检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:闫爱斌 梁华国[3] 黄正峰[3] 蒋翠云[4] 易茂祥[3]
机构地区:[1]合肥工业大学计算机与信息学院,安徽合肥230009 [2]安徽大学计算机科学与技术学院,安徽合肥230601 [3]合肥工业大学电子科学与应用物理学院,安徽合肥230009 [4]合肥工业大学数学学院,安徽合肥230009
出 处:《电子学报》2016年第12期3011-3019,共9页Acta Electronica Sinica
基 金:国家自然科学基金(No.61371025;No.61574052;No.61674048;No.61604001)
摘 要:集成电路工艺水平的提升,使得由单粒子瞬态脉冲造成的芯片失效越发不容忽视.为了准确计算单粒子瞬态脉冲对锁存器造成的失效率,提出一种考虑多时钟周期瞬态脉冲叠加的锁存窗屏蔽模型.使用提出的考虑扇出重汇聚的敏化路径逼近搜索算法查找门节点到达锁存器的敏化路径,并记录路径延迟;在扇出重汇聚路径上,使用提出的脉冲叠加计算方法对脉冲进行叠加;对传播到达锁存器的脉冲使用提出的锁存窗屏蔽模型进行失效率的计算.文中的锁存窗屏蔽模型可以准确计算扇出重汇聚导致的脉冲叠加,并对多时钟周期情形具有很好的适用性.针对ISCAS’85基准电路的软错误率评估结果表明,与不考虑多时钟周期瞬态脉冲叠加的方法相比,文中方法使用不到2倍的时间开销,平均提高7.5%的软错误率评估准确度.Technology scaling results in that chip failure caused by single event transient pulses is becoming more and more serious. In order to accurately compute the failure rates introduced by the transient pulses impacting on latches, a novel latching-window masking model considering overlapped transient pulses in multi-cycle is proposed. Firstly, sensitized paths and delays are calculated by the proposed re-convergence aware sensitized path searching algorithm. Further, on re-conver- gence paths, pulses are overlapped by the proposed pulse overlapping calculation technique. Finally, as regards transient pul- ses arriving at latches, failure rates are computed by the proposed latching-window masking model. The proposed technique can accurately compute re-convergence induced pulse overlap and it is suitable to estimate failure rates considering multi-cy- cle. Experimental results for ISCAS85 benchmarks show that, compared with the approach which has not considered pulse o- verlap in multi-cycle, the proposed technique improves 7.5 % soft error rate accuracy on average with only less than twice the simulation time overhead.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.7