Advertisement

Energy-Efficient Acceleration of Spark Machine Learning Applications on FPGAs

  • Christoforos KachrisEmail author
  • Elias Koromilas
  • Ioannis Stamelos
  • Georgios Zervakis
  • Sotirios Xydis
  • Dimitrios Soudris
Chapter

Abstract

Emerging applications like machine learning, graph computations, and generally big data analytics require powerful systems that can process large amounts of data without consuming high power. Furthermore, such emerging applications require fast time-to-market and reduced development times. So to address the large processing requirements of these applications, novel architectures are required in the domain of high-performance and energy-efficient processors.

Notes

Acknowledgements

This project has received funding from the European Union Horizon 2020 research and innovation programme under grant agreement No 687628—VINEYARD H2020. We also thank Xilinx University Program for the kind donation of the software tools and hardware platforms.

References

  1. 1.
    Esmaeilzadeh H, Blem E, Amant RS, Sankaralingam K, Burger D (2013) Power challenges may end the multicore era. Commun ACM 56(2):93–102Google Scholar
  2. 2.
    Martin C (2014) Post-dennard scaling and the final years of Moores Law. Technical reportGoogle Scholar
  3. 3.
    Esmaeilzadeh H, Blem E, Amant RS, Sankaralingam K, Burger D, Burger D (2012) Dark silicon and the end of multicore scaling. IEEE Micro 32(3):122–134Google Scholar
  4. 4.
    Ghasemi E, Chow P. Accelerating apache spark with FPGAs. In: Concurrency and computation: practice and experience, pp e4222–n/a. e4222 cpe.4222Google Scholar
  5. 5.
    Huang M, Wu D, Yu CH, Fang Z, Interlandi M, Condie T, Cong J (2016) Programming and runtime support to blaze FPGA accelerator deployment at datacenter scale. In: Proceedings of the seventh ACM symposium on cloud computing, SoCC ’16. ACM, New York, NY, USA, pp 456–469Google Scholar
  6. 6.
    Chen YT, Cong J, Fang Z, Lei J, Wei P (2016) When spark meets FPGAs: a case study for next-generation dna sequencing acceleration. In: 2016 IEEE 24th annual international symposium on field-programmable custom computing machines (FCCM), pp 29–29, May 2016Google Scholar
  7. 7.
    Cong J, Huang M, Wu D, Yu CH (2016) Invited—heterogeneous datacenters: options and opportunities. In: Proceedings of the 53rd Annual design automation conference, DAC ’16. ACM, New York, NY, USA, pp 16:1–16:6Google Scholar
  8. 8.
    Segal O, Colangelo P, Nasiri N, Qian Z, Margala M (2015) SparkCL: a unified programming framework for accelerators on heterogeneous clusters. arXiv:1505.01120
  9. 9.
    Segal O, Colangelo P, Nasiri N, Qian Z, Margala M (2015) Aparapi-Ucores: A high level programming framework for unconventional cores. In: 2015 IEEE high performance extreme computing conference (HPEC), pp 1–6, Sept 2015Google Scholar
  10. 10.
    Kachris C, Soudris D (2016) A survey on reconfigurable accelerators for cloud computing. In: 2016 26th International conference on field programmable logic and applications (FPL), pp 1–10, Aug 2016Google Scholar
  11. 11.
    Stuecheli J, Blaner B, Johns CR, Siegel MS (2015) CAPI: a coherent accelerator processor interface. IBM J Res Dev 59(1):7:1–7:7Google Scholar
  12. 12.
    Xilinx reconfigurable acceleration stack targets machine learning, data analytics and video streaming. Technical report, 2016Google Scholar
  13. 13.
    Byma S, Steffan JG, Bannazadeh H, Leon-Garcia A, Chow P (2014) FPGAs in the cloud: booting virtualized hardware accelerators with openstack. In: 2014 IEEE 22nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp 109–116, May 2014Google Scholar
  14. 14.
  15. 15.
    Zaharia M, Chowdhury M, Das T, Dave A, Ma J, McCauley M, Franklin MJ, Shenker S, Stoica I (2012) Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX conference on networked systems design and implementation, NSDI’12. USENIX Association, Berkeley, CA, USA, pp 2–2Google Scholar
  16. 16.
    Pynq: Pyhton productivity for Zynq. Technical report, 2016Google Scholar
  17. 17.
    LeCun Y, Cortes C (2010) MNIST handwritten digit databaseGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Christoforos Kachris
    • 1
    Email author
  • Elias Koromilas
    • 1
  • Ioannis Stamelos
    • 1
  • Georgios Zervakis
    • 1
  • Sotirios Xydis
    • 1
  • Dimitrios Soudris
    • 2
  1. 1.Institute of Communication and Computer Systems (ICCS/NTUA)AthensGreece
  2. 2.National Technical University of AthensAthensGreece

Personalised recommendations