期刊文献+

高性能乘法器设计

The Design of High-Performance MAC
下载PDF
导出
摘要 在许多实时高速信号处理中,需要使用FPGA硬件对复杂数字信号处理进行硬件加速或者预处理,例如广泛应用的矩阵求逆,方差等算法中[1],这些算法的关键都在于乘累加操作(MAC),目前的MAC操作多采用分裂式乘加器,文章设计一种高速4级流水MAC,对任意32bit数据进行高速的流水运算,在TSMC13工艺下进行综合,worst case下运行频率可超过400MHz。 It is necessary to use FPGA to process the complicated signal in many high-speed signal processing, such as pre-process or hardware-accelerating. The most important in the arithmetic is multiplication and addition(MAC). This paper designs a distributed MAC, which include 4 pipeline stages and can calculate at 400 MHz clock in TSMC13 worst case.
作者 周啸 代明清 Zhou Xiao;Dai Mingqing(Xi7 an Aeronautics Computing Technique Research Institute,Aviation Industry Corporation of China,Xi? an Shaanxi 710068,China)
出处 《信息通信》 2018年第5期27-29,共3页 Information & Communications
基金 航空科学基金资助项目(No.2016ZC31003)
关键词 乘加器 流水线 压缩算法 高性能 MAC Pipeline Compression Algorithm High-Performance
  • 相关文献

参考文献4

二级参考文献20

  • 1郑伟,姚庆栋,张明,蒋志迪,李东晓,赖莉亚,周莉.一种支持SIMD指令的低功耗分裂式ALU设计[J].计算机工程,2004,30(17):175-177. 被引量:1
  • 2Farooqui A A,Oklobdzija V G.General Data-path Organization of a MAC Unit for VLSI Implementation of DSP Processors[C].Proc.of ISCAS,1998,2:260-263.
  • 3Liao Yuyun,Roberts D B.A High-performance and Low-power 32-bit Multiply-accumulate Unit with Single-instruction-multiple-data (SIMD) Feature[J].IEEE Journal of Solid-State Circuits,2002,37(7):926-931.
  • 4Ling Zhuo.High-performance linear algebra on reconfigu- rable computing system[D].US,SC:University of South- em California,2007.
  • 5Pmsenjit Biswas,Pmmod P Udupa.Accelerating Numeri- cal Linear Algebra Kernels on a Scalable Run Time Recon gurable Platform[C].2010 IEEE Annual Sympo- sium on VLSI,2010:161-166.
  • 6郭磊.矩阵运算的硬件加速技术研究[D].长沙:国防科学技术大学,2010.
  • 7Falgoni Gandhi. A novel algorithm for fixed-point and floating-point matrix multiplication on a FPGA[D].Tex- as A&M University-Kingsville:2006.
  • 8Yamini Yadav.Reconfigurable matrix multiplication[D]. Texas A&M University-Kings-ville,2005.
  • 9Lionel M Ni,Kai Hwang.Vector reduction methods for arithmetic pipelines[C].Proeeedings of the 6th Interna- tional Symposium on Computer Arittmaetic,1983:144- 150.
  • 10Ling Zhuo,Viktor K Prasanna. High-performance and area-efcient reduction circuits on FPGAs[C].Proceed- ings of the 17th International Symposium on Computer Architecture and High Performance Computing,2005: 1-8.

共引文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部