SASS is: the actual machine code that runs on NVIDIA GPU hardware

nvcc does: NVIDIA's CUDA compiler that produces PTX and SASS

nvcc compiles CUDA code to PTX and SASS

a Triton kernel is

Triton kernel: Python-based GPU programming that compiles to PTX

tensor cores are

Tensor cores are specialized hardware for matrix multiply-accumulate on GPU

Arm architecture family

ARM processors are the most widely used family of instruction set architectures

Parallel Thread Execution

PTX is an intermediate GPU instruction set used in Nvidia's CUDA

XLA does for TensorFlow/JAX: compiles computation graphs for TPU/GPU execution

XLA compiles computation graphs for TPU/GPU execution