A cost/benefit approach to performance analysis

Most performance engineering approaches focus on understanding the use of runtime resources. However such approaches do not quantify the value being provided in return for the consumption of these resources. Without such a measure it is not possible to compare the e ciency of these components (that is whether the runtime cost is reasonable given the bene t being provided). We have created an empirical approach that measures the value being provided by a code path in terms of the visible data it generates for the rest of the application. Combining this with traditional performance cost data, creates an e ciency measure for every code path in the application. We have evaluated our approach using the DaCapo benchmark suite, demonstrating our analysis allows us to quantify the e ciency of the code in each benchmark and nd real optimisation opportunities, providing improvements of up to 36% in our case studies.