Deep Learning-Aided Belief Propagation Decoder for Polar Codes

Weihong Xu, Xiaosi Tan, Yair Be'Ery, Yeong Luh Ueng, Yongming Huang, Xiaohu You, Chuan Zhang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

34 Scopus citations

Abstract

This paper presents deep learning (DL) methods to optimize polar belief propagation (BP) decoding and concatenated LDPC-polar codes. First, two-dimensional offset Min-Sum (2-D OMS) decoding is proposed to improve the error-correction performance of existing normalized Min-Sum (NMS) decoding. Two optimization methods used in DL, namely back-propagation and stochastic gradient descent, are exploited to derive the parameters of proposed algorithms. Numerical results demonstrate that there is no performance gap between 2-D OMS and exact BP on various code lengths. Then the concatenated OMS algorithms with low complexity are presented for concatenated LDPC-polar codes. As a result, the optimized concatenated OMS decoding yields error-correction performance with CRC-aided successive cancellation list (CA-SCL) decoder of list size 2 on length-1024 polar codes. In addition, the efficient hardware architectures of scalable polar OMS decoder are described and the proposed decoder is reconfigurable to support three code lengths ( N= 256, 512, 1024 ) and two decoding algorithms (2-D OMS and concatenated OMS). The polar OMS decoder implemented on 65 nm CMOS technology achieves a maximum coded throughput of 5.4 Gb/s at E-{b}/N-{0} = 4 dB for code length 1024 and 7.5 Gb/s at E-{b}/N-{0} = 3.5 dB for code length 256, which are comparable to the state-of-the-art polar BP decoders. Moreover, a 5.1 Gb/s throughput at E-{b}/N-{0} = 4 dB is achieved under concatenated OMS decoding mode for code length 1024 with a latency of 200 ns, which is superior to existing CA-SCL decoders that have similar error-correction performance.

Original languageEnglish
Article number9097207
Pages (from-to)189-203
Number of pages15
JournalIEEE Journal on Emerging and Selected Topics in Circuits and Systems
Volume10
Issue number2
DOIs
StatePublished - Jun 2020

Funding

FundersFunder number
Qualcomm TechnologiesNAT-391796, SOW NAT-435533
Six Talent Peak Program of Jiangsu Province2018-DZXX-001
National Science FoundationBK20180059
National Natural Science Foundation of China61871115, 61501116
Natural Science Foundation of Jiangsu Province
Ministry of Science and Technology, TaiwanMOST 107-2221-E-007-017-MY3
Southeast University
National Key Research and Development Program of China2020YFB2205503
Fundamental Research Funds for the Central Universities

    Keywords

    • ASIC implementation
    • Polar codes
    • belief propagation (BP)
    • concatenated codes
    • deep learning

    Fingerprint

    Dive into the research topics of 'Deep Learning-Aided Belief Propagation Decoder for Polar Codes'. Together they form a unique fingerprint.

    Cite this