Translator Disclaimer
Chapter 8:
Optimization Techniques
In general, to achieve optimal performance in -image processing algorithms, designers attempt to match the hardware to the problem; for example, they use the parallel architectures discussed in Chapter 6. Failing this, a variety of techniques used in conjunction with high-level languages are employed to squeeze additional performance from the machine. These techniques include the use of assembly language patches and hand-tuning compiler output. Often, however, use of these practices leads to code that is unmaintainable and unreliable because it is poorly documented. More desirable, then, is to use coding tricks that involve direct interaction with the high-level language and that can be documented. These tricks improve real-time performance, but generally not at the expense of maintainability and reliability. Note that when optimizing average-case performance, worst-case performance is generally adversely affected. In this chapter we discuss how to calculate one measure of real-time performance, CPU utilization_. We then show how to use high-level languages in the best possible manner to achieve optimal performance.
Online access to SPIE eBooks is limited to subscribing institutions.

Back to Top