Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge

Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, Ravi Netravali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Scopus citations

Abstract

Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension. Most notably, edge-box GPUs lack the memory needed to concurrently house the growing number of (increasingly complex) models for real-time inference. Unfortunately, existing solutions that rely on time/space sharing of GPU resources are insufficient as the required swapping delays result in unacceptable frame drops and accuracy loss. We present model merging, a new memory management technique that exploits architectural similarities between edge vision models by judiciously sharing their layers (including weights) to reduce workload memory costs and swapping delays. Our system, Gemel, efficiently integrates merging into existing pipelines by (1) leveraging several guiding observations about per-model memory usage and inter-layer dependencies to quickly identify fruitful and accuracy-preserving merging configurations, and (2) altering edge inference schedules to maximize merging benefits. Experiments across diverse workloads reveal that Gemel reduces memory usage by up to 60.7%, and improves overall accuracy by 8-39% relative to time or space sharing alone.

Original languageEnglish (US)
Title of host publicationProceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023
PublisherUSENIX Association
Pages973-994
Number of pages22
ISBN (Electronic)9781939133335
StatePublished - 2023
Event20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023 - Boston, United States
Duration: Apr 17 2023Apr 19 2023

Publication series

NameProceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023

Conference

Conference20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023
Country/TerritoryUnited States
CityBoston
Period4/17/234/19/23

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge'. Together they form a unique fingerprint.

Cite this