Courses
- Lecture 31: Beginner’s guide to Metal kernels https://github.com/gpu-mode/lectures/tree/main/lecture_031
Papers
- Apple vs. Oranges: Evaluating the Apple Silicon M-Series SoCs for HPC Performance and Efficiency https://arxiv.org/abs/2502.05317
Tutorials
Optimizing a WebGPU Matmul Kernel for 1TFLOP+ Performance https://www.nuss-and-bolts.com/p/optimizing-a-webgpu-matmul-kernel
Exploratory
Setting up metal-cpp:
- WWDC22: Program Metal in C++ with metal-cpp | Apple https://www.youtube.com/watch?v=h1mOkhFOSPU
- Get started with Metal-cpp https://developer.apple.com/metal/cpp/
Difference between NVIDIA/CUDA ecosystem and M-Series/Metal ecosystem
https://chatgpt.com/share/67e4c20a-6160-8010-89cc-aaa3e9a6586c