EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Location-Aware Scheduling for Multitasking MCM-GPUs

Tiejian Zhang, Guangda Zhang, Yandong He, Chen Zhang, Jiping Gao, Hengzhu Liu, Xia Zhao

ACM Transactions on Design Automation of Electronic Systems · 31.03.2027 · 32 (2) · 1-28

DOI: 10.1145/3827618 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 11.11.2026. Verfasst von Tiejian Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the growing computational demands of high-performance computing (HPC) and machine learning (ML) applications, Graphics Processing Units (GPUs) have transitioned from single-chip designs to multi-chip module (MCM) architectures, driven by manufacturing constraints. Simultaneously, GPUs are increasingly deployed in cloud environments to accelerate a wide range of applications for multiple users. Spatial multitasking, which allows multiple applications to run concurrently on a single GPU by executing them on different sets of streaming multiprocessors (SMs), offers an efficient method for sharing GPU resources. However, effectively supporting multitasking in the emerging MCM-GPU architecture presents a significant challenge that remains an open problem. This article presents the key observation that the placement of co-executing applications in MCM-GPUs plays a critical role in system performance. Specifically, for certain multiprogram workloads, co-executing applications achieve better performance when located on the same GPU chip to maximize memory bandwidth utilization. Conversely, other workloads benefit from being distributed across different GPU chips to mitigate memory contention. To address this, we propose a Location-Aware Scheduler (LA-Scheduler) that identifies application characteristics and makes optimized scheduling decisions. The LA-Scheduler performs lightweight workload classification using a k-means-based clustering method and applies multitasking scheduling rules during runtime to determine the optimal placement of applications within the MCM-GPU architecture. Evaluation results show that the proposed LA-Scheduler improves system throughput (STP) by an average of 38.67% compared with single-task operation. Compared with the traditional methods intra-chip scheduling and inter-chip scheduling, the system throughput is improved by an average of 13.51% and 7.14% respectively.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, T., Zhang, G., He, Y., Zhang, C., Gao, J., Liu, H., & Zhao, X. (2027). Location-Aware Scheduling for Multitasking MCM-GPUs. ACM Transactions on Design Automation of Electronic Systems, 32(2), 1-28. https://doi.org/10.1145/3827618

Vancouver

Zhang T, Zhang G, He Y, Zhang C, Gao J, Liu H, et al. Location-Aware Scheduling for Multitasking MCM-GPUs. ACM Transactions on Design Automation of Electronic Systems. 2027;32(2):1-28. doi:10.1145/3827618

BibTeX
@article{Zhang2027,
  author = {Zhang, Tiejian and Zhang, Guangda and He, Yandong and Zhang, Chen and Gao, Jiping and Liu, Hengzhu and Zhao, Xia},
  title = {Location-Aware Scheduling for Multitasking MCM-GPUs},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2027},
  volume = {32},
  number = {2},
  pages = {1--28},
  doi = {10.1145/3827618}
}
Kostenlos starten →