Efficient graphics processing unit based layered decoders for quasicyclic low-density parity-check codes

摘要

Because layered low-density parity-check (LDPC) decoding algorithm was proposed, one can exploit therndiversity gain to achieve performance comparable to the traditional two-phase message passing (TPMP)rndecoding but with about twice faster decoding convergence compared to TPMP. In order to reduce therndecoding time of layered LDPC decoder, a graphics processing unit (GPU) is exploited as the modemrnprocessor so that the decoding procedure can be processed in parallel using numerous threads in the GPU.rnIn this paper, we present the parallel algorithms and efficient implementations on the GPU for two differentrnlayered message passing schemes, the row-layered and column-layered decoding. In the experiments, thernquasicyclic LDPC codes for WiFi (802.11n) and WiMAX (802.16e) are decoded by the proposed layeredrnLDPC decoders. The experimental results show that our decoder has good bit error ratio (BER) performancerncomparable to TPMP decoder. The peak throughput is 712 Mbps, which is about two orders ofrnmagnitude faster than that of CPU implementation and comparable to the dedicated hardware solutions.rnCompared to the existing fastest GPU-based implementation, the presented decoder can achieve a performancernimprovement of 2.3 times.