Francis A. Kampf

Performance as a function of compression

This paper discusses the performance of bilevel-image arithmetic coders, ABIC and JBIG, and Lempel-Ziv string compressors, ALDC and BLDC. Images are analyzed for typical and worst-case throughput and latency as a function of compression. A relationship between the compressibility of an image and the throughput performance of the compression algorithm is demonstrated. Generally, throughput performance of the bilevel-image arithmetic coders decreased as image entropy increased. Inversely, the bilevel-image string compressor (BLDC) revealed that increased entropy improved throughput performance. Experimental results based on hardware implementations have been provided and analyzed.

Design considerations for the ALDC cores

The IBM adaptive lossless data compression (ALDC) family of products uses a derivative of Lempel-Ziv encoding to compress data. Several variables affect the compression performance of the ALDC algorithm: data content, history size, and data extent. As ALDC compression is integrated into different applications, restrictions are placed upon these variables that affect the overall compression performance of the system. More complex applications require further support for higher-order data structures such as variable-length segments, error recovery, and expansion. The IBM Blue Logic ALDC and embedded lossless data compression (ELDC) cores have been developed to work in these application environments. These cores and the issues associated with integrating data compression into a system are discussed.