ABSTRACT
Deep learning has achieved tremendous success in various fields, but its significant computational demands make inference on mobile devices extremely challenging. To address this issue, we propose the COUPLE system, which enables heterogeneous processors to collaborate on mobile devices for accelerating video analytics. Additionally, we design the Co-Optimize strategy which utilizes the inference results of GPU to mitigate the accuracy loss caused by DSP. Experimental results demonstrate that COUPLE can improve the inference Average Precision by up to 5% compared to existing solutions.
- Joo Seong Jeong, Jingyu Lee, Donghyun Kim, Changmin Jeon, Changjin Jeong, Youngki Lee, and Byung-Gon Chun. 2022. Band: coordinated multi-dnn inference on heterogeneous mobile processors. In Proc. of ACM Mobisys.Google ScholarDigital Library
- Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, and Matei Zaharia. 2017. Noscope: optimizing neural network queries over video at scale. arXiv preprint arXiv:1703.02529 (2017).Google Scholar
- Wonik Seo, Sanghoon Cha, Yeonjae Kim, Jaehyuk Huh, and Jongse Park. 2021. SLO-aware inference scheduler for heterogeneous processors in edge platforms. ACM TACO 18, 4 (2021), 1--26.Google ScholarDigital Library
- Tianxiang Tan and Guohong Cao. 2021. Deep learning video analytics through edge computing and neural processing units on mobile devices. IEEE Transactions on Mobile Computing (2021).Google ScholarCross Ref
Index Terms
- COUPLE: Accelerating Video Analytics on Heterogeneous Mobile Processors
Recommendations
Video streaming to mobile handheld devices: challenges in decoding, adaptation, and browsing
MCAM'07: Proceedings of the 2007 international conference on Multimedia content analysis and miningGrowing popularity and richer functionality of contemporary mobile handheld devices such as PDAs and smart phones have enabled emerging video streaming applications to these devices via various wireless networks. However, these handheld devices are ...
Implementing Cross-Device Atomics in Heterogeneous Processors
IPDPSW '15: Proceedings of the 2015 IEEE International Parallel and Distributed Processing Symposium WorkshopIn this paper we describe how to support atomics across multiple devices in heterogeneous processors. Specifically, this paper provides an overview of how OpenCL 2.0 and Heterogeneous System Architecture (HSA) atomics are supported on integrated CPU-GPU ...
Niagara: Scheduling DNN Inference Services on Heterogeneous Edge Processors
Service-Oriented ComputingAbstractIntelligent applications heavily rely on deep neural network (DNN) inference services executed on edge devices to fulfill functional prerequisites while safeguarding user data privacy. However, the execution of such DNN services on resource-...
Comments