Quantifying Performance Changes with Effect Size Confidence Intervals

TL;DR

This paper introduces a statistical framework for quantifying uncertainty in performance measurements, improving the rigor and interpretability of experimental results in systems research.

Contribution

It presents a novel statistical model that accounts for non-determinism and provides confidence intervals for performance ratios, enhancing reproducibility and validity.

Findings

Provides a method to compute confidence intervals for execution time ratios

Addresses non-determinism in performance measurements

Enables clearer, more reliable performance comparisons

Abstract

Measuring performance & quantifying a performance change are core evaluation techniques in programming language and systems research. Of 122 recent scientific papers, as many as 65 included experimental evaluation that quantified a performance change using a ratio of execution times. Few of these papers evaluated their results with the level of rigour that has come to be expected in other experimental sciences. The uncertainty of measured results was largely ignored. Scarcely any of the papers mentioned uncertainty in the ratio of the mean execution times, and most did not even mention uncertainty in the two means themselves. Most of the papers failed to address the non-deterministic execution of computer programs (caused by factors such as memory placement, for example), and none addressed non-deterministic compilation. It turns out that the statistical methods presented in the computer systems performance evaluation literature for the design and summary of experiments do not readily allow this either. This poses a hazard to the repeatability, reproducibility and even validity of quantitative results. Inspired by statistical methods used in other fields of science, and building on results in statistics that did not make it to introductory textbooks, we present a statistical model that allows us both to quantify uncertainty in the ratio of (execution time) means and to design experiments with a rigorous treatment of those multiple sources of non-determinism that might impact measured performance. Better still, under our framework summaries can be as simple as "system A is faster than system B by 5.5% $\pm$ 2.5%, with 95% confidence", a more natural statement than those derived from typical current practice, which are often misinterpreted. November 2013