Learned garbage collection
Name
3394450.3397469.pdf
Size
835.88 KB
Format
Adobe PDF
Checksum (MD5)
fe0569d1c5b4bb0db9ae13fe0d9128c2
Author(s)
Cen, Lujing
Marcus, Ryan
Mao, Hongzi
Gottschlich, Justin
Alizadeh, Mohammad
Kraska, Tim
Date Issued
June 2020
Journal
MAPL 2020 - Proceedings of the 4th ACM SIGPLAN International Workshop on Machine Learning and Programming Languages, co-located with PLDI 2020
Publisher
ACM
Version
Final published version
Abstract
© 2020 Owner/Author. Several programming languages use garbage collectors (GCs) to automatically manage memory for the programmer. Such collectors must decide when to look for unreachable objects to free, which can have a large performance impact on some applications. In this preliminary work, we propose a design for a learned garbage collector that autonomously learns over time when to perform collections. By using reinforcement learning, our design can incorporate user-defined reward functions, allowing an autonomous garbage collector to learn to optimize the exact metric the user desires (e.g., request latency or queries per second). We conduct an initial experimental study on a prototype, demonstrating that an approach based on tabular Q learning may be promising.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3394450.3397469
