Skip to main content
SpringerLink
Log in
SpringerLink
Log in

Detecting SDCs in GPGPUs Through an Efficient Instruction Duplication Mechanism

  • Conference paper
  • First Online:
Knowledge Science, Engineering and Management (KSEM 2021)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12817))

Abstract

As General-Purpose Graphics Processing Units (GPGPUs) are widely used in High-Performance Computing (HPC) applications, the vulnerability of GPGPUs to soft errors becomes a critical concern. In this paper, we propose an efficient instruction duplication mechanism that merely duplicates SDC vulnerable instructions for reliability overhead saving. We first observe that the SDC proneness of individual instruction is related to its instruction type, fault propagation, and whether it affects shared memory. Then, leveraging these observed factors, we utilize machine learning to intelligently identify all the SDC vulnerable instructions of GPU applications and efficiently protect them. Experimental results show that our method achieves a 90.45% SDC coverage only duplicating 37.8% of static instructions, which achieves a significant improvement in terms of performance and SDC detection capability compared to the state-of-the-art duplication technique in GPUs.

This work is supported by the National Natural Science Foundation of China (NSFC) (Grants No. 61772228, No. U19A2061), National key research and development program of China under Grants No. 2017YFC1502306 and Interdisciplinary Research Funding Program for Doctoral Students of Jilin University under Grants No. 101832020DJX063, No. 101832020DJX007.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Grauer-Gray, S., Killian, W., Searles, R., Cavazos, J.: Accelerating financial applications on the GPU. In: 6th Workshop on General Purpose Processor Using Graphics Processing Units, New York, NY, USA, pp. 127–136 (2013)

    Google Scholar 

  2. Gao, Y., Iqbal, S., Zhang, P., Qiu, M.: Performance and power analysis of high-density multi-GPGPU architectures: a preliminary case study. In: IEEE 17th International Conference on High Performance Computing and Communications (HPCC), pp. 29–35 (2015)

    Google Scholar 

  3. Reis, G.A., Chang, J., Vachharajani, N., Rangan, R., August, D.: Swift: software implemented fault tolerance. In: International Symposium on Code Generation and Optimization, pp. 243–254 (2005)

    Google Scholar 

  4. Mahmoud, A., Hari, S., Sullivan, M.B., Tsai, T., Keckler, S.W.: Optimizing software-directed instruction replication for GPU error detection. In: International Conference for High Performance Computing, Networking, Storage, and Analysis (2018)

    Google Scholar 

  5. Kalra, C., Previlon, F., Rubin, N., Kaeli, D.: ArmorAll: compiler-based resilience targeting GPU applications. ACM Trans. Archit. Code Optim. 17(2), 1–24 (2020)

    Article  Google Scholar 

  6. Gai, K., Qiu, M.: Optimal resource allocation using reinforcement learning for IoT content-centric services. Appl. Soft Comput. 70, 12–21 (2018)

    Article  Google Scholar 

  7. Gai, K., Qiu, M.: Reinforcement learning-based content-centric services in mobile sensing. IEEE Netw. 32(4), 34–39 (2018)

    Article  Google Scholar 

  8. Zhao, H., Chen, M., Qiu, M., Gai, K., Liu, M.: A novel pre-cache schema for high performance android system. Future Gener. Comput. Syst. 56, 766–772 (2016)

    Article  Google Scholar 

  9. Qiu, M., Chen, Z., Liu, M.: Low-power low-latency data allocation for hybrid scratch-pad memory. IEEE Embed. Syst. Lett. 6(4), 69–72 (2014)

    Article  Google Scholar 

  10. Wei, X., Yue, H., Tan, J.: LAD-ECC: energy-efficient ECC mechanism for GPGPUs register file. In: Design Automation Test in Europe Conference Exhibition (DATE), pp. 1127–1132 (2020)

    Google Scholar 

  11. Wei, X., Yue, H., Gao, S., Li, L., Zhang, R., Tan, J.: G-SEAP: analyzing and characterizing soft-error aware approximation in GPGPUs. Future Gener. Comput. Syst. 109, 262–274 (2020)

    Article  Google Scholar 

  12. Sangchoolie, B., Pattabiraman, K., Karlsson, J.: One bit is not enough: an empirical study of the impact of single and multiple bit-flip errors. In: 47th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), pp. 97–108 (2017)

    Google Scholar 

  13. Hari, S., Tsai, T., Stephenson, M., Keckler, S.W., Emer, J.: Sassifi: an architecture-level fault injection tool for GPU application resilience evaluation. In: IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 249–258 (2017)

    Google Scholar 

  14. Anwer, A., Li, G., Pattabiraman, K., Sullivan, M., Tsai, T., Hari, S.: GPU-trident: efficient modeling of error propagation in GPU programs. In: SC’20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–15 (2020)

    Google Scholar 

  15. Weiser, M.: Program slicing. IEEE Trans. Softw. Eng. SE–10(4), 352–357 (1984)

    Article  Google Scholar 

  16. Pouchet, L.N.: Polybench: the polyhedral benchmark suite (2012). http://www.cs.ucla.edu/pouchet/software/polybench

  17. Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: IEEE International Symposium on Workload Characterization (IISWC), pp. 44–54 (2009)

    Google Scholar 

  18. Kalra, C., Previlon, F., Li, X., Rubin, N., Kaeli, D.: PRISM: predicting resilience of GPU applications using statistical methods. In: International Conference for High Performance Computing, Networking, Storage, and Analysis (2018)

    Google Scholar 

  19. Laguna, I., Schulz, M., Richards, D.F., Calhoun, J., Olson, L.: IPAS: intelligent protection against silent output corruption in scientific applications. In: International Symposium on Code Generation and Optimization, NY, USA, New York, pp. 227–238 (2016)

    Google Scholar 

  20. Niu, J., Liu, C., Gao, Y., Qiu, M.: Energy efficient task assignment with guaranteed probability satisfying timing constraints for embedded systems. IEEE Trans. Parallel Distrib. Syst. 25(8), 2043–2052 (2013)

    Article  Google Scholar 

  21. Qiu, M., Ming, Z., Wang, J., Yang, L.T., Xiang, Y.: Enabling cloud computing in emergency management systems. IEEE Cloud Comput. 1(4), 60–67 (2014)

    Article  Google Scholar 

  22. Guo, Y., Zhuge, Q., Hu, J., Yi, J., Qiu, M., Sha, E.H.M.: Data placement and duplication for embedded multicore systems with scratch pad memory. IEEE Trans. Comput.-Aided Design Integr. Circuits 32, 809–817 (2013)

    Article  Google Scholar 

  23. Dai, W., Qiu, L., Wu, A., Qiu, M.: Cloud infrastructure resource allocation for big data applications. IEEE Trans. Big Data 4(3), 313–324 (2016)

    Article  Google Scholar 

  24. Feng, S., Gupta, S., Ansari, A., Mahlke, S.: Shoestring: probabilistic soft error reliability on the cheap. SIGARCH Comput. Archit. News 38(1), 385–396 (2010)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Jilin University, Changchun, China

    Xiaohui Wei, Nan Jiang, Xiaonan Wang & Hengshan Yue

Authors
  1. Xiaohui Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaonan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hengshan Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hengshan Yue .

Editor information

Editors and Affiliations

  1. Tsinghua University, Beijing, China

    Han Qiu

  2. Ibaraki University, Hitachi, Japan

    Cheng Zhang

  3. University of Kentucky, Lexington, KY, USA

    Zongming Fei

  4. Texas A&M University – Commerce, Commerce, TX, USA

    Meikang Qiu

  5. Princeton University, Princeton, NJ, USA

    Sun-Yuan Kung

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wei, X., Jiang, N., Wang, X., Yue, H. (2021). Detecting SDCs in GPGPUs Through an Efficient Instruction Duplication Mechanism. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management. KSEM 2021. Lecture Notes in Computer Science(), vol 12817. Springer, Cham. https://doi.org/10.1007/978-3-030-82153-1_47

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-82153-1_47

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-82152-4

  • Online ISBN: 978-3-030-82153-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation