• Home
  • Search
  • Comparing floating-point and logarithmic number representations for reconfigurable acceleration
  • Cite Icon12
  • https://doi.org/10.1109/fpt.2006.270342Copy DOI Icon

Comparing floating-point and logarithmic number representations for reconfigurable acceleration

  • Dec 1, 2006
  • Haohuan Fu +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The paper investigates floating-point and logarithmic number representations for computing with FPGAs. The key issue is to select the best number format for an application to improve performance and accuracy. Using A Stream Compiler, ASC as the hardware design and compilation tool, a convenient scheme to compare the designs of both floating-point and logarithmic numbers and select the solution with the best performance and accuracy, was developed. Its contributions are: (1) optimized function evaluations for conversions between logarithmic and floating-point numbers; (2) design and implementation of logarithmic arithmetic, with optimized segmentation and polynomial degree; (3) a practical comparison case study of Monte Carlo radiative heat transfer simulation. Compared to prior work, our design supports two to six times more LNS conversion and LNS arithmetic units on one FPGA. For Monte Carlo simulation, our designs of both number systems produce 39-80% higher throughput with either a smaller area or a higher accuracy

Similar Papers
  • Research Article
  • Citations62

Using hierarchical octrees in Monte Carlo radiative transfer simulations

  • May 29, 2013
  • Astronomy & Astrophysics
  • W Saftly +6
  • Conference Article
  • Citations7

Adaptive fault tolerant digital filters with single and multiple bit errors in floating-point arithmetic

  • Jan 01, 2000
  • G Leon +1
  • Conference Article
  • Citations3

Overflow/underflow-free floating-point number representations with self-delimiting variable-length exponent field

  • Jun 26, 1991
  • H Yokoo
  • Research Article
  • Citations3

Implementation of Custom Precision Floating Point Arithmetic on FPGAs

  • Jan 31, 2013
  • Zenodo (CERN European Organization for Nuclear Research)
  • Raj Gaurav Mishra +1
  • Research Article

An Adaptive Benchmark Testing Method for Evaluating Arithmetic Precision

  • Dec 30, 2025
  • Security of Infocommunication Systems and Internet of Things
  • Denys Deineko
  • Research Article
  • Citations214

Henyey–Greenstein and Mie phase functions in Monte Carlo radiative transfer computations

  • Jun 20, 1996
  • Applied Optics
  • Dominique Toublanc
  • Conference Article
  • Citations6

A radiative heat transfer simulation on a SPARCStation farm

  • Sep 09, 1992
  • R.G Minnich +1
  • Research Article
  • Citations8

Numerical Optimization Problems of Sine-Wave Fitting Algorithms in the Presence of Roundoff Errors

  • Aug 01, 2016
  • IEEE Transactions on Instrumentation and Measurement
  • Balazs Renczes +3
  • Research Article

The Laplace Microarchitecture for Tracking Data Uncertainty

  • Jul 01, 2022
  • IEEE Micro
  • Vasileios Tsoutsouras +6
  • PDF
  • Research Article
  • Citations13

Accelerating Spike-by-Spike Neural Networks on FPGA With Hybrid Custom Floating-Point and Logarithmic Dot-Product Approximation

  • Jan 01, 2021
  • IEEE Access
  • Yarib Nevarez +3
  • Research Article
  • Citations100

SKIRT: The design of a suite of input models for Monte Carlo radiative transfer simulations

  • Jun 09, 2015
  • Astronomy and Computing
  • M Baes +1
  • Research Article

Analysis and Realization of Critical Points on Hardware Design of FPGA

  • Jun 01, 2014
  • Advanced Materials Research
  • Chang Fu Wu
  • Conference Article
  • Citations39

Decimal floating-point division using Newton-Raphson iteration

  • Sep 27, 2004
  • Liang‐Kai Wang +1
  • PDF
  • Book Chapter

Floating-Point Arithmetic with Consistent Rounding on a Quantum Computer

  • Jun 07, 2024
  • René Steijl
  • Conference Article
  • Citations2

FP-ANR: A representation format to handle floating-point cancellation at run-time

  • Apr 22, 2018
  • David Defour
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.