Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911813750226944 |
|---|---|
| author | Taufique, Zain Miele, Antonio Liljeberg, Pasi Kanduri, Anil |
| author_facet | Taufique, Zain Miele, Antonio Liljeberg, Pasi Kanduri, Anil |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_10157 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms Taufique, Zain Miele, Antonio Liljeberg, Pasi Kanduri, Anil Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance Systems and Control 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. |
| title | Adaptive Workload Distribution for Accuracy-aware DNN Inference on Collaborative Edge Platforms |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance Systems and Control |
| url | https://arxiv.org/abs/2310.10157 |