• Home
  • Search
  • Efficient floating-point polynomial evaluation on FPGAS
  • Cite Icon1
  • https://doi.org/10.1109/fpl.2013.6645530Copy DOI Icon

Efficient floating-point polynomial evaluation on FPGAS

  • Sep 1, 2013
  • Martin Langhammer +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Many applications require the evaluation of polynomials having floating-point coefficients - one example is rational polynomial approximation, often used to implement some special functions. The most resource efficient polynomial evaluation scheme (Horner) is costly to implement on FPGAs due to the high cost associated with floating-point arithmetic. Floating-point adders are particularly costly due to their alignment stages requiring large barrel shifters. In this work we present a novel FPGA-specific technique for evaluating polynomials using the Horner scheme. Our technique removes the majority of alignment shifters present in floating-point adders by building a fused evaluation operator. It pushes the possible alignment values of the monomials into tables containing multiple shifted coefficient instances which are selected using the exponent of the input argument. Compared to operator assembly this work reduces circuit latency by 30-50% and logic consumption by 40-60%. Our work can be easily extended to other polynomial evaluation methods.

Similar Papers
  • Conference Article
  • Citations1

An IEEE floating-point adder for multi-operation

  • Oct 18, 2004
  • Ping Huang +2
  • Research Article
  • Citations4

Testability Analysis and Scalable Test Generation for High-Speed Floating-Point Units

  • Nov 01, 2006
  • IEEE Transactions on Computers
  • G Xenoulis +3
  • Conference Article
  • Citations2

Design and architecture for a multi-mode pipelined, floating-point adder

  • May 20, 1991
  • K.R Gillam +1
  • Research Article
  • Citations26

Design Issues and Implementations for Floating-Point Divide–Add Fused

  • Apr 01, 2010
  • IEEE Transactions on Circuits and Systems II: Express Briefs
  • Alexandru Amaricai +2
  • Conference Article
  • Citations3

Implementation of single precision conventional and fused floating point add-sub unit using Verilog

  • Mar 01, 2017
  • Aditi Sharma +2
  • Conference Article
  • Citations8

Implementation of IEEE 754 compliant single precision floating-point adder unit supporting denormal inputs on Xilinx FPGA

  • Sep 01, 2017
  • Milind Shirke +2
  • Conference Article
  • Citations15

High-Performance and Area-Efficient Reduction Circuits on FPGAs

  • Oct 24, 2005
  • Ling Zhuo +1
  • Conference Article
  • Citations5

Floating-point L^2 -approximations to functions

  • Dec 11, 2006
  • Proceedings/Proceedings - Symposium on Computer Arithmetic
  • Nicolas Brisebarre +1
  • Research Article
  • Citations4

Fuel-optimal guidance using costate supervised learning with local refinement

  • Nov 24, 2024
  • Acta Astronautica
  • Adam Evans +3
  • Research Article
  • Citations31

Efficient evaluation of polynomials and exponentials of polynomials for equispaced arguments

  • Oct 01, 1987
  • IEEE Transactions on Acoustics, Speech, and Signal Processing
  • A Nuttall
  • Single Report

COMPUTING PROGRAMS FOR THE COMPLEX FRESNEL INTEGRAL

  • Nov 19, 1962
  • A V Hershey
  • Conference Article
  • Citations24

Flexible multi-mode embedded floating-point unit for field programmable gate arrays

  • Feb 22, 2009
  • Yee Jern Chong +1
  • Conference Article
  • Citations90

High Performance Linear Algebra Operations on Reconfigurable Systems

  • Nov 12, 2005
  • Ling Zhuo +1
  • Research Article
  • Citations6

Fast Parallel Algorithm for Polynomial Evaluation

  • Dec 01, 2003
  • Parallel Algorithms and Applications
  • Przemysław Stpiczyński
  • Research Article
  • Citations19

High-performance, low-latency field-programmable gate array-based floating-point adder and multiplier units in a Virtex 4

  • Jul 01, 2008
  • IET Computers & Digital Techniques
  • P KarlströM +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.