FPGA implementation of highly parallelized decoder logic for network coding (abstract only)

Decoding operation is one of the major performance bottlenecks in network coding applications. To address the problem caused by decoding delay, this paper proposes high-performance decoding logic on the field-programmable gate-array (FPGA). A Galois Field arithmetic logic unit (GF ALU) is implemented with a full parallelization. We claim that the complexity of hardware is reduced by use of the log and anti-log tables. In addition, the fast arithmetic operation is achieved by the parallelized GF ALU architecture, which allows one-row-calculations of a matrix to be performed concurrently. The decoders for four different sizes of the coefficient matrix have been implemented while the degree of parallelism is preserved for each size. The performance is evaluated by comparing with the performance of the decoding operation both on the ARM processor emulator and a real ARM processor. Using a modern Xilinx Virtex-5 device, the decoding time of 3.5 ms for the size 16 x 16 and 190.5 ms for 128 x 128 has been achieved at the operating frequency of 50MHz, which is equal to 12.7 and 21.7 in terms of speedup.

[1]  Sachin Katti,et al.  Trading structure for randomness in wireless opportunistic routing , 2007, SIGCOMM 2007.

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

[3]  Won Woo Ro,et al.  Efficient Parallelized Network Coding for P2P File Sharing Applications , 2009, GPC.

[4]  Chang Hoon Kim,et al.  High-speed division architecture for GF(2/sup m/) , 2002 .

[5]  Zhen Zhang,et al.  Distributed Source Coding for Satellite Communications , 1999, IEEE Trans. Inf. Theory.

[6]  Yunnan Wu,et al.  Network Coding for the Internet and Wireless Networks , 2007, IEEE Signal Processing Magazine.

[7]  F.H.P. Fitzek,et al.  Implementation and Performance Evaluation of Network Coding for Cooperative Mobile Devices , 2008, ICC Workshops - 2008 IEEE International Conference on Communications Workshops.

[8]  T. Itoh,et al.  A Fast Algorithm for Computing Multiplicative Inverses in GF(2^m) Using Normal Bases , 1988, Inf. Comput..

[9]  Zhiyuan Yan,et al.  New Systolic Architectures for Inversion and Division in GF(2^m) , 2003, IEEE Trans. Computers.

[10]  Baochun Li,et al.  How Practical is Network Coding? , 2006, 200614th IEEE International Workshop on Quality of Service.

[11]  Patrick Hamilton,et al.  FPGA implementation of a high speed network interface card for optical burst switched networks , 2004, FPGA '04.

[12]  Muriel Médard,et al.  Symbol-level network coding for wireless mesh networks , 2008, SIGCOMM '08.

[13]  Mohammed Benaissa,et al.  Fast Elliptic Curve Cryptography on FPGA , 2008, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[14]  Shyue-Win Wei,et al.  Fast inverters and dividers for finite field GF(2/sup m/) , 1994, Proceedings of APCCAS'94 - 1994 Asia Pacific Conference on Circuits and Systems.

[15]  Rudolf Ahlswede,et al.  Network information flow , 2000, IEEE Trans. Inf. Theory.

[16]  F.-X. Standaert,et al.  FPGA Implementation(s) of a Scalable Encryption Algorithm , 2008, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[17]  Tracey Ho,et al.  A Random Linear Network Coding Approach to Multicast , 2006, IEEE Transactions on Information Theory.

[18]  Baochun Li,et al.  Random network coding on the iPhone: fact or fiction? , 2009, NOSSDAV '09.