Advertisement

Advanced Computing and Optimization Infrastructure for Extremely Large-Scale Graphs on Post-peta-scale Supercomputers

  • Katsuki Fujisawa
  • Toyotaro Suzumura
  • Hitoshi Sato
  • Koji Ueno
  • Satoshi Imamura
  • Ryo Mizote
  • Akira Tanaka
  • Nozomi Hata
  • Toshio Endo
Chapter

Abstract

In this paper, we present our ongoing research project. The objective of many ongoing research projects in high-performance computing (HPC) areas is to develop an advanced computing and optimization infrastructure for extremely large-scale graphs on the peta-scale supercomputers. The extremely large-scale graphs that have recently emerged in various application fields, such as transportation, social networks, cybersecurity, disaster prevention, and bioinformatics, require fast and scalable analysis. The Graph500 benchmark measures the performance of any supercomputer performing a breadth-first search (BFS) in terms of traversed edges per second (TEPS). In 2014–2017, our project team has achieved about 38.6TeraTEPS on K computer and been a winner at the 8th and 10th to 15th Graph500 benchmark. We commenced our research project for developing the Urban OS (Operating System) for a large-scale city in 2013. The Urban OS, which is regarded as one of the emerging applications of the cyber-physical system (CPS), gathers big data sets of the distribution of people and transportation movements by utilizing sensor technologies and storing them in the cloud storage system. In the next step, we apply optimization, simulation, and deep learning techniques to solve them and check the validity of solutions obtained on the cyberspace. The Urban OS employs the graph analysis system developed by this research project and provides a feedback to a predicting and controlling center to optimize many social systems and services. We briefly explain our ongoing research project for realizing the Urban OS.

Notes

Acknowledgements

This research project was supported by the Japan Science and Technology Agency (JST), the Core Research for Evolutional Science and Technology (CREST), the Center of Innovation Science and Technology based Radical Innovation and Entrepreneurship Program (COI Program), JSPS KAKENHI Grant Number JP 16H01707, and the TSUBAME 2.0 & 2.5 Supercomputer Grand Challenge Program at the Tokyo Institute of Technology.

References

  1. 1.
    Anderson, J.S.M., Nakata, M., Igarashi, R., Fujisawa, K., Yamashita, M.: The second-order reduced density matrix method and the two-dimensional Hubbard model. Comput. Theor. Chem. 1003, 22–27 (2013)CrossRefGoogle Scholar
  2. 2.
    Beamer, S., Asanović, K., Patterson, D.A.: Searching for a parent instead of fighting over children: a fast breadth-first search implementation for Graph500. EECS Department, University of California, UCB/EECS-2011-117, Berkeley (2011)Google Scholar
  3. 3.
    Beamer, S., Asanović, K., Patterson, D.A.: Direction-optimizing breadth-first search. In: Proceedings of the ACM/IEEE International Conference on High Performance Computing, Networking, Storage and Analysis (SC12). IEEE Computer Society, Piscataway (2012)Google Scholar
  4. 4.
    Fujisawa, K., Endo, T., Sato, H., Yamashita, M., Matsuoka, S., Nakata, M.: High-performance general solver for extremely large-scale semidefinite programming problems. In: 2012 ACM/IEEE Conference on Supercomputing, SC12 (2012)Google Scholar
  5. 5.
    Fujisawa, K., Endo, T., Sato, H., Yasui, Y., Matsuzawa, N., Waki, H.: Peta-scale general solver for semidefinite programming problems with over two million constraints, SC 2013 regular, electronic, and educational poster. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC13), Denver (2013)Google Scholar
  6. 6.
    Fujisawa, K., Endo, T., Yasui, Y., Sato, H., Matsuzawa, N., Matsuoka, S., Waki, H.: Peta-scale general solver for semidefinite programming problems with over two million constraints. In: The 28th IEEE International Parallel & Distributed Processing Symposium (IPDPS 2014), Phoenix, pp. 1171–1180 (2014)Google Scholar
  7. 7.
    Fujisawa, K., Suzumura, T., Sato, H., Ueno, K., Yasui, Y., Iwabuchi, K., Endo, T.: Advanced computing & optimization infrastructure for extremely large-scale graphs on post peta-scale supercomputers. In: Proceedings of the Optimization in the Real World –Toward Solving Real-World Optimization Problems–. Series of Mathematics for Industry, pp. 1–13. Springer (2015)Google Scholar
  8. 8.
    Fujisawa, K., Endo, T., Yasui, Y.: Advanced computing & optimization infrastructure for extremely large-scale graphs on post peta-scale supercomputers. In: Proceedings of Mathematical Software, ICMS 2016, 5th International Conference, Berlin, 11–14 July 2016. Lecture Notes in Computer Science, vol. 9725, pp. 265–274. Springer (2016)CrossRefGoogle Scholar
  9. 9.
    Gotoh, J.-y., Fujisawa, K.: Convex optimization approaches to maximally predictable portfolio selection. Optim.: J. Math. Program. Oper. Res. (2012)Google Scholar
  10. 10.
    Imamura, S., Oka, K., Yasui, Y., Inadomi, Y., Fujisawa, K., Endo, T., Ueno, K., Fukazawa, K., Hata, N., Kakibuka, Y., Inoue, K., Ono, T.: Evaluating the impacts of code-level performance tunings on power efficiency. In: 2016 IEEE International Conference on BigData (IEEE BigData 2016), Washington, DCGoogle Scholar
  11. 11.
    Imamura, S., Yasui, Y., Inoue, K., Ono, T., Sasaki, H., Fujisawa, K.: Power-efficient breadth-first search with DRAM row buffer locality-aware address mapping. In: HPGDMP16: High Performance Graph Data Management and Processing Workshop. In Conjunction with International Conference for High Performance Computing, Networking, Storage and Analysis (SC16). IEEE, Piscataway (2016)Google Scholar
  12. 12.
    Iwabuchi, K., Sato, H., Yasui, Y., Fujisawa, K.: Performance analysis of hybrid BFS approach using semi-external memory, SC 2013 regular, electronic, and educational poster. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC13), Denver (2013)Google Scholar
  13. 13.
    Iwabuchi, K., Sato, H., Mizote, R., Yasui, Y., Fujisawa, K., Matsuoka, S.: Hybrid BFS approach using semi-external memory. In: International Workshop on High Performance Data Intensive Computing (HPDIC 2014) in Conjunction with IEEE IPDPS, Phoenix (2014)Google Scholar
  14. 14.
    Iwabuchi, K., Sato, H., Yasui, Y., Fujisawa, K., Matsuoka, S.: NVM-based Hybrid BFS with memory efficient data structure. In: 2014 IEEE International Conference on BigData (IEEE BigData 2014), Washington, DC (2014)Google Scholar
  15. 15.
    Kakibuka, Y., Yasui, Y., Ono, T., Fujisawa, K., Inoue, K.: Performance evaluation of Graph500 considering CPU-DRAM power shifting, SC17 regular, electronic, and educational poster. In: International Conference for High Performance Computing, Networking, Storage and Analysis 17 (SC17), Denver (2017)Google Scholar
  16. 16.
    Kira, A., Iwane, H., Hirokazu, A., Kimura, Y., Fujisawa, K.: An indirect search algorithm for disaster restoration with precedence and synchronization constraints. Pac. J. Math. Indus. 9, 7 (2017). SpringerGoogle Scholar
  17. 17.
    Koch, T., Ralphs, T., Shinano, Y.: Could we use a million cores to solve an integer program?. Math. Methods Oper. Res. 76, 67–93 (2012)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Koch, T., Martin, A., Pfetsch, M.E.: Progress in academic computational integer programming. In: Jünger, M. (eds.) Facets of Combinatorial Optimization – Festschrift for Martin Grötschel, pp. 483–506. Springer, Berlin/Heidelberg (2013)CrossRefGoogle Scholar
  19. 19.
    Nakata, M., Fukuda, M., Fujisawa, K.: Variational approach to electronic structure calculations on second-order reduced density matrices and the N-representability problem. In: Siedentop, H. (ed.) Complex Quantum Systems – Analysis of Large Coulomb Systems, Institute of Mathematical Sciences, National University of Singapore, pp. 163–194 (2013)CrossRefGoogle Scholar
  20. 20.
    Shinano, Y., Achterberg, T., Berthold, T., Heinz, S., Koch, T.: ParaSCIP: a parallel extension of SCIP. In: Competence in High Performance Computing 2010, pp. 135–148. Springer, Berlin/Heidelberg (2012)CrossRefGoogle Scholar
  21. 21.
    Shirahata, K., Sato, H., Matsuoka, S.: Out-of-core GPU memory management for MapReduce-based large-scale graph processing. In: Proceedings of the 2014 IEEE International Conference on Cluster Computing, Madrid (2014)Google Scholar
  22. 22.
    Suzumura, T., Ueno, K.: ScaleGraph: a high-performance library for billion-scale graph analytics. In: 2015 IEEE International Conference on BigData (IEEE BigData 2015), Santa Clara, pp. 76–84 (2015)Google Scholar
  23. 23.
    Suzumura, T., Ueno, K., Sato, H., Fujisawa, K., Matsuoka, S.: A performance characteristics of Graph500 on large-scale distributed environment. In: The Proceedings of the 2011 IEEE International Symposium on Workload Characterization, Austin, pp. 149–158 (2011)Google Scholar
  24. 24.
    Tanaka, A., Hata, N., Tateiwa, N., Fujisawa, K.: Practical approach to evacuation planning via network flow and deep learning. In: The Fourth International Workshop on High Performance Big Graph Data Management, Analysis, and Mining (BigGraphs 2017), to be held in Conjunction with the 2017 IEEE International Conference on Big Data (IEEE BigData 2017), in Boston (2017)Google Scholar
  25. 25.
    Tsujita, Y., Endo, T., Fujisawa, K.: The scalable petascale data-driven approach for the Cholesky factorization with multiple GPUs. In: First International Workshop on Extreme Scale Programming Models and Middleware. In Conjunction with International Conference for High Performance Computing, Networking, Storage and Analysis (SC15), Austin, pp 38–45 (2015)Google Scholar
  26. 26.
    Ueno, K., Suzumura, T.: Highly scalable graph search for the Graph500 benchmark. In: The 21st International ACM Symposium on High-Performance Parallel and Distributed Computing (HPDC 2012), Delft (2012)Google Scholar
  27. 27.
    Ueno, K., Suzumura, T.: Parallel distributed breadth first search on GPU. In: IEEE International Conference on High Performance Computing (HiPC 2013), India (2013)Google Scholar
  28. 28.
    Ueno, K., Suzumura, T., Maruyama, N., Fujisawa, K., Matsuoka, S.: Efficient breadth-first search on massively parallel and distributed memory machines. Data Sci. Eng. 2(1), 22–35 (2017). SpringerGoogle Scholar
  29. 29.
    Yamashita, M., Fujisawa, K., Fukuda, M., Kobayashi, K., Nakata, K., Nakata, M.: Latest developments in the SDPA family for solving large-scale SDPs. In: Anjos, M.F., Lasserre, J.B. (eds.) Handbook on Semidefinite, Conic and Polynomial Optimization. International Series in Operations Research & Management Science, Chapter 24. Springer, Dordrecht (2011)Google Scholar
  30. 30.
    Yamashita, M., Fujisawa, K., Fukuda, M., Nakata, K., Nakata, M.: Parallel solver for semidefinite programming problem having sparse Schur complement matrix. ACM Trans. Math. Softw. 39(12) (2012)MathSciNetCrossRefGoogle Scholar
  31. 31.
    Yasui, Y., Fujisawa, K., Goto, K., Kamiyama, N., Takamatsu, M.: NETAL: high-performance implementation of network analysis library considering computer memory hierarchy. J. Oper. Res. Soc. Jpn. 54(4), 259–280 (2011)MathSciNetCrossRefGoogle Scholar
  32. 32.
    Yasui, Y., Fujisawa, K., Goto, K.: NUMA-optimized parallel breadth-first search on multicore single-node system. In: 2013 IEEE International Conference on BigData (IEEE BigData 2013), Santa Clara (2013)Google Scholar
  33. 33.
    Yasui, Y., Fujisawa, K., Sato, Y.: Fast and energy-efficient breadth-first search on a single NUMA system. In: Intentional Supercomputing Conference (ISC 14), (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Katsuki Fujisawa
    • 1
  • Toyotaro Suzumura
    • 2
  • Hitoshi Sato
    • 3
  • Koji Ueno
    • 4
  • Satoshi Imamura
    • 5
  • Ryo Mizote
    • 3
  • Akira Tanaka
    • 6
  • Nozomi Hata
    • 6
  • Toshio Endo
    • 7
  1. 1.Institute of Mathematics for IndustryKyushu UniversityNishi-ku FukuokaJapan
  2. 2.Barcelona Supercomputer CenterBarcelonaSpain
  3. 3.Artificial Intelligence Research CenterNational Institute of Advanced Industrial Science and TechnologyTokyoJapan
  4. 4.Fixstars CorporationGatecity Osaki West TowerTokyoJapan
  5. 5.Fujitsu Laboratories LTD.KawasakiJapan
  6. 6.Graduate School of MathematicsKyushu UniversityNishi-ku FukuokaJapan
  7. 7.Global Scientific Information and Computing CenterTokyo Institute of TechnologyTokyoJapan

Personalised recommendations