Visualizing code profiling line oriented statistics

Abstract

Code tuning is a well-known technique for improving the run-time performance of software. There are several widely used profilers available that show the heavily used functions. Other profilers provide fine grain profiling detail such as basic block counts. The difficulty in using fine grain profilers is coping with the large volumes of data that they generate.We describe a visualization technique that enables us to display and analyze line count profile data. Our technique is to make a reduced picture of code with the line execution counts identified with the color. We show hot spots in red, warm spots in orange, and so on. We are also able to identify nonexecuted code and nonexecutable code such as declarations and static tables.