Abstract
The growing demand for high-performance capabilities in data centers (DCs) leads to adopt heterogeneous solutions. The advantage of specialised hardware is a better support for different types of workloads, and a reduction of the power consumption. Among the others, FPGAs offer the unique capability to provide hardware specialisation and low power consumption. In this context, large arrays of simple and reconfigurable processing elements (PEs), known as coarse-grain reconfigurable arrays (CGRAs), represent a flexible solution for supporting heterogeneous workloads through a specialised instruction set that provides high performance in specific application domains (e.g., image recognition, patterns classification). However, efficient and scalable interconnections are required to sustain throughput and performance of CGRAs. To this end, networks-on-chip (NoCs) have been recognised as a viable solution for better data packet communication. In this paper, we propose an FPGA-aware NoC design targeting CGRAs with 128+ PEs. The proposed design leverages on a two-level topology to scale well with the increasing number of PEs, while the introduction of a software-defined reconfiguration capability offers the opportunity to tailor the set of resources assigned to a specific application. Partitions of physical resources (i.e., virtual domains) are built over the physical topology to meet the required performance, as well as to ease sharing physical chip resources among applications. Experimental evaluation shows the efficiency of our solution regarding used FPGA resources and power consumption.
S. Mazumdar and A. Scionti—Both the authors contributed equally.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Curtis Harting, R., et al.: Energy and performance benefits of active messages. Concurrent VLSI Architectures Group, Stanford University. Technical report, 131 (2012)
Amit, K., et al.: Express virtual channels: towards the ideal interconnection fabric. ACM SIGARCH Comput. Architect. News 35(2), 150–161 (2007)
Hangsheng, W., et al.: Power-driven design of router microarchitectures in on-chip networks. In: IEEE/ACM, Micro (2003)
Kim, J., et al.: Technology-driven, highly-scalable dragonfly topology. ACM SIGARCH Comput. Architect. News 36, 77–88 (2008)
Kim, J., et al.: Flattened butterfly topology for on-chip networks. InL IEEE/ACM, Micro, pp. 172–182 (2007)
Ausavarungnirun, R., et al.: A case for hierarchical rings with deflection routing: an energy-efficient on-chip communication substrate. Parallel Comput. 54, 29–45 (2016)
Reetuparna, D., et al.: Design and evaluation of a hierarchical on-chip interconnect for next-generation CMPS. In: IEEE HPCA (2009)
Bourduas, S., et al.: A hybrid ring/mesh interconnect for network-on-chip using hierarchical rings for global routing. In: NOCS, pp. 195–204. IEEE (2007)
Zheng, N., et al.: Csquare: a new kilo-core-oriented topology. Microprocess. Microsyst. 39(4), 313–320 (2015)
Kim, H., et al.: Transportation-network-inspired network-on-chip. In: IEEE HPCA (2014)
Balfour, J., et al.: Design tradeoffs for tiled CMP on-chip networks. In: Proceedings of the 20th Annual International Conference on Supercomputing, pp. 187–198. ACM (2006)
Parikh, R., et al.: Power-aware NOCS through routing and topology reconfiguration. In: Proceedings of the 51st Annual Design Automation Conference (2014)
Scionti, A., Mazumdar, S., Portero, A.: Software defined network-on-chip for scalable CMPS. In: IEEE HPCS, pp. 112–115 (2016)
Zhu, S.: Hardware implementation based on FPGA of semaphore management in \(\mu \)c/OS-II real-time operating system. IJGUC 6(3–4), 192–199 (2015)
Lynar, T.M., et al.: Resource allocation to conserve energy in distributed computing. IJGUC 2(1), 1–10 (2011)
Kipp, A., et al.: Applying green metrics to optimise the energy-consumption footprint of it service centres. Int. J. Space-Based Situated Comput. 2(3), 158–174 (2012)
Sheng, M., et al.: Whole packet forwarding: efficient design of fully adaptive routing algorithms for networks-on-chip. In: IEEE HPCA (2012)
Junghee, L., et al.: Do we need wide flits in networks-on-chip? In: IEEE ISVLSI (2013)
Acknowledgement
This work is partially supported by the European Union H2020 program through the OPERA project (grant no. 688386), and by the Ministry of Education, Youth and Sports of the National Programme for Sustainability II (NPUII) under the project “IT4Innovations excellence in science – LQ1602”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Mazumdar, S., Scionti, A., Portero, A., Martinovič, J., Terzo, O. (2018). A Scalable and Low-Power FPGA-Aware Network-on-Chip Architecture. In: Barolli, L., Terzo, O. (eds) Complex, Intelligent, and Software Intensive Systems. CISIS 2017. Advances in Intelligent Systems and Computing, vol 611. Springer, Cham. https://doi.org/10.1007/978-3-319-61566-0_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-61566-0_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61565-3
Online ISBN: 978-3-319-61566-0
eBook Packages: EngineeringEngineering (R0)