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:张晓磊 戴紫彬[1] 刘燕江 曲彤洲 ZHANG Xiaolei;DAI Zibin;LIU Yanjiang;QU Tongzhou(Department of Cryptogram Engineering,PLA Information Engineering University,Zhengzhou 450001,China)
机构地区:[1]解放军信息工程大学密码工程学院,郑州450001
出 处:《信息网络安全》2023年第5期76-84,共9页Netinfo Security
基 金:国家自然科学基金[61832018]。
摘 要:模运算单元是粗粒度可重构密码阵列(Coarse Grain Reconfigurable Cryptographic Array,CGRCA)的关键部件,通过重构不同处理位宽和模数的算术类密码算子来覆盖更多类型的分组密码,然而现有的模运算单元的执行延迟高且功能覆盖率低,限制了CGRCA整体性能的提升。文章通过分析分组密码模运算特性,提出一种可重构模运算方法,统一了该类算子的数学表达方式,并设计了一种可重构模运算单元(Reconfigurable Modulo Arithmetic Unit,RMAU),该单元支持5种模乘运算、3种模加运算和3种乘法累加运算。同时,通过舍弃部分积中的无用比特位、扩展Wallace树压缩求和过程、精简模修正电路执行路径,降低了该单元的关键路径延迟。基于CMOS 180 nm工艺测试了RMAU的功能与性能,实验结果表明,文章所提的RMAU具备高功能覆盖率,与模乘RCE单元、可扩展模乘结构和RNS乘法器相比,计算延迟分别降低了39%、44%和47%。Modulo arithmetic unit is the key component of coarse grain reconfigurable cryptographic array(CGRCA).It can cover more types of block ciphers by reconfiguring arithmetic cryptographic operators with different processing width and modulus.However,the high execution latency and low functional coverage of the existing modulo arithmetic units limit the overall performance improvement of CGRCA.By analyzing the characteristics of modulo arithmetic in block ciphers,this paper proposed reconfigurable modular arithmetic unit(RMAU),which unified the mathematical expression of the operators and designed a RMAU.The unit supported five modular multiplication operations,three modular addition operations,and three multiply-accumulate operations.At the same time,the critical path delay of the unit was optimized by discarding useless bits in the partial product,extending the Wallace tree to compress the summing process,and shortening the modular correction module’s execution path.The function and performance of RMAU were tested in CMOS 180 nm process.The experimental results show that while RMAU has high functional coverage,compared with modular multiplier RCE unit,extensible modular multiplier structure and RNS multiplier,the computation delay is reduced by 39%,44% and 47%,respectively.
分 类 号:TP309[自动化与计算机技术—计算机系统结构]
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:216.73.216.62