GLB Efficient Global Load Balancing method for moderating congestion in on-chip networks
- 1 July 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Network Congestion can limit the performance of NoC due to increased transmission latency and power consumption. In this paper, to reduce the network congestion, we present an efficient congestion-aware routing method, named Global Load Balancing (GLB). In GLB, packets aggregate and carry congestion information along a path they route. Consequently, this information contains a global view of the path from where the packet is routed. This global congestion information is used as a metric in the arbitration unit in order to give more priority to the packets arriving from congested area. GLB can efficiently balance the load across the links by steering traffic from highly congested regions to low congested areas. Experimental results with synthetic test cases demonstrate that the GLB method provides significant improvement in average network latency (>;19%).Keywords
This publication has 29 references indexed in Scilit:
- An adaptive fuzzy logic-based routing algorithm for networks-on-chipPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Exploring partitioning methods for 3D Networks-on-Chip utilizing adaptive routing modelPublished by Association for Computing Machinery (ACM) ,2011
- Optimal number and placement of Through Silicon Vias in 3D Network-on-ChipPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- A generic adaptive path-based routing method for MPSoCsJournal of Systems Architecture, 2011
- Input-Output Selection Based Router for Networks-on-ChipPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Design and evaluation of a hierarchical on-chip interconnect for next-generation CMPsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- BARP-A Dynamic Routing Protocol for Balanced Distribution of Traffic in NoCsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Performance Evaluation and Design Trade-Offs for Network-on-Chip Interconnect ArchitecturesIEEE Transactions on Computers, 2005
- RASoC: a router soft-core for networks-on-chipPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- DyADPublished by Association for Computing Machinery (ACM) ,2004