HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms
This work addresses latency and resource utilization issues for edge computing applications, representing an incremental improvement over existing distributed inference techniques.
The paper tackled the problem of inefficient DNN inference on heterogeneous edge nodes by proposing a hierarchical partitioning strategy (HiDP), which achieved on average 38% lower latency, 46% lower energy, and 56% higher throughput compared to other approaches.
Edge inference techniques partition and distribute Deep Neural Network (DNN) inference tasks among multiple edge nodes for low latency inference, without considering the core-level heterogeneity of edge nodes. Further, default DNN inference frameworks also do not fully utilize the resources of heterogeneous edge nodes, resulting in higher inference latency. In this work, we propose a hierarchical DNN partitioning strategy (HiDP) for distributed inference on heterogeneous edge nodes. Our strategy hierarchically partitions DNN workloads at both global and local levels by considering the core-level heterogeneity of edge nodes. We evaluated our proposed HiDP strategy against relevant distributed inference techniques over widely used DNN models on commercial edge devices. On average our strategy achieved 38% lower latency, 46% lower energy, and 56% higher throughput in comparison with other relevant approaches.