Memory mapping in cache

• Is a technique that defines how contents of main memory are brought into cache memory

• Cache memory and main memory are divided into small fixed sized blocks

• Cache memory can hold only a small subset of main memory blocks

• An algorithm is needed for mapping main memory blocks into cache blocks

Cache memory mapping techniques

• Direct Mapping

• Associative mapping

• Set associative mapping

Address Division

Associative Mapping

• A flexible mapping

• A memory block can reside in any cache block

All blocks in the cache are freely available, then any block of main memory can map to any block of cache

• If all the cache blocks are occupied then one of the existing blocks will be replaced

A replacement algorithm is required, which suggests the block to be replaced

• Eg: FCFS, LRU etc.

Address Division

Set Associative Mapping

• A combination of direct mapping and associative mapping

• Blocks of cache are grouped into sets, and the mapping allows the block of main memory to reside in any block of specific set

. Within a set a main memory block can be mapped to any of the available cache blocks

Block j of main memory is mapped to the cache block (j modulo m) where m is the number of sets in the cache

• It requires a replacement algorithm, because, inside a set, it follows associative mapping

Address Division