• State
  • Locked Locked
  • Replies 2 replies
  • Subscribers 29 subscribers
  • Views 1091 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.

floating point multiplication using tiva c

Rajat Goyal
Prodigy 200 points

hiii,

I want to multiply 2 floating point number using arm cortex m4 ( tiva c). I know the format Sign bit (1), Exponent(8), mantissa( 23). i had tried to multiply the mantissa part seperately & add exponent seperately then merging but the result is not coming correct..

I had used 2 numbers 0.22013344550748 &  0.009765625.

  • 0
    Guru 26105 points

    Hi,

    Usually, in principle, you need to make a normalization of floating point variables to get it working correctly. But there are many other problems related to this, so the best thing is to read some other documents relating the subject, like this one - has a discussion/diagram of multiplying procedure.
    This in case you need/want to write yourself a floating point library - but I think for Tiva is not the case - the on-chip hardware has all the bells (a single .asm instruction) to perform floating point multiplication - see/search the document spmu159a.pdf on TI site (was on Tiva page, now is not anymore - if not finding I will attach here).
    Petrei
  • 0 in reply to Petrei
    Guru 11940 points

    ...see/search the document spmu159a.pdf on TI site (was on Tiva page, now is not anymore - if not finding I will attach here).

    The FPU - albeit optional for the silicon vendor - is provided by ARM, and thus identical for all Cortex-M4 implementations. That means, the FPU is documented in detail with the rest of the M4 core by ARM. Just search at infocenter.arm.com ...