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

IEEE International Symposium on Circuits and Systems proceedings

A parallel LSI architecture for LDPC decoder improving message-passing schedule

Kazumi Shimizu, Tatsuyuki Ishikawa, Nozomu Togawa, Takeshi Ikenaga, Satoshi Goto

Published Sep 22, 2006• 6 citations
Publisher

Abstract

This paper proposes a parallel LSI architecture for LDPC decoder which improves a message-passing schedule. The proposed LDPC decoder is characterized as follows: (i) the column operations follow the row operations in a pipelined architecture to ensure that the row and column operations are performed concurrently; and (ii) the proposed parallel pipelined bit functional unit enables the decoder to perform every column operation using the messages which is updated by the row operations. These column operations can be performed without extending the single iterative decoding delay. Hardware implementation and simulation results show that the proposed decoder improves the decoding throughput and bit error performance with a small hardware overhead

DOI
10.1109/iscas.2006.1693779

Related papers

Partially-Parallel LDPC Decoder Achieving High-Efficiency Message-Passing Schedule

K. SHIMIZU

In this paper, we propose a partially-parallel LDPC decoder which achieves a high-efficiency message-passing schedule. The proposed LDPC decoder is characterized as follows: (i) The column operations follow the row operations in a pipelined architecture to ensure that the row and column operations are performed concurrently. (ii) The proposed parallel pipelined bit functional unit enables the column operation module to compute every message in each bit node which is updated by the row operations. These column operations can be performed without extending the single iterative decoding delay when the row and column operations are performed concurrently. Therefore, the proposed decoder performs the column operations more frequently in a single iterative decoding, and achieves a high-efficiency message-passing schedule within the limited decoding delay time. Hardware implementation on an FPGA and simulation results show that the proposed partially-parallel LDPC decoder improves the decoding throughput and bit error performance with a small hardware overhead.

IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences•Apr 1, 2006•10 citations

Partially-parallel LDPC decoder based on high-efficiency message-passing algorithm

Kazumi Shimizu, Tatsuyuki Ishikawa, Nozomu Togawa +2 more

This paper proposes a partially-parallel LDPC decoder based on a high-efficiency message-passing algorithm. Our proposed partially-parallel LDPC decoder performs the column operations for bit nodes in conjunction with the row operations for check nodes. Bit functional unit with pipeline architecture in our LDPC decoder allows us to perform column operations for every bit node connected to each of check nodes which are updated by the row operations in parallel. Our proposed LDPC decoder improves the tuning when the column operations are performed, accordingly it improves the message-passing efficiency within the limited number of iterations for decoding. We implemented the proposed partially-parallel LDPC decoder on an FPGA, and simulated its decoding performance. Practical simulation shows that our proposed LDPC decoder reduces the number of iterations for decoding, and it improves the bit error performance with a small hardware overhead.

IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD)•Aug 15, 2006•35 citations

Scheduling Algorithm for Partially Parallel Architecture of LDPC Decoder by Matrix Permutation

In‐Cheol Park, Se-Hyeon Kang

The fully parallel LDPC decoding architecture can achieve high decoding throughput, but it suffers from large hardware complexity caused by a large set of processing units (PUs) and complex interconnections. A practical solution of area-efficient decoders is to use the partially parallel architecture in which a PU is shared for several rows or columns. It is important in the partially parallel architecture to determine the rows or columns to be processed in a PU and their processing order. The dependencies between rows and columns should be considered to minimize the overall processing time by overlapping the decoding operations. This paper proposes an efficient scheduling algorithm that can be applied to general LDPC codes, which is based on the concept of matrix permutation. Experimental results show that the proposed scheduling achieves a higher decoding rate, leading to a reduction of 25% processing time on average. A 1024-bit rate-1/2 LDPC decoder, employing the proposed scheduling algorithm, provides almost 1 Gbps decoding throughput and occupies one-fifth the area compared to the fully parallel decoder.

IEEE International Symposium on Circuits and Systems proceedings•Jul 27, 2005•27 citations

A High Throughput H-QC LDPC Decoder

Yi-Hsing Chien, Mong‐Kai Ku

In this paper, design of a high throughput low-density parity-check (LDPC) decoder using overlapped message passing scheduling algorithm is presented. Regular hierarchical quasi-cyclic (H-QC) LDPC code is used in this design to provide good coding performance at long code length. The two-level regular H-QC LDPC code matrix structure is exploited to parallelize the row and column decoding operations. Our scheduling algorithm re-arranges these operations across iteration boundaries to avoid memory access conflicts. The memory requirement is reduced by half compared to pipelined decoders without scheduling. A (12288, 6144) LDPC decoder implemented in FPGA achieves 298 Mbps throughput performance.

IEEE International Symposium on Circuits and Systems proceedings•May 1, 2007•12 citations

Interlaced Column-Row Message-Passing Schedule for Decoding LDPC Codes

Saleh Usman, Mohammad M. Mansour, Ali Chehab

This paper investigates efficient decoding algorithms for LDPC codes. Alternating column-row message-passing (ACRMP) and Interlaced column-row message-passing (I-CRMP) schedules for decoding of LDPC codes are proposed and investigated in this work. Existing serial scheduling schemes for LDPC decoding are based either on column message-passing (MP) or row MP, and roughly converge twice as fast as Gallager's flooding-based MP schedule at high signal-to-noise ratio (SNR). To further accelerate the convergence speed of serial decoders, hybrid column-row MP schedules that perform multiple message passes between check and variable nodes within or between iterations are proposed. Our proposed I-CRMP schedule converges in less than half the number of iterations compared to the best existing serial decoding schedules. Compared to column MP, the added complexity of this scheme is proportional only to check-node-degree times more additions at variable nodes. This increase in complexity is moderate compared to the convergence acceleration factor that the scheme achieves. Superior performance of the proposed I-CRMP scheme is confirmed by decoding randomly generated as well as IEEE 802.11n/ac LDPC codes.

Globecom•Dec 1, 2016•5 citations

An Efficient General-Purpose Quasi-Cyclic LDPC Decoder Architecture

Shunliang Mei

This paper presents an efficient general-purpose QC-LDPC decoder architecture by combining hardware with software.The proposed architecture can be applied to regular and irregular QC-LDPC codes of various rates,lengths and parity-check matrix structures,and supports min-sum approximation decoding algorithms and realizes different message passing scheduling strategies.Some complicated message update is implemented by a hardware accelerator,thus the decoding throughput is improved.According to the quasi-cyclic structure of the parity-check matrix,the messages are stored and processed by blocks in decoding.Parallel message processing can also be realized with a small increase in implementation complexity.

Computer Engineering and Science•Jan 1, 2008•0 citations
This paper proposes a parallel LSI architecture for LDPC decoder which improves a message-passing schedule. The proposed LDPC decoder is characterized as follows: (i) the column operations follow the row operations in a pipelined architecture to ensure that the row and column operations are performed concurrently; and (ii) the proposed parallel pipelined bit functional unit enables the decoder to perform every column operation using the messages which is updated by the row operations. These column operations can be performed without extending the single iterative decoding delay. Hardware implementation and simulation results show that the proposed decoder improves the decoding throughput and bit error performance with a small hardware overhead
In this paper, we propose a partially-parallel LDPC decoder which achieves a high-efficiency message-passing schedule. The proposed LDPC decoder is characterized as follows: (i) The column operations follow the row operations in a pipelined architecture to ensure that the row and column operations are performed concurrently. (ii) The proposed parallel pipelined bit functional unit enables the column operation module to compute every message in each bit node which is updated by the row operations. These column operations can be performed without extending the single iterative decoding delay when the row and column operations are performed concurrently. Therefore, the proposed decoder performs the column operations more frequently in a single iterative decoding, and achieves a high-efficiency message-passing schedule within the limited decoding delay time. Hardware implementation on an FPGA and simulation results show that the proposed partially-parallel LDPC decoder improves the decoding throughput and bit error performance with a small hardware overhead.
This paper proposes a partially-parallel LDPC decoder based on a high-efficiency message-passing algorithm. Our proposed partially-parallel LDPC decoder performs the column operations for bit nodes in conjunction with the row operations for check nodes. Bit functional unit with pipeline architecture in our LDPC decoder allows us to perform column operations for every bit node connected to each of check nodes which are updated by the row operations in parallel. Our proposed LDPC decoder improves the tuning when the column operations are performed, accordingly it improves the message-passing efficiency within the limited number of iterations for decoding. We implemented the proposed partially-parallel LDPC decoder on an FPGA, and simulated its decoding performance. Practical simulation shows that our proposed LDPC decoder reduces the number of iterations for decoding, and it improves the bit error performance with a small hardware overhead.
The fully parallel LDPC decoding architecture can achieve high decoding throughput, but it suffers from large hardware complexity caused by a large set of processing units (PUs) and complex interconnections. A practical solution of area-efficient decoders is to use the partially parallel architecture in which a PU is shared for several rows or columns. It is important in the partially parallel architecture to determine the rows or columns to be processed in a PU and their processing order. The dependencies between rows and columns should be considered to minimize the overall processing time by overlapping the decoding operations. This paper proposes an efficient scheduling algorithm that can be applied to general LDPC codes, which is based on the concept of matrix permutation. Experimental results show that the proposed scheduling achieves a higher decoding rate, leading to a reduction of 25% processing time on average. A 1024-bit rate-1/2 LDPC decoder, employing the proposed scheduling algorithm, provides almost 1 Gbps decoding throughput and occupies one-fifth the area compared to the fully parallel decoder.
In this paper, design of a high throughput low-density parity-check (LDPC) decoder using overlapped message passing scheduling algorithm is presented. Regular hierarchical quasi-cyclic (H-QC) LDPC code is used in this design to provide good coding performance at long code length. The two-level regular H-QC LDPC code matrix structure is exploited to parallelize the row and column decoding operations. Our scheduling algorithm re-arranges these operations across iteration boundaries to avoid memory access conflicts. The memory requirement is reduced by half compared to pipelined decoders without scheduling. A (12288, 6144) LDPC decoder implemented in FPGA achieves 298 Mbps throughput performance.
This paper investigates efficient decoding algorithms for LDPC codes. Alternating column-row message-passing (ACRMP) and Interlaced column-row message-passing (I-CRMP) schedules for decoding of LDPC codes are proposed and investigated in this work. Existing serial scheduling schemes for LDPC decoding are based either on column message-passing (MP) or row MP, and roughly converge twice as fast as Gallager's flooding-based MP schedule at high signal-to-noise ratio (SNR). To further accelerate the convergence speed of serial decoders, hybrid column-row MP schedules that perform multiple message passes between check and variable nodes within or between iterations are proposed. Our proposed I-CRMP schedule converges in less than half the number of iterations compared to the best existing serial decoding schedules. Compared to column MP, the added complexity of this scheme is proportional only to check-node-degree times more additions at variable nodes. This increase in complexity is moderate compared to the convergence acceleration factor that the scheme achieves. Superior performance of the proposed I-CRMP scheme is confirmed by decoding randomly generated as well as IEEE 802.11n/ac LDPC codes.
This paper presents an efficient general-purpose QC-LDPC decoder architecture by combining hardware with software.The proposed architecture can be applied to regular and irregular QC-LDPC codes of various rates,lengths and parity-check matrix structures,and supports min-sum approximation decoding algorithms and realizes different message passing scheduling strategies.Some complicated message update is implemented by a hardware accelerator,thus the decoding throughput is improved.According to the quasi-cyclic structure of the parity-check matrix,the messages are stored and processed by blocks in decoding.Parallel message processing can also be realized with a small increase in implementation complexity.