A comparison of floating point and logarithmic number systems for FPGAs.
Conference
·
OSTI ID:950936
- University of Washington, Seattle, WA
There have been many papers proposing the use of logarithmic numbers (LNS) as an alternative to floating point because of simpler multiplication, division and exponentiation computations. However, this advantage comes at the cost of complicated, inexact addition and subtraction, as well as the need to convert between the formats. In this work, we created a parameterized LNS library of computational units and compared them to an existing floating point library. Specifically, we considered multiplication, division, addition, subtraction, and format conversion to determine when one format should be used over the other and when it is advantageous to change formats during a calculation.
- Research Organization:
- Sandia National Laboratories
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 950936
- Report Number(s):
- SAND2005-0971C
- Country of Publication:
- United States
- Language:
- English
Similar Records
Double-Precision Floating-Point Cores V1.9
Improvements in floating point addition/subtraction operations
Trident: An FPGA Compiler Framework for Floating-Point Algorithms.
Software
·
2005
·
OSTI ID:1230855
Improvements in floating point addition/subtraction operations
Patent
·
1984
·
OSTI ID:6101400
Trident: An FPGA Compiler Framework for Floating-Point Algorithms.
Conference
·
2004
·
OSTI ID:977959