IMMSched: Interruptible Multi-DNN Scheduling via Parallel Multi-Particle Optimizing Subgraph Isomorphism

TL;DR

IMMSched introduces a parallel, probabilistic approach to efficiently schedule multiple DNNs on edge devices, significantly reducing latency and energy use for unpredictable workloads.

Contribution

It presents a novel parallel subgraph isomorphism method combining Multi-Particle Optimization with Ullmann's algorithm, enabling real-time multi-DNN scheduling on edge accelerators.

Findings

Orders-of-magnitude reduction in scheduling latency.

Significant decrease in energy consumption.

Enables real-time execution of unpredictable DNN workloads.

Abstract

The growing demand for multi-DNN workloads with unpredictable task arrival times has highlighted the need for interruptible scheduling on edge accelerators. However, existing preemptive frameworks typically assume known task arrival times and rely on CPU-based offline scheduling, which incurs heavy runtime overhead and struggles to handle unpredictable task arrivals. Even worse, prior studies have shown that multi-DNN scheduling requires solving an NP-hard subgraph isomorphism problem on large directed acyclic graphs within limited time, which is extremely challenging. To tackle this, we propose IMMSched, a parallel subgraph isomorphism method that combines Multi-Particle Optimization with the Ullmann algorithm based on a probabilistic continuous-relaxation scheme, eliminating the serial data dependencies of previous works. Finally, a quantized scheduling scheme and a global controller in the hardware architecture further combine multi-particle results for consensus-guided exploration. Evaluations demonstrate that IMMSched achieves orders-of-magnitude reductions in scheduling latency and energy consumption, enabling real-time execution of unpredictable DNN tasks on edge accelerators.