Author Topic: 16 bit floating point  (Read 223 times)

Offline JernejL

  • Imaging User
  • *
  • Posts: 3
    • View Profile
16 bit floating point
« on: 22 March 2018, 14:19:50 »
I wish to share this find with galfar and the rest here, it's related to processing 16 bit floating point values:
 
http://www.fox-toolkit.org/ftp/fasthalffloatconversion.pdf
 
There is already a pascal implementation of this that i have found:
https://github.com/SAmeis/xplib/blob/master/DeHL/Library/src/Math/DeHL.Math.Half.pas
 
I hope you find it useful, surely a lookup table based solution with no cpu code branching is a big improvement if you process 16 bit floating point values regularly.
 

Offline Galfar

  • Administrator
  • Imaging User
  • *****
  • Posts: 361
    • View Profile
    • Galfar's Homepage
Re: 16 bit floating point
« Reply #1 on: 10 May 2018, 22:50:00 »
Thanks for the tip, looks pretty nice.