Matrix Multiply

The canonical GPGPU workload: from naive triple loop to a kernel that scales.

5 tasks

1. One Cell, One Dot Product
2. The Full Grid: Matrix × Matrix
3. Rectangular: Three Different Sizes
4. Transpose: Swap the Axes
5. One Kernel, Any Size

Start this module →

This page is an interactive exercise — the editor, the GPU runner and your saved progress need JavaScript. The text above is the full brief.