MULTI-BYTE LEMPEL-ZIV 1(LZ1) DECOMPRESSION

A method and arrangement are described for decompressing three or more bytes per processor cycle from a stream of compressed data using a processing pipeline, in which the compressed data is represented by tokens of varying and unknown length by accepting as input the stream of token data, partially decoding a token from the token data to determine a boundary position of the token; and priming the processing pipeline with the token and a length marker indicating the boundary position. Literal data is detected and output directly, copy pointers are checked to find their targets and resolved either from the history buffer or from the in-process contents of the pipeline.