A reconfigurable parallel FPGA accelerator for the adapt-then-combine diffusion LMS algorithm

The combination of diffusion strategies and least-mean-square (LMS) algorithm provides many advantages for adaptive-filter to solve distributed optimization, estimation and inference problems. However, suffering from high computation complexity, software implementation of diffusion LMS algorithm is unsuitable for real-time and portable applications. In order to extend its availability, we design a reconfigurable parallel FPG accelerator by exploring multiple dimensions of parallelism, including: parallel execution of agents state updating, data combining, data training and multi-stages pipeline to speedup the execution time. The accelerator for networks with various number of agents and different input dimensions is implemented. Results demonstrate that, it can achieve a speedup of three orders of magnitude at 100Mhz compared with C implementation for a 32-nodes network with 16-dimensional input-data.

[1]  Ali H. Sayed,et al.  Distributed adaptive learning mechanisms , 2009 .

[2]  Ali H. Sayed,et al.  Incremental Adaptive Strategies Over Distributed Networks , 2007, IEEE Transactions on Signal Processing.

[3]  Federico S. Cattivelli,et al.  Diffusion LMS algorithms with information exchange , 2008, 2008 42nd Asilomar Conference on Signals, Systems and Computers.

[4]  Ali H. Sayed,et al.  Diffusion Least-Mean Squares Over Adaptive Networks: Formulation and Performance Analysis , 2008, IEEE Transactions on Signal Processing.

[5]  Baochun Li,et al.  Parallelized Progressive Network Coding With Hardware Acceleration , 2007, 2007 Fifteenth IEEE International Workshop on Quality of Service.

[6]  M. D. Edwards,et al.  Software acceleration using programmable hardware devices , 1996 .

[7]  Thomas Ertl,et al.  Accelerating 3D convolution using graphics hardware , 1999, Proceedings Visualization '99 (Cat. No.99CB37067).

[8]  Ali H. Sayed,et al.  Diffusion recursive least-squares for distributed estimation over adaptive networks , 2008, IEEE Transactions on Signal Processing.

[9]  Björn Wittenmark.  Adaptive filter theory : Simon Haykin , 1993, Autom..

[10]  Ali H. Sayed,et al.  Diffusion LMS Strategies for Distributed Estimation , 2010, IEEE Transactions on Signal Processing.