srush/GPU-Puzzles
Solve puzzles. Learn CUDA.
This interactive notebook teaches you how to write GPU code to speed up computation, crucial for modern machine learning. You'll solve coding puzzles using a Python-like syntax that directly translates to low-level GPU instructions. This is for machine learning engineers or researchers who want to understand the core GPU algorithms behind deep learning without diving into complex manuals.
11,992 stars. No commits in the last 6 months.
Use this if you are a machine learning practitioner wanting to quickly gain hands-on intuition for how GPUs execute code.
Not ideal if you are looking for a high-level library or framework to optimize your machine learning models without understanding the underlying GPU operations.
Stars
11,992
Forks
930
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/srush/GPU-Puzzles"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
brucefan1983/GPUMD
Graphics Processing Units Molecular Dynamics
iree-org/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
uxlfoundation/oneDAL
oneAPI Data Analytics Library (oneDAL)
rapidsai/cuml
cuML - RAPIDS Machine Learning Library
NVIDIA/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra