Search Results

Documents authored by Tong, Zelin

Document
DOI: 10.4230/LIPIcs.ECRTS.2024.15
Predictable GPU Sharing in Component-Based Real-Time Systems

Authors: Syed W. Ali, Zelin Tong, Joseph Goh, and James H. Anderson

Published in: LIPIcs, Volume 298, 36th Euromicro Conference on Real-Time Systems (ECRTS 2024)

Abstract
This paper presents a real-time locking protocol whose design was motivated by the goal of enabling safe GPU sharing in time-sliced component-based systems. This locking protocol enables a GPU to be shared concurrently across, and utilized within, isolated components with predictable execution times. It relies on a novel resizing technique where GPU work is dimensioned on-the-fly to run on partitions of an NVIDIA GPU. This technique can be applied to any component that internally utilizes global CPU scheduling. The proposed locking protocol enables increased GPU parallelism and reduces GPU capacity loss with analytically provable benefits.
Cite as

Syed W. Ali, Zelin Tong, Joseph Goh, and James H. Anderson. Predictable GPU Sharing in Component-Based Real-Time Systems. In 36th Euromicro Conference on Real-Time Systems (ECRTS 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 298, pp. 15:1-15:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{ali_et_al:LIPIcs.ECRTS.2024.15,
  author =	{Ali, Syed W. and Tong, Zelin and Goh, Joseph and Anderson, James H.},
  title =	{{Predictable GPU Sharing in Component-Based Real-Time Systems}},
  booktitle =	{36th Euromicro Conference on Real-Time Systems (ECRTS 2024)},
  pages =	{15:1--15:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-324-9},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{298},
  editor =	{Pellizzoni, Rodolfo},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2024.15},
  URN =		{urn:nbn:de:0030-drops-203183},
  doi =		{10.4230/LIPIcs.ECRTS.2024.15},
  annote =	{Keywords: GPU locking protocols, real-time locking protocols, priority-inversion blocking, component-based systems}
}
Document
Artifact
DOI: 10.4230/DARTS.10.1.1
Predictable GPU Sharing in Component-Based Real-Time Systems (Artifact)

Authors: Syed W. Ali, Zelin Tong, Joseph Goh, and James H. Anderson

Published in: DARTS, Volume 10, Issue 1, Special Issue of the 36th Euromicro Conference on Real-Time Systems (ECRTS 2024)

Abstract
This paper presents a real-time locking protocol whose design was motivated by the goal of enabling safe GPU sharing in time-sliced component-based systems. This locking protocol enables a GPU to be shared concurrently across, and utilized within, isolated components with predictable execution times. It relies on a novel resizing technique where GPU work is dimensioned on-the-fly to run on partitions of an NVIDIA GPU. This technique can be applied to any component that internally utilizes global CPU scheduling. The proposed locking protocol enables increased GPU parallelism and reduces GPU capacity loss with analytically provable benefits.
Cite as

Syed W. Ali, Zelin Tong, Joseph Goh, and James H. Anderson. Predictable GPU Sharing in Component-Based Real-Time Systems (Artifact). In Special Issue of the 36th Euromicro Conference on Real-Time Systems (ECRTS 2024). Dagstuhl Artifacts Series (DARTS), Volume 10, Issue 1, pp. 1:1-1:5, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@Article{ali_et_al:DARTS.10.1.1,
  author =	{Ali, Syed W. and Tong, Zelin and Goh, Joseph and Anderson, James H.},
  title =	{{Predictable GPU Sharing in Component-Based Real-Time Systems (Artifact)}},
  pages =	{1:1--1:5},
  journal =	{Dagstuhl Artifacts Series},
  ISBN =	{978-3-95977-327-0},
  ISSN =	{2509-8195},
  year =	{2024},
  volume =	{10},
  number =	{1},
  editor =	{Ali, Syed W. and Tong, Zelin and Goh, Joseph and Anderson, James H.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DARTS.10.1.1},
  URN =		{urn:nbn:de:0030-drops-203236},
  doi =		{10.4230/DARTS.10.1.1},
  annote =	{Keywords: GPU locking protocols, real-time locking protocols, priority-inversion blocking, component-based systems}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2022.10
Overrun-Resilient Multiprocessor Real-Time Locking

Authors: Zelin Tong, Shareef Ahmed, and James H. Anderson

Published in: LIPIcs, Volume 231, 34th Euromicro Conference on Real-Time Systems (ECRTS 2022)

Abstract
Existing real-time locking protocols require accurate worst-case execution time (WCET) estimates for both tasks and critical sections (CSs) in order to function correctly. On multicore platforms, however, the only seemingly viable strategy for obtaining such estimates is via measurements, which cannot produce a true WCET with certainty. The absence of correct WCETs can be partially ameliorated by enforcing execution budgets at both the task and CS levels and by using a locking protocol that is resilient to budget overruns, i.e., that ensures that the schedulability of non-overrunning tasks is not compromised by tasks that do overrun their budgets. Unfortunately, no fully overrun-resilient locking protocol has been proposed to date for multiprocessor systems. To remedy this situation, this paper presents two such protocols, the OR-FMLP and the OR-OMLP , which introduce overrun-resiliency mechanisms to two existing multiprocessor protocols, the spin-based FMLP and suspension-based global OMLP, respectively. In devising such mechanisms, undo code can be problematic. For the important locking use case of protecting shared data structures, it is shown that such code can be avoided entirely by using abortable critical sections, a concept proposed herein that leverages obstruction-free synchronization techniques. Experiments are presented that demonstrate both the effectiveness of the mechanisms introduced in this paper and their cost.
Cite as

Zelin Tong, Shareef Ahmed, and James H. Anderson. Overrun-Resilient Multiprocessor Real-Time Locking. In 34th Euromicro Conference on Real-Time Systems (ECRTS 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 231, pp. 10:1-10:25, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{tong_et_al:LIPIcs.ECRTS.2022.10,
  author =	{Tong, Zelin and Ahmed, Shareef and Anderson, James H.},
  title =	{{Overrun-Resilient Multiprocessor Real-Time Locking}},
  booktitle =	{34th Euromicro Conference on Real-Time Systems (ECRTS 2022)},
  pages =	{10:1--10:25},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-239-6},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{231},
  editor =	{Maggio, Martina},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2022.10},
  URN =		{urn:nbn:de:0030-drops-163272},
  doi =		{10.4230/LIPIcs.ECRTS.2022.10},
  annote =	{Keywords: Real-Time Systems, Real-Time Synchronization, Budget Enforcement}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact