High-Performance Embedded Computing

2.7 Additional CPU Mechanisms 109

fixed-point

method for

arithmetic

coding

A straightforward implementation of an arithmetic coder would require

floating-point arithmetic but a floating-point arithmetic unit is too slow, too

large, and too energy-intense to be used in the instruction decode path. Howard

and Vitter [How92] developed a table-based algorithm for arithmetic compres-

sion that requires only fixed-point arithmetic; an example is shown in

Figure 2-28. The table encodes the segments into which the number line has

been divided by the code.

Markov models Markov models are well-known statistical models. We use Markov models

in data compression t ...