• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 100 subscribers
  • Views 939 views
  • Users 0 members are here
Support feedback
Options
Options
Similar topics

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.

upto what extent a C55x can perform floating point operations

Shyam
Expert 1960 points

C55x is fixed point DSP, when i observe the C5x assembly user manual it clearly shows even it stores the float value in IEEE format same as a floating point DSP 

where exactly fixed point DSP falls behind a floating point dsp

from the manual its evident that even C55x can represent numbers with great precision, does it fail in operations between floating point values ???

can any one explain why C55x also uses IEEE format of 1s,8e,23m kind of representation when it cannot achieve floating point performance is there any special reason

  • 0
    TI__Guru* 84225 points

    C55x calls library functions to perform all floating-point operations.  These functions are much slower than a native floating-point CPU, but the IEEE operations can be carried out entirely in software on a fixed-point device.  The C55x chooses to keep the float values in IEEE format for consistency with other targets.  Some developers prefer to begin development with floating-point values for ease of development, and convert to fixed point when speed becomes necessary.