nic hoffs

Nvidia GPU's

Nvidia GPU's have different hardware and CUDA abstractions. CUDA is the software platform. Hardware abstraction isn't exactly the right word to use – it's really the hardware layout and terminology associated with it.

Hardware Layout and Terminology

  1. Graphics Processing Clusters
  2. Streaming Multiprocessors
  3. CUDA/Tensor Cores

Software

  1. Grid
  2. Thread Blocks – assigned to Streaming Multiprocessors – this is the software/hardware interaction bridge.
  3. Threads - directly run the

Scheduling Terminology

  1. Warps – groups of 32 threads scheduled by an SM under the SIMT (Single Instruction, Multiple Threads) model – they share a program counter and execute in lockstep.