Hello World" kernels to production-grade GPU code. The curriculum targets beginners with basic C/C++ knowledge and covers environment setup through real domain applications in deep learning, scientific computing, and HPC. Each problem includes the operation, expected time, learning objective, and test/profiling targets.
Source
Twitter / XLearning CUDA From Scratch: A 100-Problem Curriculum for GPU Programming and HPC Engineeringgithub.comKey quotes
· 5 pulled100 Problems to Become an HPC Engineer
A structured, problem-by-problem path from 'Hello World' CUDA kernels to production-grade GPU code.
This repo is a self-paced curriculum for learning GPU programming with CUDA — starting from environment setup and ending with real domain applications in deep learning, scientific computing, and HPC.
It's built for beginners with basic C/C++ knowledge who want a guided, hands-on route into GPU computing.
Every problem lists the operation, expected time, key learning objective, and (where relevant) test cases or profiling targets
You might also wanna read
Awesome CUDA Books: A Curated List of GPU Programming Resources
A curated GitHub repository listing major CUDA programming books ranging from beginner to advanced levels. The list covers C++/Python approa
github.com·1mo ago
GPU Programming Project: Implementing Parallelizable RNNs with CUDA
A student's final project for CS179: GPU Programming implementing the paper "Were RNNs All We Needed?" by Feng et al. The project focuses on
dhruvmsheth.github.io·9mo ago
nanoeuler: A GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop and FlashAttention
A developer has built a GPT-2-class language model entirely from scratch in C/CUDA without using any machine learning libraries like PyTorch
github.com·9d ago
AI-Driven Approach for Portable GPU Kernels in High-Performance Computing
This academic paper from North Carolina State University researchers presents an approach to leveraging AI ecosystems for creating portable
hgpu.org·21d ago
Building a Vulkan Game Engine: A 3-Month Learning Journey with Practical Implementation
A developer shares their 3-month journey learning Vulkan graphics API from scratch and building a small game engine with two demo games. The
Implementing Flash Attention for NVIDIA 5090 GPUs with CUDA C++
A technical tutorial explaining how to implement Flash Attention for NVIDIA 5090 GPUs using CUDA C++. The author shares their learning journ
gau-nernst.github.io·10mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.