Abstract
Hotspots are Network on-Chip (NoC) routers or modules which occasionally receive packetized traffic at a higher rate that they can process. This phenomenon reduces the performance of an NoC, especially in the case wormhole flow-control. Such situations may also lead to deadlocks, raising the need of a hotspot prevention mechanism. Such mechanism can potentially enable the system to adjust its behavior and prevent hotspot formation, subsequently sustaining performance and efficiency. This Chapter presents an Artificial Neural Network-based (ANN) hotspot prediction mechanism, potentially triggering a hotspot avoidance mechanism before the hotspot is formed. The ANN monitors buffer utilization and reactively predicts the location of an about to-be-formed hotspot, allowing enough time for the system to react to these potential hotspots. The neural network is trained using synthetic traffic models, and evaluated using both synthetic and real application traces. Results indicate that a relatively small neural network can predict hotspot formation with accuracy ranges between 76 and 92%.
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
References
Baydal E et al (2005) A Family of mechanisms for congestion control in wormhole networks. In IEEE TPDS 16(9):772–784 Sept 2005
Bell S et al (2008) TILE64 Processor: A 64-Core SoC with mesh interconnect. In: ISSCC, pp 88–598 Feb 2008
Bertozzi D, Benini L (2004) Xpipes: A Network-on-Chip architecture for gigascale Systems-on-Chip. In: IEEE Circ Syst 4(2):18–31, Second Quarter
Bjerregaard T, Mahadevan S (2006) A survey of research and practices of Network-on-Chip. In ACM CSUR 38(1):1–51 March 2006
Bolotin E et al (2004) QNoC: QoS architecture and design process for Network on Chip. In Elsevier JSA 50(2–3):105–128 Feb 2004
Dally WJ (1992) Virtual-channel flow control. In IEEE TPDS 3(2):94–205 March 1992
Dally WJ, Towles B (2001) Route packets, not wires: on-Chip interconnection networks. In: DAC, pp 684–689 June 2001
Dally WJ, Towles B (2004) Principles and practices of interconnection networks. Morgan kaufmann publishers Inc. ISBN 9780122007514
Daneshtalab M et al (2006) NoC hot spot minimization using antNet dynamic routing algorithm. In: ASAP, pp 33–38 Dec 2006
Duato J et al (2005) A new scalable and cost-effective congestion management strategy for lossless multistage interconnection networks. In: HPCA, pp 108–119 Feb 2005
Goossens K et al (2005) AEtherealn Network on chip: concepts, architectures, and implementations. In: IEEE DTC, pp 414–421 Sept-Oct 2005
Hashem S et al (1999) A novel approach for training neural networks for long-term prediction. In IJCNN 3:1594–1599 July 1999
Hashemi KS et al (1991) On the number of training points needed for adequate training of feedforward neural networks. In: IFNNPS, pp 232–236 July 1991
Ho WS, Eager DL (1989) A novel strategy for controlling hot-spot congestion. In: IEEE ICPP, pp 14–18
Gaughan PT, Yalamanchili S (1993) Adaptive routing protocols for hypercube interconnection networks. In IEEE Computer 26(5):12–23 May 1993
Jain AK et al (1996) Artificial neural networks: a tutorial. In IEEE Computer 29(29):31–44 March 1996
Maqsood I et al (2004) An ensemble of neural networks for weather forecasting. In Neural Computing & Applications 13(2):112–122 June 2004
McCoy A et al (2007) Multistep-Ahead Neural-Network Predictors for Network Traffic Reduction in Distributed Interactive Applications. In: ACM TOMACS 17(4):1–30
Nilsson E et al (2003) Load Distribution with the Proximity Congestion Awareness in a Network on Chip. In: DATE, pp 11126–11127 March 2003
Peh L-S, Dally WJ (2000) Flit-Reservation Flow Control. In: HPCA, pp 73–84 Jan 2000
Pande PP et al (2005) Performance evaluation and design trade-offs for Network-on-Chip interconnect architectures. In IEEE TPDS 54(8):1025–1040 Aug 2005
Sarbazi-Azad H et al (2001) An analytical model of fully-adaptive wormhole-routed k-ary n-cubes in the presence of hot spot traffic. In IEEE TOC 50(7):623–634 July 2001
Steven G et al (2001) Dynamic branch prediction using neural networks. In: DSD, pp 178–185 Sept 2001
Taylor MB et al (2004) Evaluation of the raw microprocessor: an exposed-wire-delay architecture for ILP and streams. In: ISCA, pp 2–13
Teixeira A et al (2000) A multi-objective optimization approach for training artificial neural networks. In: IEEE SBRN, pp 168–172 Jan 2000
Vangal S et al (2007) An 80-tile 1.28TFLOPS Network-on-Chip in 65 nm CMOS. In: ISSCC, pp 98–99 Feb 2007
Walter I et al (2007) Access regulation to hot-modules in wormhole NoCs. In: NoCs, pp 137–148 May 2007
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media B.V.
About this paper
Cite this paper
Kakoulli, E., Soteriou, V., Theocharides, T. (2011). Intelligent NOC Hotspot Prediction. In: Voros, N., Mukherjee, A., Sklavos, N., Masselos, K., Huebner, M. (eds) VLSI 2010 Annual Symposium. Lecture Notes in Electrical Engineering, vol 105. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-1488-5_1
Download citation
DOI: https://doi.org/10.1007/978-94-007-1488-5_1
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-1487-8
Online ISBN: 978-94-007-1488-5
eBook Packages: EngineeringEngineering (R0)