Cache-based data compression/decompression

摘要

A system for compressing bilevel data includes a first cache memory having a plurality of assigned levels of usage, a first usage level assigned to a most recently used data segments and a second level assigned to a plurality of less recently used data segments. A processor determines if a received data segment is found in the cache memory and, if not, it assigns the received data segment to the cache memory's first level in place of a previous data segment stored therein. The previous data segment is assigned to a position in the second level in place of a less recently used data segment. The less recently used data segment that is displaced is chosen by a pseudo-random method. A not-found indication is then transmitted to a receiving station along with the identity of the received data segment. The receiving station contains identical cache structures and updates its caches in response to received code words and data segments. A further version of the invention emplaces data segments into cache memories in accordance with the context in which the data segments are found, the cache memories being assigned in accordance with context derived addresses.