Subcode-ensemble decoders improve iterative decoding by running multiple decoders in parallel over carefully chosen subcodes, increasing the chance that at least one decoder avoids harmful local graph structures. Achieving strong diversity gains, however, requires constructing many subcodes that satisfy a linear covering property, and existing approaches do not provide an explicit recursive construction that preserves this property as the ensemble grows. This letter introduces hierarchical subcode ensemble decoding (HSCED), which recursively generates subcode parity constraints while maintaining linear covering at every depth. Applied to normalized-min-sum (NMS)-based belief propagation (BP) decoding of the evaluated short 5G NR polar codes, HSCED provides a depth-controlled BLER/decoder-multiplicity trade-off, and its deeper configurations improve the block error rate over RREF-based NMS and conventional SCED under the same fixed maximum BP iteration budget.
Subcode-ensemble decoders improve iterative decoding by running multiple decoders in parallel over carefully chosen subcodes, increasing the chance that at least one decoder avoids harmful local graph structures. Achieving strong diversity gains, however, requires constructing many subcodes that satisfy a linear covering property, and existing approaches do not provide an explicit recursive construction that preserves this property as the ensemble grows. This letter introduces hierarchical subcode ensemble decoding (HSCED), which recursively generates subcode parity constraints while maintaining linear covering at every depth. Applied to normalized-min-sum (NMS)-based belief propagation (BP) decoding of the evaluated short 5G NR polar codes, HSCED provides a depth-controlled BLER/decoder-multiplicity trade-off, and its deeper configurations improve the block error rate over RREF-based NMS and conventional SCED under the same fixed maximum BP iteration budget.
Subcode-ensemble decoders improve iterative decoding by running multiple decoders in parallel over carefully chosen subcodes, increasing the likelihood that at least one decoder avoids the dominant trapping structures. Achieving strong diversity gains, however, requires constructing many subcodes that satisfy a linear covering property-yet existing approaches lack a systematic way to scale the ensemble size while preserving this property. This paper introduces hierarchical subcode ensemble decoding (HSCED), a new ensemble decoding framework that expands the number of constituent decoders while still guaranteeing linear covering. The key idea is to recursively generate subcode parity constraints in a hierarchical structure so that coverage is maintained at every level, enabling large ensembles with controlled complexity. To demonstrate its effectiveness, we apply HSCED to belief propagation (BP) decoding of polar codes, where dense parity-check matrices induce severe stopping-set effects that limit conventional BP. Simulations confirm that HSCED delivers significant block-error-rate improvements over standard BP and conventional subcode-ensemble decoding under the same decoding-latency constraint.
In the short block length regime, ensemble decoding schemes with their inherently parallel structure can improve error correction performance and reduce latency compared to stand-alone suboptimal decoders such as belief propagation (BP). In this work, we introduce affine subcode ensemble decoding (aSCED), which uses an ensemble of decoders operating on linear block codes and both linear and strictly affine subcodes. This generalizes the recently proposed subcode ensemble decoding (SCED), which is restricted to linear subcodes. We derive BP update rules for affine subcodes and show that aSCED simplifies ensemble design compared to SCED, multiple bases BP, and automorphism ensemble decoding. Monte Carlo simulations of four low-density parity-check (LDPC) codes and four Bose–Chaudhuri–Hocquenghem (BCH) codes demonstrate improved error correction performance of aSCED over competing existing ensemble schemes. Notably, for one 5G LDPC code and two BCH codes, aSCED combined with algorithms to construct high-performance parity-check matrices can achieve near-maximum likelihood performance.
Low-density parity-check (LDPC) codes together with belief propagation (BP) decoding yield exceptional error correction capabilities in the large block length regime. Yet, there remains a gap between BP decoding and maximum likelihood decoding for short block length LDPC codes. In this context, ensemble decoding schemes yield both reduced latency and good error rates. In this paper, we propose subcode ensemble decoding (SCED), which employs an ensemble of decodings on different subcodes of the code. To ensure that all codewords are decodable, we use the concept of linear coverings and explore approaches for sampling suitable ensembles for short block length LDPC codes. Monte-Carlo simulations conducted for three LDPC codes demonstrate that SCED improves decoding performance compared to stand-alone decoding and automorphism ensemble decoding. In particular, in contrast to existing schemes, e.g., multiple bases belief propagation and automorphism ensemble decoding, SCED does not require the NP-complete search for low-weight dual codewords or knowledge of the automorphism group of the code, which is often unknown.
Belief-propagation (BP) decoding of short and moderate-length low-density parity-check (LDPC) codes is limited by finite-length graph effects: a single decoder trajectory can become trapped or oscillatory even when an alternative trajectory would decode the received word. Existing ensemble-BP decoders create the required diversity through multiple parity-check matrices, automorphisms, modified schedules, subcodes, or altered update rules. We introduce row-boosted ensemble (RBE) decoding as a minimal decoder-side diversity mechanism: all ensemble members share the same parity-check matrix and the same BP kernel, and differ only in a small set of parity-check rows whose outgoing messages are boosted. On the 5G~NR BG1 (144,96) code, RBE with 32 members lowers the frame-error rate of BP with 20 iterations (BP-20) from 1.6×10−2 to 1.6×10−3 at Eb/N0=4.0dB, outperforming saturated-min-sum and affine subcode ensembles of equal size. Increasing the ensemble size yields additional gains, indicating that RBE provides a scalable performance-complexity tradeoff. The gains transfer across 5G~NR block lengths and rates, to non-5G short LDPC codes, and across flooding and layered schedules.
In the short block length regime, pre-transformed polar codes together with successive cancellation list (SCL) decoding possess excellent error correction capabilities. However, in practice, the list size is limited due to the suboptimal scaling of the required area in hardware implementations. Automorphism ensemble decoding (AED) can improve performance for a fixed list size by running multiple parallel SCL decodings on permuted received words, yielding a list of estimates from which the final estimate is selected. Yet, AED is limited to appropriately designed polar codes. Subcode ensemble decoding (ScED) was recently proposed for low-density parity-check codes and does not impose such design constraints. It uses multiple decodings in different subcodes, ensuring that the selected subcodes jointly cover the original code. We extend ScED to polar codes by expressing polar subcodes through suitable pre-transformations (PTs). To this end, we describe a framework classifying pre-transformations for pretransformed polar codes based on their role in encoding and decoding. Within this framework, we propose a new type of PT enabling ScED for polar codes, analyze its properties, and discuss how to construct an efficient ensemble.
Polar code decoding is an algorithmic challenge that is highly sensitive to the latency and throughput. It is used in 5G NR control channels and demands good noise decoding perfor- mance. Decoders such as successive cancellation (SC) and its list variant (SCL) achieve good bit error rates (BER) throughout the signal-to-noise ratio (SNR) regimes, but suffer from high latency and challenges in parallel implementation due to their sequential nature. The belief propagation (BP) decoder is an alternative representation of the polar graph, which allows parallel decoding over the whole codeword, but requires multiple iterations to reach acceptable BER. The hardware-friendly min-sum (MS) algorithmic simplification uses cheap instructions instead of expensive transcendental operations for higher throughput and lower latency, but further negatively impacts the noise decoding performance. This thesis considers the normalized variation of min-sum (NMS), which adds trainable scales per edge in the BP graph, applied to the 5G N=128 rate 1/2 polar code. The weights are trained by treating the unrolled 5 iteration BP graph as a neural network, which achieves a better-or- equal noise performance compared to the true BP decoder, a 0.5 dB average improvement over the untrained MS, and a 5x lower BER than true BP at 6 dB SNR, making the performance roughly comparable to SC in high SNR regions. These improvements are implemented as a single optimized GPU kernel with further optimiza- tions for better throughput, and run on an NVIDIA H100 GPU. The final achieved throughput peaks at 181 million codewords per second (11.6 information Gbit/s), which is around 25x the throughput of the XLA-compiled Sionna framework running the same decoder, and around 190x of a 192-thread CPU implementation.