logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Duration-Informed Workload Scheduler

delete2026-01-01
delete0
PRE
AI
D
Daniela Loreti
D
Davide Leone
A
Andrea Borghesi *
DOI：10.1007/978-3-032-07612-0_1delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
高性能计算系统是复杂的机器，其行为由其众多子系统的正确功能决定。其中，工作负载调度器对连续提交到计算资源的作业的及时执行具有关键影响。做出高质量调度决策取决于在执行前知道提交作业的持续时间，这对用户而言是一项非平凡的任务，可通过机器学习解决。在本工作中，我们设计了一种带有通过机器学习构建的持续时间预测模块的工作负载调度器。我们评估了其有效性，并使用来自Tier-0超级计算机的工作负载跟踪数据展示了其性能，表明所有作业的平均等待时间降低了约11%。更短的等待时间直接关系到从用户角度看的服务质量提升和从系统角度看更高的周转率。
Keyword:
High-Performance Computing
Duration Prediction
Machine Learning

期刊

H
HIGH PERFORMANCE COMPUTING WORKSHOPS, ISC HIGH PERFORMANCE 2025 INTERNATIONAL WORKSHOPS
IF:
0
论文数:
54
被引数:
0

机构

U
university of bologna
学者数:
6.1K
论文数: 2.5K
被引数: 0
引用论文

引用论文

OKCM: improving parallel task scheduling in high-performance computing systems using online learning
errThe Journal of Supercomputing
IF0
err2020-11-13
err0
PREAI
errJingbo Li; Xingjun Zhang; Li Han; Zeyu Ji; Xiaoshe Dong; Chenglong Hu
err分享
err收藏
Predicting the Execution Time of Workflow Activities Based on Their Input Features
err2012 SC Companion: High Performance Computing, Networking Storage and Analysis
IF0
err2012-11-01
err0
PREAI
errTudor Miu; Paolo Missier
err分享
err收藏
Algorithm runtime prediction: Methods & evaluation
errartificial intelligence review
IF4.6
err2014-01-01
err318
errOAAI
errHutter, Frank; Xu, Lin; Hoos, Holger H.; Leyton-Brown, Kevin
err分享
err收藏
Machine learning approaches to predict the execution time of the meteorological simulation software COSMO机器学习方法预测气象模拟软件COSMO的执行时间
errJournal of Intelligent Information Systems
IF0
err2025-02-01
err0
PREAI
errDe Filippo,Allegra; Di Giacomo,Emanuele; Borghesi,Andrea
err分享
err收藏
A comprehensive model of the supercomputer workload
errProceedings of the Fourth Annual IEEE International Workshop on Workload Characterization. WWC-4 (Cat. No.01EX538)
IF0
err2024-10-23
err0
PREAI
errW. Cirne; F. Berman
err分享
err收藏
PM100: A Job Power Consumption Dataset of a Large-scale Production HPC SystemPM100：大规模生产型HPC系统的作业功耗数据集
errProceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis
IF0
err2023-11-12
err0
errOAAI
errFrancesco Antici; Mohsen Seyedkazemi Ardebili; Andrea Bartolini; Zeynep Kiziltan
err分享
err收藏
Random Forests随机森林
err
IF0
err2001-01-01
err0
PREAI
errLeo Breiman
err分享
err收藏
Improving HPC System Performance by Predicting Job Resources via Supervised Machine Learning
errProceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)
IF0
err2019-07-28
err0
errOAAI
errMohammed Tanash; Brandon Dunn; Daniel Andresen; William Hsu; Huichen Yang; Adedolapo Okanlawon
err分享
err收藏
M100 ExaData: a data collection campaign on the CINECA’s Marconi100 Tier-0 supercomputer
errScientific Data
IF0
err2023-05-18
err0
errOAAI
errAndrea Borghesi; Carmine Di Santi; Martin Molan; Mohsen Seyedkazemi Ardebili; Alessio Mauri; Massimiliano Guarrasi; Daniela Galetti; Mirko Cestari; Francesco Barchi; Luca Benini; Francesco Beneventi; Andrea Bartolini
err分享
err收藏
Evaluating the EASY-backfill job scheduling of static workloads on clusters评估静态工作负载在集群上的EASY-backfill作业调度
err2007 IEEE International Conference on Cluster Computing
IF0
err2007-01-01
err0
PREAI
errAdam K.L. Wong; Andrzej M. Goscinski
err分享
err收藏
学者 查看更多内容