Finding Near-optimal Configurations in Colossal Spaces with Statistical Guarantees-Reference-Cited by-同舟云学术

Finding Near-optimal Configurations in Colossal Spaces with Statistical Guarantees

Published:2023-11-23 Issue:1 Volume:33 Page:1-36
ISSN:1049-331X
Container-title:ACM Transactions on Software Engineering and Methodology
language:en
Short-container-title:ACM Trans. Softw. Eng. Methodol.

Author:

Oh Jeho¹^ORCID,Batory Don¹^ORCID,Heradio Rubén²^ORCID

Affiliation:

1. The University of Texas at Austin, United States

2. Universidad Nacional de Educación a Distancia, Spain

Abstract

A Software Product Line ( SPL ) is a family of similar programs. Each program is defined by a unique set of features, called a configuration , that satisfies all feature constraints. “What configuration achieves the best performance for a given workload?” is the SPL Optimization ( SPLO ) challenge. SPLO is daunting: just 80 unconstrained features yield 10 24 unique configurations, which equals the estimated number of stars in the universe. We explain (a) how uniform random sampling and random search algorithms solve SPLO more efficiently and accurately than current machine-learned performance models and (b) how to compute statistical guarantees on the quality of a returned configuration; i.e., it is within x% of optimal with y% confidence.

Funder

NSF

Universidad Nacional de Educacion a Distancia

Publisher

Association for Computing Machinery (ACM)

Subject

Software

Link

https://dl.acm.org/doi/pdf/10.1145/3611663

Reference131 articles.

1. 2021. Learning software configuration spaces: A systematic literature review. JSS 182 (2021).

2. 7z. 2021. 7z Website. https://www.7-zip.org/download.html

3. M. Acher et al. 2019. Learning Very Large Configuration Spaces: What Matters for Linux Kernel Sizes. Technical Report hal-02314830. Inria Rennes.

4. M. Acher et al. 2022. Feature subset selection for learning huge configuration spaces: The case of Linux kernel size. In SPLC.

5. D. Achlioptas, Z. S. Hammoudeh, and P. Theodoropoulos. 2018. Fast sampling of perfectly uniform satisfying assignments. In SAT.

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Optimization Space Learning: A Lightweight, Noniterative Technique for Compiler Autotuning;28th ACM International Systems and Software Product Line Conference;2024-09-02

2. Pragmatic Random Sampling of the Linux Kernel: Enhancing the Randomness and Correctness of the conf Tool;28th ACM International Systems and Software Product Line Conference;2024-09-02

3. Embracing Deep Variability For Reproducibility and Replicability;Proceedings of the 2nd ACM Conference on Reproducibility and Replicability;2024-06-18

4. Finding Near-optimal Configurations in Colossal Spaces with Statistical Guarantees;ACM Transactions on Software Engineering and Methodology;2023-11-23

5. Transforming Numerical Feature Models into Propositional Formulas and the Universal Variability Language;Journal of Systems and Software;2023-10