High-Throughput LDPC Decoders Using A Multiple Split-Row Method

Tinoosh Mohsenin
Bevan M. Baas
VLSI Computation Laboratory
Department of Electrical and Computer Engineering
University of California, Davis

Abstract:

We propose the Multi-Split method which allows further reductions in routing complexity and results in higher throughput, smaller area decoder implementations compared to previously proposed Split-Row decoding method. Multi-Split is especially useful for regular high row weight LDPC codes. A 2048-bit full parallel decoder is implemented in a 0.18 um CMOS technology using standard MinSum, Split-2 and Split-4 methods. The Split-4 decoder delivers 7.1 Gbps throughput with 15 decoding iterations and is 3.2 times smaller, has 2.9 times shorter wires, and delivers 5.2 times higher throughput than the standard MinSum decoder.

Paper

Presentation

Reference

Tinoosh Mohsenin, Bevan M. Baas. "High-Throughput LDPC Decoders Using A Multiple Split-Row Method" In Proceedings of The IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2007.

BibTeX entry

@inproceedings{UCDVCL:2007:ICASSP,
   author    = {Tinoosh Mohsenin and Bevan M. Baas},
   title     = {High-Throughput LDPC Decoders Using A Multiple Split-Row Method},
   booktitle = {EEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'07)},
   month     = April,
   year      = 2007
   }

VCL Lab | ECE Dept. | UC Davis

Last update: Dec 22, 2006