Architectural design of a fast floating-point multiplication-add fused unit using signed-digit addition

被引：7
|
作者：
Chen, CY [1 ]
Chen, LA [1 ]
Cheng, JR [1 ]
机构：
[1] Feng Chia Univ, Dept Informat Engn, Taichung 407, Taiwan
来源：
EUROMICRO SYMPOSIUM ON DIGITAL SYSTEMS DESIGN, PROCEEDINGS | 2001年
关键词：
D O I：
10.1109/DSD.2001.952324
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Signed digit (SD) addition is applied to the design of a new floating-point (FLP) multiplication-add fused (MAF) unit. This adoption, together with the proposed two-step normalization method, can reduce the three-word-length addition that is required in the conventional FLP MAF unit to two-word-length addition. Furthermore, the sign reversion of the intermediate mantissa that requires three-word-length carry propagation in the conventional MAF unit is replaced by only single-word sign detection. These two improvements can enhance the speed and cost of the MAF unit significantly. With the use of the SD addition.. the circuit of the unit can be designed in a more regular and simple manner, which is a property that is desired in VLSI design, The proposed FLP MAF unit has been designed and simulated by using Verilog hardware description language, The functions of the designed unit are verified to be correct.
引用
收藏
页码：346 / 353
页数：8
相关论文
共 46 条
  • [41] Design of Novel Multipliers-Vedic and Shift-Add for IEEE 754-2008 Single Precision Floating-point Unit in High Speed Applications
    Mohapatra, Anshuman
    Bisoyi, Abhyarthana
    Tripathy, Aruna
    2019 IEEE INTERNATIONAL SYMPOSIUM ON SMART ELECTRONIC SYSTEMS (ISES 2019), 2019, : 160 - 163
  • [42] Design of area and power efficient Radix-4 DIT FFT butterfly unit using floating point fused arithmetic
    E. Prabhu
    H. Mangalam
    S. Karthick
    Journal of Central South University, 2016, 23 : 1669 - 1681
  • [43] Design of area and power efficient Radix-4 DIT FFT butterfly unit using floating point fused arithmetic
    Prabhu E
    Mangalam H
    Karthick S
    Journal of Central South University, 2016, 23 (07) : 1669 - 1681
  • [44] Design of area and power efficient Radix-4 DIT FFT butterfly unit using floating point fused arithmetic
    Prabhu, E.
    Mangalam, H.
    Karthick, S.
    JOURNAL OF CENTRAL SOUTH UNIVERSITY, 2016, 23 (07) : 1669 - 1681
  • [45] Exascale Supercomputer Oriented Parallel Cyclic Compression Based Checking Structure for Floating-Point Fused Multiply-Add Unit; [面向犈量级超算的并行循环压缩浮点乘加校验结构]
    Gao J.-G.
    Liu X.
    Zheng F.
    Tang Y.
    Jisuanji Xuebao/Chinese Journal of Computers, 2023, 46 (06): : 1103 - 1120
  • [46] A 40nm 4.81TFLOPS/W 8b Floating-Point Training Processor for Non-Sparse Neural Networks Using Shared Exponent Bias and 24-Way Fused Multiply-Add Tree
    Park, Jeongwoo
    Lee, Sunwoo
    Jean, Dongsuk
    2021 IEEE INTERNATIONAL SOLID-STATE CIRCUITS CONFERENCE (ISSCC), 2021, 64 : 148 - +
12345