Enabling Latency-Sensitive DNN Inference via Joint Optimization of Model Surgery and Resource Allocation in Heterogeneous Edge-Reference-Cited by-同舟云学术

Enabling Latency-Sensitive DNN Inference via Joint Optimization of Model Surgery and Resource Allocation in Heterogeneous Edge

Published:2022-08-29 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 51st International Conference on Parallel Processing
language:
Short-container-title:

Author:

Huang Zhaowu¹,Dong Fang¹,Shen Dian¹,Wang Huitian¹,Guo Xiaolin¹,Fu Shucun¹

Affiliation:

1. Southeast University, China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3545008.3545071

Reference35 articles.

1. Large the price of routing unsplittable flow

2. Tolga Bolukbasi Joseph Wang Ofer Dekel and Venkatesh Saligrama. 2017. Adaptive Neural Networks for Efficient Inference. In ICML. Tolga Bolukbasi Joseph Wang Ofer Dekel and Venkatesh Saligrama. 2017. Adaptive Neural Networks for Efficient Inference. In ICML.

3. CIFAR-10 2009. dataset. http://www.cs.toronto.edu/ kriz/cifar.html/. CIFAR-10 2009. dataset. http://www.cs.toronto.edu/ kriz/cifar.html/.

4. COMCAST 2018. sendgrid/comcast. https://github.com/sendgrid/comcast. COMCAST 2018. sendgrid/comcast. https://github.com/sendgrid/comcast.

5. Docker 2022. container. https://www.docker.com/. Docker 2022. container. https://www.docker.com/.

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Low-Latency Deep Learning Inference Schedule on Multi-Core MCU;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

2. PORTEND: A Joint Performance Model for Partitioned Early-Exiting DNNs;2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS);2023-12-17

3. DNN Inference Acceleration for Smart Devices in Industry 5.0 By Decentralized Deep Reinforcement Learning;IEEE Transactions on Consumer Electronics;2023