Implementation and evaluation of a congestion aware routing algorithm for networks-on-chip

The major part of the state of art routing proposals have a limited view of the NoC congestion, since each router takes decisions based on few neighbors' status. Such local decision may lead packets to other congested regions, therefore being inefficient. The goal of this work is to propose and evaluate an adaptive source routing algorithm, where the path between source and target PEs may be modified due to congestion events. The proposed method requires QoS session establishment and traffic monitoring. A QoS session establishes a connection between two IPs, applying application constraints. Traffic monitoring carries congestion information to the target, leading to a global view of the routing path. Evaluated performance figures include latency, traffic distribution and the delay to switch to a new path. For hot-spot traffic scenarios, the average latency is reduced by 10%. The proposed routing method also achieved a better network occupation.

[1]  Lionel M. Ni,et al.  The turn model for adaptive routing , 1998, ISCA '98.

[2]  The Turn Model for Adaptive Routing , 1998, 25 Years ISCA: Retrospectives and Reprints.

[3]  Radu Marculescu,et al.  DyAD - smart routing for networks-on-chip , 2004, Proceedings. 41st Design Automation Conference, 2004..

[4]  Ming Li,et al.  DyXY - a proximity congestion-aware deadlock-free dynamic routing method for network on chip , 2006, 2006 43rd ACM/IEEE Design Automation Conference.

[5]  Petru Eles,et al.  Buffer Space Optimisation with Communication Synthesis and Traffic Shaping for NoCs , 2006, Proceedings of the Design Automation & Test in Europe Conference.

[6]  Chita R. Das,et al.  ViChaR: A Dynamic Virtual Channel Regulator for Network-on-Chip Routers , 2006, 2006 39th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'06).

[7]  Fernando Gehm Moraes,et al.  Application driven traffic modeling for NoCs , 2006, SBCCI '06.

[8]  Ney Laert Vilar Calazans,et al.  Rate-based scheduling policy for QoS flows in networks on chip , 2007, 2007 IFIP International Conference on Very Large Scale Integration.

[9]  Jörg Henkel,et al.  Run-time adaptive on-chip communication scheme , 2007, 2007 IEEE/ACM International Conference on Computer-Aided Design.

[10]  Kees G. W. Goossens,et al.  Congestion-Controlled Best-Effort Communication for Networks-on-Chip , 2007, 2007 Design, Automation & Test in Europe Conference & Exhibition.

[11]  Stephen W. Keckler,et al.  Regional congestion awareness for load balance in networks-on-chip , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.

[12]  Fabien Clermidy,et al.  A Reconfigurable Baseband Platform Based on an Asynchronous Network-on-Chip , 2008, IEEE Journal of Solid-State Circuits.

[13]  Radu Marculescu,et al.  Analysis and optimization of prediction-based flow control in networks-on-chip , 2008, TODE.

[14]  Masoud Daneshtalab,et al.  BARP-A Dynamic Routing Protocol for Balanced Distribution of Traffic in NoCs , 2008, 2008 Design, Automation and Test in Europe.

[15]  Vincenzo Catania,et al.  Implementation and Analysis of a New Selection Strategy for Adaptive Routing in Networks-on-Chip , 2008, IEEE Transactions on Computers.

[16]  Natalie D. Enright Jerger,et al.  Outstanding Research Problems in NoC Design: System, Microarchitecture, and Circuit Perspectives , 2009, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.