AutoOS: Make Your OS More Powerful by Exploiting Large Language Models

Huilai Chen, Yuanbo Wen, Limin Cheng, Shouxu Kuang, Yumeng Liu, Weijia Li, Ling Li, Rui Zhang, Xinkai Song, Wei Li, Qi Guo, Yunji Chen
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7511-7525, 2024.

Abstract

With the rapid development of Artificial Intelligence of Things (AIoT), customizing and optimizing operating system (OS) kernel configurations for various AIoT application scenarios is crucial for maximizing system performance. However, existing approaches falter due to the overwhelming problem complexity (i.e., over 15,000 configuration options in the Linux kernel), together with the huge evaluation costs and error-prone options that may result in OS boot-up failure, which all make it an unresolved problem to optimize the Linux kernel automatically. In this paper, we introduce AutoOS, a novel framework exploiting Large Language Models for customizing and optimizing OS kernel configurations automatically for various AIoT application scenarios.Inspired by the inherently directory-structured kernel configuration process, we first formulate our research problem as optimizing on a dynamic tree. We then propose a novel framework integrating a state machine-based traversal algorithm as the observe-prune-propose-act-correct loop, which can effectively refine the optimization space and ensure a successful OS boot-up.Experimental results show that AutoOS can automatically customize and optimize the OS kernel configurations without human effort. More importantly, AutoOS even achieves better performance by up to 25% than vendor-provided configuration.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-chen24at, title = {{A}uto{OS}: Make Your {OS} More Powerful by Exploiting Large Language Models}, author = {Chen, Huilai and Wen, Yuanbo and Cheng, Limin and Kuang, Shouxu and Liu, Yumeng and Li, Weijia and Li, Ling and Zhang, Rui and Song, Xinkai and Li, Wei and Guo, Qi and Chen, Yunji}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {7511--7525}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/chen24at/chen24at.pdf}, url = {https://proceedings.mlr.press/v235/chen24at.html}, abstract = {With the rapid development of Artificial Intelligence of Things (AIoT), customizing and optimizing operating system (OS) kernel configurations for various AIoT application scenarios is crucial for maximizing system performance. However, existing approaches falter due to the overwhelming problem complexity (i.e., over 15,000 configuration options in the Linux kernel), together with the huge evaluation costs and error-prone options that may result in OS boot-up failure, which all make it an unresolved problem to optimize the Linux kernel automatically. In this paper, we introduce AutoOS, a novel framework exploiting Large Language Models for customizing and optimizing OS kernel configurations automatically for various AIoT application scenarios.Inspired by the inherently directory-structured kernel configuration process, we first formulate our research problem as optimizing on a dynamic tree. We then propose a novel framework integrating a state machine-based traversal algorithm as the observe-prune-propose-act-correct loop, which can effectively refine the optimization space and ensure a successful OS boot-up.Experimental results show that AutoOS can automatically customize and optimize the OS kernel configurations without human effort. More importantly, AutoOS even achieves better performance by up to 25% than vendor-provided configuration.} }
Endnote
%0 Conference Paper %T AutoOS: Make Your OS More Powerful by Exploiting Large Language Models %A Huilai Chen %A Yuanbo Wen %A Limin Cheng %A Shouxu Kuang %A Yumeng Liu %A Weijia Li %A Ling Li %A Rui Zhang %A Xinkai Song %A Wei Li %A Qi Guo %A Yunji Chen %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-chen24at %I PMLR %P 7511--7525 %U https://proceedings.mlr.press/v235/chen24at.html %V 235 %X With the rapid development of Artificial Intelligence of Things (AIoT), customizing and optimizing operating system (OS) kernel configurations for various AIoT application scenarios is crucial for maximizing system performance. However, existing approaches falter due to the overwhelming problem complexity (i.e., over 15,000 configuration options in the Linux kernel), together with the huge evaluation costs and error-prone options that may result in OS boot-up failure, which all make it an unresolved problem to optimize the Linux kernel automatically. In this paper, we introduce AutoOS, a novel framework exploiting Large Language Models for customizing and optimizing OS kernel configurations automatically for various AIoT application scenarios.Inspired by the inherently directory-structured kernel configuration process, we first formulate our research problem as optimizing on a dynamic tree. We then propose a novel framework integrating a state machine-based traversal algorithm as the observe-prune-propose-act-correct loop, which can effectively refine the optimization space and ensure a successful OS boot-up.Experimental results show that AutoOS can automatically customize and optimize the OS kernel configurations without human effort. More importantly, AutoOS even achieves better performance by up to 25% than vendor-provided configuration.
APA
Chen, H., Wen, Y., Cheng, L., Kuang, S., Liu, Y., Li, W., Li, L., Zhang, R., Song, X., Li, W., Guo, Q. & Chen, Y.. (2024). AutoOS: Make Your OS More Powerful by Exploiting Large Language Models. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:7511-7525 Available from https://proceedings.mlr.press/v235/chen24at.html.

Related Material