学习型操作系统和编译器研究综述  

A survey on learned operating system and compiler

作　　者：高萌涓 王艺达 孙静怡 桑可佳 王奕涵 徐远超[1,2] GAO Mengjuan;WANG Yida;SUN Jingyi;SANG Kejia;WANG Yihan;XU Yuanchao(College of Information Engineering,Capital Normal University,Beijing 100048;State Key Lab of Processors,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190)

机构地区：[1]首都师范大学信息工程学院,北京100048 [2]中国科学院计算技术研究所处理器芯片全国重点实验室,北京100190

出　　处：《首都师范大学学报（自然科学版）》2024年第6期49-61,共13页Journal of Capital Normal University：Natural Science Edition

基　　金：北京市自然科学基金项目(4212017);处理器芯片全国重点实验室开放课题(CLQ202410)。

摘　　要：机器学习方法具有从大量数据中提取特征并动态优化系统性能的能力,然而机器学习赋能系统软件面临众多挑战。本文重点从学习型操作系统和学习型编译器2个方面回顾了机器学习在计算机系统中的应用,探讨了机器学习赋能系统软件的挑战以及潜在研究方向,期望能为研究者提供参考。Machine learning methods have the ability to extract features from large amounts of data and dynamically optimize system performance,but there are still many challenges for machine learning to enable system software.This paper mainly surveys the research of machine learning in computer system from two aspects of learning-based operating system and learning-based compiler,discusses the challenges and potential research directions of machine learning enabling system software,and hopes to provide references for researchers.

关 键 词：机器学习 学习型 系统软件 操作系统 调度 编译器 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]