2 papers
cs.DC2025
DARIS: An Oversubscribed Spatio-Temporal Scheduler for Real-Time DNN Inference on GPUs
Amir Fakhim Babaei, Thidapat Chantem
The widespread use of Deep Neural Networks (DNNs) is limited by high computational demands, especially in constrained environments. GPUs, though effective accelerators, often face…
cs.DC2024
SGPRS: Seamless GPU Partitioning Real-Time Scheduler for Periodic Deep Learning Workloads
Amir Fakhim Babaei, Thidapat Chantem
Deep Neural Networks (DNNs) are useful in many applications, including transportation, healthcare, and speech recognition. Despite various efforts to improve accuracy, few works ha…