DARIS: An Oversubscribed Spatio-Temporal Scheduler for Real-Time DNN Inference on GPUs

The widespread use of Deep Neural Networks (DNNs) is limited by high computational demands, especially in constrained environments. GPUs, though effective accelerators, often face underutilization and rely on coarse-grained scheduling. This paper introduces DARIS, a priority-based real-time DNN sche...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 62nd ACM/IEEE Design Automation Conference (DAC) S. 1 - 7
Hauptverfasser: Babaei, Amir Fakhim, Chantem, Thidapat
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 22.06.2025
Schlagworte:
Artificial neural networks
Design automation
Faces
Graphics processing units
Processor scheduling
Quality of service
Real-time systems
Synchronization
Throughput
Time factors
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The widespread use of Deep Neural Networks (DNNs) is limited by high computational demands, especially in constrained environments. GPUs, though effective accelerators, often face underutilization and rely on coarse-grained scheduling. This paper introduces DARIS, a priority-based real-time DNN scheduler for GPUs, utilizing NVIDIA's MPS and CUDA streaming for spatial sharing, and a synchronization-based staging method for temporal partitioning. In particular, DARIS improves GPU utilization and uniquely analyzes GPU concurrency by oversubscribing computing resources. It also supports zero-delay DNN migration between GPU partitions. Experiments show DARIS improves throughput by 15 \% and 11.5 \% over batching and state-of-the-art schedulers, respectively, even without batching. All high-priority tasks meet deadlines, with low-priority tasks having under 2% deadline miss rate. High-priority response times are 33% better than those of low-priority tasks.
DOI:10.1109/DAC63849.2025.11132423