Optimizing Multi-DNN Inference on Mobile Devices through Heterogeneous Processor Co-Execution
This addresses performance and energy efficiency issues for mobile device users, but it is incremental as it builds on prior subgraph partitioning methods.
The paper tackles the problem of inefficient multi-DNN inference on mobile devices by proposing an Advanced Multi-DNN Model Scheduling (ADMS) strategy, which reduces inference latency by 4.04 times compared to existing frameworks.
Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support. However, existing mobile inference frameworks often rely on a single processor per model, limiting hardware utilization and causing suboptimal performance and energy efficiency. Expanding DNN accessibility on mobile platforms requires adaptive, resource-efficient solutions to meet rising computational needs without compromising functionality. Parallel inference of multiple DNNs on heterogeneous processors remains challenging. Some works partition DNN operations into subgraphs for parallel execution across processors, but these often create excessive subgraphs based only on hardware compatibility, increasing scheduling complexity and memory overhead. To address this, we propose an Advanced Multi-DNN Model Scheduling (ADMS) strategy for optimizing multi-DNN inference on mobile heterogeneous processors. ADMS constructs an optimal subgraph partitioning strategy offline, balancing hardware operation support and scheduling granularity, and uses a processor-state-aware algorithm to dynamically adjust workloads based on real-time conditions. This ensures efficient workload distribution and maximizes processor utilization. Experiments show ADMS reduces multi-DNN inference latency by 4.04 times compared to vanilla frameworks.