GPU Internals: A Speed Run
This article is mostly focussed on CUDA devices. From here onwards whenever I mention GPU know it to be CUDA by NVIDIA. All the notes that have been collected are for my self study. I will put sources below GPU Architecture CUDA stands for Compute Unified Device Architecture. Figure adapted from the Modal GPU Glossary. GPU instructions are carried out by streaming multiprocessors (SMs). An SM in NVIDIA is analogous to a CPU core. SMs execute computation and store state for computation in registers and caches. ...