Algorithmic Techniques for GPU Scheduling: A Comprehensive Survey

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Algorithms vol. 18, no. 7 (2025), p. 385-437
1. Verfasser: Chab, Robert
Weitere Verfasser: Li, Fei, Setia Sanjeev
Veröffentlicht:
MDPI AG
Schlagworte:
Online-Zugang:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

MARC

LEADER 00000nab a2200000uu 4500
001 3233032077
003 UK-CbPIL
022 |a 1999-4893 
024 7 |a 10.3390/a18070385  |2 doi 
035 |a 3233032077 
045 2 |b d20250101  |b d20251231 
084 |a 231333  |2 nlm 
100 1 |a Chab, Robert 
245 1 |a Algorithmic Techniques for GPU Scheduling: A Comprehensive Survey 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a In this survey, we provide a comprehensive classification of GPU task scheduling approaches, categorized by their underlying algorithmic techniques and evaluation metrics. We examine traditional methods—including greedy algorithms, dynamic programming, and mathematical programming—alongside advanced machine learning techniques integrated into scheduling policies. We also evaluate the performance of these approaches across diverse applications. This work focuses on understanding the trade-offs among various algorithmic techniques, the architectural and job-level factors influencing scheduling decisions, and the balance between user-level and service-level objectives. The analysis shows that no one paradigm dominates; instead, the highest-performing schedulers blend the predictability of formal methods with the adaptability of learning, often moderated by queueing insights for fairness. We also discuss key challenges in optimizing GPU resource management and suggest potential solutions. 
610 4 |a NVidia Corp 
653 |a Scheduling 
653 |a Machine learning 
653 |a Dynamic programming 
653 |a Task scheduling 
653 |a Deep learning 
653 |a Performance evaluation 
653 |a Mathematical analysis 
653 |a Artificial intelligence 
653 |a Formal method 
653 |a Graphics processing units 
653 |a Bandwidths 
653 |a Mathematical programming 
653 |a Greedy algorithms 
653 |a Architecture 
653 |a Energy efficiency 
653 |a Spectrum allocation 
653 |a Algorithms 
653 |a Resource management 
653 |a Cost control 
653 |a Workloads 
653 |a Decisions 
653 |a Queueing 
700 1 |a Li, Fei 
700 1 |a Setia Sanjeev 
773 0 |t Algorithms  |g vol. 18, no. 7 (2025), p. 385-437 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3233032077/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3233032077/fulltextwithgraphics/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3233032077/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch