2 papers
cs.PF2025
A Kernel-Based Approach for Accurate Steady-State Detection in Performance Time Series
Martin Beseda, Vittorio Cortellessa, Daniele Di Pompeo +2
This paper addresses the challenge of accurately detecting the transition from the warmup phase to the steady state in performance metric time series, which is a critical step for…
cs.SE2025
Identifying and Replicating Code Patterns Driving Performance Regressions in Software Systems
Denivan Campos, Luana Martins, Emanuela Guglielmi +6
Context: Performance regressions negatively impact execution time and memory usage of software systems. Nevertheless, there is a lack of systematic methods to evaluate the effectiv…