Skip to main content
SpringerLink
Log in

Performance Evaluation of a Next-Generation SX-Aurora TSUBASA Vector Supercomputer

  • Conference paper
  • First Online:
High Performance Computing (ISC High Performance 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13948))

Included in the following conference series:

Abstract

Data movement is a key bottleneck in terms of both performance and energy efficiency in modern HPC systems. The NEC SX-series supercomputers have a long history of accelerating memory-intensive HPC applications by providing sufficient memory bandwidth to applications. In this paper, we analyze the performance of a prototype SX-Aurora TSUBASA supercomputer equipped with the brand-new Vector Engine (VE30) processor. VE30 is the first major update to the Vector Engine processor series, and offers significantly improved memory access performance due to its renewed memory subsystem. Moreover, it introduces new instructions and incorporates architectural advancements tailored for accelerating memory-intensive applications. Using standard benchmarks, we demonstrate that VE30 considerably outperforms other processors in both performance and efficiency of memory-intensive applications. We also evaluate VE30 using applications including SPEChpc, and show that VE30 can run real-world applications with high performance. Finally, we discuss performance tuning techniques to obtain maximum performance from VE30.

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 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
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

Notes

  1. 1.

    https://sxauroratsubasa.sakura.ne.jp/documents/guide/pdfs/InstallationGuide_E.pdf.

References

  1. Ariyoshi, K., Matsuzawa, T., Hasegawa, A.: The key frictional parameters controlling spatial variations in the speed of postseismic-slip propagation on a subduction plate boundary. Earth Planet. Sci. Lett. 256(1–2), 136–146 (2007)

    Article  Google Scholar 

  2. Brunst, H., et al.: First experiences in performance benchmarking with the new SPEChpc 2021 suites. In: 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pp. 675–684 (2022)

    Google Scholar 

  3. Cavelan, A., Cabezón, R.M., Grabarczyk, M., Ciorba, F.M.: A smoothed particle hydrodynamics mini-app for exascale. In: Platform for Advanced Scientific Computing Conference (PASC 2020), pp. 1–11 (2020)

    Google Scholar 

  4. Choquette, J., Gandhi, W., Giroux, O., Stam, N., Krashinsky, R.: NVIDIA A100 tensor core GPU: performance and innovation. IEEE Micro 41(2), 29–35 (2021)

    Article  Google Scholar 

  5. Dongarra, J., Heroux, M.A., Luszczek, P.: High-performance conjugate-gradient benchmark: a new metric for ranking high-performance computing systems. Int. J. High Perform. Comput. Appl. 30(1), 3–10 (2016)

    Article  Google Scholar 

  6. Dongarra, J.J., Luszczek, P., Petite, A.: The LINPACK benchmark: past, present and future. Concurr. Comput. Pract. Exp. 15(9), 803–820 (2003)

    Article  Google Scholar 

  7. Egawa, R., et al.: Exploiting the potentials of the second generation SX-Aurora TSUBASA. In: Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS 2020), vol. 2, pp. 39–49 (2020)

    Google Scholar 

  8. Himeno, R.: Himeno benchmark. https://i.riken.jp/en/supercom/documents/himenobmt/

  9. Hsu, K.C., Tseng, H.W.: Accelerating applications using edge tensor processing units. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2021), pp. 1–14 (2021)

    Google Scholar 

  10. Iyer, R., et al.: Advances in microprocessor cache architectures over the last 25 years. IEEE Micro 41(6), 78–88 (2021)

    Article  Google Scholar 

  11. Jouppi, N.P., et al.: Ten lessons from three generations shaped Google’s TPUv4i. In: 48th Annual International Symposium on Computer Architecture (ISCA), pp. 1–14 (2021)

    Google Scholar 

  12. Katoh, Y., Ono, T., Iizima, M.: Numerical simulation of resonant scattering of energetic electrons in the outer radiation belt. Earth Planets Space 57(2), 117–124 (2005). https://doi.org/10.1186/BF03352555

    Article  Google Scholar 

  13. Komatsu, K., et al.: Performance evaluation of a vector supercomputer SX-Aurora TSUBASA. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2018), pp. 685–696 (2018)

    Google Scholar 

  14. Komatsu, K., et al.: Performance and power analysis of a vector computing system. Supercomput. Front. Innov. 8(2), 75–94 (2021)

    Google Scholar 

  15. Li, J., et al.: SPEChpc 2021 benchmark suites for modern HPC systems. In: Companion of the 2022 ACM/SPEC International Conference on Performance Engineering, pp. 15–16 (2022)

    Google Scholar 

  16. Louw, T., Mcintosh-Smith, S.: Using the graphcore IPU for traditional HPC applications. In: 3rd Workshop on Accelerated Machine Learning (AccML) (2021)

    Google Scholar 

  17. Mittal, S.: A survey of cache bypassing techniques. J. Low Power Electron. Appl. 6(2) (2016)

    Google Scholar 

  18. Onodera, A., Komatsu, K., Fujimoto, S., Isobe, Y., Sato, M., Kobayashi, H.: Optimization of the himeno benchmark for SX-Aurora TSUBASA. In: Wolf, F., Gao, W. (eds.) Bench 2020. LNCS, vol. 12614, pp. 127–143. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-71058-3_8

    Chapter  Google Scholar 

  19. Papazian, I.E.: New 3rd Gen Intel® Xeon® scalable processor. In: Hot Chips Symposium (2020)

    Google Scholar 

  20. RISC-V Foundation: RISC-V “V” Vector Extension. Technical report (2021). https://github.com/riscv/riscv-v-spec/releases/tag/v1.0

  21. Rocki, K., et al.: Fast stencil-code computation on a wafer-scale processor. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC20) (2020)

    Google Scholar 

  22. Sato, H., Takagi, Y., Sawaya, K.: High gain antipodal fermi antenna with low cross polarization. IEICE Trans. Commun. E94-B(8), 2292–2297 (2011)

    Google Scholar 

  23. Sato, M., Kobayashi, T., Zeng, Z., Fang, G., Feng, X.: High resolution GPR system for landmine detection. In: Proceedings of International Conference Requirements and Technologies for the Detection, Removal and Neutralization of Landmine and UXO, pp. 548–553 (2003)

    Google Scholar 

  24. Sato, M., et al.: Co-design for A64FX manycore processor and “Fugaku”. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2020), pp. 1–15 (2020)

    Google Scholar 

  25. Shimomura, Y., et al.: A real-time flood inundation prediction on SX-Aurora TSUBASA. In: 29th International Conference on High Performance Computing, Data, and Analytics (HiPC) (2022)

    Google Scholar 

  26. Soga, T., et al.: Performance evaluation of NEC SX-9 using real science and engineering applications. In: International Conference on High Performance Computing Networking, Storage and Analysis (SC 2009), pp. 1–12 (2009)

    Google Scholar 

  27. Standard Performance Evaluation Corporation: SPEChpc 2021 (2021). https://www.spec.org/hpc2021/

  28. Stephens, N., et al.: The ARM scalable vector extension. IEEE Micro 37(2), 26–39 (2017)

    Article  Google Scholar 

  29. The International Centre for Water Hazard and Risk Management: Rainfall-Runoff-Inundation (RRI) model. https://www.pwri.go.jp/icharm/research/rri/index.html

  30. Tsukahara, T., Iwamoto, K., Kawamura, H.: Evolution of material line in turbulent channel flow. In: The 5th International Symposium on Turbulence and Shear Flow Phenomena, pp. 549–554 (2007)

    Google Scholar 

Download references

Acknowledgments

This work was partially supported by MEXT Next Generation High Performance Computing Infrastructures and Applications R &D Program “R &D of A Quantum-Annealing-Assisted Next Generation HPC Infrastructure and its Applications,” and JSPS KAKENHI Grant Numbers JP20H00593, JP20K19808, JP21H03449 and JP22K19764. Part of the experiments were carried out using AOBA-A and AOBA-C at the Cyberscience Center, Tohoku University, SQUID at the Cybermedia Center, Osaka University, and Flow at the Information Technology Center, Nagoya University.

Author information

Authors and Affiliations

  1. Tohoku University, Sendai, Japan

    Keichi Takahashi, Yoichi Shimomura & Hiroyuki Takizawa

  2. NEC Corporation, Tokyo, Japan

    Soya Fujimoto, Satoru Nagase & Yoko Isobe

  3. Tokyo Denki University, Tokyo, Japan

    Ryusuke Egawa

Authors
  1. Keichi Takahashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Soya Fujimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Satoru Nagase
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yoko Isobe
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yoichi Shimomura
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ryusuke Egawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hiroyuki Takizawa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Keichi Takahashi .

Editor information

Editors and Affiliations

  1. University of Maryland, College Park, MD, USA

    Abhinav Bhatele

  2. NVIDIA, Helsinki, Finland

    Jeff Hammond

  3. Université Paris-Saclay, Gif-sur-Yvette, France

    Marc Baboulin

  4. CERFACS, Toulouse, France

    Carola Kruse

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Takahashi, K. et al. (2023). Performance Evaluation of a Next-Generation SX-Aurora TSUBASA Vector Supercomputer. In: Bhatele, A., Hammond, J., Baboulin, M., Kruse, C. (eds) High Performance Computing. ISC High Performance 2023. Lecture Notes in Computer Science, vol 13948. Springer, Cham. https://doi.org/10.1007/978-3-031-32041-5_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-32041-5_19

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-32040-8

  • Online ISBN: 978-3-031-32041-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation