arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.16405cs.AR
收藏

面向高速计算的改进型阵列逻辑二进制乘法器设计

Design of a Reformed Array Logic Binary Multiplier for High-Speed Computations

Sakib Mohammad, Themistoklis Haniotakis

AI总结:

本文提出一种基于改进型阵列逻辑的二进制乘法器设计,利用多路复用器、桶形移位器及CSA与RCA组合加速部分积运算,在Cadence Virtuoso上实现了16位无符号数乘法,设计模块化且可扩展至任意n位。

摘要:

二进制乘法器一直是数字电路中的基础组件,在微处理器设计、数字信号处理单元及更多应用中发挥着关键作用。本研究提出了一种独特的乘法器设计,采用改进型阵列逻辑方法来计算两个无符号二进制数的乘积。我们使用多路复用器和桶形移位器在单个时钟周期内完成部分积的乘法运算,以加速传统的阵列逻辑。此外,我们采用进位保存加法器(CSA)和纹波进位加法器(RCA)的组合来累加部分积,而非使用独立的RCA,从而进一步加速乘法过程。最后,我们在Cadence Virtuoso上展示了我们的设计,实现了两个16位无符号二进制数的乘法运算。该设计具有模块化特性,可按比例放大或缩小,以适应任意n位无符号数的乘法运算。

英文摘要:

Binary multipliers have long been a staple component in digital circuitry, serving crucial roles in microprocessor design, digital signal processing units and many more applications. This work presents a unique design for a multiplier that utilizes a reformed-array-logic approach to compute the product of two unsigned binary numbers. We employed a multiplexer and a barrel shifter to multiply partial products in a single clock cycle to speed up the traditional array logic. In addition, we have employed a combination of Carry Save Adders (CSA) and Ripple Carry Adders (RCA) to accumulate the partial products instead of using standalone RCAs to speed up the multiplication process further. Finally, we have demonstrated our design to perform multiplication of two 16-bit unsigned binary numbers on Cadence Virtuoso. Our design is modular and can be scaled up or down to accommodate the multiplication of any n-bit unsigned numbers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑