电子电气工程与控制

存储系统中两级纠错编码方案设计与验证

  • 罗金飞 ,
  • 赵帅兵 ,
  • 覃落雨 ,
  • 王刚 ,
  • 刘晓光
展开
  • 1. 南开大学 计算机学院 天津市网络与数据安全技术重点实验室, 天津 300350;
    2. 中国空间技术研究院, 北京 100086

收稿日期: 2019-06-28

  修回日期: 2019-07-25

  网络出版日期: 2019-09-23

基金资助

国家自然科学基金(61872201,61702521,61602266,U1833114);天津市自然科学基金(17JCYBJC15300,16JCYBJC41900);天津市人工智能重大专项(18ZXZNGX00140,18ZXZNGX00200);中央高校基本科研业务费

Design and verification of two-level error correction coding scheme for stoage systems

  • LUO Jinfei ,
  • ZHAO Shuaibing ,
  • QIN Luoyu ,
  • WANG Gang ,
  • LIU Xiaoguang
Expand
  • 1. The Key Laboratory of Network and Data Security Technology of TianJin, College of Computer Science, Nankai University, Tianjin 300350, China;
    2. China Academy of Space Technology, Beijing 100086, China

Received date: 2019-06-28

  Revised date: 2019-07-25

  Online published: 2019-09-23

Supported by

National Natural Science Foundation of China (61872201, 61702521, 61602266, U1833114); Natural Science Foundation of TianJin(17JCYBJC15300, 16JCYBJC41900); Major Artificial Intelligence Project of TianJin(18ZXZNGX00140, 18ZXZNGX00200); Basic Scientific Research Expenses of Central Universities

摘要

针对恶劣空间环境设计了一种两级存储编码方案,以应对航天系统中存储单元发生多个单粒子翻转(SEU)错误的问题。方案设计的主要思想是根据简单低纠错编码组合出高容错编码,通过编码组合,使用字间编码来纠正字内编码无法纠正的错误,从而使存储系统更加可靠;对两级编码方案提出若干优化策略,以提高编解码性能,使得两级冗余编码效率接近于原始字内编码。实验结果表明,提出的两级冗余编码方案能够较好解决存储系统中发生多个单粒子翻转错误的问题。即与单一的字内编码相比,两级纠错编码方案能够大大降低星上存储系统出现不可修复的概率,保证了星上存储系统的可靠运行。

本文引用格式

罗金飞 , 赵帅兵 , 覃落雨 , 王刚 , 刘晓光 . 存储系统中两级纠错编码方案设计与验证[J]. 航空学报, 2019 , 40(12) : 323250 -323250 . DOI: 10.7527/S1000-6893.2019.23250

Abstract

This paper designs a two-level storage coding scheme for the terrible space environment to deal with the problem of multiple Single-Event Upset (SEU) errors in the storage system. The main idea of the scheme design is to combine high fault-tolerant coding according to simple error correction coding, that is, by combining coding, using inter-word coding to correct errors that cannot be corrected by intra-word coding, so that the storage system is more reliable; then a certain optimization is performed to improve the efficiency of the corresponding coding, so that the two-level coding efficiency is close to the original single-level coding. The experimental results show that the two-level error correction coding scheme can better solve the problem of multiple SEU errors. Compared with the single level coding, the probability of irreparable is greatly reduced, thus ensuring the reliability of the storage system in the space environment.

参考文献

[1] FEYNMAN J, GABRIEL B. High-energy charged particles in space at one astronomical unit[J]. IEEE Transactions on Nuclear Science, 1996, 43(2):344-352.
[2] NORMAND E. Single event upset at ground level[J]. IEEE Transactions on Nuclear Science, 1996, 43(6):2742-2750.
[3] CARMICHAEL C, CAFFREY M, SALAZAR A, et al. Correcting single-event upsets through Virtex partial configuration[EB/OL]. (2000-06-01)[2019-05-29]. http://ebook.pldworld.com/_semiconduc-tors/Xilinx/DataSource%20CD-ROM/Rev.5%20(Q4-2001)/appnotes/xapp216.pdf.
[4] HAMMING R W. Error detecting and error correcting codes[J]. The Bell System Technical Journal, 1950, 29(2):147-160.
[5] CHEN C L, HSIAO M Y. Error-correcting codes for semiconductor memory applications:A state-of-the-art Review[J]. IBM Journal of Research and Development, 1984, 28(2):124-134.
[6] 曹晖, 郑渊, 刘伟鑫, 等. 宇航用SRAM存储器单粒子效应试验研究[J]. 上海航天, 2013, 30(3):60-64. CAO H, ZHENG Y, LIU W X, et al. Single-event effect test of SRAM memory for aerospace[J]. Shanghai Aerospace, 2013, 30(3):60-64(in Chinese).
[7] MOON T K. Error correction coding. Mathematical methods and algorithms[M], Hoboken, NJ:Jhon Wiley and Son, 2005:2001-2006.
[8] ROBERT G. Low-density parity-check codes[J]. IRE Transactions on Information Theory, 1962, 8(1):21-28.
[9] IROM F, NGUYEN D. Single event effect characterization of high density commercial NAND and NOR nonvolatile flash memories[J]. IEEE Transactions on Nuclear Science, 2007, 54(6):2547-2553.
[10] HEIDEL D F, MARSHALL P W, PELLISH J A, et al. Single-event upsets and multiple-bit upsets on a 45 nm SOI SRAM[J]. IEEE Transactions on Nuclear Science, 2009, 56(6):3499-3504.
[11] SINGH A K. Error detection and correction by hamming code[C]//International Conference on Global Trends in Signal Processing, Information Computing and Communication. Piscataway, NJ:IEEE Press, 2016.
[12] GOPPA V D. A new class of linear correcting codes[J]. Probl Peredachi Information, 1970, 6(3):24-30.
[13] KOOPMAN P, CHAKRAVARTY T. Cyclic redundancy code (CRC) polynomial selection for embedded networks[C]//International Conference on Dependable Systems and Networks. Piscataway, NJ:IEEE Press, 2004.
[14] QUINN H, GRAHAM H, KRONE J, et al. Multi-bit upsets in the Virtex devices[R]. Washington, D.C.:NASA, 2007.
[15] PLANK J S. A tutorial on Reed-Solomon coding for fault-tolerance in RAID-like systems[J]. Software:Practice and Experience, 1997, 27(9):995-1012.
[16] ZHOU, Y, HE F Z, HOU N, et al. Parallel ant colony optimization on multi-core SIMD CPUs[J]. Future Generation Computer Systems, 2018, 79(2):473-487.
[17] PLANK J S, SCHUMAN C D, ROBISON B D, et al. Heuristics for optimizing matrix-based erasure codes for fault-tolerant storage systems[C]//IEEE/IFIP International Conference on Dependable Systems and Networks. Piscataway, NJ:IEEE Press, 2012.
[18] ZHOU J R, ROSS K A. Implementing database operations using SIMD instructions[C]//Proceedings of the International Conference on Management of Data. New York:ACM, 2002.
[19] MARTON K, RALUCA B, SUCIU A. Counting bits in parallel[C]//Networking in Education and Research (RoEduNet). Piscataway, NJ:IEEE Press, 2017.
[20] 刘凯哲. 单粒子效应在轨翻转率预计研究[D]. 哈尔滨:黑龙江大学, 2014:39-48. LIU K Z. Research on single-particle effect in-orbit flip rate prediction[D]. Harbin:Heilongjiang University, 2014:39-48(in Chinese).
文章导航

/