EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LAG-Guided Runtime Framework: Block-Level Scheduling and Dynamic Compression for Multi-DNN Environments

Hyuksoo Kim, Hyunhak Kim, Myungsun Kim

ACM Transactions on Design Automation of Electronic Systems · 30.11.2026 · 31 (6) · 1-37

DOI: 10.1145/3798107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 14.06.2026. Verfasst von Hyuksoo Kim und 2 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, there has been a growing demand for real-time intelligent systems that can execute multiple deep neural network (DNN) models simultaneously for tasks such as object recognition, detection and tracking. However, running multiple DNNs simultaneously in resource-constrained embedded environments can lead to resource contention due to limited system resources. This can result in execution delays that cause critical issues in latency-sensitive processing. This article proposes a dynamic scheduling technique that divides DNN models into functional units called blocks, which are then configured as execution units. Additionally, when running different models in parallel, it identifies blocks that actually increase execution time and controls them to run sequentially. Furthermore, to minimize execution delays while maintaining accuracy, we propose a dynamic lightweight replacement technique that replaces blocks with highly anticipated execution delays with lightweight blocks at runtime. This technique uses LAG , a metric which quantifies the degree of execution delay for each block, to dynamically adjust the balance between execution delays and accuracy. Experimental results show that when running multiple heterogeneous DNNs simultaneously on a commercial off-the-shelf board, the proposed technique improves latency by up to 29.3%, while maintaining 90% of baseline accuracy.

Förderung

  • Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport

Zitieren

APA

Kim, H., Kim, H., & Kim, M. (2026). LAG-Guided Runtime Framework: Block-Level Scheduling and Dynamic Compression for Multi-DNN Environments. ACM Transactions on Design Automation of Electronic Systems, 31(6), 1-37. https://doi.org/10.1145/3798107

Vancouver

Kim H, Kim H, Kim M. LAG-Guided Runtime Framework: Block-Level Scheduling and Dynamic Compression for Multi-DNN Environments. ACM Transactions on Design Automation of Electronic Systems. 2026;31(6):1-37. doi:10.1145/3798107

BibTeX
@article{Kim2026,
  author = {Kim, Hyuksoo and Kim, Hyunhak and Kim, Myungsun},
  title = {LAG-Guided Runtime Framework: Block-Level Scheduling and Dynamic Compression for Multi-DNN Environments},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2026},
  volume = {31},
  number = {6},
  pages = {1--37},
  doi = {10.1145/3798107}
}
Kostenlos starten →