TY - JOUR
T1 - Deep Learning-Aided Belief Propagation Decoder for Polar Codes
AU - Xu, Weihong
AU - Tan, Xiaosi
AU - Be'Ery, Yair
AU - Ueng, Yeong Luh
AU - Huang, Yongming
AU - You, Xiaohu
AU - Zhang, Chuan
N1 - Publisher Copyright:
© 2011 IEEE.
PY - 2020/6
Y1 - 2020/6
N2 - 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.
AB - 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.
KW - ASIC implementation
KW - Polar codes
KW - belief propagation (BP)
KW - concatenated codes
KW - deep learning
UR - http://www.scopus.com/inward/record.url?scp=85087199295&partnerID=8YFLogxK
U2 - 10.1109/JETCAS.2020.2995962
DO - 10.1109/JETCAS.2020.2995962
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85087199295
SN - 2156-3357
VL - 10
SP - 189
EP - 203
JO - IEEE Journal on Emerging and Selected Topics in Circuits and Systems
JF - IEEE Journal on Emerging and Selected Topics in Circuits and Systems
IS - 2
M1 - 9097207
ER -