Solutions for the 4th edition (2023) of Programming Massively Parallel Processors: a Hands-on Approach (PMPP).
Deep learning "path".
Chapter 2: Heterogeneous data parallel computing
Chapter 3: Multidimensional grids and data
Chapter 4: Compute architecture and scheduling
Chapter 5: Memory architecture and data locality
Chapter 6: Performance considerations
Chapter 7: Convolution
Chapter 16: Deep learning
Solutions are my own, and can't guarantee they are correct! Ping me on twitter to discuss or feel free to open an issue or PR.