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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
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)
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)
Mirhoseini, A., et al.: Chip placement with deep reinforcement learning. In: arXiv:2004.10746. (2020)
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)
Ding, Y., Botzer, N., Weninger, T.: HetSeq: distributed GPU training on heterogeneous infrastructure. Proc. AAAI Conf. Artif. Intell. 35(17), 15432–15438 (2021)
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)
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)
Davis, W.R., et al.: Demystifying 3D ICs: the pros and cons of going vertical. IEEE Des. Test Comput. 22(6), 498–510 (2005)
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)
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)
Deb, K., Pratap, A., Agarwal, S.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
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)
Boyan, J.A., Moore, A.W.: Learning evaluation functions to improve optimization by local search. J. Mach. Learn. Res. 1, 77–112 (2001)
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
Qualcomm: https://developer.qualcomm.com/blog/heterogeneous-computing-your-demanding-apps (2020). Accessed Apr 2022
Kayiran, O., et al.: Managing GPU concurrency in heterogeneous architectures. In: Proceedings of the IEEE/ACM MICRO. IEEE, Cambridge (2014)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
Leng, J., et al.: GPUWattch: enabling energy optimizations in GPGPUs. In: Proceedings of the ISCA, pp. 487–498. IEEE, Tel-Aviv (2013)
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)
Lysne, O., Skeie, T., Reinemo, S.A., Theiss, I.: Layered routing in irregular networks. IEEE Trans. Parallel Distrib. Syst. 17(1), 51–65 (2006)
Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: Proceedings of the IISWC, pp. 44–54. IEEE, Austin (2009)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
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)