Document Open Access Logo

Bounding the WCET of a GPU Thread Block with a Multi-Phase Representation of Warps Execution

Authors Louison Jeanmougin , Thomas Carle , Christine Rochange

PDF HTML 5

Files

Thumbnail PDF
PDF
LIPIcs.ECRTS.2025.11.pdf
  • Filesize: 1.74 MB
  • 26 pages
HTML5 Logo HTML (experimental)
LIPIcs.ECRTS.2025.11.html

Document Identifiers

Subject Classification

ACM Subject Classification
  • Computer systems organization → Real-time systems
  • Computer systems organization → Embedded systems
Keywords
  • GPU
  • WCET analysis

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

This paper proposes to model the Worst-Case Execution Time (WCET) of a GPU thread block as the Worst-Case Response Time (WCRT) of the warps composing the block. Inspired by the WCRT analyzes for classical CPU tasks, the response time of a warp is modeled as its execution time in isolation added to an interference term that accounts for the execution of higher priority warps. We provide an algorithm to build a representation of the execution of each warp of a thread block that distinguishes phases of execution on the functional units and phases of idleness due to operations latency. A simple formula relying on this model is then proposed to safely upper bound the WCRT of warps scheduled under greedy policies such as Greedy-Then-Oldest (GTO) or Loose Round-Robin (LRR). We experimented our approach using simulations of kernels from a GPU benchmark suite on the Accel-Sim simulator. We also evaluated the model on a GPU program that is likely to be found in safety critical systems : SGEMM (Single-precision GEneral Matrix Multiplication). This work constitutes a promising first building block of an analysis pipeline for enabling static WCET computation on GPUs.

Cite As Get BibTex

Louison Jeanmougin, Thomas Carle, and Christine Rochange. Bounding the WCET of a GPU Thread Block with a Multi-Phase Representation of Warps Execution. In 37th Euromicro Conference on Real-Time Systems (ECRTS 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 335, pp. 11:1-11:26, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/LIPIcs.ECRTS.2025.11

Author Details

Louison Jeanmougin
  • Université de Toulouse, IRIT, CNRS, France
Thomas Carle
  • Université de Toulouse, IRIT, CNRS, France
Christine Rochange
  • Université de Toulouse, IRIT, CNRS, France

Funding

  • Jeanmougin, Louison: This work was supported by a grant overseen by the French National Research Agency (ANR) as part of the CAOTIC ANR-22-CE25-0011 project.
  • Carle, Thomas: This work was supported by a grant overseen by the French National Research Agency (ANR) as part of the MeSCAliNe ANR-21-CE25-0012 project. Our work has also benefited from the AI Interdisciplinary Institute ANITI under the Grant agreement n°ANR-23-IACL-0002.

Supplementary Materials

References

  1. S. W. Ali, Z. Tong, J. Goh, and J. H. Anderson. Predictable GPU Sharing in Component-Based Real-Time Systems. In 36th Euromicro Conference on Real-Time Systems (ECRTS 2024), 2024. Google Scholar
  2. Tanya Amert, Nathan Otterness, Ming Yang, James H. Anderson, and F. Donelson Smith. GPU Scheduling on the NVIDIA TX2: Hidden Details Revealed. In Real-Time Systems Symposium (RTSS), 2017. Google Scholar
  3. Jayvant Anantpur and R. Govindarajan. PRO: Progress Aware GPU Warp Scheduling Algorithm. In IEEE Intl Parallel and Distributed Processing Symposium, 2015. Google Scholar
  4. J Bakita and J. H. Anderson. Demystifying nvidia gpu internals to enable reliable gpu management. In 30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS '24, 2024. Google Scholar
  5. Kostiantyn Berezovskyi, Konstantinos Bletsas, and Björn Andersson. Makespan Computation for GPU Threads Running on a Single Streaming Multiprocessor. In Euromicro Conference on Real-Time Systems (ECRTS), 2012. Google Scholar
  6. Adam Betts and Alastair Donaldson. Estimating the WCET of GPU-Accelerated Applications Using Hybrid Analysis. In Euromicro Conference on Real-Time Systems (ECRTS), 2013. Google Scholar
  7. Shuai Che, Michael Boyer, Jiayuan Meng, David Tarjan, Jeremy W Sheaffer, Sang-Ha Lee, and Kevin Skadron. Rodinia: A benchmark suite for heterogeneous computing. In 2009 IEEE international symposium on workload characterization (IISWC), pages 44-54. Ieee, 2009. URL: https://doi.org/10.1109/IISWC.2009.5306797.
  8. N. Crouzet, T. Carle, and C. Rochange. Coordinating the fetch and issue warp schedulers to increase the timing predictability of gpus. In 27th Euromicro Conference on Digital System Design, DSD 2024, Paris, France, August 28-30, 2024, pages 343-350. IEEE, 2024. URL: https://doi.org/10.1109/DSD64264.2024.00053.
  9. N. Feddal, G. Lipari, and H.-E. Zahaf. Towards efficient parallel GPU scheduling: Interference awareness with schedule abstraction. In Proceedings of the 32nd International Conference on Real-Time Networks and Systems, RTNS 2024, Porto, Portugal, November 6-8, 2024, 2024. Google Scholar
  10. S. Gray. maxas project. https://github.com/NervanaSystems/maxas/tree/master?tab=readme-ov-file, 2023.
  11. Vesa Hirvisalo. On Static Timing Analysis of GPU Kernels. In Workshop on Worst-Case Execution Time Analysis (WCET), 2014. Google Scholar
  12. Yijie Huangfu and Wei Zhang. Static WCET Analysis of GPUs with Predictable Warp Scheduling. In International Symposium on Real-Time Distributed Computing (ISORC), 2017. Google Scholar
  13. Louison Jeanmougin, Pascal Sotin, Christine Rochange, and Thomas Carle. Warp-Level CFG Construction for GPU Kernel WCET Analysis. In Workshop on Worst-Case Execution Time Analysis (WCET), 2023. Google Scholar
  14. Mahmoud Khairy, Zhesheng Shen, Tor M. Aamodt, and Timothy G. Rogers. Accel-sim: An extensible simulation framework for validated gpu modeling. In 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), pages 473-486, 2020. URL: https://doi.org/10.1109/ISCA45697.2020.00047.
  15. Shin-Ying Lee, Akhil Arunkumar, and Carole-Jean Wu. CAWA: Coordinated warp scheduling and cache prioritization for critical warp acceleration of GPGPU workloads. ACM SIGARCH Computer Architecture News, 43(3S), 2015. Google Scholar
  16. Ignacio Sañudo Olmedo, Nicola Capodieci, Jorge Luis Martinez, Andrea Marongiu, and Marko Bertogna. Dissecting the CUDA scheduling hierarchy: a Performance and Predictability Perspective. In IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2020. Google Scholar
  17. Nathan Otterness and James H. Anderson. Exploring AMD GPU scheduling details by experimenting with "worst practices". Real Time Systems, 58(2), 2022. URL: https://doi.org/10.1007/S11241-022-09381-Y.
  18. Haluk Ozaktas, Christine Rochange, and Pascal Sainrat. Automatic WCET Analysis of Real-Time Parallel Applications. In 13th Workshop on Worst-Case Execution Time Analysis, 2013. Google Scholar
  19. Timothy G. Rogers, Mike O'Connor, and Tor M. Aamodt. Cache-Conscious Wavefront Scheduling. In IEEE/ACM International Symposium on Microarchitecture, 2012. Google Scholar
  20. Timothy G. Rogers, Mike O'Connor, and Tor M. Aamodt. Divergence-aware warp scheduling. In IEEE/ACM International Symposium on Microarchitecture, 2013. Google Scholar
  21. Jayati Singh, Ignacio Sañudo Olmedo, Nicola Capodieci, Andrea Marongiu, and Marco Caccamo. Reconciling QoS and Concurrency in NVIDIA GPUs via Warp-level Scheduling. In Design, Automation & Test in Europe Conference (DATE), 2022. Google Scholar
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
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact