AsyncBTree: Revisiting Binary Tree Topology for Efficient FPGA-Based NoC Implementation

Binary tree topology generally fails to attract network on chip (NoC) implementations due to its low bisection bandwidth. Fat trees are proposed to alleviate this issue by using increasingly thicker links to connect switches towards the root node. This scheme is very efficient in interconnected networks such as computer networks, which use generic switches for interconnection. In an NoC context, especially for field programmable gate arrays (FPGAs), fat trees require more complex switches as we move higher in the hierarchy. This restricts the maximum clock frequency at which the network operates and offsets the higher bandwidth achieved through using fatter links. In this paper, we discuss the implementation of a binary tree-based NoC, which achieves better bandwidth by varying the clock frequency between the switches as we move higher in the hierarchy. This scheme enables using simpler switch architecture, thus supporting higher maximum frequency of operation. The effect on bandwidth and resource requirement of this architecture is compared with other FPGA-based NoCs for different network sizes and traffic patterns.

[1]  B. Ahirwal,et al.  Multi-core Image processing system using Network on Chip interconnect , 2007, 2007 50th Midwest Symposium on Circuits and Systems.

[2]  Norbert Wehn,et al.  Network-on-chip-centric approach to interleaving in high throughput channel decoders , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[3]  James C. Hoe,et al.  CONNECT: re-examining conventional wisdom for designing nocs in the context of FPGAs , 2012, FPGA '12.

[4]  Jens Sparsø,et al.  A router architecture for connection-oriented service guarantees in the MANGO clockless network-on-chip , 2005, Design, Automation and Test in Europe.

[5]  J. Bahn,et al.  A Generic Traffic Model for On-Chip Interconnection Networks , 2008 .

[6]  Kees Goossens,et al.  AEthereal network on chip: concepts, architectures, and implementations , 2005, IEEE Design & Test of Computers.

[7]  Luca Benini,et al.  NoC synthesis flow for customized domain specific multiprocessor systems-on-chip , 2005, IEEE Transactions on Parallel and Distributed Systems.

[8]  Charles E. Leiserson,et al.  Fat-trees: Universal networks for hardware-efficient supercomputing , 1985, IEEE Transactions on Computers.

[9]  Mohan Kumar,et al.  On generalized fat trees , 1995, Proceedings of 9th International Parallel Processing Symposium.

[10]  Alain Greiner,et al.  Bi-Synchronous FIFO for Synchronous Circuit Communication Well Suited for Network-on-Chip in GALS Architectures , 2007, First International Symposium on Networks-on-Chip (NOCS'07).

[11]  Axel Jantsch,et al.  A network on chip architecture and design methodology , 2002, Proceedings IEEE Computer Society Annual Symposium on VLSI. New Paradigms for VLSI Systems Design. ISVLSI 2002.

[12]  William J. Dally,et al.  Principles and Practices of Interconnection Networks , 2004 .

[13]  André DeHon,et al.  FPGA optimized packet-switched NoC using split and merge primitives , 2012, 2012 International Conference on Field-Programmable Technology.

[14]  Kenneth B. Kent,et al.  An Embedded Java Virtual Machine Using Network-on-Chip Design , 2006, Seventeenth IEEE International Workshop on Rapid System Prototyping (RSP'06).

[15]  Edith Beigne,et al.  Communication node architecture in a globaly asynchrone network on-chip system , 2006 .

[16]  Jens Sparsø,et al.  Implementation of guaranteed services in the MANGO clockless network-on-chip , 2006 .

[17]  Cruz Izu,et al.  Analysis of network-on-chip topologies for cost-efficient chip multiprocessors , 2016, Microprocess. Microsystems.

[18]  Sao-Jie Chen,et al.  Networks on Chips: Structure and Design Methodologies , 2012, J. Electr. Comput. Eng..