计算机科学 ›› 2023, Vol. 50 ›› Issue (6): 22-28.doi: 10.11896/jsjkx.230300005

• 高性能计算 • 上一篇    下一篇

基于多核CPU的DVB-RCS2并行Turbo译码方法

翟绪论1,2, 张永光1,2, 靳安钊1,2, 强薇1,2, 李梦冰2   

  1. 1 通信信息控制和安全技术重点实验室 浙江 嘉兴 314033
    2 中国电子科技集团公司第三十六研究所 浙江 嘉兴 314033
  • 收稿日期:2023-03-01 修回日期:2023-04-11 出版日期:2023-06-15 发布日期:2023-06-06
  • 通讯作者: 翟绪论(438753351@qq.com)

Parallel DVB-RCS2 Turbo Decoding on Multi-core CPU

ZHAI Xulun1,2, ZHANG Yongguang1,2, JIN Anzhao1,2, QIANG Wei1,2, LI Mengbing2   

  1. 1 The Science and Technology on Communication Information Security Control Laboratory,Jiaxing,Zhejiang 314033,China
    2 The 36th Research Institute of China Electronics Technology Group Corporation,Jiaxing,Zhejiang 314033,China
  • Received:2023-03-01 Revised:2023-04-11 Online:2023-06-15 Published:2023-06-06
  • About author:ZHAI Xulun,born in 1990,postgra-duate,senior engineer.His main research interests include parallel computing and channel coding.

摘要: DVB-RCS2在卫星广播、海事卫星通信、军事卫星通信等领域有着广泛应用,而无论是通信还是军事侦察都需要大吞吐量高速译码。多核CPU算力不断提升以及软件无线电SDR平台的广泛应用,使得基于多核CPU的并行译码成为一种灵活高效的应用方式。为了满足其中双二元Turbo码大吞吐量软件译码的需求,提出了一种基于多核CPU的高速并行软件译码方案。首先对比分析了双二元Turbo码与传统二进制Turbo码的计算复杂度;然后重点对并行计算过程中的内存占用和采用8比特位宽整型数据时的输入量化方法进行了分析和优化,设计了基于多核CPU并行译码的实现方案;最后在Intel 12核CPU上使用SSE并行指令集实现了大于169 Mbps的译码吞吐率,且纠错性能较浮点运算损失小于0.1 dB。通过与现有GPU译码方案对比,说明了所提方案在译码效率和能耗方面的优势,其在高速卫星接收机中具有极高的应用价值。

关键词: DVB-RCS2, 双二元Turbo码, 多核CPU, SIMD并行计算, 高速译码

Abstract: DVB-RCS2 is widely used in satellite broadcasting,maritime satellite communication and military satellite communication fields.For high-throughput software decoding of dual binary Turbo codes in DVB-RCS2 and application of software-defined radio platform,a high-speed parallel software decoding scheme based on multi-core CPU is proposed.Firstly,the computational complexity of dual binary Turbo codes and traditional binary Turbo codes is compared and analyzed.Then,a parallel decoding implementation based on multi-core CPU is designed.The memory footprint and the input quantization method in parallel computing with 8-bit integer data are analyzed and optimized.Finally,our software decoder exceeds 169 Mbps information throughput using the SSE instruction on the Intel 12-core CPU,and the BER performance degradation is less than 0.1dB compared to the floating-point decoder.The results show that proposed implementation is a challenging alternative to GPU implementation in terms of throughput and energy efficiency,and it has an extremely high application value in high-speed satellite receivers.

Key words: DVB-RCS2, Double binary Turbo code, Multi-core CPU, Single instruction multiple data parallel computing, High-throughput decoding

中图分类号: 

  • TN929
[1]ETSI EN 301 545-2 V1.3.1-2020,Digital Video Broadcasting (DVB);Second Generation DVB Interactive Satellite System(DVB-RCS2);part 2:Lower Layers for Satellite Standard[S].2020.
[2]YU S Y,SHI W,PAN Y H.Signal design of airplane-borne sa-tellite high-rate data transmission system based on DVB-RCS[C]//2021 6th International Conference on Intelligent Computing and Signal Processing(ICSP).2021:420-423.
[3]LIU J,HAN Z,LI W.Performance analysis of TCP new renoover satellite DVB-RCS2 random access links[J].IEEE Transactions on Wireless Communications,2020,19(1):435-446.
[4]CHEN H.Research on the compatibility of turbo codec and its FPGA implementation[D].Xi'an:Xidian University,2017.
[5]WANG H H,MA C,KANG C.Turbo decoding method based on multi-core DSP[J].Journal of Chinese Computer Systems,2019,40(2):374-377
[6]FOUKAS X,NIKAEIN N,KASSEM M M,et al.Demo:Flexran:a Software-Defined Ran platform[C]//Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking Conference (MOBICOM).NY,USA,2017:465-467.
[7]BI M Y.Research and implementation of 5G turbo decoderbased on multi-core CPU/GPU[D].Nanjing:Southeast University,2017.
[8]KONG F Y,JIANG X Q,WAN X F,et al.Parallel implementation of GPU-based LDPC enhanced quasi-maximum likelihood decoder[J].Computer Engineering,2020,46(5):207-215.
[9]GAL B,LEROUX C,JEGO C.Multi-Gb/s software decoding of polar codes[J].IEEE Transactions on Signal Processing,2015,63(2):349-359.
[10]GAL B,JEGO C.High-throughput multi-core LDPC decodersbased on x86 processor[J].IEEE Transactions on Parallel and Distributed Systems,2016,27(5):1373-1386
[11]ZHANG S P,QIAN R R,PENG T,et al,High throughput turbo decoder design for GPP platform[C]//7th International Conference on Communications and Networking in China.2012:817-821.
[12]ZHAO M W,CHEN Y F,LIU K,et al.Parallel acceleration of turbo code decoding based on MIC[J].Electronic measurement technology,2019,42(1):126-131.
[13]WANG Y Q,WANG F,LI R C,et al.An efficient CPU-GPU hybrid parallel implementation for DVB-RCS2 receiver[J].Concurrency and Computation:Practice and Experience,2018,30(19):e4529.1-e4529.14.
[14]CASSAGNE A,TONNELLIER T,LEROUX C,et al.Beyond Gbps turbo decoder on multi-core CPUs[C]//International Symposium on Turbo Codes and Iterative Information Proces-sing(ISTC).Brest,France,2016:136-140.
[15]GAL B,JEGO C.Low-latency and high-throughput softwareturbo decoders on multi-core architectures[J].Annals of Telecommunications,2020,75:27-42.
[16]ZHAN M.Research on decoding algorithm and decoder structure design of double binary convolutional turbo codes[D].Chengdu:University of Electronic Science and Technology of China,2013.
[17]BAHL L,COCKE J,JELINEK F,et al.Optimal decoding of li-near codes for minimizing symbol error rate (corresp.)[J].IEEE Transactions on Information Theory,1974,20(2):284-287.
[18]VOGT J,FINGER A.Improving the max-log-MAP turbo decoder[J].Electronics Letters,2000,36(23):1937-1938.
[19]MULLER O,BAGHDADI A,JEZEQUEL M.From parallelism levels to a multi-asip architecture for turbo decoding[J].IEEE Transactions on Very Large Scale Integration (VLSI) Systems,2009,17(1):92-102.
[20]ZHAO R X,PAN K G,WANG X T.A fully-parallel turbo decoding algorithm based on RADIX-4[J].Telecommunication Engineering,2021,61(4):468-475.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!