CUDA & GPU Performance
Kernels, tiles, occupancy, and the roofline model. Covers launch overhead, shared-memory bank conflicts, async pipelines, FLOPs and memory estimates, and MFU so you can reason about GPU performance on paper.
12 problems
Your progress
0/12 · 0%Continue collection · Conv Kernel Tiling
Problems
- Easy
- Easy
- Easy
- Easy
- Medium
- Medium
- Medium
- Medium
- Medium
- Hard
- Hard
- Hard