Close

Presentation

RT-MDM: Real-Time Scheduling Framework for Multi-DNN on MCU Using External Memory
DescriptionAs the application scope of DNNs executed on microcontroller units (MCUs) extends to time-critical systems, it becomes important to ensure timing guarantees for increasing demand of DNN inferences. To this end, this paper proposes RT-MDM, the first real-time scheduling framework for multiple DNN tasks executed on an MCU using external memory. Identifying execution-order dependencies among segmented DNN models and memory requirements for parallel execution subject to the dependencies, we propose (i) a segment-group-based memory management policy that achieves isolated memory usage within a segment group and sharded memory usage across different segment groups, and (ii) an intra-task scheduler specialized for the proposed policy. Implementing RT-MDM on an actual system and optimizing its parameters for DNN segmentation and segment-group mapping, we demonstrate the effectiveness of RT-MDM in accommodating more DNN tasks while providing their timing guarantees.
Event Type
Research Manuscript
TimeTuesday, June 2511:30am - 11:45am PDT
Location3001, 3rd Floor
Topics
AI
Keywords
AI/ML Algorithms