Scratchpad memory (SPM), often known as scratchpad, scratchpad RAM or native store in pc terminology, is an inner memory, usually high-pace, used for short-term storage of calculations, data, and other work in progress. In reference to a microprocessor (or CPU), scratchpad refers to a special high-pace memory used to carry small items of information for speedy retrieval. It's similar to the utilization and measurement of a scratchpad in life: a pad of paper for preliminary notes or sketches or writings, and so forth. When the scratchpad is a hidden portion of the primary Memory Wave Experience then it is generally known as bump storage. L1 cache in that it's the subsequent closest memory to the ALU after the processor registers, with express directions to maneuver information to and from foremost memory, usually utilizing DMA-primarily based knowledge switch. In contrast to a system that uses caches, a system with scratchpads is a system with non-uniform memory entry (NUMA) latencies, as a result of the memory access latencies to the totally different scratchpads and the primary memory fluctuate.

Another difference from a system that employs caches is that a scratchpad commonly doesn't comprise a copy of information that can be stored in the primary memory. Scratchpads are employed for simplification of caching logic, and to guarantee a unit can work without foremost memory contention in a system employing a number of processors, particularly in multiprocessor system-on-chip for embedded programs. They're mostly fitted to storing momentary outcomes (because it could be discovered within the CPU stack) that sometimes would not have to at all times be committing to the principle memory

Edit

Pub: 25 Nov 2025 15:31 UTC

Views: 4