Assignments

Labs

• Lab 0 - Survey

• Lab 1 – SIMD Mandelbrot

• Lab 2 – Massively-Parallel Mandelbrot

• Lab 3 – Wave Simulation

• Lab 4 – Matrix Multiply – Tiling and Reuse

• Lab 5 – Matrix Multiply – Improved Scheduling

• Lab 6 – Matrix Multiply – Tensor Cores

• Lab 7 – Run-Length Compression

Final Project

• Option 1 – Big Graph Processing – OpenMP

• Option 2 – Distributed Programming – MPI

• Option 3 – NanoGPT Attention - MLSys

• Option 4 – One Million Circles – CUDA

Telerun Information

• Telerun compiler information