Open Access
- 4 December 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 467-472
Abstract
Finding optimal message quantization is a key requirement for low complexity belief propagation (BP) decoding. To this end, we propose a floating-point surrogate model that imitates quantization effects as additions of uniform noise, whose amplitudes are trainable variables. We verify that the surrogate model closely matches the behavior of a fixed-point implementation and propose a hand-crafted loss function to realize a trade-off between complexity and error-rate performance. A deep learning-based method is then applied to optimize the message bitwidths. Moreover, we show that parameter sharing can both ensure implementation-friendly solutions and results in faster training convergence than independent parameters. We provide simulation results for 5G low-density parity-check (LDPC) codes and report an error-rate performance within 0.2 dB of floating-point decoding at an average message quantization bitwidth of 3.1 bits. In addition, we show that the learned bitwidths also generalize to other code rates and channelsKeywords
All Related Versions
This publication has 13 references indexed in Scilit:
- A fully-unrolled LDPC decoder based on quantized message passing2015
- Energy Efficient Digital Signal Processing2014
- Quantized Iterative Message Passing Decoders with Low Error Floor for LDPC CodesIEEE Transactions on Communications, 2013
- A new dimension of parallelism in ultra high throughput LDPC decoding2013
- Configurable high-throughput decoder architecture for quasi-cyclic LDPC codes2008
- Reduced-Complexity Decoding of LDPC CodesIEEE Transactions on Communications, 2005
- Reduced complexity iterative decoding of low-density parity check codes based on belief propagationIEEE Transactions on Communications, 1999
- QuantizationIEEE Transactions on Information Theory, 1998
- A recursive approach to low complexity codesIEEE Transactions on Information Theory, 1981
- Low-density parity-check codesIEEE Transactions on Information Theory, 1962