LDPC Decoding with Degree-Specific Neural Message Weights and RCQ Decoding

no code implementations • 24 Oct 2023 • Linfang Wang, Caleb Terrill, Richard Wesel, Dariush Divsalar

The neural network complexity to determine distinct weights for each edge is high, often limiting the application to relatively short LDPC codes.

Decoder Quantization

FPGA Implementations of Layered MinSum LDPC Decoders Using RCQ Message Passing

no code implementations • 19 Apr 2021 • Caleb Terrill, Linfang Wang, Sean Chen, Chester Hulse, Calvin Kuo, Richard Wesel, Dariush Divsalar

Non-uniform message quantization techniques such as reconstruction-computation-quantization (RCQ) improve error-correction performance and decrease hardware complexity of low-density parity-check (LDPC) decoders that use a flooding schedule.

Decoder Quantization