Skip to main content

Determining Average Program Execution Times and their Variance

PDF DOI 10.1145/73141.74845 dblp BibTeX

Abstract

This paper presents a general framework for determining average program execution times and their variance, based on the program's interval structure and control dependence graph. Average execution times and variance values are computed using frequency information from an optimized counter-based execution profile of the program.

Related papers

Quantifying and Reducing Execution Variance in STM via Model Driven Commit Optimization CGO 2019
Quantifying and reducing execution variance in STM via model driven commit optimization PPoPP 2018
vSensor: leveraging fixed-workload snippets of programs for performance variance detection PPoPP 2018
Boosting Performance and QoS for Concurrent GPU B+trees by Combining-Based Synchronization PPoPP 2023
Method-specific dynamic compilation using logistic regression OOPSLA 2006
Provenance-guided synthesis of Datalog programs POPL 2020
High performance GPU concurrent B+tree PPoPP 2022
Taming the wildcards: combining definition- and use-site variance PLDI 2011