{"id":16183480,"url":"https://github.com/Infatoshi/cuda-course","last_synced_at":"2025-10-24T12:31:03.767Z","repository":{"id":247428341,"uuid":"825800641","full_name":"Infatoshi/cuda-course","owner":"Infatoshi","description":null,"archived":false,"fork":false,"pushed_at":"2025-01-04T06:11:10.000Z","size":32723,"stargazers_count":726,"open_issues_count":2,"forks_count":114,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-01-04T07:26:02.917Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Cuda","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Infatoshi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-07-08T14:20:35.000Z","updated_at":"2025-01-04T06:11:14.000Z","dependencies_parsed_at":"2024-09-10T02:07:49.253Z","dependency_job_id":"3e4c8c7b-5daa-4e25-bf91-8718d265c813","html_url":"https://github.com/Infatoshi/cuda-course","commit_stats":null,"previous_names":["infatoshi/cuda-course"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Infatoshi%2Fcuda-course","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Infatoshi%2Fcuda-course/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Infatoshi%2Fcuda-course/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Infatoshi%2Fcuda-course/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Infatoshi","download_url":"https://codeload.github.com/Infatoshi/cuda-course/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237964504,"owners_count":19394413,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-10T07:01:27.645Z","updated_at":"2025-10-24T12:31:02.230Z","avatar_url":"https://github.com/Infatoshi.png","language":"Cuda","readme":"# CUDA Course\n\nGitHub Repo for CUDA Course on FreeCodeCamp\n\n\u003e Note: This course is designed for Ubuntu Linux. Windows users can use Windows Subsystem for Linux or Docker containers to simulate the ubuntu Linux environment.\n\n## Table of Contents\n\n1. [The Deep Learning Ecosystem](01_Deep_Learning_Ecosystem/README.md)\n2. [Setup/Installation](02_Setup/README.md)\n3. [C/C++ Review](03_C_and_C++_Review/README.md)\n4. [Gentle Intro to GPUs](04_Gentle_Intro_to_GPUs/README.md)\n5. [Writing Your First Kernels](05_Writing_your_First_Kernels/README.md)\n6. [CUDA APIs (cuBLAS, cuDNN, etc)](06_CUDA_APIs/README.md)\n7. [Optimizing Matrix Multiplication](07_Faster_Matmul/README.md)\n8. [Triton](08_Triton/README.md)\n9. [PyTorch Extensions (CUDA)](08_PyTorch_Extensions/README.md)\n10. [Final Project](09_Final_Project/README.md)\n11. [Extras](10_Extras/README.md)\n\n## Course Philosophy\n\nThis course aims to:\n\n- Lower the barrier to entry for HPC jobs\n- Provide a foundation for understanding projects like Karpathy's [llm.c](https://github.com/karpathy/llm.c)\n- Consolidate scattered CUDA programming resources into a comprehensive, organized course\n\n## Overview\n\n- Focus on GPU kernel optimization for performance improvement\n- Cover CUDA, PyTorch, and Triton\n- Emphasis on technical details of writing faster kernels\n- Tailored for NVIDIA GPUs\n- Culminates in a simple MLP MNIST project in CUDA\n\n## Prerequisites\n\n- Python programming (required)\n- Basic differentiation and vector calculus for backprop (recommended)\n- Linear algebra fundamentals (recommended)\n\n## Key Takeaways\n\n- Optimizing existing implementations\n- Building CUDA kernels for cutting-edge research\n- Understanding GPU performance bottlenecks, especially memory bandwidth\n\n## Hardware Requirements\n\n- Any NVIDIA GTX, RTX, or datacenter level GPU\n- Cloud GPU options available for those without local hardware\n\n## Use Cases for CUDA/GPU Programming\n\n- Deep Learning (primary focus of this course)\n- Graphics and Ray-tracing\n- Fluid Simulation\n- Video Editing\n- Crypto Mining\n- 3D modeling\n- Anything that requires parallel processing with large arrays\n\n## Resources\n\n- GitHub repo (this repository)\n- Stack Overflow\n- NVIDIA Developer Forums\n- NVIDIA and PyTorch documentation\n- LLMs for navigating the space\n- Cheatsheet [here](/11_Extras/assets/cheatsheet.md)\n## Other Learning Material\n\n- https://github.com/CoffeeBeforeArch/cuda_programming\n- https://www.youtube.com/@GPUMODE\n- https://discord.com/invite/gpumode\n\n## Fun YouTube Videos:\n- [How do GPUs works? Exploring GPU Architecture](https://www.youtube.com/watch?v=h9Z4oGN89MU)\n- [But how do GPUs actually work?](https://www.youtube.com/watch?v=58jtf24uijw\u0026ab_channel=Graphicode)\n- [Getting Started With CUDA for Python Programmers](https://www.youtube.com/watch?v=nOxKexn3iBo\u0026ab_channel=JeremyHoward)\n- [Transformers Explained From The Atom Up](https://www.youtube.com/watch?v=7lJZHbg0EQ4\u0026ab_channel=JacobRintamaki)\n- [How CUDA Programming Works - Stephen Jones, CUDA Architect, NVIDIA](https://www.youtube.com/watch?v=QQceTDjA4f4\u0026ab_channel=ChristopherHollinworth)\n- [Parallel Computing with Nvidia CUDA - NeuralNine](https://www.youtube.com/watch?v=zSCdTOKrnII\u0026ab_channel=NeuralNine)\n- [CPU vs GPU vs TPU vs DPU vs QPU](https://www.youtube.com/watch?v=r5NQecwZs1A\u0026ab_channel=Fireship)\n- [Nvidia CUDA in 100 Seconds](https://www.youtube.com/watch?v=pPStdjuYzSI\u0026ab_channel=Fireship)\n- [How AI Discovered a Faster Matrix Multiplication Algorithm](https://www.youtube.com/watch?v=fDAPJ7rvcUw\u0026t=1s\u0026ab_channel=QuantaMagazine)\n- [The fastest matrix multiplication algorithm](https://www.youtube.com/watch?v=sZxjuT1kUd0\u0026ab_channel=Dr.TreforBazett)\n- [From Scratch: Cache Tiled Matrix Multiplication in CUDA](https://www.youtube.com/watch?v=ga2ML1uGr5o\u0026ab_channel=CoffeeBeforeArch)\n- [From Scratch: Matrix Multiplication in CUDA](https://www.youtube.com/watch?v=DpEgZe2bbU0\u0026ab_channel=CoffeeBeforeArch)\n- [Intro to GPU Programming](https://www.youtube.com/watch?v=G-EimI4q-TQ\u0026ab_channel=TomNurkkala)\n- [CUDA Programming](https://www.youtube.com/watch?v=xwbD6fL5qC8\u0026ab_channel=TomNurkkala)\n- [Intro to CUDA (part 1): High Level Concepts](https://www.youtube.com/watch?v=4APkMJdiudU\u0026ab_channel=JoshHolloway)\n- [Intro to GPU Hardware](https://www.youtube.com/watch?v=kUqkOAU84bA\u0026ab_channel=TomNurkkala)\n\n## Find me\n\n- [Twitter/X](https://x.com/elliotarledge)\n- [LinkedIn](https://www.linkedin.com/in/elliot-arledge-a392b7243/)\n- [YouTube](https://www.youtube.com/channel/UCjlt_l6MIdxi4KoxuMjhYxg)\n- [Discord](https://discord.gg/JTTcFe7Pw2)\n","funding_links":[],"categories":["A01_机器学习教程","Cuda"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FInfatoshi%2Fcuda-course","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FInfatoshi%2Fcuda-course","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FInfatoshi%2Fcuda-course/lists"}