A Deeply Pipelined, Highly Parallel and Flexible LDPC Decoder

A deeply pipelined and parallel LDPC decoder architecture is proposed in this paper. The main feature of this architecture is the Δ-update scheme, which relaxes the data dependency requirement and allows for deeper pipelines than typical decoders. The proposed architecture also has the flexibility to handle a large number of codes. Frame error rate performance is shown for three codes with different quantization parameters. Finally, the impact of pipeline depth on processing time and on the energy-delay product (EDP) is evaluated from post-synthesis results. The results show that the ability to have deeper pipelines can lead to large reductions in EDP.