Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms

Autor:	Taufique, Zain, Miele, Antonio, Liljeberg, Pasi, Kanduri, Anil
Rok vydání:	2023
Předmět:	Computer Science - Distributed Parallel and Cluster Computing Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Performance Electrical Engineering and Systems Science - Systems and Control
Druh dokumentu:	Working Paper
DOI:	10.1109/ASP-DAC58780.2024.10473987
Popis:	DNN inference can be accelerated by distributing the workload among a cluster of collaborative edge nodes. Heterogeneity among edge devices and accuracy-performance trade-offs of DNN models present a complex exploration space while catering to the inference performance requirements. In this work, we propose adaptive workload distribution for DNN inference, jointly considering node-level heterogeneity of edge devices, and application-specific accuracy and performance requirements. Our proposed approach combinatorially optimizes heterogeneity-aware workload partitioning and dynamic accuracy configuration of DNN models to ensure performance and accuracy guarantees. We tested our approach on an edge cluster of Odroid XU4, Raspberry Pi4, and Jetson Nano boards and achieved an average gain of 41.52% in performance and 5.2% in output accuracy as compared to state-of-the-art workload distribution strategies. Comment: 6 pages, 9 figures, 1 table, 1 algorithm, to be published in 29th Asia and South Pacific Design Automation Conference (IEEE ASP-DAC 2024)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2310.10157 Zobrazit plný text záznamu View this record from Arxiv