首页> 外文会议>2012 4th International Conference on Intelligent and Advanced Systems >Performance comparison review of Radix-based multiplier designs
【24h】

Performance comparison review of Radix-based multiplier designs

机译:基于Radix的乘法器设计的性能比较审查

获取原文
获取原文并翻译 | 示例

摘要

This is a study of the relative performance comparison of Radix-based Booth Encoding multiplier. Multipliers included in the comparison are Radix-2 Booth Encoding multiplier, Radix-4 Booth Encoding multiplier, Radix-8 Booth Encoding multiplier, Radix-16 Booth Encoding multiplier and Radix-32 Booth Encoding multiplier. All these multiplier designs were modeled in Verilog HDL and synthesized based on TSMC 0.35-micron ASIC Design Kit standard cell library. The performance data was extracted after logic synthesis has been done by using Leonardo Spectrum for Area, Speed and Auto-Optimization modes. From the findings obtained, it is known that the gate level and delay synthesis performances of the Radix-4 Booth Encoding multiplier are reduced if it is compared to Radix-2 Booth Encoding multiplier design. Then, as the higher the number of Radix-based multiplier, both the gate level and the delay performances will increase due to the complexity of the partial products encoded. However, the largest area and longest timing delay can still be seen in Radix-2 Booth Encoding multiplier. The comparison of the 32-bit Radix-based Booth Encoding variants indicates that the Radix-4 Booth Encoding multiplier is the best multiplier in terms of high-speed applications and low area constraint.
机译:这是基于Radix的Booth Encoding乘数的相对性能比较的研究。比较中包括的乘数是Radix-2 Booth编码乘数,Radix-4 Booth编码乘数,Radix-8 Booth编码乘数,Radix-16 Booth编码乘数和Radix-32 Booth编码乘数。所有这些乘法器设计均在Verilog HDL中建模,并基于TSMC 0.35微米ASIC Design Kit标准单元库进行了合成。通过使用Leonardo Spectrum的Area,Speed和Auto-Optimization模式完成逻辑综合后,提取性能数据。根据获得的发现,可以知道,如果将Radix-4 Booth编码乘法器与Radix-2 Booth Encoding乘法器设计进行比较,则会降低门级和延迟综合性能。然后,随着基于Radix的乘法器数量的增加,由于编码的部分乘积的复杂性,门级和延迟性能都将提高。但是,在Radix-2 Booth Encoding乘法器中仍然可以看到最大的面积和最长的时序延迟。对基于Radix的32位Booth Encoding变体的比较表明,就高速应用和低面积约束而言,Radix-4 Booth Encoding乘数是最佳乘数。

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