A4 Vertaisarvioitu artikkeli konferenssijulkaisussa

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




TekijätTaufique, Zain; Vyas, Aman; Miele, Antonio; Liljeberg, Pasi; Kanduri, Anil

ToimittajaN/A

Konferenssin vakiintunut nimiDesign, Automation and Test in Europe Conference and Exhibition

KustantajaCornell University

Julkaisuvuosi2025

JournalProceedings : Design, Automation, and Test in Europe Conference and Exhibition

Kokoomateoksen nimi2025 Design, Automation & Test in Europe Conference (DATE)

ISBN979-8-3315-3464-6

eISBN978-3-9826741-0-0

ISSN1530-1591

eISSN1558-1101

DOIhttps://doi.org/10.23919/DATE64628.2025.10992692

Verkko-osoitehttps://ieeexplore.ieee.org/document/10992692

Preprintin osoitehttps://arxiv.org/abs/2411.16086


Tiivistelmä

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.



Last updated on 2025-22-05 at 08:08