Temporal and Spatial Program Hot Spot Visualization

Certain parts of computer programs are executed more often than others over the course of normal use. The most frequently visited portions of code are known as “hot spots.” It is usually in these regions where most optimization effort should be focussed. The problem of locating and identifying program hot spots is related to that of detecting program phase changes. Different phases in a program are distinguishable by the unique behavioural patterns they exhibit. Two methods of visualizing program hot spots and phase changes are discussed. The first method is a common technique that shows program activity relative to the position of the code in memory. The second technique uses a re-numbering scheme based on the order of appearance of indirect branches. A test suite of large object oriented programs are viewed and certain conclusions, based on empirical observations, are made about the relative merits and disadvantages of each visualization method.