Encoding and decoding speed optimization method of lz series compression algorithm

Abstract

The invention relates to a coding and decoding speed optimization method of LZ series compression algorithm. When data is coded, the data slice whose length is the word length of the computer is matched at one time, and the number of CPU cycles required for matching repeated data segments is reduced; unmatched data is accumulated and copied in batches To the encoding output buffer area, reducing the number of CPU cycles and additional overhead required for data copying; when decoding data, the current data is obtained by repeated copying based on historical data. If the length of the data to be copied is less than the distance between the current position and the historical data position, Direct batch copy; if it is greater than that, then adopt the method of cyclic batch copy, the historical data location remains unchanged, the current location is updated with each cycle, and the data length of each cycle batch copy is not greater than the distance between the current location and the historical data location The distance between data copies reduces the number of CPU cycles and overhead required for data copying. The invention effectively reduces the encoding and decoding time of the LZ series compression algorithm without reducing the compression rate of the algorithm.

Description

technical field [0001] This patent application belongs to the technical field of encoding and decoding, and more specifically relates to a method for optimizing the encoding and decoding speed of LZ series compression algorithms. Background technique [0002] The era of cloud computing is inseparable from the processing and transmission of massive data. The transmission of massive data often requires a large network bandwidth, and once there is a problem in data transmission, it will seriously affect the overall performance of the cloud computing center. In order to improve the transmission performance of massive data, it is often necessary to perform data compression before data transmission, and reduce the total amount of data to be transmitted through lossy / lossless compression algorithms. In general, data such as numbers, text, synthetic images, and medical images tend to use lossless compression, while data such as natural images, audio, and video tend to use lossy comp...

AI Technical Summary

Problems solved by technology

The patent also focuses on achieving higher compression ratios, but operations such as comparison, rearrangement, and re-encoding bring additional computational overhead and require longer compression operations

Images