Fluid dynamic DNNs for reliable and adaptive distributed inference on edge devices
Fluid dynamic DNNs for reliable and adaptive distributed inference on edge devices
Distributed inference is a popular approach for efficient DNN inference at the edge. However, traditional Static and Dynamic DNNs are not distribution-friendly, causing system reliability and adaptability issues. In this paper, we introduce Fluid Dynamic DNNs (Fluid DyDNNs), tailored for distributed inference. Distinct from Static and Dynamic DNNs, Fluid DyDNNs utilize a novel nested incremental training algorithm to enable independent and combined operation of its sub-networks, enhancing system reliability and adaptability. Evaluation on embedded Arm CPUs with a DNN model and the MNIST dataset, shows that in scenarios of single device failure, Fluid DyDNNs ensure continued inference, whereas Static and Dynamic DNNs fail. When devices are fully operational, Fluid DyDNNs can operate in either a High-Accuracy mode and achieve comparable accuracy with Static DNNs, or in a High-Throughput mode and achieve 2.5x and 2x throughput compared with Static and Dynamic DNNs, respectively.
Xun, Lei
d30d0c37-7c17-4eed-b02c-1a0f81844f17
Hu, Mingyu
686551f3-f76b-471d-b424-71a5c68851da
Zhao, Hengrui
9a7e2ba5-4932-4188-8aef-ae39d17fca46
Singh, Amit Kumar
bded7886-24ab-4a24-8539-f8fe106426ac
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Merrett, Geoff V.
89b3a696-41de-44c3-89aa-b0aa29f54020
Xun, Lei
d30d0c37-7c17-4eed-b02c-1a0f81844f17
Hu, Mingyu
686551f3-f76b-471d-b424-71a5c68851da
Zhao, Hengrui
9a7e2ba5-4932-4188-8aef-ae39d17fca46
Singh, Amit Kumar
bded7886-24ab-4a24-8539-f8fe106426ac
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Merrett, Geoff V.
89b3a696-41de-44c3-89aa-b0aa29f54020
Xun, Lei, Hu, Mingyu, Zhao, Hengrui, Singh, Amit Kumar, Hare, Jonathon and Merrett, Geoff V.
(2024)
Fluid dynamic DNNs for reliable and adaptive distributed inference on edge devices.
Design, Automation and Test in Europe Conference, , Valencia, Spain.
25 - 27 Mar 2024.
2 pp
.
(In Press)
Record type:
Conference or Workshop Item
(Paper)
Abstract
Distributed inference is a popular approach for efficient DNN inference at the edge. However, traditional Static and Dynamic DNNs are not distribution-friendly, causing system reliability and adaptability issues. In this paper, we introduce Fluid Dynamic DNNs (Fluid DyDNNs), tailored for distributed inference. Distinct from Static and Dynamic DNNs, Fluid DyDNNs utilize a novel nested incremental training algorithm to enable independent and combined operation of its sub-networks, enhancing system reliability and adaptability. Evaluation on embedded Arm CPUs with a DNN model and the MNIST dataset, shows that in scenarios of single device failure, Fluid DyDNNs ensure continued inference, whereas Static and Dynamic DNNs fail. When devices are fully operational, Fluid DyDNNs can operate in either a High-Accuracy mode and achieve comparable accuracy with Static DNNs, or in a High-Throughput mode and achieve 2.5x and 2x throughput compared with Static and Dynamic DNNs, respectively.
Text
Fluid Dynamic DNNs
- Accepted Manuscript
More information
Accepted/In Press date: 12 January 2024
Venue - Dates:
Design, Automation and Test in Europe Conference, , Valencia, Spain, 2024-03-25 - 2024-03-27
Identifiers
Local EPrints ID: 486257
URI: http://eprints.soton.ac.uk/id/eprint/486257
PURE UUID: bed7e9a4-0c96-40c4-85ea-75c27a10a5f1
Catalogue record
Date deposited: 16 Jan 2024 17:33
Last modified: 27 Mar 2024 05:01
Export record
Contributors
Author:
Lei Xun
Author:
Mingyu Hu
Author:
Hengrui Zhao
Author:
Amit Kumar Singh
Author:
Jonathon Hare
Author:
Geoff V. Merrett
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics