Search Results

Documents authored by Wang, Xiaorui

Document
DOI: 10.4230/LIPIcs.ECRTS.2026.16
DySM: Dynamic Scaling of GPU Streaming Multiprocessor in Spatially Shared Real-Time Embedded GPU Systems

Authors: Srinivasan Subramaniyan and Xiaorui Wang

Published in: LIPIcs, Volume 375, 38th European Conference on Real-Time Systems (ECRTS 2026)

Abstract
Many of today’s real-time embedded systems are increasingly relying on GPUs for AI-related computing. However, existing GPU scheduling solutions for spatially shared GPU systems are still mostly open-loop and rely on worst-case execution time (WCET) estimation for offline schedulability analysis, which cannot adapt to online workload variations. Although adaptive scheduling has been proposed to handle runtime execution time variations, prior approaches target either CPU or time-slicing GPUs, where only one task can execute on the GPU within a time slice. In contrast, spatial sharing enables concurrent kernel execution via Streaming Multiprocessor (SM) partitioning, allowing better GPU resource utilization. Therefore, new adaptive solutions must be designed for spatially shared GPU systems. In this paper, we propose DySM, a closed-loop response time control algorithm for spatially shared GPUs in soft real-time systems. In face of runtime workload variations, DySM leverages dynamic SM scaling to control task response times with low runtime overhead. To model GPU resource contention among tasks, we analytically derive a multi-input-multi-output (MIMO) system model that captures the impact of SM scaling on the response times of different tasks. Based on this model, DySM is designed using feedback control theory for guaranteed system stability and control accuracy. Experimental results on an Nvidia GPU testbed demonstrate that DySM outperforms state-of-the-art solutions by providing runtime real-time guarantees. Compared to the best-performing baseline, DySM can reduce the deadline miss ratio by up to 90.93%.
Cite as

Srinivasan Subramaniyan and Xiaorui Wang. DySM: Dynamic Scaling of GPU Streaming Multiprocessor in Spatially Shared Real-Time Embedded GPU Systems. In 38th European Conference on Real-Time Systems (ECRTS 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 375, pp. 16:1-16:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{subramaniyan_et_al:LIPIcs.ECRTS.2026.16,
  author =	{Subramaniyan, Srinivasan and Wang, Xiaorui},
  title =	{{DySM: Dynamic Scaling of GPU Streaming Multiprocessor in Spatially Shared Real-Time Embedded GPU Systems}},
  booktitle =	{38th European Conference on Real-Time Systems (ECRTS 2026)},
  pages =	{16:1--16:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-429-1},
  ISSN =	{1868-8969},
  year =	{2026},
  volume =	{375},
  editor =	{Kritikakou, Angeliki},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2026.16},
  URN =		{urn:nbn:de:0030-drops-266080},
  doi =		{10.4230/LIPIcs.ECRTS.2026.16},
  annote =	{Keywords: Real-time systems, GPU scheduling, response time ratio control, SM scaling, and feedback control}
}
Document
Artifact
DOI: 10.4230/DARTS.12.2.4
DySM: Dynamic Scaling of GPU Streaming Multiprocessor in Spatially Shared Real-Time Embedded GPU Systems (Artifact)

Authors: Srinivasan Subramaniyan and Xiaorui Wang

Published in: DARTS, Volume 12, Issue 2, Special Issue of the 38th European Conference on Real-Time Systems (ECRTS 2026)

Abstract
Many of today’s real-time embedded systems are increasingly relying on GPUs for AI-related computing. However, existing GPU scheduling solutions for spatially shared GPU systems are still mostly open-loop and rely on worst-case execution time (WCET) estimation for offline schedulability analysis, which cannot adapt to online workload variations. Although adaptive scheduling has been proposed to handle runtime execution time variations, prior approaches target either CPU or time-slicing GPUs, where only one task can execute on the GPU within a time slice. In contrast, spatial sharing enables concurrent kernel execution via Streaming Multiprocessor (SM) partitioning, allowing better GPU resource utilization. Therefore, new adaptive solutions must be designed for spatially shared GPU systems. In this paper, we propose DySM, a closed-loop response time control algorithm for spatially shared GPUs in soft real-time systems. In face of runtime workload variations, DySM leverages dynamic SM scaling to control task response times with low runtime overhead. To model GPU resource contention among tasks, we analytically derive a multi-input-multi-output (MIMO) system model that captures the impact of SM scaling on the response times of different tasks. Based on this model, DySM is designed using feedback control theory for guaranteed system stability and control accuracy. Experimental results on an Nvidia GPU testbed demonstrate that DySM outperforms state-of-the-art solutions by providing runtime real-time guarantees. Compared to the best-performing baseline, DySM can reduce the deadline miss ratio by up to 90.93%.
Cite as

Srinivasan Subramaniyan and Xiaorui Wang. DySM: Dynamic Scaling of GPU Streaming Multiprocessor in Spatially Shared Real-Time Embedded GPU Systems (Artifact). In Special Issue of the 38th European Conference on Real-Time Systems (ECRTS 2026). Dagstuhl Artifacts Series (DARTS), Volume 12, Issue 2, pp. 4:1-4:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@Article{subramaniyan_et_al:DARTS.12.2.4,
  author =	{Subramaniyan, Srinivasan and Wang, Xiaorui},
  title =	{{DySM: Dynamic Scaling of GPU Streaming Multiprocessor in Spatially Shared Real-Time Embedded GPU Systems (Artifact)}},
  pages =	{4:1--4:3},
  journal =	{Dagstuhl Artifacts Series},
  ISSN =	{2509-8195},
  year =	{2026},
  volume =	{12},
  number =	{2},
  editor =	{Subramaniyan, Srinivasan and Wang, Xiaorui},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DARTS.12.2.4},
  URN =		{urn:nbn:de:0030-drops-266218},
  doi =		{10.4230/DARTS.12.2.4},
  annote =	{Keywords: Real-time systems, GPU scheduling, response time ratio control, SM scaling, and feedback control}
}
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact