首页> 外文会议>International Conference on Computer Design(CDES'05); 20050627-30; Las Vegas,NV(US) >Modeling and Synthesis of a Modified Floating Point Fused Multiply-Add (FMA) Arithmetic Unit Using VHDL and FPGAs
【24h】

Modeling and Synthesis of a Modified Floating Point Fused Multiply-Add (FMA) Arithmetic Unit Using VHDL and FPGAs

机译:使用VHDL和FPGA的修正浮点融合乘法加法(FMA)算术单元的建模和综合

获取原文
获取原文并翻译 | 示例

摘要

In this paper, we model a high speed Arithmetic synthesizable modified Fused Multiply Add Unit (FMA) capable of implementing the following operations: Addition/subtraction, Multiplication. With area-speed tradeoff limitation, our focus is on modeling high speed Arithmetic units with moderate area increase. Thus, we focus on developing units that share the same hardware. We have modeled a high speed arithmetic Modified fused multiply add unit (A*B + C ) Capable of addition/subtraction and multiplication. We have concentrated on reducing the delay in critical path by identifying the most time consuming operations in the critical path of a basic multiply Add fused unit. CAD tools have been implemented to model our system. Once modeled and synthesized, the system is downloaded onto a FPGAs chip. The synthesized chip is a stand alone FMA unit capable of implementing the operations mentioned. Synthesis tools have been implemented to evaluate our designs. Our results show that the estimated minimum delay of our designed unit is 4. 624ns.
机译:在本文中,我们对能够实现以下操作的高速算术可合成的改进的融合乘法加法单元(FMA)进行建模:加法/减法,乘法。受区域速度权衡的限制,我们的重点是对面积增加适中的高速算术单元进行建模。因此,我们专注于共享相同硬件的开发单元。我们已经建模了能够进行加/减和乘法运算的高速算术修正融合乘法加法单元(A * B + C)。我们通过确定基本乘加融合单元关键路径中最耗时的操作来集中精力减少关键路径的延迟。已经使用CAD工具来对我们的系统进行建模。一旦建模和合成,就将系统下载到FPGA芯片上。合成芯片是能够执行上述操作的独立FMA单元。已使用综合工具来评估我们的设计。我们的结果表明,我们设计的单元的估计最小延迟为4. 624ns。

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