Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Communications

Deep Reinforcement Learning Aided Scheduling Design for Pipelined Layered QC-LDPC Decoder

Xia An, Chao Zhang, Jian Song, Jintao Wang

Published May 24, 2026• 0 citations
Publisher

Abstract

Due to the widespread use of Low-Density Parity-Check (LDPC) codes in modern wireless communication and broadcasting standards, the architectures of their decoders have been extensively discussed in the literature. In this paper, we propose a unified decoding framework for pipelined layered quasi-cyclic LDPC decoders, which encompasses various decoder architectures as special cases, each corresponding to a specific parameter setting within a three-dimensional parallel architecture. Based on this framework, we derive an optimal grid re-scheduling method to mitigate memory conflicts between layers under a fixed decoding order. We also explore the impact of both adjacent check nodes and previously processed check nodes on the number of inserted NOPs, which leads to a reformulation of the scheduling problem as an episodic Markov decision process. To solve this problem, we apply classical heuristic algorithms, such as genetic programming and Beam Search, and propose a Deep Reinforcement Learning aided approach to further enhance the performance. Experimental results demonstrate that our proposed method outperforms traditional approaches in terms of memory conflict resolution.

DOI
10.1109/icc59461.2026.11587464

Related papers

A Cross-Layer Scheduling Method for Pipelined Layered Multi-Edge Type QC-LDPC Decoder With Better Conflict Resolution

Dongxu Chang, Qingqing Peng, Guanghui Wang +1 more

For multi-edge type quasi-cyclic low-density parity-check (MET-QC-LDPC) codes, the presence of common variable nodes shared between rows within a single layer poses great challenges for the hardware design of the decoder. In this study, a cross-layer update scheduling method for pipelined layered MET-QC-LDPC codes is proposed to achieve improved conflict resolution. Through a probabilistic analysis, we show that by pairing layers with relatively small common degrees and performing alternating updates between the paired layers, better conflict resolution can be achieved than the layer-by-layer updating approach. Experimental results demonstrate that, at medium to low code rates, 50% to 75% of memory conflicts can be mitigated through the proposed cross-layer scheduling compared to the layer-by-layer scheduling approach, without compromising decoding performance.

IEEE Communications Letters•Apr 21, 2025•5 citations

Flexible High Throughput QC-LDPC Decoder With Perfect Pipeline Conflicts Resolution and Efficient Hardware Utilization

Vladimir L. Petrović, Milos M. Markovic, Dragomir El Mezeni +2 more

Modern communication standards, such as 5G new radio (5G NR), require a high speed decoder for highly irregular quasi-cyclic low density parity check (QC-LDPC) codes. A widely used approach in QC-LDPC decoders is a layered decoding schedule which processes the parity check matrix in parts, thus providing faster convergence. However, pipelined layered decoding architecture suffers from data hazards that reduce the throughput. This paper presents a novel architecture, which can facilitate any QC-LDPC decoding without stall cycles caused by pipeline hazards. The decoder conveniently incorporates both the layered and the flooding schedules in cases when hazards occur. The paper also presents the genetic algorithm based optimization of the decoding schedule for better signal-to-noise ratio (SNR) performance. The proposed architecture enables insertion of a large number of pipeline stages, thus providing high operating frequency. As a case study, the FPGA implementation for WiMAX, DVB-S2X, and 5G NR provided coded throughput of up to 1.77 Gbps, 4.32 Gbps, and 4.92 Gbps at 10 iterations, respectively. The results show a strong throughput increase of 30%-109% compared with the conventional layered decoder for 5G NR for the same SNR performance. The decoder provides highly efficient utilization of resources when compared with the state-of-the-art solutions.

IEEE Transactions on Circuits and Systems I Regular Papers•Aug 27, 2020•69 citations

A QC-LDPC construction algorithm for increasing the throughput of layered decoders

Jianjun Zhang, Mingke Dong, Ye Jin

Pipelined layered decoder (PLD) of quasi-cyclic low-density parity-check (QC-LDPC) codes is one of most popular high-throughput decoder in modern communication systems. However, the traditional QC-LDPC codes are not suitable for PLD and lead to memory access conflict problems (MACPs) that reduce the throughput of PLD. Therefore, an efficient layered block progressive edge-growth (EL-BPEG) algorithm is proposed to construct a class of QC-LDPC codes that can avoid MACPs and increase throughput. EL-BPEG appends check nodes, rather than variable nodes, progressively into Tanner Graph with strict concentrated check-node degrees. And it establishes edges according to the latency of the pipelines in PLD; thus, all idle clocks can be eliminated for the PLD with EL-BPEG codes. Result indicates that the throughput of PLD can be improved by 50.2% to 99.2% by using the EL-BPEG codes compared with the traditional QC-LDPC codes. Simulations show that the error performances of EL-BPEG codes are as well as the codes in standards.

IEEE International Conference on Communication Technology (ICCT)•Nov 1, 2013•2 citations

High Throughput QC-LDPC Decoder With Optimized Schedule Policy in Layered Decoding

Chang, Dongxu, Qingqing Peng, Guanghui Wang +1 more

In this study, a scheduling policy of layered decoding for quasi-cycle (QC) low-density parity-check (LDPC) codes with high throughput and good performance is designed. The influence of scheduling on the delay of the decoder's hardware implementation and on the decoding performance are considered simultaneously. Specifically, we analyze the idle time required under various scheduling sequences within a pipelined decoding architecture and formulate the problem as a traveling salesman problem (TSP) aiming at minimizing idle time. Furthermore, considering that different scheduling sequences can affect decoding performance, we refine the graph used to solve the TSP based on scheduling characteristics that promote improved decoding outcomes. Simulation results demonstrate that the identified scheduling sequence achieves a low number of hardware delays while maintaining excellent decoding performance for 5G New Radio (NR) LDPC codes.

arXiv:2505.19027•May 25, 2025•1 citation

Belief Propagation Decoding of Short Graph-Based Channel Codes via Reinforcement Learning

Salman Habib, Allison Beemer, Jörg Kliewer

In this work, we consider the decoding of short sparse graph-based channel codes via reinforcement learning (RL). Specifically, we focus on low-density parity-check (LDPC) codes, which for example have been standardized in the context of 5G cellular communication systems due to their excellent error correcting performance. LDPC codes are typically decoded via belief propagation on the corresponding bipartite (Tanner) graph of the code via flooding, i.e., all check and variable nodes in the Tanner graph are updated at once. We model the node-wise sequential LDPC scheduling scheme as a Markov decision process (MDP), and obtain optimized check node (CN) scheduling policies via RL to improve sequential decoding performance as compared to flooding. In each RL step, an agent decides which CN to schedule next by observing a reward associated with each choice. Repeated scheduling enables the agent to discover the optimized CN scheduling policy which is later incorporated in our RL-based sequential LDPC decoder. In order to reduce RL complexity, we propose a novel graph-induced CN clustering approach to partition the state space of the MDP in such a way that dependencies between clusters are minimized. Compared to standard decoding approaches from the literature, some of our proposed RL schemes not only improve the decoding performance, but also reduce the decoding complexity dramatically once the scheduling policy is learned. By concatenating an outer Hamming code with an inner LDPC code which is decoded based on our learned policy, we demonstrate significant improvements in the decoding performance compared to other LDPC decoding policies.

arXiv:2010.05637•IEEE Journal on Selected Areas in Information Theory•Apr 16, 2021•29 citations

Decoding of Moderate Length LDPC Codes via Learned Clustered Check Node Scheduling

Salman Habib, Allison Beemer, Jörg Kliewer

In this work, we consider the sequential decoding of moderate length low-density parity-check (LDPC) codes via reinforcement learning (RL). The sequential decoding scheme is modeled as a Markov decision process (MDP), and an optimized decoding policy is subsequently obtained via RL. In contrast to our previous works, where an agent learns to schedule only a single check node (CN) within a group (cluster) of CNs per iteration, in this work we train the agent to schedule all CNs in a cluster, and all clusters in every iteration. That is, in each RL step, an agent learns to schedule CN clusters sequentially depending on the reward associated with the outcome of scheduling a particular cluster. We also propose a modified MDP and a uniform sequential decoding policy, enabling the RL-based decoder to be suitable for much longer LDPC codes than the ones studied in our previous work. The proposed RL-based decoder exhibits an SNR gain of almost 0.8 dB for fixed bit error probability over the standard flooding approach.

International Symposium on Wireless Communication Systems•Sep 6, 2021•2 citations
Due to the widespread use of Low-Density Parity-Check (LDPC) codes in modern wireless communication and broadcasting standards, the architectures of their decoders have been extensively discussed in the literature. In this paper, we propose a unified decoding framework for pipelined layered quasi-cyclic LDPC decoders, which encompasses various decoder architectures as special cases, each corresponding to a specific parameter setting within a three-dimensional parallel architecture. Based on this framework, we derive an optimal grid re-scheduling method to mitigate memory conflicts between layers under a fixed decoding order. We also explore the impact of both adjacent check nodes and previously processed check nodes on the number of inserted NOPs, which leads to a reformulation of the scheduling problem as an episodic Markov decision process. To solve this problem, we apply classical heuristic algorithms, such as genetic programming and Beam Search, and propose a Deep Reinforcement Learning aided approach to further enhance the performance. Experimental results demonstrate that our proposed method outperforms traditional approaches in terms of memory conflict resolution.
For multi-edge type quasi-cyclic low-density parity-check (MET-QC-LDPC) codes, the presence of common variable nodes shared between rows within a single layer poses great challenges for the hardware design of the decoder. In this study, a cross-layer update scheduling method for pipelined layered MET-QC-LDPC codes is proposed to achieve improved conflict resolution. Through a probabilistic analysis, we show that by pairing layers with relatively small common degrees and performing alternating updates between the paired layers, better conflict resolution can be achieved than the layer-by-layer updating approach. Experimental results demonstrate that, at medium to low code rates, 50% to 75% of memory conflicts can be mitigated through the proposed cross-layer scheduling compared to the layer-by-layer scheduling approach, without compromising decoding performance.
Modern communication standards, such as 5G new radio (5G NR), require a high speed decoder for highly irregular quasi-cyclic low density parity check (QC-LDPC) codes. A widely used approach in QC-LDPC decoders is a layered decoding schedule which processes the parity check matrix in parts, thus providing faster convergence. However, pipelined layered decoding architecture suffers from data hazards that reduce the throughput. This paper presents a novel architecture, which can facilitate any QC-LDPC decoding without stall cycles caused by pipeline hazards. The decoder conveniently incorporates both the layered and the flooding schedules in cases when hazards occur. The paper also presents the genetic algorithm based optimization of the decoding schedule for better signal-to-noise ratio (SNR) performance. The proposed architecture enables insertion of a large number of pipeline stages, thus providing high operating frequency. As a case study, the FPGA implementation for WiMAX, DVB-S2X, and 5G NR provided coded throughput of up to 1.77 Gbps, 4.32 Gbps, and 4.92 Gbps at 10 iterations, respectively. The results show a strong throughput increase of 30%-109% compared with the conventional layered decoder for 5G NR for the same SNR performance. The decoder provides highly efficient utilization of resources when compared with the state-of-the-art solutions.
Pipelined layered decoder (PLD) of quasi-cyclic low-density parity-check (QC-LDPC) codes is one of most popular high-throughput decoder in modern communication systems. However, the traditional QC-LDPC codes are not suitable for PLD and lead to memory access conflict problems (MACPs) that reduce the throughput of PLD. Therefore, an efficient layered block progressive edge-growth (EL-BPEG) algorithm is proposed to construct a class of QC-LDPC codes that can avoid MACPs and increase throughput. EL-BPEG appends check nodes, rather than variable nodes, progressively into Tanner Graph with strict concentrated check-node degrees. And it establishes edges according to the latency of the pipelines in PLD; thus, all idle clocks can be eliminated for the PLD with EL-BPEG codes. Result indicates that the throughput of PLD can be improved by 50.2% to 99.2% by using the EL-BPEG codes compared with the traditional QC-LDPC codes. Simulations show that the error performances of EL-BPEG codes are as well as the codes in standards.
In this study, a scheduling policy of layered decoding for quasi-cycle (QC) low-density parity-check (LDPC) codes with high throughput and good performance is designed. The influence of scheduling on the delay of the decoder's hardware implementation and on the decoding performance are considered simultaneously. Specifically, we analyze the idle time required under various scheduling sequences within a pipelined decoding architecture and formulate the problem as a traveling salesman problem (TSP) aiming at minimizing idle time. Furthermore, considering that different scheduling sequences can affect decoding performance, we refine the graph used to solve the TSP based on scheduling characteristics that promote improved decoding outcomes. Simulation results demonstrate that the identified scheduling sequence achieves a low number of hardware delays while maintaining excellent decoding performance for 5G New Radio (NR) LDPC codes.
In this work, we consider the decoding of short sparse graph-based channel codes via reinforcement learning (RL). Specifically, we focus on low-density parity-check (LDPC) codes, which for example have been standardized in the context of 5G cellular communication systems due to their excellent error correcting performance. LDPC codes are typically decoded via belief propagation on the corresponding bipartite (Tanner) graph of the code via flooding, i.e., all check and variable nodes in the Tanner graph are updated at once. We model the node-wise sequential LDPC scheduling scheme as a Markov decision process (MDP), and obtain optimized check node (CN) scheduling policies via RL to improve sequential decoding performance as compared to flooding. In each RL step, an agent decides which CN to schedule next by observing a reward associated with each choice. Repeated scheduling enables the agent to discover the optimized CN scheduling policy which is later incorporated in our RL-based sequential LDPC decoder. In order to reduce RL complexity, we propose a novel graph-induced CN clustering approach to partition the state space of the MDP in such a way that dependencies between clusters are minimized. Compared to standard decoding approaches from the literature, some of our proposed RL schemes not only improve the decoding performance, but also reduce the decoding complexity dramatically once the scheduling policy is learned. By concatenating an outer Hamming code with an inner LDPC code which is decoded based on our learned policy, we demonstrate significant improvements in the decoding performance compared to other LDPC decoding policies.
In this work, we consider the sequential decoding of moderate length low-density parity-check (LDPC) codes via reinforcement learning (RL). The sequential decoding scheme is modeled as a Markov decision process (MDP), and an optimized decoding policy is subsequently obtained via RL. In contrast to our previous works, where an agent learns to schedule only a single check node (CN) within a group (cluster) of CNs per iteration, in this work we train the agent to schedule all CNs in a cluster, and all clusters in every iteration. That is, in each RL step, an agent learns to schedule CN clusters sequentially depending on the reward associated with the outcome of scheduling a particular cluster. We also propose a modified MDP and a uniform sequential decoding policy, enabling the RL-based decoder to be suitable for much longer LDPC codes than the ones studied in our previous work. The proposed RL-based decoder exhibits an SNR gain of almost 0.8 dB for fixed bit error probability over the standard flooding approach.