首页> 外文期刊>IEEE Transactions on Circuits and Systems. II, Express Briefs >A new division algorithm based on lookahead of partial-remainder(LAPR) for high-speed/low-power coding applications
【24h】

A new division algorithm based on lookahead of partial-remainder(LAPR) for high-speed/low-power coding applications

机译:一种基于局部余数超前(LAPR)的高速/低功率编码应用新除法算法

获取原文
获取原文并翻译 | 示例

摘要

A new polynomial division algorithm in finite field GF(2mn) based on the lookahead of partial-remainder (LAPR) is proposed.nSince our algorithm is based on partial division on group basis andnlookahead technique exploiting the linearity in finite field arithmetic,nit is possible to completely eliminate polynomial multiplicationsnleading to highly increased throughput per unit time. The inherentnregularity and feedforward nature of our algorithm make it possible tonbe fully pipelined. When pipelined, its throughput is one quotient andnone remainder per clock cycle, regardless of the degree of dividendnpolynomial, which is orders of magnitude faster than the conventionalnarchitecture using linear feedback shift register. An area-efficientnsequential architecture based on LAPR is also presented, Although thenthroughput rate of sequential architecture is lower than that of thenpipelined one, it is still higher than that of any division architecturenever reported. They are shown to be efficient, regular, and easilynexpandable, and hence, naturally suitable for very large scalenintegration implementation. In systems requiring modest speed, thenhigh-speed nature of our proposed architecture can be traded for lownpower consumption by reducing clock rate. We verified the generalnvalidity of the division algorithm based on LAPR by mathematicalnmanipulation and simulation. The superiority of our proposednarchitecture compared with other reported ones is demonstrated withnregard to its throughput, latency delays, and power
机译:提出了一种基于局部余数提前(LAPR)的有限域GF(2mn)多项式除法算法。完全消除多项式乘法,从而大大提高了单位时间的吞吐量。我们算法的固有不规则性和前馈性质使得有可能完全流水线化。当进行流水线处理时,其吞吐量为一个商,每个时钟周期无余数,而不论被除数多项式的程度如何,这比使用线性反馈移位寄存器的传统体系结构快几个数量级。还提出了一种基于LAPR的面积有效的顺序体系结构,尽管顺序体系结构的吞吐率低于流水线体系结构的吞吐率,但仍高于从未报道过的任何分区体系结构。它们被证明是有效的,有规律的,易于扩展的,因此自然适用于非常大规模的集成。在需要适度速度的系统中,可以通过降低时钟速率将我们提议的体系结构的高速性换为低功耗。通过数学运算和仿真验证了基于LAPR的除法算法的一般有效性。无论其吞吐量,延迟延迟和功耗如何,都证明了我们提出的架构与其他已报道架构相比的优越性

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号