Skip to main content
SpringerLink
Log in

Machine Learning for Heterogeneous Manycore Design

  • Chapter
  • First Online:
Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing

  • 350 Accesses

Abstract

Heterogeneous manycore architectures are the key to efficiently execute compute- and data-intensive applications. This is evident as latest commercial products increasingly rely on heterogeneity for high performance (e.g., Apple M1). However, designing such systems is challenging. As systems use heterogeneity (e.g., a combination of CPUs, GPUs, and accelerators) to improve performance and efficiency, it is important to find designs that optimize simultaneously for each of its different elements. Unfortunately, it is difficult to quickly explore the hardware design space and choose appropriate trade-offs between these heterogeneous requirements in a cost-efficient manner. Machine learning (ML) presents an effective solution to this problem. ML-based design space exploration methods can learn the behavior of the search space in a sample-efficient manner. By learning the behavior of the search space, these algorithms can guide future searches, thereby reducing the effective size of the search space that we need to explore. Here, we present two instances of how ML can be used for heterogeneous manycore design.

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 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover 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

Similar content being viewed by others

References

  1. Kim, R.G., et al.: Imitation learning for dynamic VFI control in large-scale manycore systems. IEEE Trans. Very Large Scale Integr. VLSI Syst. 25(9), 2458–2471 (2017)

    Article  Google Scholar 

  2. Joardar, B.K., Kim, R.G., Doppa, J.R., Pande, P.P., Marculescu, D., Marculescu, R.: Learning-based application-agnostic 3D NoC design for heterogeneous manycore systems. IEEE Trans. Comput. 68(6), 852–866 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  3. Mirhoseini, A., et al.: Chip placement with deep reinforcement learning. In: arXiv:2004.10746. (2020)

    Google Scholar 

  4. Deshwal, A., Jayakodi, N.K., Joardar, B.K., Doppa, J.R., Pande, P.P.: MOOS: a multi-objective design space exploration and optimization framework for NoC enabled manycore systems. ACM Trans. Embed. Comput. Syst. 18(5s, Article 77), 1–23 (2019)

    Article  Google Scholar 

  5. Ding, Y., Botzer, N., Weninger, T.: HetSeq: distributed GPU training on heterogeneous infrastructure. Proc. AAAI Conf. Artif. Intell. 35(17), 15432–15438 (2021)

    Google Scholar 

  6. Hestness, J., Keckler, S.W., Wood, D.A.: GPU computing pipeline inefficiencies and optimization opportunities in heterogeneous CPU-GPU processors. In: Proceedings of the IEEE IISWC, pp. 87–97. IEEE, Atlanta (2015)

    Google Scholar 

  7. Power, J., et al.: Heterogeneous system coherence for integrated CPU-GPU systems. In: Proceedings of the IEEE/ACM MICRO, pp. 457–467. IEEE, Davis (2013)

    Google Scholar 

  8. Davis, W.R., et al.: Demystifying 3D ICs: the pros and cons of going vertical. IEEE Des. Test Comput. 22(6), 498–510 (2005)

    Article  Google Scholar 

  9. Feero, B.S., Pande, P.P.: Networks-on-chip in a three-dimensional environment: a performance evaluation. IEEE Trans. Comput. 53(1), 32–45 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  10. Choi, W., et al.: On-chip communication network for efficient training of deep convolutional networks on heterogeneous manycore systems. IEEE Trans. Comput. 67(5), 672–686 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  11. Deb, K., Pratap, A., Agarwal, S.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)

    Article  Google Scholar 

  12. Bandyopadhyay, S., Saha, S., Maulik, U., Deb, K.: A simulated annealing-based multi-objective optimization algorithm: AMOSA. IEEE Trans. Evol. Comput. 12(3), 269–283 (2008)

    Article  Google Scholar 

  13. Boyan, J.A., Moore, A.W.: Learning evaluation functions to improve optimization by local search. J. Mach. Learn. Res. 1, 77–112 (2001)

    MATH  Google Scholar 

  14. Apple: https://www.apple.com/newsroom/2021/10/introducing-m1-pro-and-m1-max-the-most-powerful-chips-apple-has-ever-built/ (2021). Accessed Apr 2022

  15. Qualcomm: https://developer.qualcomm.com/blog/heterogeneous-computing-your-demanding-apps (2020). Accessed Apr 2022

  16. Kayiran, O., et al.: Managing GPU concurrency in heterogeneous architectures. In: Proceedings of the IEEE/ACM MICRO. IEEE, Cambridge (2014)

    Google Scholar 

  17. Lee, J., Li, S., Kim, H., Yalamanchilli, S.: Design space exploration of on chip ring interconnection for a CPU-GPU heterogeneous architecture. ACM J. Parallel Distrib. Comput. 73(12), 1525–1538 (2013)

    Article  Google Scholar 

  18. Joardar, B.K., et al.: 3D NoC-enabled heterogeneous manycore architectures for accelerating CNN training: performance and thermal trade-offs. In: Proceedings of the IEEE/ACM NOCS. IEEE, Seoul (2017)

    Google Scholar 

  19. Alam, S.M., Jones, R.E., Pozder, S., Jain, A.: Die/wafer stacking with reciprocal design symmetry (RDS) for mask reuse in three-dimensional (3D) integration technology. In: Proceedings of the ISQED, pp. 569–575. IEEE, San Jose (2009)

    Google Scholar 

  20. Zhou, X., Xu, Y., Du, Y., Zhang, Y., Yang, J.: Thermal management for 3D processors via task scheduling. In: Proceedings of the International Conference on Parallel Processing, pp. 115–122. IEEE, Portland (2008)

    Google Scholar 

  21. Mariani, G., Palermo, G., Zaccaria, V., Silvano, C.: OSCAR: an optimization methodology exploiting spatial correlation in multicore design spaces. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 31(5), 740–753 (2012)

    Article  Google Scholar 

  22. Morgan, A.A., Elmiligi, H., El-Kharashi, M.W., Gebali, F.: Multi-objective optimization for networks-on-chip architectures using genetic algorithms. In: Proceedings of the IEEE ISCAS, pp. 3725–3728. IEEE, Paris (2010)

    Google Scholar 

  23. Ozisikyilmaz, B., Memik, G., Choudhary, A.: Efficient system design space exploration using machine learning techniques. In: Proceedings of the ACM/IEEE DAC, pp. 966–969. IEEE, Anaheim (2008)

    Google Scholar 

  24. Ascia, G., Catania, V., Di Nuovo, A.G., Palesi, M., Patti, D.: Efficient design space exploration for application specific systems-on-a-chip. J. Syst. Archit. 53(10), 733–750 (2007)

    Article  Google Scholar 

  25. Wu, C., et al.: A multi-objective model oriented mapping approach for NoC-based computing systems. IEEE Trans. Parallel Distrib. Syst. 28(3), 662–676 (2017)

    Article  Google Scholar 

  26. Das, S., Doppa, J.R., Pande, P.P., Chakrabarty, K.: Design-space exploration and optimization of an energy-efficient and reliable 3-D small-world network-on-chip. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 36(5), 719–732 (2017)

    Article  Google Scholar 

  27. Cong, J., Wei, J., Zhang, Y.: A thermal-driven floorplanning algorithm for 3D ICs. In: Proceedings of the ICCAD, pp. 306–313. IEEE, San Jose (2004)

    Google Scholar 

  28. GitHub: https://github.com/CSU-rgkim/TC_2018_code

  29. Sridhar, A., Vincenzi, A., Ruggiero, M., Brunschwiler, T., Atienza, D.: 3D-ICE: fast compact transient thermal modeling for 3D ICs with inter-tier liquid cooling. In: Proceedings of the ICCAD, pp. 463–470. IEEE, San Jose (2010)

    Google Scholar 

  30. Power, J., Hestness, J., Orr, M., Hill, M., Wood, D.: gem5-gpu: a heterogeneous CPU-GPU simulator. IEEE Comput. Archit. Lett. 14(1), 34–36 (2015)

    Article  Google Scholar 

  31. Zitzler, E., Brockhoff, D., Thiele, L.: The hypervolume indicator revisited: on the design of pareto-compliant indicators via weighted integration. In: Proceedings of the EMO, pp. 862–876. IEEE, Matsushima (2007)

    Google Scholar 

  32. Auger, A., Bader, J., Brockhoff, D., Zitzler, E.: Theory of the hypervolume indicator: optimal mu-distributions and the choice of the reference point. In: Proceedings of the ACM FOGA, pp. 87–102. IEEE, Orlando (2009)

    MATH  Google Scholar 

  33. Leng, J., et al.: GPUWattch: enabling energy optimizations in GPGPUs. In: Proceedings of the ISCA, pp. 487–498. IEEE, Tel-Aviv (2013)

    Google Scholar 

  34. Li, S., et al.: McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures. In: Proceedings of the IEEE/ACM MICRO, pp. 469–480. IEEE, New York (2009)

    Google Scholar 

  35. Lysne, O., Skeie, T., Reinemo, S.A., Theiss, I.: Layered routing in irregular networks. IEEE Trans. Parallel Distrib. Syst. 17(1), 51–65 (2006)

    Article  Google Scholar 

  36. Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: Proceedings of the IISWC, pp. 44–54. IEEE, Austin (2009)

    Google Scholar 

  37. Ross, S., Gordon, G.J., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the AISTATS, pp. 627–635. IEEE, Ft. Lauderdale (2011)

    Google Scholar 

  38. Samal, S.K., Nayak, D., Ichihashi, M., Banna, S., Lim, S.K.: Monolithic 3D IC vs. TSV-based 3D IC in 14 nm FinFET technology. In: 2016 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S), pp. 1–2. IEEE (2016)

    Google Scholar 

  39. Samal, S.K., Panth, S., Samadi, K., Saedi, M., Du, Y., Lim, S.K.: Fast and accurate thermal modeling and optimization for monolithic 3D ICs. In: 2014 51st ACM/EDAC/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2014)

    Google Scholar 

  40. Panth, S., Samadi, K., Du, Y., Lim, S.K.: High-density integration of functional modules using monolithic 3D-IC technology. In: 2013 18th Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 681–686. IEEE (2013)

    Chapter  Google Scholar 

  41. Lee, Y., Lim, S.K.: Ultrahigh density logic designs using monolithic 3-D integration. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 32, 1892–1905 (2013)

    Article  Google Scholar 

  42. Shi, J., et al.: A 14 nm FinFET transistor-level 3D partitioning design to enable high-performance and low-cost monolithic 3D IC. In: 2016 IEEE International Electron Devices Meeting (IEDM), pp. 2.5.1–2.5.4. IEEE (2016)

    Chapter  Google Scholar 

  43. Liu, C., Lim, A.N.D.S.K.: A design tradeoff study with monolithic 3D integration. In: Thirteenth International Symposium on Quality Electronic Design (ISQED), pp. 529–536. IEEE (2012)

    Chapter  Google Scholar 

  44. Panth, S., Samadi, K., Du, Y., Lim, S.K.: Power-performance study of block-level monolithic 3D-ICs considering inter-tier performance variations. In: 2014 51st ACM/EDAC/IEEE Design Automation Conference (DAC), pp. 1–6. IEEE (2014)

    Google Scholar 

  45. Gong, Y., Kong, J., Chung, S.W.: Quantifying the impact of monolithic 3D (M3D) integration on L1 caches. IEEE Trans. Emerg. Top. Comput. 1, 854–865 (2019)

    Google Scholar 

  46. Arka, A.I., et al.: HeM3D: heterogeneous manycore architecture based on monolithic 3D vertical integration. ACM Trans. Des. Autom. Electron. Syst. 26(2, Article 16), 1–21 (2021)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of ECE, University of Houston, Houston, TX, USA

    Biresh Kumar Joardar

  2. School of EECS, Washington State University, Pullman, WA, USA

    Janardhan Rao Doppa & Partha Pratim Pande

Authors
  1. Biresh Kumar Joardar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Janardhan Rao Doppa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Partha Pratim Pande
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Partha Pratim Pande .

Editor information

Editors and Affiliations

  1. Colorado State University, Fort Collins, CO, USA

    Sudeep Pasricha

  2. New York University Abu Dhabi, Abu Dhabi, Abu Dhabi, United Arab Emirates

    Muhammad Shafique

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Joardar, B.K., Doppa, J.R., Pande, P.P. (2024). Machine Learning for Heterogeneous Manycore Design. In: Pasricha, S., Shafique, M. (eds) Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing. Springer, Cham. https://doi.org/10.1007/978-3-031-39932-9_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-39932-9_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-39931-2

  • Online ISBN: 978-3-031-39932-9

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation