國立虎尾科技大學 |

Machine Learning for High Performance Computing Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Machine Learning for High Performance Computing Applications./
Author:	Hutchison, Scott.
Description:	1 online resource (93 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798382818030

Machine Learning for High Performance Computing Applications.
Hutchison, Scott.

Machine Learning for High Performance Computing Applications. - 1 online resource (93 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--Kansas State University, 2024.

Includes bibliographical references

The focus of this study was to apply state-of-the-art Machine Learning (ML) techniques to problems in the High Performance Computing (HPC) domain. The ML techniques included clustering, various types of regression, a recommendor system, and reinforcement learning using proximal policy optimization. Included are three different advancements applying these techniques.The first application used K-means clustering and Gradient Boosted Tree Regression (GBTR) to predict estimated queue time for jobs submitted to an HPC system. This method achieved a 96% accuracy when predicting whether or not a job would start prior to a specified deadline. The second application focused on optimizing hardware procurement for HPC systems while remaining under a fixed budget. Vendor quotes for new hardware were used with a custom Discrete Event Simulator (DES) to simulate the execution of a job workload on proposed hardware. An Extreme Gradient Boosting (XGBoost) regression model powers a recommendor system that provides a precision 50 of 92%.The third application used Proximal Policy Optimization (PPO) with Invalid Action Masking (IAM) to train a Reinforcement Learning (RL) agent to schedule jobs on a simulated HPC system. The performance of this RL agent was compared to modern scheduling algorithms. The RL agent performed 18.44% better than the algorithmic baselines for one metric and comparably to the baselines for another.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382818030Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

High Performance ComputingIndex Terms--Genre/Form:

554714
Electronic books.

Machine Learning for High Performance Computing Applications.
LDR:02826ntm a22003977 4500 001 1148373
005 20240924101908.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382818030
035 $a (MiAaPQ)AAI31147963
035 $a AAI31147963
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Hutchison, Scott. $3 1474321
245 1 0 $a Machine Learning for High Performance Computing Applications.
264 0 $c 2024
300 $a 1 online resource (93 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Andresen, Daniel.
502 $a Thesis (Ph.D.)--Kansas State University, 2024.
504 $a Includes bibliographical references
520 $a The focus of this study was to apply state-of-the-art Machine Learning (ML) techniques to problems in the High Performance Computing (HPC) domain. The ML techniques included clustering, various types of regression, a recommendor system, and reinforcement learning using proximal policy optimization. Included are three different advancements applying these techniques.The first application used K-means clustering and Gradient Boosted Tree Regression (GBTR) to predict estimated queue time for jobs submitted to an HPC system. This method achieved a 96% accuracy when predicting whether or not a job would start prior to a specified deadline. The second application focused on optimizing hardware procurement for HPC systems while remaining under a fixed budget. Vendor quotes for new hardware were used with a custom Discrete Event Simulator (DES) to simulate the execution of a job workload on proposed hardware. An Extreme Gradient Boosting (XGBoost) regression model powers a recommendor system that provides a precision 50 of 92%.The third application used Proximal Policy Optimization (PPO) with Invalid Action Masking (IAM) to train a Reinforcement Learning (RL) agent to schedule jobs on a simulated HPC system. The performance of this RL agent was compared to modern scheduling algorithms. The RL agent performed 18.44% better than the algorithmic baselines for one metric and comparably to the baselines for another.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Information technology. $3 559429
653 $a High Performance Computing
653 $a Machine Learning
653 $a Gradient Boosted Tree Regression
653 $a Reinforcement Learning
653 $a Invalid Action Masking
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0489
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Kansas State University. $b Department of Computing and Information Sciences. $3 1190764
773 0 $t Dissertations Abstracts International $g 85-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31147963 $z click for full text (PQDT)