Get the latest tech news
GPU Puzzles
Solve puzzles. Learn CUDA. Contribute to srush/GPU-Puzzles development by creating an account on GitHub.
This notebook is an attempt to teach beginner GPU programming in a completely interactive fashion. Tip: The most efficient algorithm here will copy a block into shared memory before computing each of the individual row-column dot products. Then update your code to compute a partial dot-product and iteratively move the part you copied into shared memory.
Or read this on Hacker News