Just like a CPU, the GPU relies on a memory hierarchy—from RAM, through cache levels—to ensure that its processing engines are kept supplied with the data they need to do useful work. And just like the cores in a CPU, the streaming multiprocessors (SMs) in a GPU ultimately require the data to be in registers to be available for computations. This topic looks at the sizes and properties of the different elements of the GPU's memory hierarchy and how they compare to those found in CPUs.