Analysis and Design of Cost-Effective, High-Throughput LDPC Decoders

TL;DR

This paper presents NS-FAID, a novel hardware-efficient LDPC decoder design that balances complexity and performance, achieving up to 58.75% throughput improvement over traditional Min-Sum decoders.

Contribution

Introduction of NS-FAID, a unified, robust framework for high-throughput LDPC decoding optimized via density evolution, with hardware architectures demonstrating significant throughput-area improvements.

Findings

NS-FAID decoders improve throughput-to-area ratio by up to 58.75%.

NS-FAID maintains comparable error correction performance to Min-Sum decoders.

Hardware architectures integrating NS-FAID achieve high throughput for practical applications.

Abstract

This paper introduces a new approach to cost-effective, high-throughput hardware designs for Low Density Parity Check (LDPC) decoders. The proposed approach, called Non-Surjective Finite Alphabet Iterative Decoders (NS-FAIDs), exploits the robustness of message-passing LDPC decoders to inaccuracies in the calculation of exchanged messages, and it is shown to provide a unified framework for several designs previously proposed in the literature. NS-FAIDs are optimized by density evolution for regular and irregular LDPC codes, and are shown to provide different trade-offs between hardware complexity and decoding performance. Two hardware architectures targeting high-throughput applications are also proposed, integrating both Min-Sum (MS) and NS-FAID decoding kernels. ASIC post synthesis implementation results on 65nm CMOS technology show that NS-FAIDs yield significant improvements in the throughput to area ratio, by up to 58.75% with respect to the MS decoder, with even better or only slightly degraded error correction performance.