基于周期粒度的级间寄存器备份机制

doi:10.3969/j.issn.0372-2112.2018.10.024

电子学报 ›› 2018, Vol. 46 ›› Issue (10): 2486-2494.DOI: 10.3969/j.issn.0372-2112.2018.10.024

基于周期粒度的级间寄存器备份机制

王晶^1,2,3, 申娇¹, 丁利华¹, 杨星¹, 邱柯妮³, 张伟功³

1. 首都师范大学信息工程学院, 北京 100048;
2. 中国科学院计算技术研究所, 计算机体系结构国家重点实验室, 北京 100190;
3. 首都师范大学电子系统可靠性技术北京市重点实验室, 北京 100048

收稿日期:2017-01-16 修回日期:2017-04-18 出版日期:2018-10-25
- 通讯作者:
- 张伟功
- 作者简介:
- 王晶,女,1982年生于黑龙江哈尔滨,首都师范大学副教授.研究兴趣包括计算机系统结构、容错计算、高能效计算;申娇,女,1991年生于湖北钟祥,硕士研究生,研究方向为计算机体系结构.
- 基金资助:
- 国防973项目; 国家自然科学基金 (No.61772350，No.61472260，No.61741211）; 北京市高水平教师队伍建设计划 (No.CIT&TCD201704082，No.CIT&TCD20170322）; 体系结构国家重点实验室开放课题 (No.CARCH201607）; 北京市科技新星计划 (No.XX2018081）; 深圳市科技计划项目 (No.JCYJ20150529164656096，No.JCYJ20170302153955969）

Backup Mechanism of Pipeline Register Based on Cycle Granularity

WANG Jing^1,2,3, SHEN Jiao¹, DING Li-hua¹, YANG Xing¹, QIU Ke-ni³, ZHANG Wei-gong³

1.College of Information Engineering, Capital Normal University, Beijing 100048, China;
2.State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;
3.Beijing Key Laboratory of Electronic System Reliability and Prognostics, Beijing 100048, China

Received:2017-01-16 Revised:2017-04-18 Online:2018-10-25 Published:2018-10-25
- Corresponding author:
- ZHANG Wei-gong
- Supported by:
- Program of National Program on Key Basic Research Project of China (973 Program); National Natural Science Foundation of China (No.61772350, No.61472260, No.61741211); Construction Plan of Beijing High-level Teacher Team (No.CIT&TCD201704082, No.CIT&TCD20170322); Open Project of State Key Laboratory of Computer Architecture, ICT, CAS (No.CARCH201607); Beijing Nova Program for Science and Technology (No.XX2018081); Science and Technology Program of Shenzhen (No.JCYJ20150529164656096, No.JCYJ20170302153955969)

摘要/Abstract

摘要： 单粒子翻转是空间环境下微处理器发生异常的重要诱因之一，随着集成电路特征尺寸的缩小，单粒子翻转不仅会引发单位错误，还会引发大量的多位错误，如何有效解决处理器所面临的多位故障是容错处理器设计面临的新挑战.本文提出了一种基于周期粒度的级间寄存器备份机制的容错方法，采用双流水线冗余结构，通过比较器对比两条流水线的级间寄存器以检测单粒子故障；以周期粒度对级间寄存器的内容进行备份，当检测到单粒子故障时，使用2个周期对流水线进行恢复；为避免脏数据流出流水线，在数据缓存和寄存器堆的入口设置写缓冲，通过延迟写入保证信息可靠性.本文基于实际的SPARC V8结构处理器，对提出的方法进行了具体实现，在实验平台上进行了仿真，仿真结果显示，本文提出的容错方法能够以一定的面积开销实现对SEU、SET、和MBU故障容错，加固处理器的主频最高可以提升70%.

关键词: 单粒子翻转, 多位故障, 容错, 备份, 写缓冲, 流水线加固

Abstract: SEU is one of the important causes for the microprocessor in which the exception occurs in space environment. SEU not only causes single-bit error, but does lead to a number of multi-bit errors, along with the reduction of the IC feature size. It is a great challenge that we find a way to effectively cope with the multi-bit error. This paper proposes a fault-tolerant method which backs up the pipeline registers based on cycle granularity, the dual modular redundancy is applied in this method. The pipeline registers on the two pipelines are compared through the comparators to detect the error and the pipeline registers are backed up based on cycle granularity. It takes two cycles to restore the error pipeline when the error is detected. The write buffer is set in the entrance to the data cache and register file to avoid dirty data flowing out of the pipeline. And we can ensure the data is correct through delay write. This paper implements the fault-tolerant method based on SPARC V8 processor and tests in the simulation environment. The simulation results shows that the CPU clock speed of the hardened processor in which the proposed fault-tolerant method is applied can increase 70% at most and the fault-tolerance of the SEU, SET and MBU is implemented with the limited area overhead.

Key words: SEU, MBU, fault tolerance, back-up, write-buffer, pipeline hardened

中图分类号:

TP302.8

王晶, 申娇, 丁利华, 等. 基于周期粒度的级间寄存器备份机制[J]. 电子学报, 2018, 46(10): 2486-2494.

WANG Jing, SHEN Jiao, DING Li-hua, et al. Backup Mechanism of Pipeline Register Based on Cycle Granularity[J]. Acta Electronica Sinica, 2018, 46(10): 2486-2494.

参考文献

[1] El-Sayed.N,Schroeder.B.Reading between the lines of failure logs:Understanding how HPC systems fail[A].343rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks[C].IEEE,2013.1-12.
[2] Dan Ernst,Nam Sung Kim,et al.Razor:A low-power pipeline based on circuit-level timing speculation[A].IEEE Micro[C].IEEE,2003.1-9.
[3] N.Wand and S.Patel.Restore:Symptom-based soft error detection in microprocessors[J].IEEE Trans Dependable Secure Comput,2006,3(3):188-201.
[4] Cristian Constantinescu.Trends and Challenges in VLSI Circuit Reliability[J].IEEE Micro,2003,23(4):14-19.
[5] 毛南,黄岚,王忠义,刘志存.实时嵌入式容错系统的关键技术研究[J].计算机工程与设计,2007,28(14):3433-3435. Mao Nan,Huang Lan,Wang Zhong-yi,Liu Zhi-cun.Key techniques for fault-tolerant real-time embedded system[J].Computer Engineering and Design,2007,28(14):3433-3435.(in Chinese)
[6] L Spainhower,T A.Gregg.IBM S/390 parallel enterprise server G5 fault tolerance:A historical perspective[J].IBM Journal of Research and Development,1999,43(5/6):863-873.
[7] P Meaney,S Swaney,et al.IBM z990 Soft error detection and recovery[J].IEEE Tran on Device and Materials Reliability,2005,5(3):419-427.
[8] Todd M Austin.DIVA:A reliable substrate for deep submicron microarchitecture design[A].32nd International Symposium on Microarchitecture[C].IEEE,1999.1-12.
[9] Wang Jing,Yang Xing,Zhao Yuanfu,Zhang Weigong,Shen Jiao and Qiu Keni.Multi-bits error detection and fast recovery in RISC core[J].Journal of Emiconductors,2016,36(11):115009(1-8).
[10] Gaisler Research.The LEON2 Processor User's Manual[R].2004-05.
[11] 于航,王晶,周继芹,等.面向单粒子翻转效应的模拟故障注入技术[J].计算机工程与设计,2016,37(1):107-111. Yu Hang,Wang Jing,Zhou Ji-qin,et al.Simulation fault injection technology for single event upset[J].Computer Engineering and Design,2016,37(1):107-111.(in Chinese)
[12] EEMBC CoreMark Benchmark[/OL].https://www.eembc.org/coremark/,2018-08-04.
[13] 王芳良,张伟功,于立新.基准集在嵌入式系统性能分析中的应用[J].计算机工程与设计,2015(1):115-119. Wang Fang-liang,Zhang Wei-gong,Yu Li-xin.Applications of benchmark in embedded system performance analysis[J].Computer Engineering and Design,2015(1):115-119.(in Chinese)
[14] S Das,C Tokunaga,et al.Razorii:In situ error detection and correction for pvt and ser tolerance[J].IEEE Journal of Solid-State Circuits,2009,44(1):32-48.
[15] 郝亚男,高欣,许仕龙.SRAM型FPGA的SEU容错技术研究[J].中国集成电路,2015,10(197):31-36. Hao Ya-nan,Gao Xin,Xu Shi-long.Study on the SEU-tolerant techniques for SRAM-based FPGAs[J].China Integrated Circult,2015,10(197):31-36.(in Chinese)
[16] 陈志辉,章淳,王颖,王伶俐.一种FPGA抗辐射工艺映射方法研究[J].电子学报,2011,39(11):2507-2511. Chen Zhi-hui,Zhang Chun,Wang Ying,Wang Ling-li.An FPGA robust technology mapping method[J].Acta Electronica Sinica,2011,39(11):2507-2511.(in Chinese)
[17] 徐建军,谭庆平,熊磊,叶俊.一种针对软错误的程序可靠性定量分析方法[J].电子学报,2011,39(3):675-679. Xu Jian-jun,Tan Qing-ping,Xiong Lei,Ye Jun.A quantitative approach for program reliability analysis of soft errors[J].Acta Electronica Sinica,2011,39(3):675-679.(in Chinese)
[18] WANG Yongqing,MA Yuanxing,LIU Donglei,WU Siliang.An seu-tolerant approach for space-borne viterbi decoders[J].Chinese Journal of Electronics,2014,24(3):857-861.

基于周期粒度的级间寄存器备份机制

Backup Mechanism of Pipeline Register Based on Cycle Granularity

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张文芳, 孙海锋, 张晏端, 唐荣骏, 王小敏, 马征, 李暄, 黄路非. 基于树形结构构造的联盟链主从多链共识算法[J]. 电子学报, 2022, 50(2): 257-266.
[2]	王鹏, 邹彬, 刘金枝, 周丹阳. 基于Xilinx型FPGA系统单粒子效应评估方法研究[J]. 电子学报, 2022, 50(11): 2716-2721.
[3]	黄正峰, 潘尚杰, 曹剑飞, 宋钛, 欧阳一鸣, 梁华国, 倪天明, 鲁迎春. 32nm CMOS工艺三点翻转自恢复锁存器设计[J]. 电子学报, 2021, 49(2): 394-400.
[4]	欧阳一鸣, 贾博远, 李建华, 黄正峰, 梁华国. WiNoC中无线通信拥塞与故障感知的容错路由算法[J]. 电子学报, 2020, 48(4): 662-669.
[5]	蒋婵, 梁俊斌, 马方强, 李陶深. 移动低占空比传感网中基于分段拟合压缩的数据容灾存储算法[J]. 电子学报, 2020, 48(12): 2376-2383.
[6]	邵利平, 乐志芳. 多版本备份和限制性双重认证主密钥(t,s,k,n)图像分存[J]. 电子学报, 2019, 47(2): 390-403.
[7]	欧阳一鸣, 钱昌, 杜高明, 黄正峰, 李建华, 梁华国. WiNoC中EF-ACK容错无线接口设计[J]. 电子学报, 2018, 46(11): 2561-2570.
[8]	王晶, 荣金叶, 周继芹, 于航, 申娇, 张伟功. 软硬件协同设计的SEU故障注入技术研究[J]. 电子学报, 2018, 46(10): 2534-2538.
[9]	吴珊, 周学功, 王伶俐. 基于SRAM型FPGA单粒子效应的故障传播模型[J]. 电子学报, 2017, 45(8): 1976-1984.
[10]	蔡金燕, 朱赛, 孟亚峰. 一种新型的仿生电子细胞基因存储结构[J]. 电子学报, 2016, 44(8): 1915-1923.
[11]	欧阳一鸣, 何鑫城, 梁华国, 易茂祥, 杜高明, 安鑫. 针对路径故障与局部拥塞的NoC容错路由算法[J]. 电子学报, 2016, 44(4): 920-925.
[12]	王文博, 汪斌强, 陈飞宇, 王志明, 宫阳阳. 一种软件定义网络中的控制器热备份及选举算法[J]. 电子学报, 2016, 44(4): 913-919.
[13]	辛丹, 顾纯祥, 郑永辉, 光焱, 康元基. 利用RLWE构造基于身份的全同态加密体制[J]. 电子学报, 2016, 44(12): 2887-2893.
[14]	欧阳一鸣, 孙成龙, 陈奇, 梁华国, 易茂祥, 黄正峰, 闫爱斌. 3D NoC关键通信部件容错方法研究综述[J]. 电子学报, 2016, 44(12): 3053-3063.
[15]	张伟功, 周继芹, 李杰, 王晶, 丁瑞, 邓哲, 王嘉佳, 杜瑞. UM-BUS总线及接入式体系结构[J]. 电子学报, 2015, 43(9): 1776-1785.