• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 82 subscribers
  • Views 227 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

fix-point dsp

wang shenhang
Prodigy 210 points

Other Parts Discussed in Thread: TMS320LF2407A

There are C language as follows: Float A; Float B; A=0.36; B=A; Then how is A stored in fix-point dsp ,such as TMS320LF2407A,and what is the real number of B? whether dose fix-point Dsp mean it can’t store float point number?

  • 0
    Expert 1500 points

    Floating point and fixed point numbers, storage wont have any difference.

    IEE754 single precision floating point takes 4 bytes to store a number, same way one long (32 bit) int also takes same space. It is all bytes only finally.

    The floating point support, it can be either through software library (in the case of fixed point) or hardware (f28069, f28335 etc). 

    The number 0.36 = 3EB851EC (in single precision). So the point is fixed point as well as floating point processor can support floating point numbers but hardware support makes it much faster (1:50) than software library.

    Hope it helps

    Cheers

    Joy