Abstract

This paper presents a high-speed low-density parity-check (LDPC) decoder chip using a new decoding algorithm, called a flooding-type update-schedule algorithm. Since node computations are performed using partially updated messages in the proposed algorithm, because of the good similarity among time-consecutive messages, data-transmission bottleneck between nodes for node computation is greatly reduced. Moreover, longer wires between nodes are appropriately divided into several subwires by inserting flip-flops so that system clock frequency for the LDPC decoding scheme can be much increased while maintaining the same BER as a conventional algorithm using fully updated messages. In fact, a throughput of 3.2 Gb/s in a 1024-b LDPC decoder chip under 90 nm CMOS technology is attained with the sufficient BER.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call