SELF-ADAPTIVE NOC POWER MANAGEMENT WITH DUAL-LEVEL AGENTS - Architecture and Implementation

Syed M. A. H. Jafri, Liang Guang, Axel Jantsch, Kolin Paul, Ahmed Hemani, Hannu Tenhunen

Abstract

Architecture and Implementation of adaptive NoC to improve performance and power consumption is presented. On platforms hosting multiple applications, hardware variations and unpredictable workloads make static design-time assignments highly sub-optimal e.g. in terms of power and performance. As a solution to this problem, adaptive NoCs are designed, which dynamically adapt towards optimal implementation. This paper addresses the architectural design of adaptive NoC, which is an essential step towards design automation. The architecture involves two levels of agents: a system level agent implemented in software on a dedicated general purpose processor and the local agents implemented as microcontrollers of each network node. The system agent issues specific instructions to perform monitoring and reconfiguration operations, while the local agents operate according to the commands from the system agent. To demonstrate the system architecture, best-effort power management with distributed voltage and frequency scaling is implemented, while meeting run-time execution requirements. Four benchmarks (matrix multiplication, FFT, wavefront, and hiperLAN transmitter) are experimented on a cycle-accurate RTL-level shared-memory NoC simulator. Power analysis with 65nm multi-Vdd library shows a significant reduction in energy consumption (from 21 % to 36 %). The synthesis also shows minimal area overhead (4 %) of the local agent compared to the original NoC switch.

References

  1. Asanovic, K., Bodik, R., Catanzaro, B. C., Gebis, J. J., Husbands, P., Keutzer, K., Patterson, D. A., Plishker, W. L., Shalf, J., Williams, S. W., and Yelick, K. A. (2006). The landscape of parallel computing research: A view from berkeley. Technical report, U.C.Berkeley.
  2. Borkar, S., Karnik, T., Narendra, S., Tschanz, J., Keshavarzi, A., and De, V. (2003). Parameter variations and impact on circuits and microarchitecture. In Proc. Design Automation Conference, pages 338-342.
  3. Chabloz, J. M. and Hemani, A. (2010). Distributed dvfs using rationally-related frequencies and discrete voltage levels. In Low-Power Electronics and Design (ISLPED), 2010 ACM/IEEE International Symposium on, pages 247 -252.
  4. Chen, X., Lu, Z., Jantsch, A., and Chen, S. (2010). Supporting distributed shared memory on multi-core networkon-chips using a dual microcoded controller. In Proc. Design, Automation & Test in Europe Conf. & Exhibition (DATE), pages 39-44.
  5. Ciordas, C. (2008). Monitoring-Aware Network-on-Chip Design. PhD thesis, Eindhoven University of Technology.
  6. Ciordas, C., Hansson, A., Goossens, K., and Basten, T. (2008). A monitoring-aware network-on-chip design flow. J. Syst. Archit., 54:397-410.
  7. Dafali, R. and Diguet, J.-P. (2009). Self-adaptive network interface (sani): Local component of a noc configuration manager. In Proc. Int. Conf. Reconfigurable Computing and FPGAs ReConFig 7809, pages 296-301.
  8. Guang, L., Nigussie, E., Isoaho, J., Rantala, P., and Tenhunen, H. (2010). Interconnection alternatives for hierarchical monitoring communication in parallel socs. Microprocessors and Microsystems, 34(5):118-128.
  9. Hoffmann, H., Eastep, J., Santambrogio, M. D., Miller, J. E., and Agarwal, A. (2010). Application heartbeats for software performance and health. In Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming, PPoPP 7810, pages 347-348, New York, NY, USA. ACM.
  10. Howard, J., Dighe, S., Vangal, S. R., Ruhl, G., Borkar, N., Jain, S., Erraguntla, V., Konow, M., Riepen, M., Gries, M., Droege, G., Lund-Larsen, T., Steibl, S., Borkar, S., De, V. K., and Van Der Wijngaart, R. (2011). A 48-core ia-32 processor in 45 nm cmos using on-die message-passing and dvfs for performance and power scaling. IEEE Journal of Solid-State Circuits, 46(1):173-183.
  11. Jean-Michel Chabloz, A. H. (2012). Scalable Multicore Architectures, chapter PowerManagement ArchitectureinMcNoC, pages 55-80. Springer Science+Business Media, LLC.
  12. Nostrum (2011). http://www.ict.kth.se/nostrum/.
  13. Rabaey, J. M. (2007). Scaling the power wall: Revisiting the low-power design rules. Keynote speech at SoC 07 Symposium.
  14. Salehie, M. and Tahvildari, L. (2009). Self-adaptive software: Landscape and research challenges. ACM Trans. Auton. Adapt. Syst., 4:14:1-14:42.
  15. Sylvester, D., Blaauw, D., and Karl, E. (2006). Elastic: An adaptive self-healing architecture for unpredictable silicon. IEEE Design & Test of Computers, 23(6):484-490.
  16. Truong, D., Cheng, W., Mohsenin, T., Yu, Z., Jacobson, A., Landge, G., Meeuwsen, M., Watnik, C., Tran, A., Xiao, Z., Work, E., Webb, J., Mejia, P., and Baas, B. (2009). A 167-processor computational platform in 65 nm cmos. IEEE Journal of Solid State Circuits, 44(4):1130-1144.
  17. van Berkel, C. (2009). Multi-core for mobile phones. In Design, Automation & Test in Europe Conference & Exhibition, 2009. DATE 7809.
Download


Paper Citation


in Harvard Style

M. A. H. Jafri S., Guang L., Jantsch A., Paul K., Hemani A. and Tenhunen H. (2012). SELF-ADAPTIVE NOC POWER MANAGEMENT WITH DUAL-LEVEL AGENTS - Architecture and Implementation . In Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems - Volume 1: SANES, (PECCS 2012) ISBN 978-989-8565-00-6, pages 450-458. DOI: 10.5220/0003942204500458


in Bibtex Style

@conference{sanes12,
author={Syed M. A. H. Jafri and Liang Guang and Axel Jantsch and Kolin Paul and Ahmed Hemani and Hannu Tenhunen},
title={SELF-ADAPTIVE NOC POWER MANAGEMENT WITH DUAL-LEVEL AGENTS - Architecture and Implementation},
booktitle={Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems - Volume 1: SANES, (PECCS 2012)},
year={2012},
pages={450-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003942204500458},
isbn={978-989-8565-00-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems - Volume 1: SANES, (PECCS 2012)
TI - SELF-ADAPTIVE NOC POWER MANAGEMENT WITH DUAL-LEVEL AGENTS - Architecture and Implementation
SN - 978-989-8565-00-6
AU - M. A. H. Jafri S.
AU - Guang L.
AU - Jantsch A.
AU - Paul K.
AU - Hemani A.
AU - Tenhunen H.
PY - 2012
SP - 450
EP - 458
DO - 10.5220/0003942204500458