HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Taufique, Zain, Vyas, Aman, Miele, Antonio, Liljeberg, Pasi, Kanduri, Anil
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929603800465408
author Taufique, Zain
Vyas, Aman
Miele, Antonio
Liljeberg, Pasi
Kanduri, Anil
author_facet Taufique, Zain
Vyas, Aman
Miele, Antonio
Liljeberg, Pasi
Kanduri, Anil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16086
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms
Taufique, Zain
Vyas, Aman
Miele, Antonio
Liljeberg, Pasi
Kanduri, Anil
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
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.
title HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.16086