Provides efficient lossless compression for small blocks of data in processor-based systems

摘要

Providing efficient lossless compression for small blocks of data in processor-based systems is provided. In an aspect, a method includes receiving a plurality of input words. To generate a corresponding plurality of patterns, each mask of a plurality of masks is applied to each unassigned input word. For each mask, if the most frequently occurring pattern is present in the plurality of patterns, the most frequently occurring pattern, associated with the prefix associated with the mask, and the uncompressed data portion of each unassigned input word Is stored. The prefix is also assigned to each unassigned input word corresponding to the most frequently occurring pattern. A compressed output block is generated and the compressed output block includes prefixes assigned to a plurality of input words, most frequently occurring patterns associated with assigned prefixes, and one or more input words of a plurality of input words Lt; / RTI corresponding to the uncompressed data portions.